Re: [3.13.y.z extended stable] Linux 3.13.11.7

From: Kamal Mostafa
Date: Thu Sep 18 2014 - 16:43:33 EST

Next message: Theodore Ts'o: "Re: [PATCH 1/1 linux-next] jbd2: Fix sparse context imbalance warning"
Previous message: Kamal Mostafa: "[3.13.y.z extended stable] Linux 3.13.11.7"
In reply to: Kamal Mostafa: "[3.13.y.z extended stable] Linux 3.13.11.7"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index b8dd0df..0fd40b1 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -2026,8 +2026,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
-------------------

Module for sound cards based on the Asus AV66/AV100/AV200 chips,
- i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX,
- HDAV1.3 (Deluxe), and HDAV1.3 Slim.
+ i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe),
+ Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim.

This module supports autoprobe and multiple cards.

diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index b0714d8..8dfb6a5 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -29,6 +29,9 @@ Rules on what kind of patches are accepted, and which ones are not, into the

Procedure for submitting patches to the -stable tree:

+ - If the patch covers files in net/ or drivers/net please follow netdev stable
+ submission guidelines as described in
+ Documentation/networking/netdev-FAQ.txt
- Send the patch, after verifying that it follows the above rules, to
stable@xxxxxxxxxxxxxxxx You must note the upstream commit ID in the
changelog of your submission, as well as the kernel version you wish
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f..bd43704 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0
ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
diff --git a/Makefile b/Makefile
index 805e22f..4820269 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 3
PATCHLEVEL = 13
SUBLEVEL = 11
-EXTRAVERSION = .6
+EXTRAVERSION = .7
NAME = King of Alienated Frog Porn

# *DOCUMENTATION*
diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c
index 44bb4d5..89cde07 100644
--- a/arch/arm/mach-omap2/control.c
+++ b/arch/arm/mach-omap2/control.c
@@ -314,7 +314,8 @@ void omap3_save_scratchpad_contents(void)
scratchpad_contents.public_restore_ptr =
virt_to_phys(omap3_restore_3630);
else if (omap_rev() != OMAP3430_REV_ES3_0 &&
- omap_rev() != OMAP3430_REV_ES3_1)
+ omap_rev() != OMAP3430_REV_ES3_1 &&
+ omap_rev() != OMAP3430_REV_ES3_1_2)
scratchpad_contents.public_restore_ptr =
virt_to_phys(omap3_restore);
else
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 7bba9da..6d019ca 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -23,7 +23,7 @@
struct pt_regs {
#ifdef CONFIG_32BIT
/* Pad bytes for argument save space on the stack. */
- unsigned long pad0[6];
+ unsigned long pad0[8];
#endif

/* Saved main processor registers. */
diff --git a/arch/mips/include/asm/reg.h b/arch/mips/include/asm/reg.h
index 910e71a..b8343cc 100644
--- a/arch/mips/include/asm/reg.h
+++ b/arch/mips/include/asm/reg.h
@@ -12,116 +12,194 @@
#ifndef __ASM_MIPS_REG_H
#define __ASM_MIPS_REG_H

-
-#if defined(CONFIG_32BIT) || defined(WANT_COMPAT_REG_H)
-
-#define EF_R0 6
-#define EF_R1 7
-#define EF_R2 8
-#define EF_R3 9
-#define EF_R4 10
-#define EF_R5 11
-#define EF_R6 12
-#define EF_R7 13
-#define EF_R8 14
-#define EF_R9 15
-#define EF_R10 16
-#define EF_R11 17
-#define EF_R12 18
-#define EF_R13 19
-#define EF_R14 20
-#define EF_R15 21
-#define EF_R16 22
-#define EF_R17 23
-#define EF_R18 24
-#define EF_R19 25
-#define EF_R20 26
-#define EF_R21 27
-#define EF_R22 28
-#define EF_R23 29
-#define EF_R24 30
-#define EF_R25 31
+#define MIPS32_EF_R0 6
+#define MIPS32_EF_R1 7
+#define MIPS32_EF_R2 8
+#define MIPS32_EF_R3 9
+#define MIPS32_EF_R4 10
+#define MIPS32_EF_R5 11
+#define MIPS32_EF_R6 12
+#define MIPS32_EF_R7 13
+#define MIPS32_EF_R8 14
+#define MIPS32_EF_R9 15
+#define MIPS32_EF_R10 16
+#define MIPS32_EF_R11 17
+#define MIPS32_EF_R12 18
+#define MIPS32_EF_R13 19
+#define MIPS32_EF_R14 20
+#define MIPS32_EF_R15 21
+#define MIPS32_EF_R16 22
+#define MIPS32_EF_R17 23
+#define MIPS32_EF_R18 24
+#define MIPS32_EF_R19 25
+#define MIPS32_EF_R20 26
+#define MIPS32_EF_R21 27
+#define MIPS32_EF_R22 28
+#define MIPS32_EF_R23 29
+#define MIPS32_EF_R24 30
+#define MIPS32_EF_R25 31

/*
* k0/k1 unsaved
*/
-#define EF_R26 32
-#define EF_R27 33
+#define MIPS32_EF_R26 32
+#define MIPS32_EF_R27 33

-#define EF_R28 34
-#define EF_R29 35
-#define EF_R30 36
-#define EF_R31 37
+#define MIPS32_EF_R28 34
+#define MIPS32_EF_R29 35
+#define MIPS32_EF_R30 36
+#define MIPS32_EF_R31 37

/*
* Saved special registers
*/
-#define EF_LO 38
-#define EF_HI 39
-
-#define EF_CP0_EPC 40
-#define EF_CP0_BADVADDR 41
-#define EF_CP0_STATUS 42
-#define EF_CP0_CAUSE 43
-#define EF_UNUSED0 44
-
-#define EF_SIZE 180
-
-#endif
-
-#if defined(CONFIG_64BIT) && !defined(WANT_COMPAT_REG_H)
-
-#define EF_R0 0
-#define EF_R1 1
-#define EF_R2 2
-#define EF_R3 3
-#define EF_R4 4
-#define EF_R5 5
-#define EF_R6 6
-#define EF_R7 7
-#define EF_R8 8
-#define EF_R9 9
-#define EF_R10 10
-#define EF_R11 11
-#define EF_R12 12
-#define EF_R13 13
-#define EF_R14 14
-#define EF_R15 15
-#define EF_R16 16
-#define EF_R17 17
-#define EF_R18 18
-#define EF_R19 19
-#define EF_R20 20
-#define EF_R21 21
-#define EF_R22 22
-#define EF_R23 23
-#define EF_R24 24
-#define EF_R25 25
+#define MIPS32_EF_LO 38
+#define MIPS32_EF_HI 39
+
+#define MIPS32_EF_CP0_EPC 40
+#define MIPS32_EF_CP0_BADVADDR 41
+#define MIPS32_EF_CP0_STATUS 42
+#define MIPS32_EF_CP0_CAUSE 43
+#define MIPS32_EF_UNUSED0 44
+
+#define MIPS32_EF_SIZE 180
+
+#define MIPS64_EF_R0 0
+#define MIPS64_EF_R1 1
+#define MIPS64_EF_R2 2
+#define MIPS64_EF_R3 3
+#define MIPS64_EF_R4 4
+#define MIPS64_EF_R5 5
+#define MIPS64_EF_R6 6
+#define MIPS64_EF_R7 7
+#define MIPS64_EF_R8 8
+#define MIPS64_EF_R9 9
+#define MIPS64_EF_R10 10
+#define MIPS64_EF_R11 11
+#define MIPS64_EF_R12 12
+#define MIPS64_EF_R13 13
+#define MIPS64_EF_R14 14
+#define MIPS64_EF_R15 15
+#define MIPS64_EF_R16 16
+#define MIPS64_EF_R17 17
+#define MIPS64_EF_R18 18
+#define MIPS64_EF_R19 19
+#define MIPS64_EF_R20 20
+#define MIPS64_EF_R21 21
+#define MIPS64_EF_R22 22
+#define MIPS64_EF_R23 23
+#define MIPS64_EF_R24 24
+#define MIPS64_EF_R25 25

/*
* k0/k1 unsaved
*/
-#define EF_R26 26
-#define EF_R27 27
+#define MIPS64_EF_R26 26
+#define MIPS64_EF_R27 27

-#define EF_R28 28
-#define EF_R29 29
-#define EF_R30 30
-#define EF_R31 31
+#define MIPS64_EF_R28 28
+#define MIPS64_EF_R29 29
+#define MIPS64_EF_R30 30
+#define MIPS64_EF_R31 31

/*
* Saved special registers
*/
-#define EF_LO 32
-#define EF_HI 33
-
-#define EF_CP0_EPC 34
-#define EF_CP0_BADVADDR 35
-#define EF_CP0_STATUS 36
-#define EF_CP0_CAUSE 37
-
-#define EF_SIZE 304 /* size in bytes */
+#define MIPS64_EF_LO 32
+#define MIPS64_EF_HI 33
+
+#define MIPS64_EF_CP0_EPC 34
+#define MIPS64_EF_CP0_BADVADDR 35
+#define MIPS64_EF_CP0_STATUS 36
+#define MIPS64_EF_CP0_CAUSE 37
+
+#define MIPS64_EF_SIZE 304 /* size in bytes */
+
+#if defined(CONFIG_32BIT)
+
+#define EF_R0 MIPS32_EF_R0
+#define EF_R1 MIPS32_EF_R1
+#define EF_R2 MIPS32_EF_R2
+#define EF_R3 MIPS32_EF_R3
+#define EF_R4 MIPS32_EF_R4
+#define EF_R5 MIPS32_EF_R5
+#define EF_R6 MIPS32_EF_R6
+#define EF_R7 MIPS32_EF_R7
+#define EF_R8 MIPS32_EF_R8
+#define EF_R9 MIPS32_EF_R9
+#define EF_R10 MIPS32_EF_R10
+#define EF_R11 MIPS32_EF_R11
+#define EF_R12 MIPS32_EF_R12
+#define EF_R13 MIPS32_EF_R13
+#define EF_R14 MIPS32_EF_R14
+#define EF_R15 MIPS32_EF_R15
+#define EF_R16 MIPS32_EF_R16
+#define EF_R17 MIPS32_EF_R17
+#define EF_R18 MIPS32_EF_R18
+#define EF_R19 MIPS32_EF_R19
+#define EF_R20 MIPS32_EF_R20
+#define EF_R21 MIPS32_EF_R21
+#define EF_R22 MIPS32_EF_R22
+#define EF_R23 MIPS32_EF_R23
+#define EF_R24 MIPS32_EF_R24
+#define EF_R25 MIPS32_EF_R25
+#define EF_R26 MIPS32_EF_R26
+#define EF_R27 MIPS32_EF_R27
+#define EF_R28 MIPS32_EF_R28
+#define EF_R29 MIPS32_EF_R29
+#define EF_R30 MIPS32_EF_R30
+#define EF_R31 MIPS32_EF_R31
+#define EF_LO MIPS32_EF_LO
+#define EF_HI MIPS32_EF_HI
+#define EF_CP0_EPC MIPS32_EF_CP0_EPC
+#define EF_CP0_BADVADDR MIPS32_EF_CP0_BADVADDR
+#define EF_CP0_STATUS MIPS32_EF_CP0_STATUS
+#define EF_CP0_CAUSE MIPS32_EF_CP0_CAUSE
+#define EF_UNUSED0 MIPS32_EF_UNUSED0
+#define EF_SIZE MIPS32_EF_SIZE
+
+#elif defined(CONFIG_64BIT)
+
+#define EF_R0 MIPS64_EF_R0
+#define EF_R1 MIPS64_EF_R1
+#define EF_R2 MIPS64_EF_R2
+#define EF_R3 MIPS64_EF_R3
+#define EF_R4 MIPS64_EF_R4
+#define EF_R5 MIPS64_EF_R5
+#define EF_R6 MIPS64_EF_R6
+#define EF_R7 MIPS64_EF_R7
+#define EF_R8 MIPS64_EF_R8
+#define EF_R9 MIPS64_EF_R9
+#define EF_R10 MIPS64_EF_R10
+#define EF_R11 MIPS64_EF_R11
+#define EF_R12 MIPS64_EF_R12
+#define EF_R13 MIPS64_EF_R13
+#define EF_R14 MIPS64_EF_R14
+#define EF_R15 MIPS64_EF_R15
+#define EF_R16 MIPS64_EF_R16
+#define EF_R17 MIPS64_EF_R17
+#define EF_R18 MIPS64_EF_R18
+#define EF_R19 MIPS64_EF_R19
+#define EF_R20 MIPS64_EF_R20
+#define EF_R21 MIPS64_EF_R21
+#define EF_R22 MIPS64_EF_R22
+#define EF_R23 MIPS64_EF_R23
+#define EF_R24 MIPS64_EF_R24
+#define EF_R25 MIPS64_EF_R25
+#define EF_R26 MIPS64_EF_R26
+#define EF_R27 MIPS64_EF_R27
+#define EF_R28 MIPS64_EF_R28
+#define EF_R29 MIPS64_EF_R29
+#define EF_R30 MIPS64_EF_R30
+#define EF_R31 MIPS64_EF_R31
+#define EF_LO MIPS64_EF_LO
+#define EF_HI MIPS64_EF_HI
+#define EF_CP0_EPC MIPS64_EF_CP0_EPC
+#define EF_CP0_BADVADDR MIPS64_EF_CP0_BADVADDR
+#define EF_CP0_STATUS MIPS64_EF_CP0_STATUS
+#define EF_CP0_CAUSE MIPS64_EF_CP0_CAUSE
+#define EF_SIZE MIPS64_EF_SIZE

#endif /* CONFIG_64BIT */

diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 202e581..7fdf1de 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -58,12 +58,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];

#include <asm/processor.h>

-/*
- * When this file is selected, we are definitely running a 64bit kernel.
- * So using the right regs define in asm/reg.h
- */
-#define WANT_COMPAT_REG_H
-
/* These MUST be defined before elf.h gets included */
extern void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs);
#define ELF_CORE_COPY_REGS(_dest, _regs) elf32_core_copy_regs(_dest, _regs);
@@ -135,21 +129,21 @@ void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs)
{
int i;

- for (i = 0; i < EF_R0; i++)
+ for (i = 0; i < MIPS32_EF_R0; i++)
grp[i] = 0;
- grp[EF_R0] = 0;
+ grp[MIPS32_EF_R0] = 0;
for (i = 1; i <= 31; i++)
- grp[EF_R0 + i] = (elf_greg_t) regs->regs[i];
- grp[EF_R26] = 0;
- grp[EF_R27] = 0;
- grp[EF_LO] = (elf_greg_t) regs->lo;
- grp[EF_HI] = (elf_greg_t) regs->hi;
- grp[EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
- grp[EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
- grp[EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
- grp[EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
-#ifdef EF_UNUSED0
- grp[EF_UNUSED0] = 0;
+ grp[MIPS32_EF_R0 + i] = (elf_greg_t) regs->regs[i];
+ grp[MIPS32_EF_R26] = 0;
+ grp[MIPS32_EF_R27] = 0;
+ grp[MIPS32_EF_LO] = (elf_greg_t) regs->lo;
+ grp[MIPS32_EF_HI] = (elf_greg_t) regs->hi;
+ grp[MIPS32_EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
+ grp[MIPS32_EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
+ grp[MIPS32_EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
+ grp[MIPS32_EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
+#ifdef MIPS32_EF_UNUSED0
+ grp[MIPS32_EF_UNUSED0] = 0;
#endif
}

diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index 5b5ddb2..78f1843 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -255,11 +255,13 @@ static void __init gic_setup_intr(unsigned int intr, unsigned int cpu,

/* Setup Intr to Pin mapping */
if (pin & GIC_MAP_TO_NMI_MSK) {
+ int i;
+
GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin);
/* FIXME: hack to route NMI to all cpu's */
- for (cpu = 0; cpu < NR_CPUS; cpu += 32) {
+ for (i = 0; i < NR_CPUS; i += 32) {
GICWRITE(GIC_REG_ADDR(SHARED,
- GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)),
+ GIC_SH_MAP_TO_VPE_REG_OFF(intr, i)),
0xffffffff);
}
} else {
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index b52e1d2..e1d02d5 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -170,6 +170,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
__get_user(fregs[i], i + (__u64 __user *) data);

__get_user(child->thread.fpu.fcr31, data + 64);
+ child->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;

/* FIR may not be written. */

@@ -265,36 +266,160 @@ int ptrace_set_watch_regs(struct task_struct *child,

/* regset get/set implementations */

-static int gpr_get(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
+static int gpr32_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
{
struct pt_regs *regs = task_pt_regs(target);
+ u32 uregs[ELF_NGREG] = {};
+ unsigned i;

- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- regs, 0, sizeof(*regs));
+ for (i = MIPS32_EF_R1; i <= MIPS32_EF_R31; i++) {
+ /* k0/k1 are copied as zero. */
+ if (i == MIPS32_EF_R26 || i == MIPS32_EF_R27)
+ continue;
+
+ uregs[i] = regs->regs[i - MIPS32_EF_R0];
+ }
+
+ uregs[MIPS32_EF_LO] = regs->lo;
+ uregs[MIPS32_EF_HI] = regs->hi;
+ uregs[MIPS32_EF_CP0_EPC] = regs->cp0_epc;
+ uregs[MIPS32_EF_CP0_BADVADDR] = regs->cp0_badvaddr;
+ uregs[MIPS32_EF_CP0_STATUS] = regs->cp0_status;
+ uregs[MIPS32_EF_CP0_CAUSE] = regs->cp0_cause;
+
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0,
+ sizeof(uregs));
}

-static int gpr_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
+static int gpr32_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
{
- struct pt_regs newregs;
- int ret;
+ struct pt_regs *regs = task_pt_regs(target);
+ u32 uregs[ELF_NGREG];
+ unsigned start, num_regs, i;
+ int err;

- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &newregs,
- 0, sizeof(newregs));
- if (ret)
- return ret;
+ start = pos / sizeof(u32);
+ num_regs = count / sizeof(u32);
+
+ if (start + num_regs > ELF_NGREG)
+ return -EIO;

- *task_pt_regs(target) = newregs;
+ err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0,
+ sizeof(uregs));
+ if (err)
+ return err;
+
+ for (i = start; i < num_regs; i++) {
+ /*
+ * Cast all values to signed here so that if this is a 64-bit
+ * kernel, the supplied 32-bit values will be sign extended.
+ */
+ switch (i) {
+ case MIPS32_EF_R1 ... MIPS32_EF_R25:
+ /* k0/k1 are ignored. */
+ case MIPS32_EF_R28 ... MIPS32_EF_R31:
+ regs->regs[i - MIPS32_EF_R0] = (s32)uregs[i];
+ break;
+ case MIPS32_EF_LO:
+ regs->lo = (s32)uregs[i];
+ break;
+ case MIPS32_EF_HI:
+ regs->hi = (s32)uregs[i];
+ break;
+ case MIPS32_EF_CP0_EPC:
+ regs->cp0_epc = (s32)uregs[i];
+ break;
+ }
+ }

return 0;
}

+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
+static int gpr64_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct pt_regs *regs = task_pt_regs(target);
+ u64 uregs[ELF_NGREG] = {};
+ unsigned i;
+
+ for (i = MIPS64_EF_R1; i <= MIPS64_EF_R31; i++) {
+ /* k0/k1 are copied as zero. */
+ if (i == MIPS64_EF_R26 || i == MIPS64_EF_R27)
+ continue;
+
+ uregs[i] = regs->regs[i - MIPS64_EF_R0];
+ }
+
+ uregs[MIPS64_EF_LO] = regs->lo;
+ uregs[MIPS64_EF_HI] = regs->hi;
+ uregs[MIPS64_EF_CP0_EPC] = regs->cp0_epc;
+ uregs[MIPS64_EF_CP0_BADVADDR] = regs->cp0_badvaddr;
+ uregs[MIPS64_EF_CP0_STATUS] = regs->cp0_status;
+ uregs[MIPS64_EF_CP0_CAUSE] = regs->cp0_cause;
+
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0,
+ sizeof(uregs));
+}
+
+static int gpr64_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct pt_regs *regs = task_pt_regs(target);
+ u64 uregs[ELF_NGREG];
+ unsigned start, num_regs, i;
+ int err;
+
+ start = pos / sizeof(u64);
+ num_regs = count / sizeof(u64);
+
+ if (start + num_regs > ELF_NGREG)
+ return -EIO;
+
+ err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0,
+ sizeof(uregs));
+ if (err)
+ return err;
+
+ for (i = start; i < num_regs; i++) {
+ switch (i) {
+ case MIPS64_EF_R1 ... MIPS64_EF_R25:
+ /* k0/k1 are ignored. */
+ case MIPS64_EF_R28 ... MIPS64_EF_R31:
+ regs->regs[i - MIPS64_EF_R0] = uregs[i];
+ break;
+ case MIPS64_EF_LO:
+ regs->lo = uregs[i];
+ break;
+ case MIPS64_EF_HI:
+ regs->hi = uregs[i];
+ break;
+ case MIPS64_EF_CP0_EPC:
+ regs->cp0_epc = uregs[i];
+ break;
+ }
+ }
+
+ return 0;
+}
+
+#endif /* CONFIG_64BIT */
+
static int fpr_get(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
@@ -322,14 +447,16 @@ enum mips_regset {
REGSET_FPR,
};

+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
static const struct user_regset mips_regsets[] = {
[REGSET_GPR] = {
.core_note_type = NT_PRSTATUS,
.n = ELF_NGREG,
.size = sizeof(unsigned int),
.align = sizeof(unsigned int),
- .get = gpr_get,
- .set = gpr_set,
+ .get = gpr32_get,
+ .set = gpr32_set,
},
[REGSET_FPR] = {
.core_note_type = NT_PRFPREG,
@@ -349,14 +476,18 @@ static const struct user_regset_view user_mips_view = {
.n = ARRAY_SIZE(mips_regsets),
};

+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
static const struct user_regset mips64_regsets[] = {
[REGSET_GPR] = {
.core_note_type = NT_PRSTATUS,
.n = ELF_NGREG,
.size = sizeof(unsigned long),
.align = sizeof(unsigned long),
- .get = gpr_get,
- .set = gpr_set,
+ .get = gpr64_get,
+ .set = gpr64_set,
},
[REGSET_FPR] = {
.core_note_type = NT_PRFPREG,
@@ -369,25 +500,26 @@ static const struct user_regset mips64_regsets[] = {
};

static const struct user_regset_view user_mips64_view = {
- .name = "mips",
+ .name = "mips64",
.e_machine = ELF_ARCH,
.ei_osabi = ELF_OSABI,
.regsets = mips64_regsets,
- .n = ARRAY_SIZE(mips_regsets),
+ .n = ARRAY_SIZE(mips64_regsets),
};

+#endif /* CONFIG_64BIT */
+
const struct user_regset_view *task_user_regset_view(struct task_struct *task)
{
#ifdef CONFIG_32BIT
return &user_mips_view;
-#endif
-
+#else
#ifdef CONFIG_MIPS32_O32
- if (test_thread_flag(TIF_32BIT_REGS))
- return &user_mips_view;
+ if (test_tsk_thread_flag(task, TIF_32BIT_REGS))
+ return &user_mips_view;
#endif
-
return &user_mips64_view;
+#endif
}

long arch_ptrace(struct task_struct *child, long request,
@@ -587,7 +719,7 @@ long arch_ptrace(struct task_struct *child, long request,
break;
#endif
case FPC_CSR:
- child->thread.fpu.fcr31 = data;
+ child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X;
break;
case DSP_BASE ... DSP_BASE + 5: {
dspreg_t *dregs;
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index c369a5d..b897dde 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -605,7 +605,6 @@ static void emulate_load_store_insn(struct pt_regs *regs,
case sdc1_op:
die_if_kernel("Unaligned FP access in kernel code", regs);
BUG_ON(!used_math());
- BUG_ON(!is_fpu_owner());

lose_fpu(1); /* Save FPU state for the emulator. */
res = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 183f2b5..ec90a27 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1295,6 +1295,7 @@ static void build_r4000_tlb_refill_handler(void)
}
#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
uasm_l_tlb_huge_update(&l, p);
+ UASM_i_LW(&p, K0, 0, K1);
build_huge_update_entries(&p, htlb_info.huge_pte, K1);
build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random,
htlb_info.restore_scratch);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index ad3025d..f207868 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -57,10 +57,10 @@ struct machdep_calls {
void (*hpte_removebolted)(unsigned long ea,
int psize, int ssize);
void (*flush_hash_range)(unsigned long number, int local);
- void (*hugepage_invalidate)(struct mm_struct *mm,
+ void (*hugepage_invalidate)(unsigned long vsid,
+ unsigned long addr,
unsigned char *hpte_slot_array,
- unsigned long addr, int psize);
-
+ int psize, int ssize);
/* special for kexec, to be called in real mode, linear mapping is
* destroyed as well */
void (*hpte_clear_all)(void);
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index bc141c9..b26cc32 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -411,7 +411,7 @@ static inline char *get_hpte_slot_array(pmd_t *pmdp)
}

extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmdp);
+ pmd_t *pmdp, unsigned long old_pmd);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index d836d94..9ecede1 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -46,11 +46,31 @@
* in order to deal with 64K made of 4K HW pages. Thus we override the
* generic accessors and iterators here
*/
-#define __real_pte(e,p) ((real_pte_t) { \
- (e), (pte_val(e) & _PAGE_COMBO) ? \
- (pte_val(*((p) + PTRS_PER_PTE))) : 0 })
-#define __rpte_to_hidx(r,index) ((pte_val((r).pte) & _PAGE_COMBO) ? \
- (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf))
+#define __real_pte __real_pte
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
+{
+ real_pte_t rpte;
+
+ rpte.pte = pte;
+ rpte.hidx = 0;
+ if (pte_val(pte) & _PAGE_COMBO) {
+ /*
+ * Make sure we order the hidx load against the _PAGE_COMBO
+ * check. The store side ordering is done in __hash_page_4K
+ */
+ smp_rmb();
+ rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE));
+ }
+ return rpte;
+}
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+ if ((pte_val(rpte.pte) & _PAGE_COMBO))
+ return (rpte.hidx >> (index<<2)) & 0xf;
+ return (pte_val(rpte.pte) >> 12) & 0xf;
+}
+
#define __rpte_to_pte(r) ((r).pte)
#define __rpte_sub_valid(rpte, index) \
(pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index)))
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index 5efa97b..7a801b5 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -258,6 +258,8 @@ static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)

int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
{
+ int rc, idx;
+
switch (cmd) {
case H_ENTER:
return kvmppc_h_pr_enter(vcpu);
@@ -286,8 +288,11 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
break;
case H_RTAS:
if (list_empty(&vcpu->kvm->arch.rtas_tokens))
- return RESUME_HOST;
- if (kvmppc_rtas_hcall(vcpu))
+ break;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+ rc = kvmppc_rtas_hcall(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ if (rc)
break;
kvmppc_set_gpr(vcpu, 3, 0);
return EMULATE_DONE;
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 3ea26c2..838de8e 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -418,18 +418,18 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
local_irq_restore(flags);
}

-static void native_hugepage_invalidate(struct mm_struct *mm,
+static void native_hugepage_invalidate(unsigned long vsid,
+ unsigned long addr,
unsigned char *hpte_slot_array,
- unsigned long addr, int psize)
+ int psize, int ssize)
{
- int ssize = 0, i;
- int lock_tlbie;
+ int i;
struct hash_pte *hptep;
int actual_psize = MMU_PAGE_16M;
unsigned int max_hpte_count, valid;
unsigned long flags, s_addr = addr;
unsigned long hpte_v, want_v, shift;
- unsigned long hidx, vpn = 0, vsid, hash, slot;
+ unsigned long hidx, vpn = 0, hash, slot;

shift = mmu_psize_defs[psize].shift;
max_hpte_count = 1U << (PMD_SHIFT - shift);
@@ -443,15 +443,6 @@ static void native_hugepage_invalidate(struct mm_struct *mm,

/* get the vpn */
addr = s_addr + (i * (1ul << shift));
- if (!is_kernel_addr(addr)) {
- ssize = user_segment_size(addr);
- vsid = get_vsid(mm->context.id, addr, ssize);
- WARN_ON(vsid == 0);
- } else {
- vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
- ssize = mmu_kernel_ssize;
- }
-
vpn = hpt_vpn(addr, vsid, ssize);
hash = hpt_hash(vpn, shift, ssize);
if (hidx & _PTEIDX_SECONDARY)
@@ -471,22 +462,13 @@ static void native_hugepage_invalidate(struct mm_struct *mm,
else
/* Invalidate the hpte. NOTE: this also unlocks it */
hptep->v = 0;
+ /*
+ * We need to do tlb invalidate for all the address, tlbie
+ * instruction compares entry_VA in tlb with the VA specified
+ * here
+ */
+ tlbie(vpn, psize, actual_psize, ssize, 0);
}
- /*
- * Since this is a hugepage, we just need a single tlbie.
- * use the last vpn.
- */
- lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
- if (lock_tlbie)
- raw_spin_lock(&native_tlbie_lock);
-
- asm volatile("ptesync":::"memory");
- __tlbie(vpn, psize, actual_psize, ssize);
- asm volatile("eieio; tlbsync; ptesync":::"memory");
-
- if (lock_tlbie)
- raw_spin_unlock(&native_tlbie_lock);
-
local_irq_restore(flags);
}

diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 34de9e0..7d86c86 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -18,6 +18,57 @@
#include <linux/mm.h>
#include <asm/machdep.h>

+static void invalidate_old_hpte(unsigned long vsid, unsigned long addr,
+ pmd_t *pmdp, unsigned int psize, int ssize)
+{
+ int i, max_hpte_count, valid;
+ unsigned long s_addr;
+ unsigned char *hpte_slot_array;
+ unsigned long hidx, shift, vpn, hash, slot;
+
+ s_addr = addr & HPAGE_PMD_MASK;
+ hpte_slot_array = get_hpte_slot_array(pmdp);
+ /*
+ * IF we try to do a HUGE PTE update after a withdraw is done.
+ * we will find the below NULL. This happens when we do
+ * split_huge_page_pmd
+ */
+ if (!hpte_slot_array)
+ return;
+
+ if (ppc_md.hugepage_invalidate)
+ return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+ psize, ssize);
+ /*
+ * No bluk hpte removal support, invalidate each entry
+ */
+ shift = mmu_psize_defs[psize].shift;
+ max_hpte_count = HPAGE_PMD_SIZE >> shift;
+ for (i = 0; i < max_hpte_count; i++) {
+ /*
+ * 8 bits per each hpte entries
+ * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+ */
+ valid = hpte_valid(hpte_slot_array, i);
+ if (!valid)
+ continue;
+ hidx = hpte_hash_index(hpte_slot_array, i);
+
+ /* get the vpn */
+ addr = s_addr + (i * (1ul << shift));
+ vpn = hpt_vpn(addr, vsid, ssize);
+ hash = hpt_hash(vpn, shift, ssize);
+ if (hidx & _PTEIDX_SECONDARY)
+ hash = ~hash;
+
+ slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+ slot += hidx & _PTEIDX_GROUP_IX;
+ ppc_md.hpte_invalidate(slot, vpn, psize,
+ MMU_PAGE_16M, ssize, 0);
+ }
+}
+
+
int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
pmd_t *pmdp, unsigned long trap, int local, int ssize,
unsigned int psize)
@@ -33,7 +84,9 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
* atomically mark the linux large page PMD busy and dirty
*/
do {
- old_pmd = pmd_val(*pmdp);
+ pmd_t pmd = ACCESS_ONCE(*pmdp);
+
+ old_pmd = pmd_val(pmd);
/* If PMD busy, retry the access */
if (unlikely(old_pmd & _PAGE_BUSY))
return 0;
@@ -85,6 +138,15 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
vpn = hpt_vpn(ea, vsid, ssize);
hash = hpt_hash(vpn, shift, ssize);
hpte_slot_array = get_hpte_slot_array(pmdp);
+ if (psize == MMU_PAGE_4K) {
+ /*
+ * invalidate the old hpte entry if we have that mapped via 64K
+ * base page size. This is because demote_segment won't flush
+ * hash page table entries.
+ */
+ if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
+ invalidate_old_hpte(vsid, ea, pmdp, MMU_PAGE_64K, ssize);
+ }

valid = hpte_valid(hpte_slot_array, index);
if (valid) {
@@ -107,11 +169,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
* safely update this here.
*/
valid = 0;
- new_pmd &= ~_PAGE_HPTEFLAGS;
hpte_slot_array[index] = 0;
- } else
- /* clear the busy bits and set the hash pte bits */
- new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+ }
}

if (!valid) {
@@ -119,15 +178,13 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,

/* insert new entry */
pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT;
-repeat:
- hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
-
- /* clear the busy bits and set the hash pte bits */
- new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+ new_pmd |= _PAGE_HASHPTE;

/* Add in WIMG bits */
rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
_PAGE_COHERENT | _PAGE_GUARDED));
+repeat:
+ hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;

/* Insert into the hash table, primary slot */
slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
@@ -168,8 +225,17 @@ repeat:
mark_hpte_slot_valid(hpte_slot_array, index, slot);
}
/*
- * No need to use ldarx/stdcx here
+ * Mark the pte with _PAGE_COMBO, if we are trying to hash it with
+ * base page size 4k.
+ */
+ if (psize == MMU_PAGE_4K)
+ new_pmd |= _PAGE_COMBO;
+ /*
+ * The hpte valid is stored in the pgtable whose address is in the
+ * second half of the PMD. Order this against clearing of the busy bit in
+ * huge pmd.
*/
+ smp_wmb();
*pmdp = __pmd(new_pmd & ~_PAGE_BUSY);
return 0;
}
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 6847d50..c752d50 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -588,8 +588,8 @@ static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action,
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
unmap_cpu_from_node(lcpu);
- break;
ret = NOTIFY_OK;
+ break;
#endif
}
return ret;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 9d95786..3e575db 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -525,7 +525,7 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
*pmdp = __pmd(old & ~clr);
#endif
if (old & _PAGE_HASHPTE)
- hpte_do_hugepage_flush(mm, addr, pmdp);
+ hpte_do_hugepage_flush(mm, addr, pmdp, old);
return old;
}

@@ -632,7 +632,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma,
if (!(old & _PAGE_SPLITTING)) {
/* We need to flush the hpte */
if (old & _PAGE_HASHPTE)
- hpte_do_hugepage_flush(vma->vm_mm, address, pmdp);
+ hpte_do_hugepage_flush(vma->vm_mm, address, pmdp, old);
}
}

@@ -705,7 +705,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
* neesd to be flushed.
*/
void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmdp)
+ pmd_t *pmdp, unsigned long old_pmd)
{
int ssize, i;
unsigned long s_addr;
@@ -727,12 +727,29 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
if (!hpte_slot_array)
return;

- /* get the base page size */
+ /* get the base page size,vsid and segment size */
+#ifdef CONFIG_DEBUG_VM
psize = get_slice_psize(mm, s_addr);
+ BUG_ON(psize == MMU_PAGE_16M);
+#endif
+ if (old_pmd & _PAGE_COMBO)
+ psize = MMU_PAGE_4K;
+ else
+ psize = MMU_PAGE_64K;
+
+ if (!is_kernel_addr(s_addr)) {
+ ssize = user_segment_size(s_addr);
+ vsid = get_vsid(mm->context.id, s_addr, ssize);
+ WARN_ON(vsid == 0);
+ } else {
+ vsid = get_kernel_vsid(s_addr, mmu_kernel_ssize);
+ ssize = mmu_kernel_ssize;
+ }

if (ppc_md.hugepage_invalidate)
- return ppc_md.hugepage_invalidate(mm, hpte_slot_array,
- s_addr, psize);
+ return ppc_md.hugepage_invalidate(vsid, s_addr,
+ hpte_slot_array,
+ psize, ssize);
/*
* No bluk hpte removal support, invalidate each entry
*/
@@ -750,15 +767,6 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,

/* get the vpn */
addr = s_addr + (i * (1ul << shift));
- if (!is_kernel_addr(addr)) {
- ssize = user_segment_size(addr);
- vsid = get_vsid(mm->context.id, addr, ssize);
- WARN_ON(vsid == 0);
- } else {
- vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
- ssize = mmu_kernel_ssize;
- }
-
vpn = hpt_vpn(addr, vsid, ssize);
hash = hpt_hash(vpn, shift, ssize);
if (hidx & _PTEIDX_SECONDARY)
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 36e44b4..c66e445 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -217,7 +217,7 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
if (!(pte & _PAGE_HASHPTE))
continue;
if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte)))
- hpte_do_hugepage_flush(mm, start, (pmd_t *)pte);
+ hpte_do_hugepage_flush(mm, start, (pmd_t *)ptep, pte);
else
hpte_need_flush(mm, start, ptep, pte, 0);
}
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 9590dbb..b97b895 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -164,7 +164,7 @@ static inline int pseries_remove_memblock(unsigned long base,
}
static inline int pseries_remove_memory(struct device_node *np)
{
- return -EOPNOTSUPP;
+ return 0;
}
#endif /* CONFIG_MEMORY_HOTREMOVE */

diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 4fca3de..bf410d9 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -429,16 +429,17 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
}

-static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,
- unsigned char *hpte_slot_array,
- unsigned long addr, int psize)
+static void pSeries_lpar_hugepage_invalidate(unsigned long vsid,
+ unsigned long addr,
+ unsigned char *hpte_slot_array,
+ int psize, int ssize)
{
- int ssize = 0, i, index = 0;
+ int i, index = 0;
unsigned long s_addr = addr;
unsigned int max_hpte_count, valid;
unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH];
unsigned long slot_array[PPC64_HUGE_HPTE_BATCH];
- unsigned long shift, hidx, vpn = 0, vsid, hash, slot;
+ unsigned long shift, hidx, vpn = 0, hash, slot;

shift = mmu_psize_defs[psize].shift;
max_hpte_count = 1U << (PMD_SHIFT - shift);
@@ -451,15 +452,6 @@ static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,

/* get the vpn */
addr = s_addr + (i * (1ul << shift));
- if (!is_kernel_addr(addr)) {
- ssize = user_segment_size(addr);
- vsid = get_vsid(mm->context.id, addr, ssize);
- WARN_ON(vsid == 0);
- } else {
- vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
- ssize = mmu_kernel_ssize;
- }
-
vpn = hpt_vpn(addr, vsid, ssize);
hash = hpt_hash(vpn, shift, ssize);
if (hidx & _PTEIDX_SECONDARY)
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index efe6137..e68922b 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -118,10 +118,10 @@ int remove_phb_dynamic(struct pci_controller *phb)
}
}

- /* Unregister the bridge device from sysfs and remove the PCI bus */
- device_unregister(b->bridge);
+ /* Remove the PCI bus and unregister the bridge device from sysfs */
phb->bus = NULL;
pci_remove_bus(b);
+ device_unregister(b->bridge);

/* Now release the IO resource */
if (res->flags & IORESOURCE_IO)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index c8d8283..8993c96 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -93,6 +93,7 @@ config S390
select ARCH_INLINE_WRITE_UNLOCK_IRQ
select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
select ARCH_SAVE_PAGE_KEYS if HIBERNATION
+ select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_USE_CMPXCHG_LOCKREF
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_EXTABLE_SORT
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 0f9e945..1a49ffd 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -24,7 +24,8 @@

/* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
* The page copy blockops can use 0x6000000 to 0x8000000.
- * The TSB is mapped in the 0x8000000 to 0xa000000 range.
+ * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range.
+ * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range.
* The PROM resides in an area spanning 0xf0000000 to 0x100000000.
* The vmalloc area spans 0x100000000 to 0x200000000.
* Since modules need to be in the lowest 32-bits of the address space,
@@ -33,7 +34,8 @@
* 0x400000000.
*/
#define TLBTEMP_BASE _AC(0x0000000006000000,UL)
-#define TSBMAP_BASE _AC(0x0000000008000000,UL)
+#define TSBMAP_8K_BASE _AC(0x0000000008000000,UL)
+#define TSBMAP_4M_BASE _AC(0x0000000008400000,UL)
#define MODULES_VADDR _AC(0x0000000010000000,UL)
#define MODULES_LEN _AC(0x00000000e0000000,UL)
#define MODULES_END _AC(0x00000000f0000000,UL)
@@ -71,6 +73,23 @@

#include <linux/sched.h>

+extern unsigned long sparc64_valid_addr_bitmap[];
+
+/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
+static inline bool __kern_addr_valid(unsigned long paddr)
+{
+ if ((paddr >> MAX_PHYS_ADDRESS_BITS) != 0UL)
+ return false;
+ return test_bit(paddr >> ILOG2_4MB, sparc64_valid_addr_bitmap);
+}
+
+static inline bool kern_addr_valid(unsigned long addr)
+{
+ unsigned long paddr = __pa(addr);
+
+ return __kern_addr_valid(paddr);
+}
+
/* Entries per page directory level. */
#define PTRS_PER_PTE (1UL << (PAGE_SHIFT-3))
#define PTRS_PER_PMD (1UL << PMD_BITS)
@@ -79,9 +98,12 @@
/* Kernel has a separate 44bit address space. */
#define FIRST_USER_ADDRESS 0

-#define pte_ERROR(e) __builtin_trap()
-#define pmd_ERROR(e) __builtin_trap()
-#define pgd_ERROR(e) __builtin_trap()
+#define pmd_ERROR(e) \
+ pr_err("%s:%d: bad pmd %p(%016lx) seen at (%pS)\n", \
+ __FILE__, __LINE__, &(e), pmd_val(e), __builtin_return_address(0))
+#define pgd_ERROR(e) \
+ pr_err("%s:%d: bad pgd %p(%016lx) seen at (%pS)\n", \
+ __FILE__, __LINE__, &(e), pgd_val(e), __builtin_return_address(0))

#endif /* !(__ASSEMBLY__) */

@@ -258,8 +280,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
{
unsigned long mask, tmp;

- /* SUN4U: 0x600307ffffffecb8 (negated == 0x9ffcf80000001347)
- * SUN4V: 0x30ffffffffffee17 (negated == 0xcf000000000011e8)
+ /* SUN4U: 0x630107ffffffec38 (negated == 0x9cfef800000013c7)
+ * SUN4V: 0x33ffffffffffee07 (negated == 0xcc000000000011f8)
*
* Even if we use negation tricks the result is still a 6
* instruction sequence, so don't try to play fancy and just
@@ -289,10 +311,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
" .previous\n"
: "=r" (mask), "=r" (tmp)
: "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
- _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_PRESENT_4U |
+ _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U |
_PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U),
"i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
- _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_PRESENT_4V |
+ _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V |
_PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V));

return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
@@ -633,7 +655,7 @@ static inline unsigned long pmd_large(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));

- return (pte_val(pte) & _PAGE_PMD_HUGE) && pte_present(pte);
+ return pte_val(pte) & _PAGE_PMD_HUGE;
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -719,20 +741,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
return __pmd(pte_val(pte));
}

-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
-{
- unsigned long mask;
-
- if (tlb_type == hypervisor)
- mask = _PAGE_PRESENT_4V;
- else
- mask = _PAGE_PRESENT_4U;
-
- pmd_val(pmd) &= ~mask;
-
- return pmd;
-}
-
static inline pmd_t pmd_mksplitting(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
@@ -757,6 +765,20 @@ static inline int pmd_present(pmd_t pmd)

#define pmd_none(pmd) (!pmd_val(pmd))

+/* pmd_bad() is only called on non-trans-huge PMDs. Our encoding is
+ * very simple, it's just the physical address. PTE tables are of
+ * size PAGE_SIZE so make sure the sub-PAGE_SIZE bits are clear and
+ * the top bits outside of the range of any physical address size we
+ * support are clear as well. We also validate the physical itself.
+ */
+#define pmd_bad(pmd) ((pmd_val(pmd) & ~PAGE_MASK) || \
+ !__kern_addr_valid(pmd_val(pmd)))
+
+#define pud_none(pud) (!pud_val(pud))
+
+#define pud_bad(pud) ((pud_val(pud) & ~PAGE_MASK) || \
+ !__kern_addr_valid(pud_val(pud)))
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd);
@@ -790,10 +812,7 @@ static inline unsigned long __pmd_page(pmd_t pmd)
#define pud_page_vaddr(pud) \
((unsigned long) __va(pud_val(pud)))
#define pud_page(pud) virt_to_page((void *)pud_page_vaddr(pud))
-#define pmd_bad(pmd) (0)
#define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0UL)
-#define pud_none(pud) (!pud_val(pud))
-#define pud_bad(pud) (0)
#define pud_present(pud) (pud_val(pud) != 0U)
#define pud_clear(pudp) (pud_val(*(pudp)) = 0UL)

@@ -893,6 +912,10 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd);

+#define __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmdp);
+
#define __HAVE_ARCH_PGTABLE_DEPOSIT
extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
pgtable_t pgtable);
@@ -919,18 +942,6 @@ extern unsigned long pte_file(pte_t);
extern pte_t pgoff_to_pte(unsigned long);
#define PTE_FILE_MAX_BITS (64UL - PAGE_SHIFT - 1UL)

-extern unsigned long sparc64_valid_addr_bitmap[];
-
-/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
-static inline bool kern_addr_valid(unsigned long addr)
-{
- unsigned long paddr = __pa(addr);
-
- if ((paddr >> 41UL) != 0UL)
- return false;
- return test_bit(paddr >> 22, sparc64_valid_addr_bitmap);
-}
-
extern int page_in_phys_avail(unsigned long paddr);

/*
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index 3c3c89f..7f9bab2 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -34,6 +34,8 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
{
}

+void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE

extern void flush_tlb_pending(void);
@@ -48,11 +50,6 @@ extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);

#ifndef CONFIG_SMP

-#define flush_tlb_kernel_range(start,end) \
-do { flush_tsb_kernel_range(start,end); \
- __flush_tlb_kernel_range(start,end); \
-} while (0)
-
static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
{
__flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
@@ -63,11 +60,6 @@ static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vad
extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);

-#define flush_tlb_kernel_range(start, end) \
-do { flush_tsb_kernel_range(start,end); \
- smp_flush_tlb_kernel_range(start, end); \
-} while (0)
-
#define global_flush_tlb_page(mm, vaddr) \
smp_flush_tlb_page(mm, vaddr)

diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index 2230f80..90916f9 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -171,7 +171,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
andcc REG1, REG2, %g0; \
be,pt %xcc, 700f; \
sethi %hi(4 * 1024 * 1024), REG2; \
- andn REG1, REG2, REG1; \
+ brgez,pn REG1, FAIL_LABEL; \
+ andn REG1, REG2, REG1; \
and VADDR, REG2, REG2; \
brlz,pt REG1, PTE_LABEL; \
or REG1, REG2, REG1; \
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 26b706a..452f04f 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -282,8 +282,8 @@ sun4v_chip_type:
stx %l2, [%l4 + 0x0]
ldx [%sp + 2047 + 128 + 0x50], %l3 ! physaddr low
/* 4MB align */
- srlx %l3, 22, %l3
- sllx %l3, 22, %l3
+ srlx %l3, ILOG2_4MB, %l3
+ sllx %l3, ILOG2_4MB, %l3
stx %l3, [%l4 + 0x8]

/* Leave service as-is, "call-method" */
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 542e96a..605d492 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -277,7 +277,7 @@ kvmap_dtlb_load:
#ifdef CONFIG_SPARSEMEM_VMEMMAP
kvmap_vmemmap:
sub %g4, %g5, %g5
- srlx %g5, 22, %g5
+ srlx %g5, ILOG2_4MB, %g5
sethi %hi(vmemmap_table), %g1
sllx %g5, 3, %g5
or %g1, %lo(vmemmap_table), %g1
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index e01d75d..66dacd5 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1336,7 +1336,7 @@ int ldc_connect(struct ldc_channel *lp)
if (!(lp->flags & LDC_FLAG_ALLOCED_QUEUES) ||
!(lp->flags & LDC_FLAG_REGISTERED_QUEUES) ||
lp->hs_state != LDC_HS_OPEN)
- err = -EINVAL;
+ err = ((lp->hs_state > LDC_HS_OPEN) ? 0 : -EINVAL);
else
err = start_handshake(lp);

diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b085311..8416d7f 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -151,7 +151,7 @@ void cpu_panic(void)
#define NUM_ROUNDS 64 /* magic value */
#define NUM_ITERS 5 /* likewise */

-static DEFINE_SPINLOCK(itc_sync_lock);
+static DEFINE_RAW_SPINLOCK(itc_sync_lock);
static unsigned long go[SLAVE + 1];

#define DEBUG_TICK_SYNC 0
@@ -259,7 +259,7 @@ static void smp_synchronize_one_tick(int cpu)
go[MASTER] = 0;
membar_safe("#StoreLoad");

- spin_lock_irqsave(&itc_sync_lock, flags);
+ raw_spin_lock_irqsave(&itc_sync_lock, flags);
{
for (i = 0; i < NUM_ROUNDS*NUM_ITERS; i++) {
while (!go[MASTER])
@@ -270,7 +270,7 @@ static void smp_synchronize_one_tick(int cpu)
membar_safe("#StoreLoad");
}
}
- spin_unlock_irqrestore(&itc_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&itc_sync_lock, flags);
}

#if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU)
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index f7c72b6..d066eb1 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -44,7 +44,7 @@ SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1)
SIGN1(sys32_io_submit, compat_sys_io_submit, %o1)
SIGN1(sys32_mq_open, compat_sys_mq_open, %o1)
SIGN1(sys32_select, compat_sys_select, %o0)
-SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5)
+SIGN1(sys32_futex, compat_sys_futex, %o1)
SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0)
SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0)
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 3c1a7cb..35ab8b6 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -166,17 +166,23 @@ static unsigned long *fetch_reg_addr(unsigned int reg, struct pt_regs *regs)
unsigned long compute_effective_address(struct pt_regs *regs,
unsigned int insn, unsigned int rd)
{
+ int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
unsigned int rs1 = (insn >> 14) & 0x1f;
unsigned int rs2 = insn & 0x1f;
- int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
+ unsigned long addr;

if (insn & 0x2000) {
maybe_flush_windows(rs1, 0, rd, from_kernel);
- return (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
+ addr = (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
} else {
maybe_flush_windows(rs1, rs2, rd, from_kernel);
- return (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
+ addr = (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
}
+
+ if (!from_kernel && test_thread_flag(TIF_32BIT))
+ addr &= 0xffffffff;
+
+ return addr;
}

/* This is just to make gcc think die_if_kernel does return... */
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 2c20ad6..30eee6e 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -236,6 +236,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
*/
VISEntryHalf

+ membar #Sync
alignaddr %o1, %g0, %g0

add %o1, (64 - 1), %o4
diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c
index aa4d55b..5ce8f2f 100644
--- a/arch/sparc/math-emu/math_32.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -499,7 +499,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs)
case 0: fsr = *pfsr;
if (IR == -1) IR = 2;
/* fcc is always fcc0 */
- fsr &= ~0xc00; fsr |= (IR << 10); break;
+ fsr &= ~0xc00; fsr |= (IR << 10);
*pfsr = fsr;
break;
case 1: rd->s = IR; break;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 69bb818..4ced3fc 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -96,38 +96,51 @@ static unsigned int get_user_insn(unsigned long tpc)
pte_t *ptep, pte;
unsigned long pa;
u32 insn = 0;
- unsigned long pstate;

- if (pgd_none(*pgdp))
- goto outret;
+ if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp)))
+ goto out;
pudp = pud_offset(pgdp, tpc);
- if (pud_none(*pudp))
- goto outret;
- pmdp = pmd_offset(pudp, tpc);
- if (pmd_none(*pmdp))
- goto outret;
+ if (pud_none(*pudp) || unlikely(pud_bad(*pudp)))
+ goto out;

/* This disables preemption for us as well. */
- __asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
- __asm__ __volatile__("wrpr %0, %1, %%pstate"
- : : "r" (pstate), "i" (PSTATE_IE));
- ptep = pte_offset_map(pmdp, tpc);
- pte = *ptep;
- if (!pte_present(pte))
- goto out;
+ local_irq_disable();
+
+ pmdp = pmd_offset(pudp, tpc);
+ if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
+ goto out_irq_enable;

- pa = (pte_pfn(pte) << PAGE_SHIFT);
- pa += (tpc & ~PAGE_MASK);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (pmd_trans_huge(*pmdp)) {
+ if (pmd_trans_splitting(*pmdp))
+ goto out_irq_enable;

- /* Use phys bypass so we don't pollute dtlb/dcache. */
- __asm__ __volatile__("lduwa [%1] %2, %0"
- : "=r" (insn)
- : "r" (pa), "i" (ASI_PHYS_USE_EC));
+ pa = pmd_pfn(*pmdp) << PAGE_SHIFT;
+ pa += tpc & ~HPAGE_MASK;

+ /* Use phys bypass so we don't pollute dtlb/dcache. */
+ __asm__ __volatile__("lduwa [%1] %2, %0"
+ : "=r" (insn)
+ : "r" (pa), "i" (ASI_PHYS_USE_EC));
+ } else
+#endif
+ {
+ ptep = pte_offset_map(pmdp, tpc);
+ pte = *ptep;
+ if (pte_present(pte)) {
+ pa = (pte_pfn(pte) << PAGE_SHIFT);
+ pa += (tpc & ~PAGE_MASK);
+
+ /* Use phys bypass so we don't pollute dtlb/dcache. */
+ __asm__ __volatile__("lduwa [%1] %2, %0"
+ : "=r" (insn)
+ : "r" (pa), "i" (ASI_PHYS_USE_EC));
+ }
+ pte_unmap(ptep);
+ }
+out_irq_enable:
+ local_irq_enable();
out:
- pte_unmap(ptep);
- __asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate));
-outret:
return insn;
}

@@ -153,7 +166,8 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
}

static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
- unsigned int insn, int fault_code)
+ unsigned long fault_addr, unsigned int insn,
+ int fault_code)
{
unsigned long addr;
siginfo_t info;
@@ -161,10 +175,18 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
info.si_code = code;
info.si_signo = sig;
info.si_errno = 0;
- if (fault_code & FAULT_CODE_ITLB)
+ if (fault_code & FAULT_CODE_ITLB) {
addr = regs->tpc;
- else
- addr = compute_effective_address(regs, insn, 0);
+ } else {
+ /* If we were able to probe the faulting instruction, use it
+ * to compute a precise fault address. Otherwise use the fault
+ * time provided address which may only have page granularity.
+ */
+ if (insn)
+ addr = compute_effective_address(regs, insn, 0);
+ else
+ addr = fault_addr;
+ }
info.si_addr = (void __user *) addr;
info.si_trapno = 0;

@@ -239,7 +261,7 @@ static void __kprobes do_kernel_fault(struct pt_regs *regs, int si_code,
/* The si_code was set to make clear whether
* this was a SEGV_MAPERR or SEGV_ACCERR fault.
*/
- do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code);
+ do_fault_siginfo(si_code, SIGSEGV, regs, address, insn, fault_code);
return;
}

@@ -259,18 +281,6 @@ static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs)
show_regs(regs);
}

-static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs,
- unsigned long addr)
-{
- static int times;
-
- if (times++ < 10)
- printk(KERN_ERR "FAULT[%s:%d]: 32-bit process "
- "reports 64-bit fault address [%lx]\n",
- current->comm, current->pid, addr);
- show_regs(regs);
-}
-
asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
{
enum ctx_state prev_state = exception_enter();
@@ -300,10 +310,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
goto intr_or_no_mm;
}
}
- if (unlikely((address >> 32) != 0)) {
- bogus_32bit_fault_address(regs, address);
+ if (unlikely((address >> 32) != 0))
goto intr_or_no_mm;
- }
}

if (regs->tstate & TSTATE_PRIV) {
@@ -525,7 +533,7 @@ do_sigbus:
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
- do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code);
+ do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, address, insn, fault_code);

/* Kernel mode? Handle exceptions or die */
if (regs->tstate & TSTATE_PRIV)
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index c4d3da6..1aed043 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -73,7 +73,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
struct page *head, *page, *tail;
int refs;

- if (!pmd_large(pmd))
+ if (!(pmd_val(pmd) & _PAGE_VALID))
return 0;

if (write && !pmd_write(pmd))
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 5322e53..e275cde 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -350,6 +350,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *

mm = vma->vm_mm;

+ /* Don't insert a non-valid PTE into the TSB, we'll deadlock. */
+ if (!pte_accessible(mm, pte))
+ return;
+
spin_lock_irqsave(&mm->context.lock, flags);

#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -588,7 +592,7 @@ static void __init remap_kernel(void)
int i, tlb_ent = sparc64_highest_locked_tlbent();

tte_vaddr = (unsigned long) KERNBASE;
- phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
+ phys_page = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB;
tte_data = kern_large_tte(phys_page);

kern_locked_tte_data = tte_data;
@@ -1880,7 +1884,7 @@ void __init paging_init(void)

BUILD_BUG_ON(NR_CPUS > 4096);

- kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
+ kern_base = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB;
kern_size = (unsigned long)&_end - (unsigned long)KERNBASE;

/* Invalidate both kernel TSBs. */
@@ -1936,7 +1940,7 @@ void __init paging_init(void)
shift = kern_base + PAGE_OFFSET - ((unsigned long)KERNBASE);

real_end = (unsigned long)_end;
- num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << 22);
+ num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << ILOG2_4MB);
printk("Kernel: Using %d locked TLB entries for main kernel image.\n",
num_kernel_image_mappings);

@@ -2093,7 +2097,7 @@ static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap)

if (new_start <= old_start &&
new_end >= (old_start + PAGE_SIZE)) {
- set_bit(old_start >> 22, bitmap);
+ set_bit(old_start >> ILOG2_4MB, bitmap);
goto do_next_page;
}
}
@@ -2142,7 +2146,7 @@ void __init mem_init(void)
addr = PAGE_OFFSET + kern_base;
last = PAGE_ALIGN(kern_size) + addr;
while (addr < last) {
- set_bit(__pa(addr) >> 22, sparc64_valid_addr_bitmap);
+ set_bit(__pa(addr) >> ILOG2_4MB, sparc64_valid_addr_bitmap);
addr += PAGE_SIZE;
}

@@ -2266,7 +2270,7 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
void *block;

if (!(*vmem_pp & _PAGE_VALID)) {
- block = vmemmap_alloc_block(1UL << 22, node);
+ block = vmemmap_alloc_block(1UL << ILOG2_4MB, node);
if (!block)
return -ENOMEM;

@@ -2613,6 +2617,10 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,

pte = pmd_val(entry);

+ /* Don't insert a non-valid PMD into the TSB, we'll deadlock. */
+ if (!(pte & _PAGE_VALID))
+ return;
+
/* We are fabricating 8MB pages using 4MB real hw pages. */
pte |= (addr & (1UL << REAL_HPAGE_SHIFT));

@@ -2693,3 +2701,26 @@ void hugetlb_setup(struct pt_regs *regs)
}
}
#endif
+
+#ifdef CONFIG_SMP
+#define do_flush_tlb_kernel_range smp_flush_tlb_kernel_range
+#else
+#define do_flush_tlb_kernel_range __flush_tlb_kernel_range
+#endif
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+ if (start < HI_OBP_ADDRESS && end > LOW_OBP_ADDRESS) {
+ if (start < LOW_OBP_ADDRESS) {
+ flush_tsb_kernel_range(start, LOW_OBP_ADDRESS);
+ do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS);
+ }
+ if (end > HI_OBP_ADDRESS) {
+ flush_tsb_kernel_range(end, HI_OBP_ADDRESS);
+ do_flush_tlb_kernel_range(end, HI_OBP_ADDRESS);
+ }
+ } else {
+ flush_tsb_kernel_range(start, end);
+ do_flush_tlb_kernel_range(start, end);
+ }
+}
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index ad3bf4b..28ae593 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -135,7 +135,7 @@ no_cache_flush:

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
- pmd_t pmd, bool exec)
+ pmd_t pmd)
{
unsigned long end;
pte_t *pte;
@@ -143,8 +143,11 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
pte = pte_offset_map(&pmd, vaddr);
end = vaddr + HPAGE_SIZE;
while (vaddr < end) {
- if (pte_val(*pte) & _PAGE_VALID)
+ if (pte_val(*pte) & _PAGE_VALID) {
+ bool exec = pte_exec(*pte);
+
tlb_batch_add_one(mm, vaddr, exec);
+ }
pte++;
vaddr += PAGE_SIZE;
}
@@ -178,19 +181,30 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
}

if (!pmd_none(orig)) {
- pte_t orig_pte = __pte(pmd_val(orig));
- bool exec = pte_exec(orig_pte);
-
addr &= HPAGE_MASK;
if (pmd_trans_huge(orig)) {
+ pte_t orig_pte = __pte(pmd_val(orig));
+ bool exec = pte_exec(orig_pte);
+
tlb_batch_add_one(mm, addr, exec);
tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec);
} else {
- tlb_batch_pmd_scan(mm, addr, orig, exec);
+ tlb_batch_pmd_scan(mm, addr, orig);
}
}
}

+void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmdp)
+{
+ pmd_t entry = *pmdp;
+
+ pmd_val(entry) &= ~_PAGE_VALID;
+
+ set_pmd_at(vma->vm_mm, address, pmdp, entry);
+ flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+}
+
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
pgtable_t pgtable)
{
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 3b3a360..10a69f4 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -133,7 +133,19 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
mm->context.tsb_block[tsb_idx].tsb_nentries =
tsb_bytes / sizeof(struct tsb);

- base = TSBMAP_BASE;
+ switch (tsb_idx) {
+ case MM_TSB_BASE:
+ base = TSBMAP_8K_BASE;
+ break;
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+ case MM_TSB_HUGE:
+ base = TSBMAP_4M_BASE;
+ break;
+#endif
+ default:
+ BUG();
+ }
+
tte = pgprot_val(PAGE_KERNEL_LOCKED);
tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb);
BUG_ON(tsb_paddr & (tsb_bytes - 1UL));
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9562fc3..03e74b3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -978,10 +978,27 @@ config VM86
default y
depends on X86_32
---help---
- This option is required by programs like DOSEMU to run 16-bit legacy
- code on X86 processors. It also may be needed by software like
- XFree86 to initialize some video cards via BIOS. Disabling this
- option saves about 6k.
+ This option is required by programs like DOSEMU to run
+ 16-bit real mode legacy code on x86 processors. It also may
+ be needed by software like XFree86 to initialize some video
+ cards via BIOS. Disabling this option saves about 6K.
+
+config X86_16BIT
+ bool "Enable support for 16-bit segments" if EXPERT
+ default y
+ ---help---
+ This option is required by programs like Wine to run 16-bit
+ protected mode legacy code on x86 processors. Disabling
+ this option saves about 300 bytes on i386, or around 6K text
+ plus 16K runtime memory on x86-64,
+
+config X86_ESPFIX32
+ def_bool y
+ depends on X86_16BIT && X86_32
+
+config X86_ESPFIX64
+ def_bool y
+ depends on X86_16BIT && X86_64

config TOSHIBA
tristate "Toshiba Laptop support"
@@ -1596,6 +1613,7 @@ config EFI
config EFI_STUB
bool "EFI stub support"
depends on EFI
+ select RELOCATABLE
---help---
This kernel feature allows a bzImage to be loaded directly
by EFI firmware without the use of a bootloader.
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
new file mode 100644
index 0000000..99efebb
--- /dev/null
+++ b/arch/x86/include/asm/espfix.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_ESPFIX_H
+#define _ASM_X86_ESPFIX_H
+
+#ifdef CONFIG_X86_64
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf8..0a8b519 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void)

#define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */

-#define INTERRUPT_RETURN iretq
+#define INTERRUPT_RETURN jmp native_iret
#define USERGS_SYSRET64 \
swapgs; \
sysretq;
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 2d88344..b1609f2 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t;
#define MODULES_VADDR _AC(0xffffffffa0000000, UL)
#define MODULES_END _AC(0xffffffffff000000, UL)
#define MODULES_LEN (MODULES_END - MODULES_VADDR)
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)

#define EARLY_DYNAMIC_PAGE_TABLES 64

diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 59bcf4e..c2003c0 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -64,6 +64,8 @@ static inline void x86_ce4100_early_setup(void) { }

#ifndef _SETUP

+#include <asm/espfix.h>
+
/*
* This is set up by the setup-routine at boot-time
*/
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9b0a34e..eb1d03b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-y += syscall_$(BITS).o
obj-$(CONFIG_X86_64) += vsyscall_64.o
obj-$(CONFIG_X86_64) += vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-y += bootflag.o e820.o
obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index c87810b..c5a9cb9 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -529,6 +529,7 @@ syscall_exit:
restore_all:
TRACE_IRQS_IRET
restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
# are returning to the kernel.
@@ -539,6 +540,7 @@ restore_all_notrace:
cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
CFI_REMEMBER_STATE
je ldt_ss # returning to user-space with LDT SS
+#endif
restore_nocheck:
RESTORE_REGS 4 # skip orig_eax/error_code
irq_return:
@@ -551,6 +553,7 @@ ENTRY(iret_exc)
.previous
_ASM_EXTABLE(irq_return,iret_exc)

+#ifdef CONFIG_X86_ESPFIX32
CFI_RESTORE_STATE
ldt_ss:
#ifdef CONFIG_PARAVIRT
@@ -594,6 +597,7 @@ ldt_ss:
lss (%esp), %esp /* switch to espfix segment */
CFI_ADJUST_CFA_OFFSET -8
jmp restore_nocheck
+#endif
CFI_ENDPROC
ENDPROC(system_call)

@@ -706,6 +710,7 @@ END(syscall_badsys)
* the high word of the segment base from the GDT and swiches to the
* normal stack and adjusts ESP with the matching offset.
*/
+#ifdef CONFIG_X86_ESPFIX32
/* fixup the stack */
mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -715,8 +720,10 @@ END(syscall_badsys)
pushl_cfi %eax
lss (%esp), %esp /* switch to the normal stack segment */
CFI_ADJUST_CFA_OFFSET -8
+#endif
.endm
.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
movl %ss, %eax
/* see if on espfix stack */
cmpw $__ESPFIX_SS, %ax
@@ -727,6 +734,7 @@ END(syscall_badsys)
/* switch to normal stack */
FIXUP_ESPFIX_STACK
27:
+#endif
.endm

/*
@@ -1357,11 +1365,13 @@ END(debug)
ENTRY(nmi)
RING0_INT_FRAME
ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
pushl_cfi %eax
movl %ss, %eax
cmpw $__ESPFIX_SS, %ax
popl_cfi %eax
je nmi_espfix_stack
+#endif
cmpl $ia32_sysenter_target,(%esp)
je nmi_stack_fixup
pushl_cfi %eax
@@ -1401,6 +1411,7 @@ nmi_debug_stack_check:
FIX_STACK 24, nmi_stack_correct, 1
jmp nmi_stack_correct

+#ifdef CONFIG_X86_ESPFIX32
nmi_espfix_stack:
/* We have a RING0_INT_FRAME here.
*
@@ -1422,6 +1433,7 @@ nmi_espfix_stack:
lss 12+4(%esp), %esp # back to espfix stack
CFI_ADJUST_CFA_OFFSET -24
jmp irq_return
+#endif
CFI_ENDPROC
END(nmi)

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1e96c36..03cd2a8 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -58,6 +58,7 @@
#include <asm/asm.h>
#include <asm/context_tracking.h>
#include <asm/smap.h>
+#include <asm/pgtable_types.h>
#include <linux/err.h>

/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
@@ -1041,12 +1042,45 @@ restore_args:

irq_return:
INTERRUPT_RETURN
- _ASM_EXTABLE(irq_return, bad_iret)

-#ifdef CONFIG_PARAVIRT
ENTRY(native_iret)
+ /*
+ * Are we returning to a stack segment from the LDT? Note: in
+ * 64-bit mode SS:RSP on the exception stack is always valid.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ testb $4,(SS-RIP)(%rsp)
+ jnz native_irq_return_ldt
+#endif
+
+native_irq_return_iret:
iretq
- _ASM_EXTABLE(native_iret, bad_iret)
+ _ASM_EXTABLE(native_irq_return_iret, bad_iret)
+
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+ pushq_cfi %rax
+ pushq_cfi %rdi
+ SWAPGS
+ movq PER_CPU_VAR(espfix_waddr),%rdi
+ movq %rax,(0*8)(%rdi) /* RAX */
+ movq (2*8)(%rsp),%rax /* RIP */
+ movq %rax,(1*8)(%rdi)
+ movq (3*8)(%rsp),%rax /* CS */
+ movq %rax,(2*8)(%rdi)
+ movq (4*8)(%rsp),%rax /* RFLAGS */
+ movq %rax,(3*8)(%rdi)
+ movq (6*8)(%rsp),%rax /* SS */
+ movq %rax,(5*8)(%rdi)
+ movq (5*8)(%rsp),%rax /* RSP */
+ movq %rax,(4*8)(%rdi)
+ andl $0xffff0000,%eax
+ popq_cfi %rdi
+ orq PER_CPU_VAR(espfix_stack),%rax
+ SWAPGS
+ movq %rax,%rsp
+ popq_cfi %rax
+ jmp native_irq_return_iret
#endif

.section .fixup,"ax"
@@ -1110,9 +1144,40 @@ ENTRY(retint_kernel)
call preempt_schedule_irq
jmp exit_intr
#endif
-
CFI_ENDPROC
END(common_interrupt)
+
+ /*
+ * If IRET takes a fault on the espfix stack, then we
+ * end up promoting it to a doublefault. In that case,
+ * modify the stack to make it look like we just entered
+ * the #GP handler from user space, similar to bad_iret.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ ALIGN
+__do_double_fault:
+ XCPT_FRAME 1 RDI+8
+ movq RSP(%rdi),%rax /* Trap on the espfix stack? */
+ sarq $PGDIR_SHIFT,%rax
+ cmpl $ESPFIX_PGD_ENTRY,%eax
+ jne do_double_fault /* No, just deliver the fault */
+ cmpl $__KERNEL_CS,CS(%rdi)
+ jne do_double_fault
+ movq RIP(%rdi),%rax
+ cmpq $native_irq_return_iret,%rax
+ jne do_double_fault /* This shouldn't happen... */
+ movq PER_CPU_VAR(kernel_stack),%rax
+ subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */
+ movq %rax,RSP(%rdi)
+ movq $0,(%rax) /* Missing (lost) #GP error code */
+ movq $general_protection,RIP(%rdi)
+ retq
+ CFI_ENDPROC
+END(__do_double_fault)
+#else
+# define __do_double_fault do_double_fault
+#endif
+
/*
* End of kprobes section
*/
@@ -1314,7 +1379,7 @@ zeroentry overflow do_overflow
zeroentry bounds do_bounds
zeroentry invalid_op do_invalid_op
zeroentry device_not_available do_device_not_available
-paranoiderrorentry double_fault do_double_fault
+paranoiderrorentry double_fault __do_double_fault
zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun
errorentry invalid_TSS do_invalid_TSS
errorentry segment_not_present do_segment_not_present
@@ -1601,7 +1666,7 @@ error_sti:
*/
error_kernelspace:
incl %ebx
- leaq irq_return(%rip),%rcx
+ leaq native_irq_return_iret(%rip),%rcx
cmpq %rcx,RIP+8(%rsp)
je error_swapgs
movl %ecx,%eax /* zero extend */
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
new file mode 100644
index 0000000..94d857f
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,208 @@
+/* ----------------------------------------------------------------------- *
+ *
+ * Copyright 2014 Intel Corporation; author: H. Peter Anvin
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The IRET instruction, when returning to a 16-bit segment, only
+ * restores the bottom 16 bits of the user space stack pointer. This
+ * causes some 16-bit software to break, but it also leaks kernel state
+ * to user space.
+ *
+ * This works around this by creating percpu "ministacks", each of which
+ * is mapped 2^16 times 64K apart. When we detect that the return SS is
+ * on the LDT, we copy the IRET frame to the ministack and use the
+ * relevant alias to return to userspace. The ministacks are mapped
+ * readonly, so if the IRET fault we promote #GP to #DF which is an IST
+ * vector and thus has its own stack; we then do the fixup in the #DF
+ * handler.
+ *
+ * This file sets up the ministacks and the related page tables. The
+ * actual ministack invocation is in entry_64.S.
+ */
+
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/random.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/setup.h>
+#include <asm/espfix.h>
+
+/*
+ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
+ * it up to a cache line to avoid unnecessary sharing.
+ */
+#define ESPFIX_STACK_SIZE (8*8UL)
+#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE)
+
+/* There is address space for how many espfix pages? */
+#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+
+#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
+#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
+# error "Need more than one PGD for the ESPFIX hack"
+#endif
+
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/* This contains the *bottom* address of the espfix stack */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+/* Initialization mutex - should this be a spinlock? */
+static DEFINE_MUTEX(espfix_init_mutex);
+
+/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */
+#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE)
+static void *espfix_pages[ESPFIX_MAX_PAGES];
+
+static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD]
+ __aligned(PAGE_SIZE);
+
+static unsigned int page_random, slot_random;
+
+/*
+ * This returns the bottom address of the espfix stack for a specific CPU.
+ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case
+ * we have to account for some amount of padding at the end of each page.
+ */
+static inline unsigned long espfix_base_addr(unsigned int cpu)
+{
+ unsigned long page, slot;
+ unsigned long addr;
+
+ page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random;
+ slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE;
+ addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE);
+ addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16);
+ addr += ESPFIX_BASE_ADDR;
+ return addr;
+}
+
+#define PTE_STRIDE (65536/PAGE_SIZE)
+#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE)
+#define ESPFIX_PMD_CLONES PTRS_PER_PMD
+#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES))
+
+#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX)
+
+static void init_espfix_random(void)
+{
+ unsigned long rand;
+
+ /*
+ * This is run before the entropy pools are initialized,
+ * but this is hopefully better than nothing.
+ */
+ if (!arch_get_random_long(&rand)) {
+ /* The constant is an arbitrary large prime */
+ rdtscll(rand);
+ rand *= 0xc345c6b72fd16123UL;
+ }
+
+ slot_random = rand % ESPFIX_STACKS_PER_PAGE;
+ page_random = (rand / ESPFIX_STACKS_PER_PAGE)
+ & (ESPFIX_PAGE_SPACE - 1);
+}
+
+void __init init_espfix_bsp(void)
+{
+ pgd_t *pgd_p;
+ pteval_t ptemask;
+
+ ptemask = __supported_pte_mask;
+
+ /* Install the espfix pud into the kernel page directory */
+ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+ pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+
+ /* Randomize the locations */
+ init_espfix_random();
+
+ /* The rest is the same as for any other processor */
+ init_espfix_ap();
+}
+
+void init_espfix_ap(void)
+{
+ unsigned int cpu, page;
+ unsigned long addr;
+ pud_t pud, *pud_p;
+ pmd_t pmd, *pmd_p;
+ pte_t pte, *pte_p;
+ int n;
+ void *stack_page;
+ pteval_t ptemask;
+
+ /* We only have to do this once... */
+ if (likely(this_cpu_read(espfix_stack)))
+ return; /* Already initialized */
+
+ cpu = smp_processor_id();
+ addr = espfix_base_addr(cpu);
+ page = cpu/ESPFIX_STACKS_PER_PAGE;
+
+ /* Did another CPU already set this up? */
+ stack_page = ACCESS_ONCE(espfix_pages[page]);
+ if (likely(stack_page))
+ goto done;
+
+ mutex_lock(&espfix_init_mutex);
+
+ /* Did we race on the lock? */
+ stack_page = ACCESS_ONCE(espfix_pages[page]);
+ if (stack_page)
+ goto unlock_done;
+
+ ptemask = __supported_pte_mask;
+
+ pud_p = &espfix_pud_page[pud_index(addr)];
+ pud = *pud_p;
+ if (!pud_present(pud)) {
+ pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+ pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
+ paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+ for (n = 0; n < ESPFIX_PUD_CLONES; n++)
+ set_pud(&pud_p[n], pud);
+ }
+
+ pmd_p = pmd_offset(&pud, addr);
+ pmd = *pmd_p;
+ if (!pmd_present(pmd)) {
+ pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+ pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
+ paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+ for (n = 0; n < ESPFIX_PMD_CLONES; n++)
+ set_pmd(&pmd_p[n], pmd);
+ }
+
+ pte_p = pte_offset_kernel(&pmd, addr);
+ stack_page = (void *)__get_free_page(GFP_KERNEL);
+ pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+ for (n = 0; n < ESPFIX_PTE_CLONES; n++)
+ set_pte(&pte_p[n*PTE_STRIDE], pte);
+
+ /* Job is done for this CPU and any CPU which shares this page */
+ ACCESS_ONCE(espfix_pages[page]) = stack_page;
+
+unlock_done:
+ mutex_unlock(&espfix_init_mutex);
+done:
+ this_cpu_write(espfix_stack, addr);
+ this_cpu_write(espfix_waddr, (unsigned long)stack_page
+ + (addr & ~PAGE_MASK));
+}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index dcbbaa1..c37886d 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -20,8 +20,6 @@
#include <asm/mmu_context.h>
#include <asm/syscalls.h>

-int sysctl_ldt16 = 0;
-
#ifdef CONFIG_SMP
static void flush_ldt(void *current_mm)
{
@@ -231,16 +229,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
}
}

- /*
- * On x86-64 we do not support 16-bit segments due to
- * IRET leaking the high bits of the kernel stack address.
- */
-#ifdef CONFIG_X86_64
- if (!ldt_info.seg_32bit && !sysctl_ldt16) {
+ if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
error = -EINVAL;
goto out_unlock;
}
-#endif

fill_ldt(&ldt, &ldt_info);
if (oldmode)
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34..a1da673 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_irq_ops, save_fl);
PATCH_SITE(pv_irq_ops, irq_enable);
PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, iret);
PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
PATCH_SITE(pv_cpu_ops, usergs_sysret32);
PATCH_SITE(pv_cpu_ops, usergs_sysret64);
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 2a26819..80eab01 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail)

void arch_remove_reservations(struct resource *avail)
{
- /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+ /*
+ * Trim out BIOS area (high 2MB) and E820 regions. We do not remove
+ * the low 1MB unconditionally, as this area is needed for some ISA
+ * cards requiring a memory range, e.g. the i82365 PCMCIA controller.
+ */
if (avail->flags & IORESOURCE_MEM) {
- if (avail->start < BIOS_END)
- avail->start = BIOS_END;
resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);

remove_e820_regions(avail);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 85dc05a..a965665 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -243,6 +243,13 @@ static void notrace start_secondary(void *unused)
check_tsc_sync_target();

/*
+ * Enable the espfix hack for this CPU
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ init_espfix_ap();
+#endif
+
+ /*
* We need to hold vector_lock so there the set of online cpus
* does not change while we are assigning vectors to cpus. Holding
* this lock ensures we don't half assign or remove an irq from a cpu.
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 1f96f93..09ce23a 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
if (!show_unhandled_signals)
return;

- pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
- level, current->comm, task_pid_nr(current),
- message, regs->ip, regs->cs,
- regs->sp, regs->ax, regs->si, regs->di);
+ printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+ level, current->comm, task_pid_nr(current),
+ message, regs->ip, regs->cs,
+ regs->sp, regs->ax, regs->si, regs->di);
}

static int addr_to_vsyscall_nr(unsigned long addr)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 07ffca0..7bff3e2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2006,6 +2006,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
unsigned long cs;
+ int cpl = ctxt->ops->cpl(ctxt);

rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
@@ -2015,6 +2016,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
+ /* Outer-privilege level return is not implemented */
+ if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
+ return X86EMUL_UNHANDLEABLE;
rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS);
return rc;
}
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 484bc87..3ec38cb 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -108,7 +108,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)

vector = kvm_cpu_get_extint(v);

- if (kvm_apic_vid_enabled(v->kvm) || vector != -1)
+ if (vector != -1)
return vector; /* PIC */

return kvm_get_apic_interrupt(v); /* APIC */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 92bbb39..f52e300 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -352,25 +352,46 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)

static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
{
- apic->irr_pending = false;
+ struct kvm_vcpu *vcpu;
+
+ vcpu = apic->vcpu;
+
apic_clear_vector(vec, apic->regs + APIC_IRR);
- if (apic_search_irr(apic) != -1)
- apic->irr_pending = true;
+ if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+ /* try to update RVI */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ else {
+ vec = apic_search_irr(apic);
+ apic->irr_pending = (vec != -1);
+ }
}

static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
{
- /* Note that we never get here with APIC virtualization enabled. */
+ struct kvm_vcpu *vcpu;
+
+ if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+ return;
+
+ vcpu = apic->vcpu;

- if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
- ++apic->isr_count;
- BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
/*
- * ISR (in service register) bit is set when injecting an interrupt.
- * The highest vector is injected. Thus the latest bit set matches
- * the highest bit in ISR.
+ * With APIC virtualization enabled, all caching is disabled
+ * because the processor can modify ISR under the hood. Instead
+ * just set SVI.
*/
- apic->highest_isr_cache = vec;
+ if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+ kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec);
+ else {
+ ++apic->isr_count;
+ BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+ /*
+ * ISR (in service register) bit is set when injecting an interrupt.
+ * The highest vector is injected. Thus the latest bit set matches
+ * the highest bit in ISR.
+ */
+ apic->highest_isr_cache = vec;
+ }
}

static inline int apic_find_highest_isr(struct kvm_lapic *apic)
@@ -1627,11 +1648,16 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
int vector = kvm_apic_has_interrupt(vcpu);
struct kvm_lapic *apic = vcpu->arch.apic;

- /* Note that we never get here with APIC virtualization enabled. */
-
if (vector == -1)
return -1;

+ /*
+ * We get here even with APIC virtualization enabled, if doing
+ * nested virtualization and L1 runs with the "acknowledge interrupt
+ * on exit" mode. Then we cannot inject the interrupt via RVI,
+ * because the process would deliver it through the IDT.
+ */
+
apic_set_isr(vector, apic);
apic_update_ppr(apic);
apic_clear_irr(vector, apic);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0002a3a..8f556f7 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -30,11 +30,13 @@ struct pg_state {
unsigned long start_address;
unsigned long current_address;
const struct addr_marker *marker;
+ unsigned long lines;
};

struct addr_marker {
unsigned long start_address;
const char *name;
+ unsigned long max_lines;
};

/* indices for address_markers; keep sync'd w/ address_markers below */
@@ -45,6 +47,7 @@ enum address_markers_idx {
LOW_KERNEL_NR,
VMALLOC_START_NR,
VMEMMAP_START_NR,
+ ESPFIX_START_NR,
HIGH_KERNEL_NR,
MODULES_VADDR_NR,
MODULES_END_NR,
@@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = {
{ PAGE_OFFSET, "Low Kernel Mapping" },
{ VMALLOC_START, "vmalloc() Area" },
{ VMEMMAP_START, "Vmemmap" },
+ { ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
{ __START_KERNEL_map, "High Kernel Mapping" },
{ MODULES_VADDR, "Modules" },
{ MODULES_END, "End Modules" },
@@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
pgprot_t new_prot, int level)
{
pgprotval_t prot, cur;
- static const char units[] = "KMGTPE";
+ static const char units[] = "BKMGTPE";

/*
* If we have a "break" in the series, we need to flush the state that
@@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
st->current_prot = new_prot;
st->level = level;
st->marker = address_markers;
+ st->lines = 0;
seq_printf(m, "---[ %s ]---\n", st->marker->name);
} else if (prot != cur || level != st->level ||
st->current_address >= st->marker[1].start_address) {
@@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st,
/*
* Now print the actual finished series
*/
- seq_printf(m, "0x%0*lx-0x%0*lx ",
- width, st->start_address,
- width, st->current_address);
-
- delta = (st->current_address - st->start_address) >> 10;
- while (!(delta & 1023) && unit[1]) {
- delta >>= 10;
- unit++;
+ if (!st->marker->max_lines ||
+ st->lines < st->marker->max_lines) {
+ seq_printf(m, "0x%0*lx-0x%0*lx ",
+ width, st->start_address,
+ width, st->current_address);
+
+ delta = st->current_address - st->start_address;
+ while (!(delta & 1023) && unit[1]) {
+ delta >>= 10;
+ unit++;
+ }
+ seq_printf(m, "%9lu%c ", delta, *unit);
+ printk_prot(m, st->current_prot, st->level);
}
- seq_printf(m, "%9lu%c ", delta, *unit);
- printk_prot(m, st->current_prot, st->level);
+ st->lines++;

/*
* We print markers for special areas of address space,
@@ -206,7 +215,16 @@ static void note_page(struct seq_file *m, struct pg_state *st,
* This helps in the interpretation.
*/
if (st->current_address >= st->marker[1].start_address) {
+ if (st->marker->max_lines &&
+ st->lines > st->marker->max_lines) {
+ unsigned long nskip =
+ st->lines - st->marker->max_lines;
+ seq_printf(m, "... %lu entr%s skipped ... \n",
+ nskip,
+ nskip == 1 ? "y" : "ies");
+ }
st->marker++;
+ st->lines = 0;
seq_printf(m, "---[ %s ]---\n", st->marker->name);
}

diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index db6b1ab..96a159a 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -162,6 +162,10 @@ pcibios_align_resource(void *data, const struct resource *res,
return start;
if (start & 0x300)
start = (start + 0x3ff) & ~0x3ff;
+ } else if (res->flags & IORESOURCE_MEM) {
+ /* The low 1MB range is reserved for ISA cards */
+ if (start < BIOS_END)
+ start = BIOS_END;
}
return start;
}
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index f1d633a..d6bfb87 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -41,7 +41,6 @@ enum {
#ifdef CONFIG_X86_64
#define vdso_enabled sysctl_vsyscall32
#define arch_setup_additional_pages syscall32_setup_pages
-extern int sysctl_ldt16;
#endif

/*
@@ -381,13 +380,6 @@ static struct ctl_table abi_table2[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
- {
- .procname = "ldt16",
- .data = &sysctl_ldt16,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
{}
};

diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 12a1ca7..f314067 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -444,7 +444,7 @@ void xen_setup_timer(int cpu)

irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER|
- IRQF_FORCE_RESUME,
+ IRQF_FORCE_RESUME|IRQF_EARLY_RESUME,
name, NULL);

memcpy(evt, xen_clockevent, sizeof(*evt));
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 7f9b1f6..2192cf4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -179,6 +179,8 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,

rq->mq_ctx = ctx;
rq->cmd_flags = rw_flags;
+ rq->start_time = jiffies;
+ set_start_time_ns(rq);
ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
}

diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c
index edff4e6..c66bca1 100644
--- a/drivers/acpi/acpica/utcopy.c
+++ b/drivers/acpi/acpica/utcopy.c
@@ -1001,5 +1001,11 @@ acpi_ut_copy_iobject_to_iobject(union acpi_operand_object *source_desc,
status = acpi_ut_copy_simple_object(source_desc, *dest_desc);
}

+ /* Delete the allocated object if copy failed */
+
+ if (ACPI_FAILURE(status)) {
+ acpi_ut_remove_reference(*dest_desc);
+ }
+
return_ACPI_STATUS(status);
}
diff --git a/drivers/bluetooth/btmrvl_drv.h b/drivers/bluetooth/btmrvl_drv.h
index f9d1833..c401de2 100644
--- a/drivers/bluetooth/btmrvl_drv.h
+++ b/drivers/bluetooth/btmrvl_drv.h
@@ -70,6 +70,7 @@ struct btmrvl_adapter {
u8 hs_state;
u8 wakeup_tries;
wait_queue_head_t cmd_wait_q;
+ wait_queue_head_t event_hs_wait_q;
u8 cmd_complete;
bool is_suspended;
};
diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c
index 5cf31c4..245e9c7 100644
--- a/drivers/bluetooth/btmrvl_main.c
+++ b/drivers/bluetooth/btmrvl_main.c
@@ -115,6 +115,7 @@ int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb)
adapter->hs_state = HS_ACTIVATED;
if (adapter->psmode)
adapter->ps_state = PS_SLEEP;
+ wake_up_interruptible(&adapter->event_hs_wait_q);
BT_DBG("HS ACTIVATED!");
} else {
BT_DBG("HS Enable failed");
@@ -254,11 +255,31 @@ EXPORT_SYMBOL_GPL(btmrvl_enable_ps);

int btmrvl_enable_hs(struct btmrvl_private *priv)
{
+ struct btmrvl_adapter *adapter = priv->adapter;
int ret;

ret = btmrvl_send_sync_cmd(priv, BT_CMD_HOST_SLEEP_ENABLE, NULL, 0);
- if (ret)
+ if (ret) {
BT_ERR("Host sleep enable command failed\n");
+ return ret;
+ }
+
+ ret = wait_event_interruptible_timeout(adapter->event_hs_wait_q,
+ adapter->hs_state,
+ msecs_to_jiffies(WAIT_UNTIL_HS_STATE_CHANGED));
+ if (ret < 0) {
+ BT_ERR("event_hs_wait_q terminated (%d): %d,%d,%d",
+ ret, adapter->hs_state, adapter->ps_state,
+ adapter->wakeup_tries);
+ } else if (!ret) {
+ BT_ERR("hs_enable timeout: %d,%d,%d", adapter->hs_state,
+ adapter->ps_state, adapter->wakeup_tries);
+ ret = -ETIMEDOUT;
+ } else {
+ BT_DBG("host sleep enabled: %d,%d,%d", adapter->hs_state,
+ adapter->ps_state, adapter->wakeup_tries);
+ ret = 0;
+ }

return ret;
}
@@ -344,6 +365,7 @@ static void btmrvl_init_adapter(struct btmrvl_private *priv)
priv->adapter->ps_state = PS_AWAKE;

init_waitqueue_head(&priv->adapter->cmd_wait_q);
+ init_waitqueue_head(&priv->adapter->event_hs_wait_q);
}

static void btmrvl_free_adapter(struct btmrvl_private *priv)
@@ -716,6 +738,7 @@ int btmrvl_remove_card(struct btmrvl_private *priv)
hdev = priv->btmrvl_dev.hcidev;

wake_up_interruptible(&priv->adapter->cmd_wait_q);
+ wake_up_interruptible(&priv->adapter->event_hs_wait_q);

kthread_stop(priv->main_thread.task);

diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 6ae41d3..901b370 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -1400,13 +1400,13 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
int err, total = 0, retries = 5;
u8 *dest = out;

+ if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
+ return -EINVAL;
+
chip = tpm_chip_find_get(chip_num);
if (chip == NULL)
return -ENODEV;

- if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
- return -EINVAL;
-
do {
tpm_cmd.header.in = tpm_getrandom_header;
tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes);
@@ -1425,6 +1425,7 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
num_bytes -= recd;
} while (retries-- && total < max);

+ tpm_chip_put(chip);
return total ? total : -EIO;
}
EXPORT_SYMBOL_GPL(tpm_get_random);
diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c
index cf68403..b2cb24c 100644
--- a/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ b/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -750,6 +750,7 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
}

tpm_get_timeouts(chip);
+ tpm_do_selftest(chip);

dev_info(chip->dev, "TPM I2C Initialized\n");
return 0;
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index a999f53..92105f3 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -190,7 +190,7 @@ static void add_session_id(struct cryp_ctx *ctx)
static irqreturn_t cryp_interrupt_handler(int irq, void *param)
{
struct cryp_ctx *ctx;
- int i;
+ int count;
struct cryp_device_data *device_data;

if (param == NULL) {
@@ -215,12 +215,11 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
if (cryp_pending_irq_src(device_data,
CRYP_IRQ_SRC_OUTPUT_FIFO)) {
if (ctx->outlen / ctx->blocksize > 0) {
- for (i = 0; i < ctx->blocksize / 4; i++) {
- *(ctx->outdata) = readl_relaxed(
- &device_data->base->dout);
- ctx->outdata += 4;
- ctx->outlen -= 4;
- }
+ count = ctx->blocksize / 4;
+
+ readsl(&device_data->base->dout, ctx->outdata, count);
+ ctx->outdata += count;
+ ctx->outlen -= count;

if (ctx->outlen == 0) {
cryp_disable_irq_src(device_data,
@@ -230,12 +229,12 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
} else if (cryp_pending_irq_src(device_data,
CRYP_IRQ_SRC_INPUT_FIFO)) {
if (ctx->datalen / ctx->blocksize > 0) {
- for (i = 0 ; i < ctx->blocksize / 4; i++) {
- writel_relaxed(ctx->indata,
- &device_data->base->din);
- ctx->indata += 4;
- ctx->datalen -= 4;
- }
+ count = ctx->blocksize / 4;
+
+ writesl(&device_data->base->din, ctx->indata, count);
+
+ ctx->indata += count;
+ ctx->datalen -= count;

if (ctx->datalen == 0)
cryp_disable_irq_src(device_data,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 53f5458..dfb8546 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -473,6 +473,9 @@ static int init_ring_common(struct intel_ring_buffer *ring)
}
}

+ /* Enforce ordering by reading HEAD register back */
+ I915_READ_HEAD(ring);
+
/* Initialize the ring. This must happen _after_ we've cleared the ring
* registers with the above sequence (the readback of the HEAD registers
* also enforces ordering), otherwise the hw might lose the new ring
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h
index 4b0fb6c..a6949ec 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.h
@@ -10,7 +10,7 @@

#define DRIVER_MAJOR 1
#define DRIVER_MINOR 1
-#define DRIVER_PATCHLEVEL 1
+#define DRIVER_PATCHLEVEL 2

/*
* 1.1.1:
@@ -21,6 +21,8 @@
* to control registers on the MPs to enable performance counters,
* and to control the warp error enable mask (OpenGL requires out of
* bounds access to local memory to be silently ignored / return 0).
+ * 1.1.2:
+ * - fixes multiple bugs in flip completion events and timestamping
*/

#include <core/client.h>
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index ca13ab5..8bfab60 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -923,7 +923,18 @@ static void ci_get_leakage_voltages(struct radeon_device *rdev)
pi->vddc_leakage.count = 0;
pi->vddci_leakage.count = 0;

- if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) {
+ if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_EVV) {
+ for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) {
+ virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i;
+ if (radeon_atom_get_voltage_evv(rdev, virtual_voltage_id, &vddc) != 0)
+ continue;
+ if (vddc != 0 && vddc != virtual_voltage_id) {
+ pi->vddc_leakage.actual_voltage[pi->vddc_leakage.count] = vddc;
+ pi->vddc_leakage.leakage_id[pi->vddc_leakage.count] = virtual_voltage_id;
+ pi->vddc_leakage.count++;
+ }
+ }
+ } else if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) {
for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) {
virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i;
if (radeon_atom_get_leakage_vddc_based_on_leakage_params(rdev, &vddc, &vddci,
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 17649ac..1523902 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -5332,12 +5332,13 @@ static void cik_vm_decode_fault(struct radeon_device *rdev,
void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
{
struct radeon_ring *ring = &rdev->ring[ridx];
+ int usepfp = (ridx == RADEON_RING_TYPE_GFX_INDEX);

if (vm == NULL)
return;

radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
- radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+ radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
WRITE_DATA_DST_SEL(0)));
if (vm->id < 8) {
radeon_ring_write(ring,
@@ -5396,7 +5397,7 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
radeon_ring_write(ring, 1 << vm->id);

/* compute doesn't have PFP */
- if (ridx == RADEON_RING_TYPE_GFX_INDEX) {
+ if (usepfp) {
/* sync PFP to ME, otherwise we might get invalid PFP reads */
radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
radeon_ring_write(ring, 0x0);
@@ -7575,6 +7576,7 @@ restart_ih:
static int cik_startup(struct radeon_device *rdev)
{
struct radeon_ring *ring;
+ u32 nop;
int r;

/* enable pcie gen2/3 link */
@@ -7692,10 +7694,16 @@ static int cik_startup(struct radeon_device *rdev)
}
cik_irq_set(rdev);

+ if (rdev->family == CHIP_HAWAII) {
+ nop = RADEON_CP_PACKET2;
+ } else {
+ nop = PACKET3(PACKET3_NOP, 0x3FFF);
+ }
+
ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
CP_RB0_RPTR, CP_RB0_WPTR,
- PACKET3(PACKET3_NOP, 0x3FFF));
+ nop);
if (r)
return r;

@@ -7704,7 +7712,7 @@ static int cik_startup(struct radeon_device *rdev)
ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP1_RPTR_OFFSET,
CP_HQD_PQ_RPTR, CP_HQD_PQ_WPTR,
- PACKET3(PACKET3_NOP, 0x3FFF));
+ nop);
if (r)
return r;
ring->me = 1; /* first MEC */
@@ -7716,7 +7724,7 @@ static int cik_startup(struct radeon_device *rdev)
ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP2_RPTR_OFFSET,
CP_HQD_PQ_RPTR, CP_HQD_PQ_WPTR,
- PACKET3(PACKET3_NOP, 0x3FFF));
+ nop);
if (r)
return r;
/* dGPU only have 1 MEC */
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 68b29d9..6cc9331 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -289,6 +289,9 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r
u16 *vddc, u16 *vddci,
u16 virtual_voltage_id,
u16 vbios_voltage_id);
+int radeon_atom_get_voltage_evv(struct radeon_device *rdev,
+ u16 virtual_voltage_id,
+ u16 *voltage);
int radeon_atom_round_to_true_voltage(struct radeon_device *rdev,
u8 voltage_type,
u16 nominal_voltage,
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index dfa6412..4af5a78 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1963,7 +1963,7 @@ static const char *thermal_controller_names[] = {
"adm1032",
"adm1030",
"max6649",
- "lm64",
+ "lm63", /* lm64 */
"f75375",
"asc7xxx",
};
@@ -1974,7 +1974,7 @@ static const char *pp_lib_thermal_controller_names[] = {
"adm1032",
"adm1030",
"max6649",
- "lm64",
+ "lm63", /* lm64 */
"f75375",
"RV6xx",
"RV770",
@@ -3236,6 +3236,41 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r
return 0;
}

+union get_voltage_info {
+ struct _GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 in;
+ struct _GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 evv_out;
+};
+
+int radeon_atom_get_voltage_evv(struct radeon_device *rdev,
+ u16 virtual_voltage_id,
+ u16 *voltage)
+{
+ int index = GetIndexIntoMasterTable(COMMAND, GetVoltageInfo);
+ u32 entry_id;
+ u32 count = rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count;
+ union get_voltage_info args;
+
+ for (entry_id = 0; entry_id < count; entry_id++) {
+ if (rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].v ==
+ virtual_voltage_id)
+ break;
+ }
+
+ if (entry_id >= count)
+ return -EINVAL;
+
+ args.in.ucVoltageType = VOLTAGE_TYPE_VDDC;
+ args.in.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE;
+ args.in.ulSCLKFreq =
+ cpu_to_le32(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].clk);
+
+ atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+
+ *voltage = le16_to_cpu(args.evv_out.usVoltageLevel);
+
+ return 0;
+}
+
int radeon_atom_get_voltage_gpio_settings(struct radeon_device *rdev,
u16 voltage_level, u8 voltage_type,
u32 *gpio_value, u32 *gpio_mask)
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 5ef56ad..ecffe85 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -254,7 +254,14 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
}
break;
case RADEON_INFO_ACCEL_WORKING2:
- *value = rdev->accel_working;
+ if (rdev->family == CHIP_HAWAII) {
+ if (rdev->accel_working)
+ *value = 2;
+ else
+ *value = 0;
+ } else {
+ *value = rdev->accel_working;
+ }
break;
case RADEON_INFO_TILING_CONFIG:
if (rdev->family >= CHIP_BONAIRE)
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 446e67f..b19ac0d 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1271,10 +1271,6 @@ int radeon_pm_init(struct radeon_device *rdev)
case CHIP_RS780:
case CHIP_RS880:
case CHIP_RV770:
- case CHIP_BARTS:
- case CHIP_TURKS:
- case CHIP_CAICOS:
- case CHIP_CAYMAN:
case CHIP_BONAIRE:
case CHIP_KABINI:
case CHIP_KAVERI:
@@ -1302,6 +1298,10 @@ int radeon_pm_init(struct radeon_device *rdev)
case CHIP_PALM:
case CHIP_SUMO:
case CHIP_SUMO2:
+ case CHIP_BARTS:
+ case CHIP_TURKS:
+ case CHIP_CAICOS:
+ case CHIP_CAYMAN:
case CHIP_ARUBA:
case CHIP_TAHITI:
case CHIP_PITCAIRN:
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index d5c8438..18c197f 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4697,7 +4697,7 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)

/* write new base address */
radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
- radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+ radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
WRITE_DATA_DST_SEL(0)));

if (vm->id < 8) {
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index ae1cb31..614e8ef 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -1252,6 +1252,7 @@ static struct of_device_id tegra_dc_of_match[] = {
{ .compatible = "nvidia,tegra20-dc", },
{ },
};
+MODULE_DEVICE_TABLE(of, tegra_dc_of_match);

struct platform_driver tegra_dc_driver = {
.driver = {
diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c
index 7ec4259..684ad13 100644
--- a/drivers/gpu/drm/tegra/gr2d.c
+++ b/drivers/gpu/drm/tegra/gr2d.c
@@ -129,6 +129,7 @@ static const struct of_device_id gr2d_match[] = {
{ .compatible = "nvidia,tegra20-gr2d" },
{ },
};
+MODULE_DEVICE_TABLE(of, gr2d_match);

static const u32 gr2d_addr_regs[] = {
GR2D_UA_BASE_ADDR,
diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c
index 4cec8f5..b8503b2 100644
--- a/drivers/gpu/drm/tegra/gr3d.c
+++ b/drivers/gpu/drm/tegra/gr3d.c
@@ -127,6 +127,7 @@ static const struct of_device_id tegra_gr3d_match[] = {
{ .compatible = "nvidia,tegra20-gr3d" },
{ }
};
+MODULE_DEVICE_TABLE(of, tegra_gr3d_match);

static const u32 gr3d_addr_regs[] = {
GR3D_IDX_ATTRIBUTE( 0),
diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c
index 0cd9bc2..a2eb3c0 100644
--- a/drivers/gpu/drm/tegra/hdmi.c
+++ b/drivers/gpu/drm/tegra/hdmi.c
@@ -1309,6 +1309,7 @@ static const struct of_device_id tegra_hdmi_of_match[] = {
{ .compatible = "nvidia,tegra20-hdmi", .data = &tegra20_hdmi_config },
{ },
};
+MODULE_DEVICE_TABLE(of, tegra_hdmi_of_match);

static int tegra_hdmi_probe(struct platform_device *pdev)
{
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index 116da19..af1b17a 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -122,6 +122,7 @@ static int tilcdc_unload(struct drm_device *dev)
struct tilcdc_drm_private *priv = dev->dev_private;
struct tilcdc_module *mod, *cur;

+ drm_fbdev_cma_fini(priv->fbdev);
drm_kms_helper_poll_fini(dev);
drm_mode_config_cleanup(dev);
drm_vblank_cleanup(dev);
@@ -628,10 +629,10 @@ static int __init tilcdc_drm_init(void)
static void __exit tilcdc_drm_fini(void)
{
DBG("fini");
- tilcdc_tfp410_fini();
- tilcdc_slave_fini();
- tilcdc_panel_fini();
platform_driver_unregister(&tilcdc_platform_driver);
+ tilcdc_panel_fini();
+ tilcdc_slave_fini();
+ tilcdc_tfp410_fini();
}

late_initcall(tilcdc_drm_init);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index 86c6732..b085dcc 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -151,6 +151,7 @@ struct panel_connector {
static void panel_connector_destroy(struct drm_connector *connector)
{
struct panel_connector *panel_connector = to_panel_connector(connector);
+ drm_sysfs_connector_remove(connector);
drm_connector_cleanup(connector);
kfree(panel_connector);
}
@@ -285,10 +286,8 @@ static void panel_destroy(struct tilcdc_module *mod)
{
struct panel_module *panel_mod = to_panel_module(mod);

- if (panel_mod->timings) {
+ if (panel_mod->timings)
display_timings_release(panel_mod->timings);
- kfree(panel_mod->timings);
- }

tilcdc_module_cleanup(mod);
kfree(panel_mod->info);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_slave.c b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
index 595068b..2f83ffb 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_slave.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
@@ -166,6 +166,7 @@ struct slave_connector {
static void slave_connector_destroy(struct drm_connector *connector)
{
struct slave_connector *slave_connector = to_slave_connector(connector);
+ drm_sysfs_connector_remove(connector);
drm_connector_cleanup(connector);
kfree(slave_connector);
}
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index c38b56b..ce75ac8 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -167,6 +167,7 @@ struct tfp410_connector {
static void tfp410_connector_destroy(struct drm_connector *connector)
{
struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector);
+ drm_sysfs_connector_remove(connector);
drm_connector_cleanup(connector);
kfree(tfp410_connector);
}
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 863bef9..cf4bad2 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -297,8 +297,10 @@ static void ttm_pool_update_free_locked(struct ttm_page_pool *pool,
*
* @pool: to free the pages from
* @free_all: If set to true will free all pages in pool
+ * @gfp: GFP flags.
**/
-static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free)
+static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free,
+ gfp_t gfp)
{
unsigned long irq_flags;
struct page *p;
@@ -309,8 +311,7 @@ static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free)
if (NUM_PAGES_TO_ALLOC < nr_free)
npages_to_free = NUM_PAGES_TO_ALLOC;

- pages_to_free = kmalloc(npages_to_free * sizeof(struct page *),
- GFP_KERNEL);
+ pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp);
if (!pages_to_free) {
pr_err("Failed to allocate memory for pool free operation\n");
return 0;
@@ -382,32 +383,35 @@ out:
*
* XXX: (dchinner) Deadlock warning!
*
- * ttm_page_pool_free() does memory allocation using GFP_KERNEL. that means
- * this can deadlock when called a sc->gfp_mask that is not equal to
- * GFP_KERNEL.
+ * We need to pass sc->gfp_mask to ttm_page_pool_free().
*
* This code is crying out for a shrinker per pool....
*/
static unsigned long
ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
- static atomic_t start_pool = ATOMIC_INIT(0);
+ static DEFINE_MUTEX(lock);
+ static unsigned start_pool;
unsigned i;
- unsigned pool_offset = atomic_add_return(1, &start_pool);
+ unsigned pool_offset;
struct ttm_page_pool *pool;
int shrink_pages = sc->nr_to_scan;
unsigned long freed = 0;

- pool_offset = pool_offset % NUM_POOLS;
+ if (!mutex_trylock(&lock))
+ return SHRINK_STOP;
+ pool_offset = ++start_pool % NUM_POOLS;
/* select start pool in round robin fashion */
for (i = 0; i < NUM_POOLS; ++i) {
unsigned nr_free = shrink_pages;
if (shrink_pages == 0)
break;
pool = &_manager->pools[(i + pool_offset)%NUM_POOLS];
- shrink_pages = ttm_page_pool_free(pool, nr_free);
+ shrink_pages = ttm_page_pool_free(pool, nr_free,
+ sc->gfp_mask);
freed += nr_free - shrink_pages;
}
+ mutex_unlock(&lock);
return freed;
}

@@ -706,7 +710,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
}
spin_unlock_irqrestore(&pool->lock, irq_flags);
if (npages)
- ttm_page_pool_free(pool, npages);
+ ttm_page_pool_free(pool, npages, GFP_KERNEL);
}

/*
@@ -846,7 +850,8 @@ void ttm_page_alloc_fini(void)
ttm_pool_mm_shrink_fini(_manager);

for (i = 0; i < NUM_POOLS; ++i)
- ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES);
+ ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES,
+ GFP_KERNEL);

kobject_put(&_manager->kobj);
_manager = NULL;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index fb8259f..ca65df1 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -411,8 +411,10 @@ static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
*
* @pool: to free the pages from
* @nr_free: If set to true will free all pages in pool
+ * @gfp: GFP flags.
**/
-static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free)
+static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free,
+ gfp_t gfp)
{
unsigned long irq_flags;
struct dma_page *dma_p, *tmp;
@@ -430,8 +432,7 @@ static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free)
npages_to_free, nr_free);
}
#endif
- pages_to_free = kmalloc(npages_to_free * sizeof(struct page *),
- GFP_KERNEL);
+ pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp);

if (!pages_to_free) {
pr_err("%s: Failed to allocate memory for pool free operation\n",
@@ -530,7 +531,7 @@ static void ttm_dma_free_pool(struct device *dev, enum pool_type type)
if (pool->type != type)
continue;
/* Takes a spinlock.. */
- ttm_dma_page_pool_free(pool, FREE_ALL_PAGES);
+ ttm_dma_page_pool_free(pool, FREE_ALL_PAGES, GFP_KERNEL);
WARN_ON(((pool->npages_in_use + pool->npages_free) != 0));
/* This code path is called after _all_ references to the
* struct device has been dropped - so nobody should be
@@ -983,7 +984,7 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)

/* shrink pool if necessary (only on !is_cached pools)*/
if (npages)
- ttm_dma_page_pool_free(pool, npages);
+ ttm_dma_page_pool_free(pool, npages, GFP_KERNEL);
ttm->state = tt_unpopulated;
}
EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
@@ -993,10 +994,7 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
*
* XXX: (dchinner) Deadlock warning!
*
- * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention
- * needs to be paid to sc->gfp_mask to determine if this can be done or not.
- * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really
- * bad.
+ * We need to pass sc->gfp_mask to ttm_dma_page_pool_free().
*
* I'm getting sadder as I hear more pathetical whimpers about needing per-pool
* shrinkers
@@ -1004,9 +1002,9 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
static unsigned long
ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
- static atomic_t start_pool = ATOMIC_INIT(0);
+ static unsigned start_pool;
unsigned idx = 0;
- unsigned pool_offset = atomic_add_return(1, &start_pool);
+ unsigned pool_offset;
unsigned shrink_pages = sc->nr_to_scan;
struct device_pools *p;
unsigned long freed = 0;
@@ -1014,8 +1012,11 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
if (list_empty(&_manager->pools))
return SHRINK_STOP;

- mutex_lock(&_manager->lock);
- pool_offset = pool_offset % _manager->npools;
+ if (!mutex_trylock(&_manager->lock))
+ return SHRINK_STOP;
+ if (!_manager->npools)
+ goto out;
+ pool_offset = ++start_pool % _manager->npools;
list_for_each_entry(p, &_manager->pools, pools) {
unsigned nr_free;

@@ -1027,13 +1028,15 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
if (++idx < pool_offset)
continue;
nr_free = shrink_pages;
- shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free);
+ shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free,
+ sc->gfp_mask);
freed += nr_free - shrink_pages;

pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n",
p->pool->dev_name, p->pool->name, current->pid,
nr_free, shrink_pages);
}
+out:
mutex_unlock(&_manager->lock);
return freed;
}
@@ -1044,7 +1047,8 @@ ttm_dma_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
struct device_pools *p;
unsigned long count = 0;

- mutex_lock(&_manager->lock);
+ if (!mutex_trylock(&_manager->lock))
+ return 0;
list_for_each_entry(p, &_manager->pools, pools)
count += p->pool->npages_free;
mutex_unlock(&_manager->lock);
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index 7f9dc2f..1265164 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -198,7 +198,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
}

channel = be32_to_cpup(property);
- if (channel > ADS1015_CHANNELS) {
+ if (channel >= ADS1015_CHANNELS) {
dev_err(&client->dev,
"invalid channel index %d on %s\n",
channel, node->full_name);
@@ -212,6 +212,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
dev_err(&client->dev,
"invalid gain on %s\n",
node->full_name);
+ return -EINVAL;
}
}

@@ -222,6 +223,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
dev_err(&client->dev,
"invalid data_rate on %s\n",
node->full_name);
+ return -EINVAL;
}
}

diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index 9f2be3d..8a67ec6 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -360,11 +360,13 @@ static ssize_t set_pwm1_enable(
if (config)
return config;

+ mutex_lock(&data->update_lock);
config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF1);
if (config < 0) {
dev_err(&client->dev,
"Error reading configuration register, aborting.\n");
- return config;
+ count = config;
+ goto unlock;
}

switch (val) {
@@ -381,14 +383,15 @@ static ssize_t set_pwm1_enable(
config |= AMC6821_CONF1_FDRC1;
break;
default:
- return -EINVAL;
+ count = -EINVAL;
+ goto unlock;
}
- mutex_lock(&data->update_lock);
if (i2c_smbus_write_byte_data(client, AMC6821_REG_CONF1, config)) {
dev_err(&client->dev,
"Configuration register write error, aborting.\n");
count = -EIO;
}
+unlock:
mutex_unlock(&data->update_lock);
return count;
}
@@ -493,8 +496,9 @@ static ssize_t set_temp_auto_point_temp(
return -EINVAL;
}

- data->valid = 0;
mutex_lock(&data->update_lock);
+ data->valid = 0;
+
switch (ix) {
case 0:
ptemp[0] = clamp_val(val / 1000, 0,
@@ -658,13 +662,14 @@ static ssize_t set_fan1_div(
if (config)
return config;

+ mutex_lock(&data->update_lock);
config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF4);
if (config < 0) {
dev_err(&client->dev,
"Error reading configuration register, aborting.\n");
- return config;
+ count = config;
+ goto EXIT;
}
- mutex_lock(&data->update_lock);
switch (val) {
case 2:
config &= ~AMC6821_CONF4_PSPR;
diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c
index 4ae3fff..bea0a34 100644
--- a/drivers/hwmon/dme1737.c
+++ b/drivers/hwmon/dme1737.c
@@ -247,8 +247,8 @@ struct dme1737_data {
u8 pwm_acz[3];
u8 pwm_freq[6];
u8 pwm_rr[2];
- u8 zone_low[3];
- u8 zone_abs[3];
+ s8 zone_low[3];
+ s8 zone_abs[3];
u8 zone_hyst[2];
u32 alarms;
};
@@ -277,7 +277,7 @@ static inline int IN_FROM_REG(int reg, int nominal, int res)
return (reg * nominal + (3 << (res - 3))) / (3 << (res - 2));
}

-static inline int IN_TO_REG(int val, int nominal)
+static inline int IN_TO_REG(long val, int nominal)
{
return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255);
}
@@ -293,7 +293,7 @@ static inline int TEMP_FROM_REG(int reg, int res)
return (reg * 1000) >> (res - 8);
}

-static inline int TEMP_TO_REG(int val)
+static inline int TEMP_TO_REG(long val)
{
return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127);
}
@@ -308,7 +308,7 @@ static inline int TEMP_RANGE_FROM_REG(int reg)
return TEMP_RANGE[(reg >> 4) & 0x0f];
}

-static int TEMP_RANGE_TO_REG(int val, int reg)
+static int TEMP_RANGE_TO_REG(long val, int reg)
{
int i;

@@ -331,7 +331,7 @@ static inline int TEMP_HYST_FROM_REG(int reg, int ix)
return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000;
}

-static inline int TEMP_HYST_TO_REG(int val, int ix, int reg)
+static inline int TEMP_HYST_TO_REG(long val, int ix, int reg)
{
int hyst = clamp_val((val + 500) / 1000, 0, 15);

@@ -347,7 +347,7 @@ static inline int FAN_FROM_REG(int reg, int tpc)
return (reg == 0 || reg == 0xffff) ? 0 : 90000 * 60 / reg;
}

-static inline int FAN_TO_REG(int val, int tpc)
+static inline int FAN_TO_REG(long val, int tpc)
{
if (tpc) {
return clamp_val(val / tpc, 0, 0xffff);
@@ -379,7 +379,7 @@ static inline int FAN_TYPE_FROM_REG(int reg)
return (edge > 0) ? 1 << (edge - 1) : 0;
}

-static inline int FAN_TYPE_TO_REG(int val, int reg)
+static inline int FAN_TYPE_TO_REG(long val, int reg)
{
int edge = (val == 4) ? 3 : val;

@@ -402,7 +402,7 @@ static int FAN_MAX_FROM_REG(int reg)
return 1000 + i * 500;
}

-static int FAN_MAX_TO_REG(int val)
+static int FAN_MAX_TO_REG(long val)
{
int i;

@@ -460,7 +460,7 @@ static inline int PWM_ACZ_FROM_REG(int reg)
return acz[(reg >> 5) & 0x07];
}

-static inline int PWM_ACZ_TO_REG(int val, int reg)
+static inline int PWM_ACZ_TO_REG(long val, int reg)
{
int acz = (val == 4) ? 2 : val - 1;

@@ -476,7 +476,7 @@ static inline int PWM_FREQ_FROM_REG(int reg)
return PWM_FREQ[reg & 0x0f];
}

-static int PWM_FREQ_TO_REG(int val, int reg)
+static int PWM_FREQ_TO_REG(long val, int reg)
{
int i;

@@ -510,7 +510,7 @@ static inline int PWM_RR_FROM_REG(int reg, int ix)
return (rr & 0x08) ? PWM_RR[rr & 0x07] : 0;
}

-static int PWM_RR_TO_REG(int val, int ix, int reg)
+static int PWM_RR_TO_REG(long val, int ix, int reg)
{
int i;

@@ -528,7 +528,7 @@ static inline int PWM_RR_EN_FROM_REG(int reg, int ix)
return PWM_RR_FROM_REG(reg, ix) ? 1 : 0;
}

-static inline int PWM_RR_EN_TO_REG(int val, int ix, int reg)
+static inline int PWM_RR_EN_TO_REG(long val, int ix, int reg)
{
int en = (ix == 1) ? 0x80 : 0x08;

@@ -1481,13 +1481,16 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct dme1737_data *data = dev_get_drvdata(dev);
- long val;
+ unsigned long val;
int err;

- err = kstrtol(buf, 10, &val);
+ err = kstrtoul(buf, 10, &val);
if (err)
return err;

+ if (val > 255)
+ return -EINVAL;
+
data->vrm = val;
return count;
}
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 73181be..814f7ee 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -173,7 +173,7 @@ static int get_fan_speed_index(struct gpio_fan_data *fan_data)
return -ENODEV;
}

-static int rpm_to_speed_index(struct gpio_fan_data *fan_data, int rpm)
+static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm)
{
struct gpio_fan_speed *speed = fan_data->speed;
int i;
diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c
index a2f3b4a..b879427 100644
--- a/drivers/hwmon/lm78.c
+++ b/drivers/hwmon/lm78.c
@@ -108,7 +108,7 @@ static inline int FAN_FROM_REG(u8 val, int div)
* TEMP: mC (-128C to +127C)
* REG: 1C/bit, two's complement
*/
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
{
int nval = clamp_val(val, -128000, 127000) ;
return nval < 0 ? (nval - 500) / 1000 : (nval + 500) / 1000;
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index 3894c40..b9d6e7d 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -158,7 +158,7 @@ static inline u16 FAN_TO_REG(unsigned long val)

/* Temperature is reported in .001 degC increments */
#define TEMP_TO_REG(val) \
- clamp_val(SCALE(val, 1000, 1), -127, 127)
+ DIV_ROUND_CLOSEST(clamp_val((val), -127000, 127000), 1000)
#define TEMPEXT_FROM_REG(val, ext) \
SCALE(((val) << 4) + (ext), 16, 1000)
#define TEMP_FROM_REG(val) ((val) * 1000)
@@ -192,7 +192,7 @@ static const int lm85_range_map[] = {
13300, 16000, 20000, 26600, 32000, 40000, 53300, 80000
};

-static int RANGE_TO_REG(int range)
+static int RANGE_TO_REG(long range)
{
int i;

@@ -214,7 +214,7 @@ static const int adm1027_freq_map[8] = { /* 1 Hz */
11, 15, 22, 29, 35, 44, 59, 88
};

-static int FREQ_TO_REG(const int *map, int freq)
+static int FREQ_TO_REG(const int *map, unsigned long freq)
{
int i;

@@ -463,6 +463,9 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
if (err)
return err;

+ if (val > 255)
+ return -EINVAL;
+
data->vrm = val;
return count;
}
diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c
index 72a8897..9ec7d2e 100644
--- a/drivers/hwmon/sis5595.c
+++ b/drivers/hwmon/sis5595.c
@@ -159,7 +159,7 @@ static inline int TEMP_FROM_REG(s8 val)
{
return val * 830 + 52120;
}
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
{
int nval = clamp_val(val, -54120, 157530) ;
return nval < 0 ? (nval - 5212 - 415) / 830 : (nval - 5212 + 415) / 830;
diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c
index 8edba9d..d13d3bb 100644
--- a/drivers/i2c/busses/i2c-at91.c
+++ b/drivers/i2c/busses/i2c-at91.c
@@ -210,7 +210,7 @@ static void at91_twi_write_data_dma_callback(void *data)
struct at91_twi_dev *dev = (struct at91_twi_dev *)data;

dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
- dev->buf_len, DMA_MEM_TO_DEV);
+ dev->buf_len, DMA_TO_DEVICE);

at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
}
@@ -289,7 +289,7 @@ static void at91_twi_read_data_dma_callback(void *data)
struct at91_twi_dev *dev = (struct at91_twi_dev *)data;

dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
- dev->buf_len, DMA_DEV_TO_MEM);
+ dev->buf_len, DMA_FROM_DEVICE);

/* The last two bytes have to be read without using dma */
dev->buf += dev->buf_len - 2;
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 0717940..a86b6ca 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -46,6 +46,7 @@
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/module.h>
+#include <linux/sysctl.h>

#include <rdma/iw_cm.h>
#include <rdma/ib_addr.h>
@@ -65,6 +66,20 @@ struct iwcm_work {
struct list_head free_list;
};

+static unsigned int default_backlog = 256;
+
+static struct ctl_table_header *iwcm_ctl_table_hdr;
+static struct ctl_table iwcm_ctl_table[] = {
+ {
+ .procname = "default_backlog",
+ .data = &default_backlog,
+ .maxlen = sizeof(default_backlog),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ { }
+};
+
/*
* The following services provide a mechanism for pre-allocating iwcm_work
* elements. The design pre-allocates them based on the cm_id type:
@@ -426,6 +441,9 @@ int iw_cm_listen(struct iw_cm_id *cm_id, int backlog)

cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);

+ if (!backlog)
+ backlog = default_backlog;
+
ret = alloc_work_entries(cm_id_priv, backlog);
if (ret)
return ret;
@@ -1031,11 +1049,20 @@ static int __init iw_cm_init(void)
if (!iwcm_wq)
return -ENOMEM;

+ iwcm_ctl_table_hdr = register_net_sysctl(&init_net, "net/iw_cm",
+ iwcm_ctl_table);
+ if (!iwcm_ctl_table_hdr) {
+ pr_err("iw_cm: couldn't register sysctl paths\n");
+ destroy_workqueue(iwcm_wq);
+ return -ENOMEM;
+ }
+
return 0;
}

static void __exit iw_cm_cleanup(void)
{
+ unregister_net_sysctl_table(iwcm_ctl_table_hdr);
destroy_workqueue(iwcm_wq);
}

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index c74d8b6..a7d51c5 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -120,6 +120,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr);
static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event);

static struct scsi_transport_template *ib_srp_transport_template;
+static struct workqueue_struct *srp_remove_wq;

static struct ib_client srp_client = {
.name = "srp",
@@ -539,7 +540,7 @@ static bool srp_queue_remove_work(struct srp_target_port *target)
spin_unlock_irq(&target->lock);

if (changed)
- queue_work(system_long_wq, &target->remove_work);
+ queue_work(srp_remove_wq, &target->remove_work);

return changed;
}
@@ -2885,9 +2886,10 @@ static void srp_remove_one(struct ib_device *device)
spin_unlock(&host->target_lock);

/*
- * Wait for target port removal tasks.
+ * Wait for tl_err and target port removal tasks.
*/
flush_workqueue(system_long_wq);
+ flush_workqueue(srp_remove_wq);

kfree(host);
}
@@ -2939,16 +2941,22 @@ static int __init srp_init_module(void)
indirect_sg_entries = cmd_sg_entries;
}

+ srp_remove_wq = create_workqueue("srp_remove");
+ if (IS_ERR(srp_remove_wq)) {
+ ret = PTR_ERR(srp_remove_wq);
+ goto out;
+ }
+
+ ret = -ENOMEM;
ib_srp_transport_template =
srp_attach_transport(&ib_srp_transport_functions);
if (!ib_srp_transport_template)
- return -ENOMEM;
+ goto destroy_wq;

ret = class_register(&srp_class);
if (ret) {
pr_err("couldn't register class infiniband_srp\n");
- srp_release_transport(ib_srp_transport_template);
- return ret;
+ goto release_tr;
}

ib_sa_register_client(&srp_sa_client);
@@ -2956,13 +2964,22 @@ static int __init srp_init_module(void)
ret = ib_register_client(&srp_client);
if (ret) {
pr_err("couldn't register IB client\n");
- srp_release_transport(ib_srp_transport_template);
- ib_sa_unregister_client(&srp_sa_client);
- class_unregister(&srp_class);
- return ret;
+ goto unreg_sa;
}

- return 0;
+out:
+ return ret;
+
+unreg_sa:
+ ib_sa_unregister_client(&srp_sa_client);
+ class_unregister(&srp_class);
+
+release_tr:
+ srp_release_transport(ib_srp_transport_template);
+
+destroy_wq:
+ destroy_workqueue(srp_remove_wq);
+ goto out;
}

static void __exit srp_cleanup_module(void)
@@ -2971,6 +2988,7 @@ static void __exit srp_cleanup_module(void)
ib_sa_unregister_client(&srp_sa_client);
class_unregister(&srp_class);
srp_release_transport(ib_srp_transport_template);
+ destroy_workqueue(srp_remove_wq);
}

module_init(srp_init_module);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 5166401..f4d5e52 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1500,12 +1500,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
mddev->degraded++;
set_bit(Faulty, &rdev->flags);
spin_unlock_irqrestore(&conf->device_lock, flags);
- /*
- * if recovery is running, make sure it aborts.
- */
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
} else
set_bit(Faulty, &rdev->flags);
+ /*
+ * if recovery is running, make sure it aborts.
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT
"md/raid1:%s: Disk failure on %s, disabling device.\n"
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 06eeb99..496a46e 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1698,13 +1698,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
spin_unlock_irqrestore(&conf->device_lock, flags);
return;
}
- if (test_and_clear_bit(In_sync, &rdev->flags)) {
+ if (test_and_clear_bit(In_sync, &rdev->flags))
mddev->degraded++;
- /*
- * if recovery is running, make sure it aborts.
- */
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- }
+ /*
+ * If recovery is running, make sure it aborts.
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(Blocked, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index 703560f..88c1606 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -106,8 +106,6 @@ static long media_device_enum_entities(struct media_device *mdev,
if (ent->name) {
strncpy(u_ent.name, ent->name, sizeof(u_ent.name));
u_ent.name[sizeof(u_ent.name) - 1] = '\0';
- } else {
- memset(u_ent.name, 0, sizeof(u_ent.name));
}
u_ent.type = ent->type;
u_ent.revision = ent->revision;
diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c
index 4b0ac07..daa992c 100644
--- a/drivers/media/platform/vsp1/vsp1_video.c
+++ b/drivers/media/platform/vsp1/vsp1_video.c
@@ -622,8 +622,6 @@ static int vsp1_video_buffer_prepare(struct vb2_buffer *vb)
if (vb->num_planes < format->num_planes)
return -EINVAL;

- buf->video = video;
-
for (i = 0; i < vb->num_planes; ++i) {
buf->addr[i] = vb2_dma_contig_plane_dma_addr(vb, i);
buf->length[i] = vb2_plane_size(vb, i);
diff --git a/drivers/media/platform/vsp1/vsp1_video.h b/drivers/media/platform/vsp1/vsp1_video.h
index d8612a3..47b7a8a 100644
--- a/drivers/media/platform/vsp1/vsp1_video.h
+++ b/drivers/media/platform/vsp1/vsp1_video.h
@@ -89,7 +89,6 @@ static inline struct vsp1_pipeline *to_vsp1_pipeline(struct media_entity *e)
}

struct vsp1_video_buffer {
- struct vsp1_video *video;
struct vb2_buffer buf;
struct list_head queue;

diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index 2018bef..e71decb 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -93,7 +93,7 @@ struct xc4000_priv {
struct firmware_description *firm;
int firm_size;
u32 if_khz;
- u32 freq_hz;
+ u32 freq_hz, freq_offset;
u32 bandwidth;
u8 video_standard;
u8 rf_mode;
@@ -1157,14 +1157,14 @@ static int xc4000_set_params(struct dvb_frontend *fe)
case SYS_ATSC:
dprintk(1, "%s() VSB modulation\n", __func__);
priv->rf_mode = XC_RF_MODE_AIR;
- priv->freq_hz = c->frequency - 1750000;
+ priv->freq_offset = 1750000;
priv->video_standard = XC4000_DTV6;
type = DTV6;
break;
case SYS_DVBC_ANNEX_B:
dprintk(1, "%s() QAM modulation\n", __func__);
priv->rf_mode = XC_RF_MODE_CABLE;
- priv->freq_hz = c->frequency - 1750000;
+ priv->freq_offset = 1750000;
priv->video_standard = XC4000_DTV6;
type = DTV6;
break;
@@ -1173,23 +1173,23 @@ static int xc4000_set_params(struct dvb_frontend *fe)
dprintk(1, "%s() OFDM\n", __func__);
if (bw == 0) {
if (c->frequency < 400000000) {
- priv->freq_hz = c->frequency - 2250000;
+ priv->freq_offset = 2250000;
} else {
- priv->freq_hz = c->frequency - 2750000;
+ priv->freq_offset = 2750000;
}
priv->video_standard = XC4000_DTV7_8;
type = DTV78;
} else if (bw <= 6000000) {
priv->video_standard = XC4000_DTV6;
- priv->freq_hz = c->frequency - 1750000;
+ priv->freq_offset = 1750000;
type = DTV6;
} else if (bw <= 7000000) {
priv->video_standard = XC4000_DTV7;
- priv->freq_hz = c->frequency - 2250000;
+ priv->freq_offset = 2250000;
type = DTV7;
} else {
priv->video_standard = XC4000_DTV8;
- priv->freq_hz = c->frequency - 2750000;
+ priv->freq_offset = 2750000;
type = DTV8;
}
priv->rf_mode = XC_RF_MODE_AIR;
@@ -1200,6 +1200,8 @@ static int xc4000_set_params(struct dvb_frontend *fe)
goto fail;
}

+ priv->freq_hz = c->frequency - priv->freq_offset;
+
dprintk(1, "%s() frequency=%d (compensated)\n",
__func__, priv->freq_hz);

@@ -1520,7 +1522,7 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq)
{
struct xc4000_priv *priv = fe->tuner_priv;

- *freq = priv->freq_hz;
+ *freq = priv->freq_hz + priv->freq_offset;

if (debug) {
mutex_lock(&priv->lock);
diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c
index 5cd09a6..b2d9e9c 100644
--- a/drivers/media/tuners/xc5000.c
+++ b/drivers/media/tuners/xc5000.c
@@ -55,7 +55,7 @@ struct xc5000_priv {

u32 if_khz;
u16 xtal_khz;
- u32 freq_hz;
+ u32 freq_hz, freq_offset;
u32 bandwidth;
u8 video_standard;
u8 rf_mode;
@@ -755,13 +755,13 @@ static int xc5000_set_params(struct dvb_frontend *fe)
case SYS_ATSC:
dprintk(1, "%s() VSB modulation\n", __func__);
priv->rf_mode = XC_RF_MODE_AIR;
- priv->freq_hz = freq - 1750000;
+ priv->freq_offset = 1750000;
priv->video_standard = DTV6;
break;
case SYS_DVBC_ANNEX_B:
dprintk(1, "%s() QAM modulation\n", __func__);
priv->rf_mode = XC_RF_MODE_CABLE;
- priv->freq_hz = freq - 1750000;
+ priv->freq_offset = 1750000;
priv->video_standard = DTV6;
break;
case SYS_ISDBT:
@@ -776,15 +776,15 @@ static int xc5000_set_params(struct dvb_frontend *fe)
switch (bw) {
case 6000000:
priv->video_standard = DTV6;
- priv->freq_hz = freq - 1750000;
+ priv->freq_offset = 1750000;
break;
case 7000000:
priv->video_standard = DTV7;
- priv->freq_hz = freq - 2250000;
+ priv->freq_offset = 2250000;
break;
case 8000000:
priv->video_standard = DTV8;
- priv->freq_hz = freq - 2750000;
+ priv->freq_offset = 2750000;
break;
default:
printk(KERN_ERR "xc5000 bandwidth not set!\n");
@@ -798,15 +798,15 @@ static int xc5000_set_params(struct dvb_frontend *fe)
priv->rf_mode = XC_RF_MODE_CABLE;
if (bw <= 6000000) {
priv->video_standard = DTV6;
- priv->freq_hz = freq - 1750000;
+ priv->freq_offset = 1750000;
b = 6;
} else if (bw <= 7000000) {
priv->video_standard = DTV7;
- priv->freq_hz = freq - 2250000;
+ priv->freq_offset = 2250000;
b = 7;
} else {
priv->video_standard = DTV7_8;
- priv->freq_hz = freq - 2750000;
+ priv->freq_offset = 2750000;
b = 8;
}
dprintk(1, "%s() Bandwidth %dMHz (%d)\n", __func__,
@@ -817,6 +817,8 @@ static int xc5000_set_params(struct dvb_frontend *fe)
return -EINVAL;
}

+ priv->freq_hz = freq - priv->freq_offset;
+
dprintk(1, "%s() frequency=%d (compensated to %d)\n",
__func__, freq, priv->freq_hz);

@@ -1067,7 +1069,7 @@ static int xc5000_get_frequency(struct dvb_frontend *fe, u32 *freq)
{
struct xc5000_priv *priv = fe->tuner_priv;
dprintk(1, "%s()\n", __func__);
- *freq = priv->freq_hz;
+ *freq = priv->freq_hz + priv->freq_offset;
return 0;
}

diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index f615454..7ed75ef 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -787,11 +787,27 @@ static int au0828_i2s_init(struct au0828_dev *dev)

/*
* Auvitek au0828 analog stream enable
- * Please set interface0 to AS5 before enable the stream
*/
static int au0828_analog_stream_enable(struct au0828_dev *d)
{
+ struct usb_interface *iface;
+ int ret;
+
dprintk(1, "au0828_analog_stream_enable called\n");
+
+ iface = usb_ifnum_to_if(d->usbdev, 0);
+ if (iface && iface->cur_altsetting->desc.bAlternateSetting != 5) {
+ dprintk(1, "Changing intf#0 to alt 5\n");
+ /* set au0828 interface0 to AS5 here again */
+ ret = usb_set_interface(d->usbdev, 0, 5);
+ if (ret < 0) {
+ printk(KERN_INFO "Au0828 can't set alt setting to 5!\n");
+ return -EBUSY;
+ }
+ }
+
+ /* FIXME: size should be calculated using d->width, d->height */
+
au0828_writereg(d, AU0828_SENSORCTRL_VBI_103, 0x00);
au0828_writereg(d, 0x106, 0x00);
/* set x position */
@@ -1002,15 +1018,6 @@ static int au0828_v4l2_open(struct file *filp)
return -ERESTARTSYS;
}
if (dev->users == 0) {
- /* set au0828 interface0 to AS5 here again */
- ret = usb_set_interface(dev->usbdev, 0, 5);
- if (ret < 0) {
- mutex_unlock(&dev->lock);
- printk(KERN_INFO "Au0828 can't set alternate to 5!\n");
- kfree(fh);
- return -EBUSY;
- }
-
au0828_analog_stream_enable(dev);
au0828_analog_stream_reset(dev);

@@ -1252,13 +1259,6 @@ static int au0828_set_format(struct au0828_dev *dev, unsigned int cmd,
}
}

- /* set au0828 interface0 to AS5 here again */
- ret = usb_set_interface(dev->usbdev, 0, 5);
- if (ret < 0) {
- printk(KERN_INFO "Au0828 can't set alt setting to 5!\n");
- return -EBUSY;
- }
-
au0828_analog_stream_enable(dev);

return 0;
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 142650f..fcf426d 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -445,7 +445,7 @@ static unsigned omap_usbhs_rev1_hostconfig(struct usbhs_hcd_omap *omap,

for (i = 0; i < omap->nports; i++) {
if (is_ehci_phy_mode(pdata->port_mode[i])) {
- reg &= OMAP_UHH_HOSTCONFIG_ULPI_BYPASS;
+ reg &= ~OMAP_UHH_HOSTCONFIG_ULPI_BYPASS;
break;
}
}
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 714a998..0a91a23 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -436,7 +436,7 @@ int mei_cl_disconnect(struct mei_cl *cl)
{
struct mei_device *dev;
struct mei_cl_cb *cb;
- int rets, err;
+ int rets;

if (WARN_ON(!cl || !cl->dev))
return -ENODEV;
@@ -460,6 +460,7 @@ int mei_cl_disconnect(struct mei_cl *cl)
cl_err(dev, cl, "failed to disconnect.\n");
goto free;
}
+ cl->timer_count = MEI_CONNECT_TIMEOUT;
mdelay(10); /* Wait for hardware disconnection ready */
list_add_tail(&cb->list, &dev->ctrl_rd_list.list);
} else {
@@ -469,24 +470,18 @@ int mei_cl_disconnect(struct mei_cl *cl)
}
mutex_unlock(&dev->device_lock);

- err = wait_event_timeout(dev->wait_recvd_msg,
+ wait_event_timeout(dev->wait_recvd_msg,
MEI_FILE_DISCONNECTED == cl->state,
mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT));

mutex_lock(&dev->device_lock);
+
if (MEI_FILE_DISCONNECTED == cl->state) {
rets = 0;
cl_dbg(dev, cl, "successfully disconnected from FW client.\n");
} else {
- rets = -ENODEV;
- if (MEI_FILE_DISCONNECTED != cl->state)
- cl_err(dev, cl, "wrong status client disconnect.\n");
-
- if (err)
- cl_dbg(dev, cl, "wait failed disconnect err=%08x\n",
- err);
-
- cl_err(dev, cl, "failed to disconnect from FW client.\n");
+ cl_dbg(dev, cl, "timeout on disconnect from FW client.\n");
+ rets = -ETIME;
}

mei_io_list_flush(&dev->ctrl_rd_list, cl);
diff --git a/drivers/mtd/ftl.c b/drivers/mtd/ftl.c
index 19d6372..71e4f6c 100644
--- a/drivers/mtd/ftl.c
+++ b/drivers/mtd/ftl.c
@@ -1075,7 +1075,6 @@ static void ftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
return;
}

- ftl_freepart(partition);
kfree(partition);
}

diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 81576c6..ac73553 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -623,8 +623,10 @@ static void emac_rx(struct net_device *dev)
}

/* Move data from EMAC */
- skb = dev_alloc_skb(rxlen + 4);
- if (good_packet && skb) {
+ if (good_packet) {
+ skb = netdev_alloc_skb(dev, rxlen + 4);
+ if (!skb)
+ continue;
skb_reserve(skb, 2);
rdptr = (u8 *) skb_put(skb, rxlen - 4);

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index ec61190..a162f82 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -337,6 +337,7 @@ struct sw_tx_bd {
u8 flags;
/* Set on the first BD descriptor when there is a split BD */
#define BNX2X_TSO_SPLIT_BD (1<<0)
+#define BNX2X_HAS_SECOND_PBD (1<<1)
};

struct sw_rx_page {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index db7654a..a9324f4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -186,6 +186,12 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
--nbd;
bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));

+ if (tx_buf->flags & BNX2X_HAS_SECOND_PBD) {
+ /* Skip second parse bd... */
+ --nbd;
+ bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
+ }
+
/* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */
if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) {
tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd;
@@ -862,6 +868,18 @@ int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
bd_prod = RX_BD(bd_prod);
bd_cons = RX_BD(bd_cons);

+ /* A rmb() is required to ensure that the CQE is not read
+ * before it is written by the adapter DMA. PCI ordering
+ * rules will make sure the other fields are written before
+ * the marker at the end of struct eth_fast_path_rx_cqe
+ * but without rmb() a weakly ordered processor can process
+ * stale data. Without the barrier TPA state-machine might
+ * enter inconsistent state and kernel stack might be
+ * provided with incorrect packet description - these lead
+ * to various kernel crashed.
+ */
+ rmb();
+
cqe_fp_flags = cqe_fp->type_error_flags;
cqe_fp_type = cqe_fp_flags & ETH_FAST_PATH_RX_CQE_TYPE;

@@ -3825,6 +3843,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
/* set encapsulation flag in start BD */
SET_FLAG(tx_start_bd->general_data,
ETH_TX_START_BD_TUNNEL_EXIST, 1);
+
+ tx_buf->flags |= BNX2X_HAS_SECOND_PBD;
+
nbd++;
} else if (xmit_type & XMIT_CSUM) {
/* Set PBD in checksum offload case w/o encapsulation */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 0067b97..71d3f0c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12998,8 +12998,8 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp)
netdev_reset_tc(bp->dev);

del_timer_sync(&bp->timer);
- cancel_delayed_work(&bp->sp_task);
- cancel_delayed_work(&bp->period_task);
+ cancel_delayed_work_sync(&bp->sp_task);
+ cancel_delayed_work_sync(&bp->period_task);

spin_lock_bh(&bp->stats_lock);
bp->stats_state = STATS_STATE_DISABLED;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 333f8bc..a430b99 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -549,6 +549,7 @@ static int macvlan_init(struct net_device *dev)
(lowerdev->state & MACVLAN_STATE_MASK);
dev->features = lowerdev->features & MACVLAN_FEATURES;
dev->features |= ALWAYS_ON_FEATURES;
+ dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES;
dev->gso_max_size = lowerdev->gso_max_size;
dev->iflink = lowerdev->ifindex;
dev->hard_header_len = lowerdev->hard_header_len;
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 0180531..1aff970 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
nf_reset(skb);

skb->ip_summed = CHECKSUM_NONE;
- ip_select_ident(skb, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
ip_send_check(iph);

ip_local_out(skb);
diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h
index 8596aba..237d0cd 100644
--- a/drivers/net/wireless/ath/carl9170/carl9170.h
+++ b/drivers/net/wireless/ath/carl9170/carl9170.h
@@ -256,6 +256,7 @@ struct ar9170 {
atomic_t rx_work_urbs;
atomic_t rx_pool_urbs;
kernel_ulong_t features;
+ bool usb_ep_cmd_is_bulk;

/* firmware settings */
struct completion fw_load_wait;
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index ca115f3..bc931f6 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -621,9 +621,16 @@ int __carl9170_exec_cmd(struct ar9170 *ar, struct carl9170_cmd *cmd,
goto err_free;
}

- usb_fill_int_urb(urb, ar->udev, usb_sndintpipe(ar->udev,
- AR9170_USB_EP_CMD), cmd, cmd->hdr.len + 4,
- carl9170_usb_cmd_complete, ar, 1);
+ if (ar->usb_ep_cmd_is_bulk)
+ usb_fill_bulk_urb(urb, ar->udev,
+ usb_sndbulkpipe(ar->udev, AR9170_USB_EP_CMD),
+ cmd, cmd->hdr.len + 4,
+ carl9170_usb_cmd_complete, ar);
+ else
+ usb_fill_int_urb(urb, ar->udev,
+ usb_sndintpipe(ar->udev, AR9170_USB_EP_CMD),
+ cmd, cmd->hdr.len + 4,
+ carl9170_usb_cmd_complete, ar, 1);

if (free_buf)
urb->transfer_flags |= URB_FREE_BUFFER;
@@ -1032,9 +1039,10 @@ static void carl9170_usb_firmware_step2(const struct firmware *fw,
static int carl9170_usb_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
+ struct usb_endpoint_descriptor *ep;
struct ar9170 *ar;
struct usb_device *udev;
- int err;
+ int i, err;

err = usb_reset_device(interface_to_usbdev(intf));
if (err)
@@ -1050,6 +1058,21 @@ static int carl9170_usb_probe(struct usb_interface *intf,
ar->intf = intf;
ar->features = id->driver_info;

+ /* We need to remember the type of endpoint 4 because it differs
+ * between high- and full-speed configuration. The high-speed
+ * configuration specifies it as interrupt and the full-speed
+ * configuration as bulk endpoint. This information is required
+ * later when sending urbs to that endpoint.
+ */
+ for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; ++i) {
+ ep = &intf->cur_altsetting->endpoint[i].desc;
+
+ if (usb_endpoint_num(ep) == AR9170_USB_EP_CMD &&
+ usb_endpoint_dir_out(ep) &&
+ usb_endpoint_type(ep) == USB_ENDPOINT_XFER_BULK)
+ ar->usb_ep_cmd_is_bulk = true;
+ }
+
usb_set_intfdata(intf, ar);
SET_IEEE80211_DEV(ar->hw, &intf->dev);

diff --git a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
index 1fc0332..07d78ac 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
@@ -1148,10 +1148,18 @@ int iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm,
static void iwl_mvm_beacon_loss_iterator(void *_data, u8 *mac,
struct ieee80211_vif *vif)
{
- u16 *id = _data;
+ struct iwl_missed_beacons_notif *missed_beacons = _data;
struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);

- if (mvmvif->id == *id)
+ if (mvmvif->id != (u16)le32_to_cpu(missed_beacons->mac_id))
+ return;
+
+ /*
+ * TODO: the threshold should be adjusted based on latency conditions,
+ * and/or in case of a CS flow on one of the other AP vifs.
+ */
+ if (le32_to_cpu(missed_beacons->consec_missed_beacons_since_last_rx) >
+ IWL_MVM_MISSED_BEACONS_THRESHOLD)
ieee80211_beacon_loss(vif);
}

@@ -1160,12 +1168,19 @@ int iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm,
struct iwl_device_cmd *cmd)
{
struct iwl_rx_packet *pkt = rxb_addr(rxb);
- struct iwl_missed_beacons_notif *missed_beacons = (void *)pkt->data;
- u16 id = (u16)le32_to_cpu(missed_beacons->mac_id);
+ struct iwl_missed_beacons_notif *mb = (void *)pkt->data;
+
+ IWL_DEBUG_INFO(mvm,
+ "missed bcn mac_id=%u, consecutive=%u (%u, %u, %u)\n",
+ le32_to_cpu(mb->mac_id),
+ le32_to_cpu(mb->consec_missed_beacons),
+ le32_to_cpu(mb->consec_missed_beacons_since_last_rx),
+ le32_to_cpu(mb->num_recvd_beacons),
+ le32_to_cpu(mb->num_expected_beacons));

ieee80211_iterate_active_interfaces_atomic(mvm->hw,
IEEE80211_IFACE_ITER_NORMAL,
iwl_mvm_beacon_loss_iterator,
- &id);
+ mb);
return 0;
}
diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h
index 17f1096..0f0de23 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h
@@ -81,6 +81,7 @@
#define IWL_MVM_MAX_ADDRESSES 5
/* RSSI offset for WkP */
#define IWL_RSSI_OFFSET 50
+#define IWL_MVM_MISSED_BEACONS_THRESHOLD 8

enum iwl_mvm_tx_fifo {
IWL_MVM_TX_FIFO_BK = 0,
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1a8a4fd..49ca284 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -782,12 +782,6 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)

if (!__pci_complete_power_transition(dev, state))
error = 0;
- /*
- * When aspm_policy is "powersave" this call ensures
- * that ASPM is configured.
- */
- if (!error && dev->bus->self)
- pcie_aspm_powersave_config_link(dev->bus->self);

return error;
}
@@ -1120,12 +1114,18 @@ EXPORT_SYMBOL_GPL(pci_load_and_free_saved_state);
static int do_pci_enable_device(struct pci_dev *dev, int bars)
{
int err;
+ struct pci_dev *bridge;
u16 cmd;
u8 pin;

err = pci_set_power_state(dev, PCI_D0);
if (err < 0 && err != -EIO)
return err;
+
+ bridge = pci_upstream_bridge(dev);
+ if (bridge)
+ pcie_aspm_powersave_config_link(bridge);
+
err = pcibios_enable_device(dev, bars);
if (err < 0)
return err;
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index f0ea4fd..8b963a7 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -141,8 +141,6 @@ static struct regulator_ops arizona_ldo1_ops = {
.map_voltage = regulator_map_voltage_linear,
.get_voltage_sel = regulator_get_voltage_sel_regmap,
.set_voltage_sel = regulator_set_voltage_sel_regmap,
- .get_bypass = regulator_get_bypass_regmap,
- .set_bypass = regulator_set_bypass_regmap,
};

static const struct regulator_desc arizona_ldo1 = {
diff --git a/drivers/sbus/char/bbc_envctrl.c b/drivers/sbus/char/bbc_envctrl.c
index 160e751..0787b97 100644
--- a/drivers/sbus/char/bbc_envctrl.c
+++ b/drivers/sbus/char/bbc_envctrl.c
@@ -452,6 +452,9 @@ static void attach_one_temp(struct bbc_i2c_bus *bp, struct platform_device *op,
if (!tp)
return;

+ INIT_LIST_HEAD(&tp->bp_list);
+ INIT_LIST_HEAD(&tp->glob_list);
+
tp->client = bbc_i2c_attach(bp, op);
if (!tp->client) {
kfree(tp);
@@ -497,6 +500,9 @@ static void attach_one_fan(struct bbc_i2c_bus *bp, struct platform_device *op,
if (!fp)
return;

+ INIT_LIST_HEAD(&fp->bp_list);
+ INIT_LIST_HEAD(&fp->glob_list);
+
fp->client = bbc_i2c_attach(bp, op);
if (!fp->client) {
kfree(fp);
diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c
index c1441ed..e0e6cd6 100644
--- a/drivers/sbus/char/bbc_i2c.c
+++ b/drivers/sbus/char/bbc_i2c.c
@@ -301,13 +301,18 @@ static struct bbc_i2c_bus * attach_one_i2c(struct platform_device *op, int index
if (!bp)
return NULL;

+ INIT_LIST_HEAD(&bp->temps);
+ INIT_LIST_HEAD(&bp->fans);
+
bp->i2c_control_regs = of_ioremap(&op->resource[0], 0, 0x2, "bbc_i2c_regs");
if (!bp->i2c_control_regs)
goto fail;

- bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
- if (!bp->i2c_bussel_reg)
- goto fail;
+ if (op->num_resources == 2) {
+ bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
+ if (!bp->i2c_bussel_reg)
+ goto fail;
+ }

bp->waiting = 0;
init_waitqueue_head(&bp->wq);
diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h
index 90814fe..d5b3f66 100644
--- a/drivers/scsi/bfa/bfa_ioc.h
+++ b/drivers/scsi/bfa/bfa_ioc.h
@@ -72,7 +72,7 @@ struct bfa_sge_s {
} while (0)

#define bfa_swap_words(_x) ( \
- ((_x) << 32) | ((_x) >> 32))
+ ((u64)(_x) << 32) | ((u64)(_x) >> 32))

#ifdef __BIG_ENDIAN
#define bfa_sge_to_be(_x)
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index ad034ab..d518bba 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -3151,7 +3151,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp)
}
if (ioc->Request.Type.Direction == XFER_WRITE) {
if (copy_from_user(buff[sg_used], data_ptr, sz)) {
- status = -ENOMEM;
+ status = -EFAULT;
goto cleanup1;
}
} else
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index f969aca..49014a1 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -222,6 +222,7 @@ static struct {
{"PIONEER", "CD-ROM DRM-602X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
{"PIONEER", "CD-ROM DRM-604X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
{"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
+ {"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC},
{"Promise", "", NULL, BLIST_SPARSELUN},
{"QUANTUM", "XP34301", "1071", BLIST_NOTQ},
{"REGAL", "CDC-4X", NULL, BLIST_MAX5LUN | BLIST_SINGLELUN},
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 307a811..f194e43 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -898,6 +898,12 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
if (*bflags & BLIST_USE_10_BYTE_MS)
sdev->use_10_for_ms = 1;

+ /* some devices don't like REPORT SUPPORTED OPERATION CODES
+ * and will simply timeout causing sd_mod init to take a very
+ * very long time */
+ if (*bflags & BLIST_NO_RSOC)
+ sdev->no_report_opcodes = 1;
+
/* set the device running here so that slave configure
* may do I/O */
ret = scsi_device_set_state(sdev, SDEV_RUNNING);
@@ -926,7 +932,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,

sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT;

- if (*bflags & BLIST_SKIP_VPD_PAGES)
+ if (*bflags & BLIST_TRY_VPD_PAGES)
+ sdev->try_vpd_pages = 1;
+ else if (*bflags & BLIST_SKIP_VPD_PAGES)
sdev->skip_vpd_pages = 1;

transport_configure_device(&sdev->sdev_gendev);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 8ee2f56..2735c50 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2691,6 +2691,11 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer)

static int sd_try_extended_inquiry(struct scsi_device *sdp)
{
+ /* Attempt VPD inquiry if the device blacklist explicitly calls
+ * for it.
+ */
+ if (sdp->try_vpd_pages)
+ return 1;
/*
* Although VPD inquiries can go to SCSI-2 type devices,
* some USB ones crash on receiving them, and the pages
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 9969fa1..ed0f899 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -33,6 +33,7 @@
#include <linux/device.h>
#include <linux/hyperv.h>
#include <linux/mempool.h>
+#include <linux/blkdev.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_host.h>
@@ -330,17 +331,17 @@ static int storvsc_timeout = 180;

static void storvsc_on_channel_callback(void *context);

-/*
- * In Hyper-V, each port/path/target maps to 1 scsi host adapter. In
- * reality, the path/target is not used (ie always set to 0) so our
- * scsi host adapter essentially has 1 bus with 1 target that contains
- * up to 256 luns.
- */
-#define STORVSC_MAX_LUNS_PER_TARGET 64
-#define STORVSC_MAX_TARGETS 1
-#define STORVSC_MAX_CHANNELS 1
+#define STORVSC_MAX_LUNS_PER_TARGET 255
+#define STORVSC_MAX_TARGETS 2
+#define STORVSC_MAX_CHANNELS 8

+#define STORVSC_FC_MAX_LUNS_PER_TARGET 255
+#define STORVSC_FC_MAX_TARGETS 128
+#define STORVSC_FC_MAX_CHANNELS 8

+#define STORVSC_IDE_MAX_LUNS_PER_TARGET 64
+#define STORVSC_IDE_MAX_TARGETS 1
+#define STORVSC_IDE_MAX_CHANNELS 1

struct storvsc_cmd_request {
struct list_head entry;
@@ -1017,6 +1018,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
case ATA_12:
set_host_byte(scmnd, DID_PASSTHROUGH);
break;
+ /*
+ * On Some Windows hosts TEST_UNIT_READY command can return
+ * SRB_STATUS_ERROR, let the upper level code deal with it
+ * based on the sense information.
+ */
+ case TEST_UNIT_READY:
+ break;
default:
set_host_byte(scmnd, DID_TARGET_FAILURE);
}
@@ -1518,6 +1526,16 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
return SUCCESS;
}

+/*
+ * The host guarantees to respond to each command, although I/O latencies might
+ * be unbounded on Azure. Reset the timer unconditionally to give the host a
+ * chance to perform EH.
+ */
+static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
+{
+ return BLK_EH_RESET_TIMER;
+}
+
static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd)
{
bool allowed = true;
@@ -1553,9 +1571,19 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
struct vmscsi_request *vm_srb;
struct stor_mem_pools *memp = scmnd->device->hostdata;

- if (!storvsc_scsi_cmd_ok(scmnd)) {
- scmnd->scsi_done(scmnd);
- return 0;
+ if (vmstor_current_major <= VMSTOR_WIN8_MAJOR) {
+ /*
+ * On legacy hosts filter unimplemented commands.
+ * Future hosts are expected to correctly handle
+ * unsupported commands. Furthermore, it is
+ * possible that some of the currently
+ * unsupported commands maybe supported in
+ * future versions of the host.
+ */
+ if (!storvsc_scsi_cmd_ok(scmnd)) {
+ scmnd->scsi_done(scmnd);
+ return 0;
+ }
}

request_size = sizeof(struct storvsc_cmd_request);
@@ -1580,26 +1608,24 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
vm_srb = &cmd_request->vstor_packet.vm_srb;
vm_srb->win8_extension.time_out_value = 60;

+ vm_srb->win8_extension.srb_flags |=
+ (SRB_FLAGS_QUEUE_ACTION_ENABLE |
+ SRB_FLAGS_DISABLE_SYNCH_TRANSFER);

/* Build the SRB */
switch (scmnd->sc_data_direction) {
case DMA_TO_DEVICE:
vm_srb->data_in = WRITE_TYPE;
vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_OUT;
- vm_srb->win8_extension.srb_flags |=
- (SRB_FLAGS_QUEUE_ACTION_ENABLE |
- SRB_FLAGS_DISABLE_SYNCH_TRANSFER);
break;
case DMA_FROM_DEVICE:
vm_srb->data_in = READ_TYPE;
vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_IN;
- vm_srb->win8_extension.srb_flags |=
- (SRB_FLAGS_QUEUE_ACTION_ENABLE |
- SRB_FLAGS_DISABLE_SYNCH_TRANSFER);
break;
default:
vm_srb->data_in = UNKNOWN_TYPE;
- vm_srb->win8_extension.srb_flags = 0;
+ vm_srb->win8_extension.srb_flags |= (SRB_FLAGS_DATA_IN |
+ SRB_FLAGS_DATA_OUT);
break;
}

@@ -1687,11 +1713,11 @@ static struct scsi_host_template scsi_driver = {
.bios_param = storvsc_get_chs,
.queuecommand = storvsc_queuecommand,
.eh_host_reset_handler = storvsc_host_reset_handler,
+ .eh_timed_out = storvsc_eh_timed_out,
.slave_alloc = storvsc_device_alloc,
.slave_destroy = storvsc_device_destroy,
.slave_configure = storvsc_device_configure,
- .cmd_per_lun = 1,
- /* 64 max_queue * 1 target */
+ .cmd_per_lun = 255,
.can_queue = STORVSC_MAX_IO_REQUESTS*STORVSC_MAX_TARGETS,
.this_id = -1,
/* no use setting to 0 since ll_blk_rw reset it to 1 */
@@ -1743,19 +1769,25 @@ static int storvsc_probe(struct hv_device *device,
* set state to properly communicate with the host.
*/

- if (vmbus_proto_version == VERSION_WIN8) {
- sense_buffer_size = POST_WIN7_STORVSC_SENSE_BUFFER_SIZE;
- vmscsi_size_delta = 0;
- vmstor_current_major = VMSTOR_WIN8_MAJOR;
- vmstor_current_minor = VMSTOR_WIN8_MINOR;
- } else {
+ switch (vmbus_proto_version) {
+ case VERSION_WS2008:
+ case VERSION_WIN7:
sense_buffer_size = PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE;
vmscsi_size_delta = sizeof(struct vmscsi_win8_extension);
vmstor_current_major = VMSTOR_WIN7_MAJOR;
vmstor_current_minor = VMSTOR_WIN7_MINOR;
+ break;
+ default:
+ sense_buffer_size = POST_WIN7_STORVSC_SENSE_BUFFER_SIZE;
+ vmscsi_size_delta = 0;
+ vmstor_current_major = VMSTOR_WIN8_MAJOR;
+ vmstor_current_minor = VMSTOR_WIN8_MINOR;
+ break;
}

-
+ if (dev_id->driver_data == SFC_GUID)
+ scsi_driver.can_queue = (STORVSC_MAX_IO_REQUESTS *
+ STORVSC_FC_MAX_TARGETS);
host = scsi_host_alloc(&scsi_driver,
sizeof(struct hv_host_device));
if (!host)
@@ -1789,12 +1821,25 @@ static int storvsc_probe(struct hv_device *device,
host_dev->path = stor_device->path_id;
host_dev->target = stor_device->target_id;

- /* max # of devices per target */
- host->max_lun = STORVSC_MAX_LUNS_PER_TARGET;
- /* max # of targets per channel */
- host->max_id = STORVSC_MAX_TARGETS;
- /* max # of channels */
- host->max_channel = STORVSC_MAX_CHANNELS - 1;
+ switch (dev_id->driver_data) {
+ case SFC_GUID:
+ host->max_lun = STORVSC_FC_MAX_LUNS_PER_TARGET;
+ host->max_id = STORVSC_FC_MAX_TARGETS;
+ host->max_channel = STORVSC_FC_MAX_CHANNELS - 1;
+ break;
+
+ case SCSI_GUID:
+ host->max_lun = STORVSC_MAX_LUNS_PER_TARGET;
+ host->max_id = STORVSC_MAX_TARGETS;
+ host->max_channel = STORVSC_MAX_CHANNELS - 1;
+ break;
+
+ default:
+ host->max_lun = STORVSC_IDE_MAX_LUNS_PER_TARGET;
+ host->max_id = STORVSC_IDE_MAX_TARGETS;
+ host->max_channel = STORVSC_IDE_MAX_CHANNELS - 1;
+ break;
+ }
/* max cmd length */
host->max_cmd_len = STORVSC_MAX_CMD_LEN;

diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 744841e..fbc9ac9 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -404,8 +404,6 @@ static int orion_spi_probe(struct platform_device *pdev)
struct resource *r;
unsigned long tclk_hz;
int status = 0;
- const u32 *iprop;
- int size;

master = spi_alloc_master(&pdev->dev, sizeof(*spi));
if (master == NULL) {
@@ -416,10 +414,10 @@ static int orion_spi_probe(struct platform_device *pdev)
if (pdev->id != -1)
master->bus_num = pdev->id;
if (pdev->dev.of_node) {
- iprop = of_get_property(pdev->dev.of_node, "cell-index",
- &size);
- if (iprop && size == sizeof(*iprop))
- master->bus_num = *iprop;
+ u32 cell_index;
+ if (!of_property_read_u32(pdev->dev.of_node, "cell-index",
+ &cell_index))
+ master->bus_num = cell_index;
}

/* we support only mode 0, and no options */
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 0f02351..b5180c1 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -235,6 +235,9 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state)
/*
* Turn off DTR and RTS early.
*/
+ if (uart_console(uport) && tty)
+ uport->cons->cflag = tty->termios.c_cflag;
+
if (!tty || (tty->termios.c_cflag & HUPCL))
uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS);

diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 380fb53..1c0e2a4 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -157,6 +157,15 @@ receive_chars(struct uart_sunsab_port *up,
(up->port.line == up->port.cons->index))
saw_console_brk = 1;

+ if (count == 0) {
+ if (unlikely(stat->sreg.isr1 & SAB82532_ISR1_BRK)) {
+ stat->sreg.isr0 &= ~(SAB82532_ISR0_PERR |
+ SAB82532_ISR0_FERR);
+ up->port.icount.brk++;
+ uart_handle_break(&up->port);
+ }
+ }
+
for (i = 0; i < count; i++) {
unsigned char ch = buf[i], flag;

diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 967152a..74185cc 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -1411,7 +1411,7 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb,
u = (is_in ? URB_DIR_IN : URB_DIR_OUT);
if (uurb->flags & USBDEVFS_URB_ISO_ASAP)
u |= URB_ISO_ASAP;
- if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK)
+ if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK && is_in)
u |= URB_SHORT_NOT_OK;
if (uurb->flags & USBDEVFS_URB_NO_FSBR)
u |= URB_NO_FSBR;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 2de2f27..9d30359 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -3165,6 +3165,43 @@ static int finish_port_resume(struct usb_device *udev)
}

/*
+ * There are some SS USB devices which take longer time for link training.
+ * XHCI specs 4.19.4 says that when Link training is successful, port
+ * sets CSC bit to 1. So if SW reads port status before successful link
+ * training, then it will not find device to be present.
+ * USB Analyzer log with such buggy devices show that in some cases
+ * device switch on the RX termination after long delay of host enabling
+ * the VBUS. In few other cases it has been seen that device fails to
+ * negotiate link training in first attempt. It has been
+ * reported till now that few devices take as long as 2000 ms to train
+ * the link after host enabling its VBUS and termination. Following
+ * routine implements a 2000 ms timeout for link training. If in a case
+ * link trains before timeout, loop will exit earlier.
+ *
+ * FIXME: If a device was connected before suspend, but was removed
+ * while system was asleep, then the loop in the following routine will
+ * only exit at timeout.
+ *
+ * This routine should only be called when persist is enabled for a SS
+ * device.
+ */
+static int wait_for_ss_port_enable(struct usb_device *udev,
+ struct usb_hub *hub, int *port1,
+ u16 *portchange, u16 *portstatus)
+{
+ int status = 0, delay_ms = 0;
+
+ while (delay_ms < 2000) {
+ if (status || *portstatus & USB_PORT_STAT_CONNECTION)
+ break;
+ msleep(20);
+ delay_ms += 20;
+ status = hub_port_status(hub, *port1, portstatus, portchange);
+ }
+ return status;
+}
+
+/*
* usb_port_resume - re-activate a suspended usb device's upstream port
* @udev: device to re-activate, not a root hub
* Context: must be able to sleep; device not locked; pm locks held
@@ -3266,6 +3303,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)

clear_bit(port1, hub->busy_bits);

+ if (udev->persist_enabled && hub_is_superspeed(hub->hdev))
+ status = wait_for_ss_port_enable(udev, hub, &port1, &portchange,
+ &portstatus);
+
status = check_port_resume_type(udev,
hub, port1, status, portchange, portstatus);
if (status == 0)
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 3e86bf4..ca7b964 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -35,6 +35,21 @@ static const char hcd_name[] = "ehci-pci";
#define PCI_DEVICE_ID_INTEL_CE4100_USB 0x2e70

/*-------------------------------------------------------------------------*/
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC 0x0939
+static inline bool is_intel_quark_x1000(struct pci_dev *pdev)
+{
+ return pdev->vendor == PCI_VENDOR_ID_INTEL &&
+ pdev->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC;
+}
+
+/*
+ * 0x84 is the offset of in/out threshold register,
+ * and it is the same offset as the register of 'hostpc'.
+ */
+#define intel_quark_x1000_insnreg01 hostpc
+
+/* Maximum usable threshold value is 0x7f dwords for both IN and OUT */
+#define INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD 0x007f007f

/* called after powerup, by probe or system-pm "wakeup" */
static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev)
@@ -50,6 +65,16 @@ static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev)
if (!retval)
ehci_dbg(ehci, "MWI active\n");

+ /* Reset the threshold limit */
+ if (is_intel_quark_x1000(pdev)) {
+ /*
+ * For the Intel QUARK X1000, raise the I/O threshold to the
+ * maximum usable value in order to improve performance.
+ */
+ ehci_writel(ehci, INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD,
+ ehci->regs->intel_quark_x1000_insnreg01);
+ }
+
return 0;
}

diff --git a/drivers/usb/host/ohci-dbg.c b/drivers/usb/host/ohci-dbg.c
index 3fca52e..80f9f2a 100644
--- a/drivers/usb/host/ohci-dbg.c
+++ b/drivers/usb/host/ohci-dbg.c
@@ -289,7 +289,7 @@ ohci_dump_roothub (
}
}

-static void ohci_dump (struct ohci_hcd *controller, int verbose)
+static void ohci_dump(struct ohci_hcd *controller)
{
ohci_dbg (controller, "OHCI controller state\n");

@@ -408,7 +408,7 @@ ohci_dump_ed (const struct ohci_hcd *ohci, const char *label,
}

#else
-static inline void ohci_dump (struct ohci_hcd *controller, int verbose) {}
+static inline void ohci_dump (struct ohci_hcd *controller) {}

#undef OHCI_VERBOSE_DEBUG

@@ -531,15 +531,16 @@ show_list (struct ohci_hcd *ohci, char *buf, size_t count, struct ed *ed)
static ssize_t fill_async_buffer(struct debug_buffer *buf)
{
struct ohci_hcd *ohci;
- size_t temp;
+ size_t temp, size;
unsigned long flags;

ohci = buf->ohci;
+ size = PAGE_SIZE;

/* display control and bulk lists together, for simplicity */
spin_lock_irqsave (&ohci->lock, flags);
- temp = show_list(ohci, buf->page, buf->count, ohci->ed_controltail);
- temp += show_list(ohci, buf->page + temp, buf->count - temp,
+ temp = show_list(ohci, buf->page, size, ohci->ed_controltail);
+ temp += show_list(ohci, buf->page + temp, size - temp,
ohci->ed_bulktail);
spin_unlock_irqrestore (&ohci->lock, flags);

diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 8ada13f..b32fd8b 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -78,8 +78,8 @@ static const char hcd_name [] = "ohci_hcd";
#include "ohci.h"
#include "pci-quirks.h"

-static void ohci_dump (struct ohci_hcd *ohci, int verbose);
-static void ohci_stop (struct usb_hcd *hcd);
+static void ohci_dump(struct ohci_hcd *ohci);
+static void ohci_stop(struct usb_hcd *hcd);

#include "ohci-hub.c"
#include "ohci-dbg.c"
@@ -754,7 +754,7 @@ retry:
ohci->ed_to_check = NULL;
}

- ohci_dump (ohci, 1);
+ ohci_dump(ohci);

return 0;
}
@@ -835,7 +835,7 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd)
usb_hc_died(hcd);
}

- ohci_dump (ohci, 1);
+ ohci_dump(ohci);
ohci_usb_reset (ohci);
}

@@ -935,7 +935,7 @@ static void ohci_stop (struct usb_hcd *hcd)
{
struct ohci_hcd *ohci = hcd_to_ohci (hcd);

- ohci_dump (ohci, 1);
+ ohci_dump(ohci);

if (quirk_nec(ohci))
flush_work(&ohci->nec_work);
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index e7f577e..4e9f6a4 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -315,8 +315,7 @@ static void periodic_unlink (struct ohci_hcd *ohci, struct ed *ed)
* - ED_OPER: when there's any request queued, the ED gets rescheduled
* immediately. HC should be working on them.
*
- * - ED_IDLE: when there's no TD queue. there's no reason for the HC
- * to care about this ED; safe to disable the endpoint.
+ * - ED_IDLE: when there's no TD queue or the HC isn't running.
*
* When finish_unlinks() runs later, after SOF interrupt, it will often
* complete one or more URB unlinks before making that state change.
@@ -930,6 +929,10 @@ rescan_all:
int completed, modified;
__hc32 *prev;

+ /* Is this ED already invisible to the hardware? */
+ if (ed->state == ED_IDLE)
+ goto ed_idle;
+
/* only take off EDs that the HC isn't using, accounting for
* frame counter wraps and EDs with partially retired TDs
*/
@@ -959,12 +962,20 @@ skip_ed:
}
}

+ /* ED's now officially unlinked, hc doesn't see */
+ ed->state = ED_IDLE;
+ if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
+ ohci->eds_scheduled--;
+ ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
+ ed->hwNextED = 0;
+ wmb();
+ ed->hwINFO &= ~cpu_to_hc32(ohci, ED_SKIP | ED_DEQUEUE);
+ed_idle:
+
/* reentrancy: if we drop the schedule lock, someone might
* have modified this list. normally it's just prepending
* entries (which we'd ignore), but paranoia won't hurt.
*/
- *last = ed->ed_next;
- ed->ed_next = NULL;
modified = 0;

/* unlink urbs as requested, but rescan the list after
@@ -1022,19 +1033,20 @@ rescan_this:
if (completed && !list_empty (&ed->td_list))
goto rescan_this;

- /* ED's now officially unlinked, hc doesn't see */
- ed->state = ED_IDLE;
- if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
- ohci->eds_scheduled--;
- ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
- ed->hwNextED = 0;
- wmb ();
- ed->hwINFO &= ~cpu_to_hc32 (ohci, ED_SKIP | ED_DEQUEUE);
-
- /* but if there's work queued, reschedule */
- if (!list_empty (&ed->td_list)) {
- if (ohci->rh_state == OHCI_RH_RUNNING)
- ed_schedule (ohci, ed);
+ /*
+ * If no TDs are queued, take ED off the ed_rm_list.
+ * Otherwise, if the HC is running, reschedule.
+ * If not, leave it on the list for further dequeues.
+ */
+ if (list_empty(&ed->td_list)) {
+ *last = ed->ed_next;
+ ed->ed_next = NULL;
+ } else if (ohci->rh_state == OHCI_RH_RUNNING) {
+ *last = ed->ed_next;
+ ed->ed_next = NULL;
+ ed_schedule(ohci, ed);
+ } else {
+ last = &ed->ed_next;
}

if (modified)
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 44771a0..594a707 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -674,6 +674,8 @@ static struct usb_device_id id_table_combined [] = {
{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) },
{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) },
{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) },
+ { USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
+ { USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index c4777bc..1e58d90 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -140,12 +140,15 @@
/*
* Xsens Technologies BV products (http://www.xsens.com).
*/
-#define XSENS_CONVERTER_0_PID 0xD388
-#define XSENS_CONVERTER_1_PID 0xD389
+#define XSENS_VID 0x2639
+#define XSENS_CONVERTER_PID 0xD00D /* Xsens USB-serial converter */
+#define XSENS_MTW_PID 0x0200 /* Xsens MTw */
+#define XSENS_CONVERTER_0_PID 0xD388 /* Xsens USB converter */
+#define XSENS_CONVERTER_1_PID 0xD389 /* Xsens Wireless Receiver */
#define XSENS_CONVERTER_2_PID 0xD38A
-#define XSENS_CONVERTER_3_PID 0xD38B
-#define XSENS_CONVERTER_4_PID 0xD38C
-#define XSENS_CONVERTER_5_PID 0xD38D
+#define XSENS_CONVERTER_3_PID 0xD38B /* Xsens USB-serial converter */
+#define XSENS_CONVERTER_4_PID 0xD38C /* Xsens Wireless Receiver */
+#define XSENS_CONVERTER_5_PID 0xD38D /* Xsens Awinda Station */
#define XSENS_CONVERTER_6_PID 0xD38E
#define XSENS_CONVERTER_7_PID 0xD38F

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 3775947..5ee99e3 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -263,9 +263,8 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
}
if (ret > 0)
goto next;
- ret = ulist_add_merge(parents, eb->start,
- (uintptr_t)eie,
- (u64 *)&old, GFP_NOFS);
+ ret = ulist_add_merge_ptr(parents, eb->start,
+ eie, (void **)&old, GFP_NOFS);
if (ret < 0)
break;
if (!ret && extent_item_pos) {
@@ -961,9 +960,9 @@ again:
goto out;
ref->inode_list = eie;
}
- ret = ulist_add_merge(refs, ref->parent,
- (uintptr_t)ref->inode_list,
- (u64 *)&eie, GFP_NOFS);
+ ret = ulist_add_merge_ptr(refs, ref->parent,
+ ref->inode_list,
+ (void **)&eie, GFP_NOFS);
if (ret < 0)
goto out;
if (!ret && extent_item_pos) {
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 6f38488..bb91764 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -755,7 +755,7 @@ again:
found_next = 1;
if (ret != 0)
goto insert;
- slot = 0;
+ slot = path->slots[0];
}
btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h
index fb36731..3e62b57 100644
--- a/fs/btrfs/ulist.h
+++ b/fs/btrfs/ulist.h
@@ -74,6 +74,21 @@ void ulist_free(struct ulist *ulist);
int ulist_add(struct ulist *ulist, u64 val, u64 aux, gfp_t gfp_mask);
int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux,
u64 *old_aux, gfp_t gfp_mask);
+
+/* just like ulist_add_merge() but take a pointer for the aux data */
+static inline int ulist_add_merge_ptr(struct ulist *ulist, u64 val, void *aux,
+ void **old_aux, gfp_t gfp_mask)
+{
+#if BITS_PER_LONG == 32
+ u64 old64 = (uintptr_t)*old_aux;
+ int ret = ulist_add_merge(ulist, val, (uintptr_t)aux, &old64, gfp_mask);
+ *old_aux = (void *)((uintptr_t)old64);
+ return ret;
+#else
+ return ulist_add_merge(ulist, val, (u64)aux, (u64 *)old_aux, gfp_mask);
+#endif
+}
+
struct ulist_node *ulist_next(struct ulist *ulist,
struct ulist_iterator *uiter);

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 4911dc8..dd4aaca 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2847,7 +2847,7 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
total_read += result;
}

- return total_read > 0 ? total_read : result;
+ return total_read > 0 && result != -EAGAIN ? total_read : result;
}

static ssize_t
@@ -3270,7 +3270,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
total_read += result;
}

- return total_read > 0 ? total_read : result;
+ return total_read > 0 && result != -EAGAIN ? total_read : result;
}

static int cifs_readpages(struct file *file, struct address_space *mapping,
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 94bd4fb..e31a9df 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -605,7 +605,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
{STATUS_MAPPED_FILE_SIZE_ZERO, -EIO, "STATUS_MAPPED_FILE_SIZE_ZERO"},
{STATUS_TOO_MANY_OPENED_FILES, -EMFILE, "STATUS_TOO_MANY_OPENED_FILES"},
{STATUS_CANCELLED, -EIO, "STATUS_CANCELLED"},
- {STATUS_CANNOT_DELETE, -EIO, "STATUS_CANNOT_DELETE"},
+ {STATUS_CANNOT_DELETE, -EACCES, "STATUS_CANNOT_DELETE"},
{STATUS_INVALID_COMPUTER_NAME, -EIO, "STATUS_INVALID_COMPUTER_NAME"},
{STATUS_FILE_DELETED, -EIO, "STATUS_FILE_DELETED"},
{STATUS_SPECIAL_ACCOUNT, -EIO, "STATUS_SPECIAL_ACCOUNT"},
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 9c0444c..1576195 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -533,7 +533,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove);
*/
void debugfs_remove_recursive(struct dentry *dentry)
{
- struct dentry *child, *next, *parent;
+ struct dentry *child, *parent;

if (IS_ERR_OR_NULL(dentry))
return;
@@ -545,30 +545,49 @@ void debugfs_remove_recursive(struct dentry *dentry)
parent = dentry;
down:
mutex_lock(&parent->d_inode->i_mutex);
- list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) {
+ loop:
+ /*
+ * The parent->d_subdirs is protected by the d_lock. Outside that
+ * lock, the child can be unlinked and set to be freed which can
+ * use the d_u.d_child as the rcu head and corrupt this list.
+ */
+ spin_lock(&parent->d_lock);
+ list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) {
if (!debugfs_positive(child))
continue;

/* perhaps simple_empty(child) makes more sense */
if (!list_empty(&child->d_subdirs)) {
+ spin_unlock(&parent->d_lock);
mutex_unlock(&parent->d_inode->i_mutex);
parent = child;
goto down;
}
- up:
+
+ spin_unlock(&parent->d_lock);
+
if (!__debugfs_remove(child, parent))
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+
+ /*
+ * The parent->d_lock protects agaist child from unlinking
+ * from d_subdirs. When releasing the parent->d_lock we can
+ * no longer trust that the next pointer is valid.
+ * Restart the loop. We'll skip this one with the
+ * debugfs_positive() check.
+ */
+ goto loop;
}
+ spin_unlock(&parent->d_lock);

mutex_unlock(&parent->d_inode->i_mutex);
child = parent;
parent = parent->d_parent;
mutex_lock(&parent->d_inode->i_mutex);

- if (child != dentry) {
- next = list_next_entry(child, d_u.d_child);
- goto up;
- }
+ if (child != dentry)
+ /* go up */
+ goto loop;

if (!__debugfs_remove(child, parent))
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 62f024c..e531054 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2151,8 +2151,8 @@ extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
-extern int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t first, ext4_lblk_t stop);
+extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
+ ext4_lblk_t start, ext4_lblk_t end);

/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index e6574d7..4353522 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -1297,97 +1297,220 @@ do_indirects:
}
}

-static int free_hole_blocks(handle_t *handle, struct inode *inode,
- struct buffer_head *parent_bh, __le32 *i_data,
- int level, ext4_lblk_t first,
- ext4_lblk_t count, int max)
+/**
+ * ext4_ind_remove_space - remove space from the range
+ * @handle: JBD handle for this transaction
+ * @inode: inode we are dealing with
+ * @start: First block to remove
+ * @end: One block after the last block to remove (exclusive)
+ *
+ * Free the blocks in the defined range (end is exclusive endpoint of
+ * range). This is used by ext4_punch_hole().
+ */
+int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
+ ext4_lblk_t start, ext4_lblk_t end)
{
- struct buffer_head *bh = NULL;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ __le32 *i_data = ei->i_data;
int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- int ret = 0;
- int i, inc;
- ext4_lblk_t offset;
- __le32 blk;
-
- inc = 1 << ((EXT4_BLOCK_SIZE_BITS(inode->i_sb) - 2) * level);
- for (i = 0, offset = 0; i < max; i++, i_data++, offset += inc) {
- if (offset >= count + first)
- break;
- if (*i_data == 0 || (offset + inc) <= first)
- continue;
- blk = *i_data;
- if (level > 0) {
- ext4_lblk_t first2;
- ext4_lblk_t count2;
+ ext4_lblk_t offsets[4], offsets2[4];
+ Indirect chain[4], chain2[4];
+ Indirect *partial, *partial2;
+ ext4_lblk_t max_block;
+ __le32 nr = 0, nr2 = 0;
+ int n = 0, n2 = 0;
+ unsigned blocksize = inode->i_sb->s_blocksize;

- bh = sb_bread(inode->i_sb, le32_to_cpu(blk));
- if (!bh) {
- EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk),
- "Read failure");
- return -EIO;
- }
- if (first > offset) {
- first2 = first - offset;
- count2 = count;
+ max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
+ >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+ if (end >= max_block)
+ end = max_block;
+ if ((start >= end) || (start > max_block))
+ return 0;
+
+ n = ext4_block_to_path(inode, start, offsets, NULL);
+ n2 = ext4_block_to_path(inode, end, offsets2, NULL);
+
+ BUG_ON(n > n2);
+
+ if ((n == 1) && (n == n2)) {
+ /* We're punching only within direct block range */
+ ext4_free_data(handle, inode, NULL, i_data + offsets[0],
+ i_data + offsets2[0]);
+ return 0;
+ } else if (n2 > n) {
+ /*
+ * Start and end are on a different levels so we're going to
+ * free partial block at start, and partial block at end of
+ * the range. If there are some levels in between then
+ * do_indirects label will take care of that.
+ */
+
+ if (n == 1) {
+ /*
+ * Start is at the direct block level, free
+ * everything to the end of the level.
+ */
+ ext4_free_data(handle, inode, NULL, i_data + offsets[0],
+ i_data + EXT4_NDIR_BLOCKS);
+ goto end_range;
+ }
+
+
+ partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+ if (nr) {
+ if (partial == chain) {
+ /* Shared branch grows from the inode */
+ ext4_free_branches(handle, inode, NULL,
+ &nr, &nr+1, (chain+n-1) - partial);
+ *partial->p = 0;
} else {
- first2 = 0;
- count2 = count - (offset - first);
+ /* Shared branch grows from an indirect block */
+ BUFFER_TRACE(partial->bh, "get_write_access");
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p,
+ partial->p+1, (chain+n-1) - partial);
}
- ret = free_hole_blocks(handle, inode, bh,
- (__le32 *)bh->b_data, level - 1,
- first2, count2,
- inode->i_sb->s_blocksize >> 2);
- if (ret) {
- brelse(bh);
- goto err;
+ }
+
+ /*
+ * Clear the ends of indirect blocks on the shared branch
+ * at the start of the range
+ */
+ while (partial > chain) {
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p + 1,
+ (__le32 *)partial->bh->b_data+addr_per_block,
+ (chain+n-1) - partial);
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse(partial->bh);
+ partial--;
+ }
+
+end_range:
+ partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+ if (nr2) {
+ if (partial2 == chain2) {
+ /*
+ * Remember, end is exclusive so here we're at
+ * the start of the next level we're not going
+ * to free. Everything was covered by the start
+ * of the range.
+ */
+ return 0;
+ } else {
+ /* Shared branch grows from an indirect block */
+ partial2--;
}
+ } else {
+ /*
+ * ext4_find_shared returns Indirect structure which
+ * points to the last element which should not be
+ * removed by truncate. But this is end of the range
+ * in punch_hole so we need to point to the next element
+ */
+ partial2->p++;
}
- if (level == 0 ||
- (bh && all_zeroes((__le32 *)bh->b_data,
- (__le32 *)bh->b_data + addr_per_block))) {
- ext4_free_data(handle, inode, parent_bh, &blk, &blk+1);
- *i_data = 0;
+
+ /*
+ * Clear the ends of indirect blocks on the shared branch
+ * at the end of the range
+ */
+ while (partial2 > chain2) {
+ ext4_free_branches(handle, inode, partial2->bh,
+ (__le32 *)partial2->bh->b_data,
+ partial2->p,
+ (chain2+n2-1) - partial2);
+ BUFFER_TRACE(partial2->bh, "call brelse");
+ brelse(partial2->bh);
+ partial2--;
}
- brelse(bh);
- bh = NULL;
+ goto do_indirects;
}

-err:
- return ret;
-}
-
-int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t first, ext4_lblk_t stop)
-{
- int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- int level, ret = 0;
- int num = EXT4_NDIR_BLOCKS;
- ext4_lblk_t count, max = EXT4_NDIR_BLOCKS;
- __le32 *i_data = EXT4_I(inode)->i_data;
-
- count = stop - first;
- for (level = 0; level < 4; level++, max *= addr_per_block) {
- if (first < max) {
- ret = free_hole_blocks(handle, inode, NULL, i_data,
- level, first, count, num);
- if (ret)
- goto err;
- if (count > max - first)
- count -= max - first;
- else
- break;
- first = 0;
- } else {
- first -= max;
+ /* Punch happened within the same level (n == n2) */
+ partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+ partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+ /*
+ * ext4_find_shared returns Indirect structure which
+ * points to the last element which should not be
+ * removed by truncate. But this is end of the range
+ * in punch_hole so we need to point to the next element
+ */
+ partial2->p++;
+ while ((partial > chain) || (partial2 > chain2)) {
+ /* We're at the same block, so we're almost finished */
+ if ((partial->bh && partial2->bh) &&
+ (partial->bh->b_blocknr == partial2->bh->b_blocknr)) {
+ if ((partial > chain) && (partial2 > chain2)) {
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p + 1,
+ partial2->p,
+ (chain+n-1) - partial);
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse(partial->bh);
+ BUFFER_TRACE(partial2->bh, "call brelse");
+ brelse(partial2->bh);
+ }
+ return 0;
}
- i_data += num;
- if (level == 0) {
- num = 1;
- max = 1;
+ /*
+ * Clear the ends of indirect blocks on the shared branch
+ * at the start of the range
+ */
+ if (partial > chain) {
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p + 1,
+ (__le32 *)partial->bh->b_data+addr_per_block,
+ (chain+n-1) - partial);
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse(partial->bh);
+ partial--;
+ }
+ /*
+ * Clear the ends of indirect blocks on the shared branch
+ * at the end of the range
+ */
+ if (partial2 > chain2) {
+ ext4_free_branches(handle, inode, partial2->bh,
+ (__le32 *)partial2->bh->b_data,
+ partial2->p,
+ (chain2+n-1) - partial2);
+ BUFFER_TRACE(partial2->bh, "call brelse");
+ brelse(partial2->bh);
+ partial2--;
}
}

-err:
- return ret;
+do_indirects:
+ /* Kill the remaining (whole) subtrees */
+ switch (offsets[0]) {
+ default:
+ if (++n >= n2)
+ return 0;
+ nr = i_data[EXT4_IND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
+ i_data[EXT4_IND_BLOCK] = 0;
+ }
+ case EXT4_IND_BLOCK:
+ if (++n >= n2)
+ return 0;
+ nr = i_data[EXT4_DIND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
+ i_data[EXT4_DIND_BLOCK] = 0;
+ }
+ case EXT4_DIND_BLOCK:
+ if (++n >= n2)
+ return 0;
+ nr = i_data[EXT4_TIND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
+ i_data[EXT4_TIND_BLOCK] = 0;
+ }
+ case EXT4_TIND_BLOCK:
+ ;
+ }
+ return 0;
}
-
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0fc189b..23e8c80 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3629,7 +3629,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
ret = ext4_ext_remove_space(inode, first_block,
stop_block - 1);
else
- ret = ext4_free_hole_blocks(handle, inode, first_block,
+ ret = ext4_ind_remove_space(handle, inode, first_block,
stop_block);

ext4_discard_preallocations(inode);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 502f0fd..242226a 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1398,6 +1398,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
int last = first + count - 1;
struct super_block *sb = e4b->bd_sb;

+ if (WARN_ON(count == 0))
+ return;
BUG_ON(last >= (sb->s_blocksize << 3));
assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
/* Don't bother if the block group is corrupt. */
@@ -3196,8 +3198,30 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
{
struct ext4_prealloc_space *pa = ac->ac_pa;
+ struct ext4_buddy e4b;
+ int err;

- if (pa && pa->pa_type == MB_INODE_PA)
+ if (pa == NULL) {
+ if (ac->ac_f_ex.fe_len == 0)
+ return;
+ err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b);
+ if (err) {
+ /*
+ * This should never happen since we pin the
+ * pages in the ext4_allocation_context so
+ * ext4_mb_load_buddy() should never fail.
+ */
+ WARN(1, "mb_load_buddy failed (%d)", err);
+ return;
+ }
+ ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+ mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start,
+ ac->ac_f_ex.fe_len);
+ ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+ ext4_mb_unload_buddy(&e4b);
+ return;
+ }
+ if (pa->pa_type == MB_INODE_PA)
pa->pa_free += ac->ac_b_ex.fe_len;
}

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 1d09289..180d1ec 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1205,7 +1205,7 @@ static const struct file_operations nfs_server_list_fops = {
.open = nfs_server_list_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = seq_release_net,
.owner = THIS_MODULE,
};

@@ -1226,7 +1226,7 @@ static const struct file_operations nfs_volume_list_fops = {
.open = nfs_volume_list_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = seq_release_net,
.owner = THIS_MODULE,
};

@@ -1236,19 +1236,8 @@ static const struct file_operations nfs_volume_list_fops = {
*/
static int nfs_server_list_open(struct inode *inode, struct file *file)
{
- struct seq_file *m;
- int ret;
- struct pid_namespace *pid_ns = file->f_dentry->d_sb->s_fs_info;
- struct net *net = pid_ns->child_reaper->nsproxy->net_ns;
-
- ret = seq_open(file, &nfs_server_list_ops);
- if (ret < 0)
- return ret;
-
- m = file->private_data;
- m->private = net;
-
- return 0;
+ return seq_open_net(inode, file, &nfs_server_list_ops,
+ sizeof(struct seq_net_private));
}

/*
@@ -1256,7 +1245,7 @@ static int nfs_server_list_open(struct inode *inode, struct file *file)
*/
static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
{
- struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+ struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id);

/* lock the list against modification */
spin_lock(&nn->nfs_client_lock);
@@ -1268,7 +1257,7 @@ static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
*/
static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
{
- struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+ struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id);

return seq_list_next(v, &nn->nfs_client_list, pos);
}
@@ -1278,7 +1267,7 @@ static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
*/
static void nfs_server_list_stop(struct seq_file *p, void *v)
{
- struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+ struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id);

spin_unlock(&nn->nfs_client_lock);
}
@@ -1289,7 +1278,7 @@ static void nfs_server_list_stop(struct seq_file *p, void *v)
static int nfs_server_list_show(struct seq_file *m, void *v)
{
struct nfs_client *clp;
- struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+ struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id);

/* display header on line 1 */
if (v == &nn->nfs_client_list) {
@@ -1321,19 +1310,8 @@ static int nfs_server_list_show(struct seq_file *m, void *v)
*/
static int nfs_volume_list_open(struct inode *inode, struct file *file)
{
- struct seq_file *m;
- int ret;
- struct pid_namespace *pid_ns = file->f_dentry->d_sb->s_fs_info;
- struct net *net = pid_ns->child_reaper->nsproxy->net_ns;
-
- ret = seq_open(file, &nfs_volume_list_ops);
- if (ret < 0)
- return ret;
-
- m = file->private_data;
- m->private = net;
-
- return 0;
+ return seq_open_net(inode, file, &nfs_server_list_ops,
+ sizeof(struct seq_net_private));
}

/*
@@ -1341,7 +1319,7 @@ static int nfs_volume_list_open(struct inode *inode, struct file *file)
*/
static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
{
- struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+ struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id);

/* lock the list against modification */
spin_lock(&nn->nfs_client_lock);
@@ -1353,7 +1331,7 @@ static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
*/
static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
{
- struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+ struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id);

return seq_list_next(v, &nn->nfs_volume_list, pos);
}
@@ -1363,7 +1341,7 @@ static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
*/
static void nfs_volume_list_stop(struct seq_file *p, void *v)
{
- struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+ struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id);

spin_unlock(&nn->nfs_client_lock);
}
@@ -1376,7 +1354,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
struct nfs_server *server;
struct nfs_client *clp;
char dev[8], fsid[17];
- struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+ struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id);

/* display header on line 1 */
if (v == &nn->nfs_volume_list) {
@@ -1407,6 +1385,45 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
return 0;
}

+int nfs_fs_proc_net_init(struct net *net)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+ struct proc_dir_entry *p;
+
+ nn->proc_nfsfs = proc_net_mkdir(net, "nfsfs", net->proc_net);
+ if (!nn->proc_nfsfs)
+ goto error_0;
+
+ /* a file of servers with which we're dealing */
+ p = proc_create("servers", S_IFREG|S_IRUGO,
+ nn->proc_nfsfs, &nfs_server_list_fops);
+ if (!p)
+ goto error_1;
+
+ /* a file of volumes that we have mounted */
+ p = proc_create("volumes", S_IFREG|S_IRUGO,
+ nn->proc_nfsfs, &nfs_volume_list_fops);
+ if (!p)
+ goto error_2;
+ return 0;
+
+error_2:
+ remove_proc_entry("servers", nn->proc_nfsfs);
+error_1:
+ remove_proc_entry("fs/nfsfs", NULL);
+error_0:
+ return -ENOMEM;
+}
+
+void nfs_fs_proc_net_exit(struct net *net)
+{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+ remove_proc_entry("volumes", nn->proc_nfsfs);
+ remove_proc_entry("servers", nn->proc_nfsfs);
+ remove_proc_entry("fs/nfsfs", NULL);
+}
+
/*
* initialise the /proc/fs/nfsfs/ directory
*/
@@ -1419,14 +1436,12 @@ int __init nfs_fs_proc_init(void)
goto error_0;

/* a file of servers with which we're dealing */
- p = proc_create("servers", S_IFREG|S_IRUGO,
- proc_fs_nfs, &nfs_server_list_fops);
+ p = proc_symlink("servers", proc_fs_nfs, "../../net/nfsfs/servers");
if (!p)
goto error_1;

/* a file of volumes that we have mounted */
- p = proc_create("volumes", S_IFREG|S_IRUGO,
- proc_fs_nfs, &nfs_volume_list_fops);
+ p = proc_symlink("volumes", proc_fs_nfs, "../../net/nfsfs/volumes");
if (!p)
goto error_2;
return 0;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 25063e1..be955cf 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1767,11 +1767,12 @@ EXPORT_SYMBOL_GPL(nfs_net_id);
static int nfs_net_init(struct net *net)
{
nfs_clients_init(net);
- return 0;
+ return nfs_fs_proc_net_init(net);
}

static void nfs_net_exit(struct net *net)
{
+ nfs_fs_proc_net_exit(net);
nfs_cleanup_cb_ident_idr(net);
}

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b46cf5a..18537f9 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -195,7 +195,16 @@ extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
#ifdef CONFIG_PROC_FS
extern int __init nfs_fs_proc_init(void);
extern void nfs_fs_proc_exit(void);
+extern int nfs_fs_proc_net_init(struct net *net);
+extern void nfs_fs_proc_net_exit(struct net *net);
#else
+static inline int nfs_fs_proc_net_init(struct net *net)
+{
+ return 0;
+}
+static inline void nfs_fs_proc_net_exit(struct net *net)
+{
+}
static inline int nfs_fs_proc_init(void)
{
return 0;
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index 8ee1fab..ef221fb 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -29,6 +29,9 @@ struct nfs_net {
#endif
spinlock_t nfs_client_lock;
struct timespec boot_time;
+#ifdef CONFIG_PROC_FS
+ struct proc_dir_entry *proc_nfsfs;
+#endif
};

extern int nfs_net_id;
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index cb70bdd..4c7bd2c 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -10,6 +10,7 @@
#include <linux/sunrpc/auth.h>
#include <linux/sunrpc/xprt.h>
#include <linux/sunrpc/bc_xprt.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
#include "internal.h"
#include "callback.h"
#include "delegation.h"
@@ -370,7 +371,11 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
__set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags);
__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
- error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I);
+
+ error = -EINVAL;
+ if (gssd_running(clp->cl_net))
+ error = nfs_create_rpc_client(clp, timeparms,
+ RPC_AUTH_GSS_KRB5I);
if (error == -EINVAL)
error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
if (error < 0)
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 760c85a..4942f43 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -221,7 +221,8 @@ static int nfsd_startup_generic(int nrservs)
*/
ret = nfsd_racache_init(2*nrservs);
if (ret)
- return ret;
+ goto dec_users;
+
ret = nfs4_state_start();
if (ret)
goto out_racache;
@@ -229,6 +230,8 @@ static int nfsd_startup_generic(int nrservs)

out_racache:
nfsd_racache_shutdown();
+dec_users:
+ nfsd_users--;
return ret;
}

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 1bd2077..fafb03d 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -306,15 +306,11 @@ static void render_cap_t(struct seq_file *m, const char *header,
seq_puts(m, header);
CAP_FOR_EACH_U32(__capi) {
seq_printf(m, "%08x",
- a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
+ a->cap[CAP_LAST_U32 - __capi]);
}
seq_putc(m, '\n');
}

-/* Remove non-existent capabilities */
-#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \
- CAP_TO_MASK(CAP_LAST_CAP + 1) - 1)
-
static inline void task_cap(struct seq_file *m, struct task_struct *p)
{
const struct cred *cred;
@@ -328,11 +324,6 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p)
cap_bset = cred->cap_bset;
rcu_read_unlock();

- NORM_CAPS(cap_inheritable);
- NORM_CAPS(cap_permitted);
- NORM_CAPS(cap_effective);
- NORM_CAPS(cap_bset);
-
render_cap_t(m, "CapInh:\t", &cap_inheritable);
render_cap_t(m, "CapPrm:\t", &cap_permitted);
render_cap_t(m, "CapEff:\t", &cap_effective);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index eae1692..fefa456 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2116,6 +2116,17 @@ xlog_recover_validate_buf_type(
__uint16_t magic16;
__uint16_t magicda;

+ /*
+ * We can only do post recovery validation on items on CRC enabled
+ * fielsystems as we need to know when the buffer was written to be able
+ * to determine if we should have replayed the item. If we replay old
+ * metadata over a newer buffer, then it will enter a temporarily
+ * inconsistent state resulting in verification failures. Hence for now
+ * just avoid the verification stage for non-crc filesystems
+ */
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
magic32 = be32_to_cpu(*(__be32 *)bp->b_addr);
magic16 = be16_to_cpu(*(__be16*)bp->b_addr);
magicda = be16_to_cpu(info->magic);
@@ -2151,8 +2162,6 @@ xlog_recover_validate_buf_type(
bp->b_ops = &xfs_agf_buf_ops;
break;
case XFS_BLFT_AGFL_BUF:
- if (!xfs_sb_version_hascrc(&mp->m_sb))
- break;
if (magic32 != XFS_AGFL_MAGIC) {
xfs_warn(mp, "Bad AGFL block magic!");
ASSERT(0);
@@ -2185,10 +2194,6 @@ xlog_recover_validate_buf_type(
#endif
break;
case XFS_BLFT_DINO_BUF:
- /*
- * we get here with inode allocation buffers, not buffers that
- * track unlinked list changes.
- */
if (magic16 != XFS_DINODE_MAGIC) {
xfs_warn(mp, "Bad INODE block magic!");
ASSERT(0);
@@ -2268,8 +2273,6 @@ xlog_recover_validate_buf_type(
bp->b_ops = &xfs_attr3_leaf_buf_ops;
break;
case XFS_BLFT_ATTR_RMT_BUF:
- if (!xfs_sb_version_hascrc(&mp->m_sb))
- break;
if (magic32 != XFS_ATTR3_RMT_MAGIC) {
xfs_warn(mp, "Bad attr remote magic!");
ASSERT(0);
@@ -2376,16 +2379,7 @@ xlog_recover_do_reg_buffer(
/* Shouldn't be any more regions */
ASSERT(i == item->ri_total);

- /*
- * We can only do post recovery validation on items on CRC enabled
- * fielsystems as we need to know when the buffer was written to be able
- * to determine if we should have replayed the item. If we replay old
- * metadata over a newer buffer, then it will enter a temporarily
- * inconsistent state resulting in verification failures. Hence for now
- * just avoid the verification stage for non-crc filesystems
- */
- if (xfs_sb_version_hascrc(&mp->m_sb))
- xlog_recover_validate_buf_type(mp, bp, buf_f);
+ xlog_recover_validate_buf_type(mp, bp, buf_f);
}

/*
@@ -2493,12 +2487,29 @@ xlog_recover_buffer_pass2(
}

/*
- * recover the buffer only if we get an LSN from it and it's less than
+ * Recover the buffer only if we get an LSN from it and it's less than
* the lsn of the transaction we are replaying.
+ *
+ * Note that we have to be extremely careful of readahead here.
+ * Readahead does not attach verfiers to the buffers so if we don't
+ * actually do any replay after readahead because of the LSN we found
+ * in the buffer if more recent than that current transaction then we
+ * need to attach the verifier directly. Failure to do so can lead to
+ * future recovery actions (e.g. EFI and unlinked list recovery) can
+ * operate on the buffers and they won't get the verifier attached. This
+ * can lead to blocks on disk having the correct content but a stale
+ * CRC.
+ *
+ * It is safe to assume these clean buffers are currently up to date.
+ * If the buffer is dirtied by a later transaction being replayed, then
+ * the verifier will be reset to match whatever recover turns that
+ * buffer into.
*/
lsn = xlog_recover_get_buf_lsn(mp, bp);
- if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0)
+ if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
+ xlog_recover_validate_buf_type(mp, bp, buf_f);
goto out_release;
+ }

if (buf_f->blf_flags & XFS_BLF_INODE_BUF) {
error = xlog_recover_do_inode_buffer(mp, item, bp, buf_f);
diff --git a/include/linux/capability.h b/include/linux/capability.h
index 84b13ad..aa93e5e 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -78,8 +78,11 @@ extern const kernel_cap_t __cap_init_eff_set;
# error Fix up hand-coded capability macro initializers
#else /* HAND-CODED capability initializers */

+#define CAP_LAST_U32 ((_KERNEL_CAPABILITY_U32S) - 1)
+#define CAP_LAST_U32_VALID_MASK (CAP_TO_MASK(CAP_LAST_CAP + 1) -1)
+
# define CAP_EMPTY_SET ((kernel_cap_t){{ 0, 0 }})
-# define CAP_FULL_SET ((kernel_cap_t){{ ~0, ~0 }})
+# define CAP_FULL_SET ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }})
# define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \
| CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \
CAP_FS_MASK_B1 } })
diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index a353e03..7f490be 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -84,7 +84,8 @@ enum {

extern struct dentry *rpc_d_lookup_sb(const struct super_block *sb,
const unsigned char *dir_name);
-extern void rpc_pipefs_init_net(struct net *net);
+extern int rpc_pipefs_init_net(struct net *net);
+extern void rpc_pipefs_exit_net(struct net *net);
extern struct super_block *rpc_get_sb_net(const struct net *net);
extern void rpc_put_sb_net(const struct net *net);

@@ -130,5 +131,7 @@ extern int rpc_unlink(struct dentry *);
extern int register_rpc_pipefs(void);
extern void unregister_rpc_pipefs(void);

+extern bool gssd_running(struct net *net);
+
#endif
#endif
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 9a93930..83cf417 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -41,14 +41,13 @@ struct inet_peer {
struct rcu_head gc_rcu;
};
/*
- * Once inet_peer is queued for deletion (refcnt == -1), following fields
- * are not available: rid, ip_id_count
+ * Once inet_peer is queued for deletion (refcnt == -1), following field
+ * is not available: rid
* We can share memory with rcu_head to help keep inet_peer small.
*/
union {
struct {
atomic_t rid; /* Frag reception counter */
- atomic_t ip_id_count; /* IP ID for the next packet */
};
struct rcu_head rcu;
struct inet_peer *gc_next;
@@ -166,7 +165,7 @@ void inetpeer_invalidate_tree(struct inet_peer_base *);
void inetpeer_invalidate_family(int family);

/*
- * temporary check to make sure we dont access rid, ip_id_count, tcp_ts,
+ * temporary check to make sure we dont access rid, tcp_ts,
* tcp_ts_stamp if no refcount is taken on inet_peer
*/
static inline void inet_peer_refcheck(const struct inet_peer *p)
@@ -174,13 +173,4 @@ static inline void inet_peer_refcheck(const struct inet_peer *p)
WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0);
}

-
-/* can be called with or without local BH being disabled */
-static inline int inet_getid(struct inet_peer *p, int more)
-{
- more++;
- inet_peer_refcheck(p);
- return atomic_add_return(more, &p->ip_id_count) - more;
-}
-
#endif /* _NET_INETPEER_H */
diff --git a/include/net/ip.h b/include/net/ip.h
index 5a25f36..d48b2e8 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -269,9 +269,10 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst)
!(dst_metric_locked(dst, RTAX_MTU)));
}

-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
+u32 ip_idents_reserve(u32 hash, int segs);
+void __ip_select_ident(struct iphdr *iph, int segs);

-static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk)
+static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs)
{
struct iphdr *iph = ip_hdr(skb);

@@ -281,24 +282,20 @@ static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, s
* does not change, they drop every other packet in
* a TCP stream using header compression.
*/
- iph->id = (sk && inet_sk(sk)->inet_daddr) ?
- htons(inet_sk(sk)->inet_id++) : 0;
- } else
- __ip_select_ident(iph, dst, 0);
-}
-
-static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more)
-{
- struct iphdr *iph = ip_hdr(skb);
-
- if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) {
if (sk && inet_sk(sk)->inet_daddr) {
iph->id = htons(inet_sk(sk)->inet_id);
- inet_sk(sk)->inet_id += 1 + more;
- } else
+ inet_sk(sk)->inet_id += segs;
+ } else {
iph->id = 0;
- } else
- __ip_select_ident(iph, dst, more);
+ }
+ } else {
+ __ip_select_ident(iph, segs);
+ }
+}
+
+static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk)
+{
+ ip_select_ident_segs(skb, sk, 1);
}

/*
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 488316e..d164d0c 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -660,8 +660,6 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
}

-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
-
int ip6_dst_hoplimit(struct dst_entry *dst);

/*
diff --git a/include/net/netlabel.h b/include/net/netlabel.h
index 2c95d55..e84d71b 100644
--- a/include/net/netlabel.h
+++ b/include/net/netlabel.h
@@ -286,11 +286,11 @@ static inline void netlbl_secattr_catmap_free(
{
struct netlbl_lsm_secattr_catmap *iter;

- do {
+ while (catmap) {
iter = catmap;
catmap = catmap->next;
kfree(iter);
- } while (catmap);
+ }
}

/**
@@ -395,13 +395,20 @@ int netlbl_secattr_catmap_walk(struct netlbl_lsm_secattr_catmap *catmap,
u32 offset);
int netlbl_secattr_catmap_walk_rng(struct netlbl_lsm_secattr_catmap *catmap,
u32 offset);
-int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap *catmap,
+int netlbl_secattr_catmap_getlong(struct netlbl_lsm_secattr_catmap *catmap,
+ u32 *offset,
+ unsigned long *bitmap);
+int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap **catmap,
u32 bit,
gfp_t flags);
-int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap *catmap,
+int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap **catmap,
u32 start,
u32 end,
gfp_t flags);
+int netlbl_secattr_catmap_setlong(struct netlbl_lsm_secattr_catmap **catmap,
+ u32 offset,
+ unsigned long bitmap,
+ gfp_t flags);

/*
* LSM protocol operations (NetLabel LSM/kernel API)
@@ -505,21 +512,36 @@ static inline int netlbl_secattr_catmap_walk_rng(
{
return -ENOENT;
}
+static inline int netlbl_secattr_catmap_getlong(
+ struct netlbl_lsm_secattr_catmap *catmap,
+ u32 *offset,
+ unsigned long *bitmap)
+{
+ return 0;
+}
static inline int netlbl_secattr_catmap_setbit(
- struct netlbl_lsm_secattr_catmap *catmap,
+ struct netlbl_lsm_secattr_catmap **catmap,
u32 bit,
gfp_t flags)
{
return 0;
}
static inline int netlbl_secattr_catmap_setrng(
- struct netlbl_lsm_secattr_catmap *catmap,
+ struct netlbl_lsm_secattr_catmap **catmap,
u32 start,
u32 end,
gfp_t flags)
{
return 0;
}
+static int netlbl_secattr_catmap_setlong(
+ struct netlbl_lsm_secattr_catmap **catmap,
+ u32 offset,
+ unsigned long bitmap,
+ gfp_t flags)
+{
+ return 0;
+}
static inline int netlbl_enabled(void)
{
return 0;
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index f257486..3f36d45 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -3,8 +3,6 @@

#include <linux/types.h>

-__u32 secure_ip_id(__be32 daddr);
-__u32 secure_ipv6_id(const __be32 daddr[4]);
u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
__be16 dport);
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 8e6b70f..9695cf5 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -149,6 +149,7 @@ struct scsi_device {
unsigned skip_ms_page_8:1; /* do not use MODE SENSE page 0x08 */
unsigned skip_ms_page_3f:1; /* do not use MODE SENSE page 0x3f */
unsigned skip_vpd_pages:1; /* do not read VPD pages */
+ unsigned try_vpd_pages:1; /* attempt to read VPD pages */
unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */
unsigned no_start_on_add:1; /* do not issue start on add */
unsigned allow_restart:1; /* issue START_UNIT in error handler */
diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h
index 447d2d7..428b023 100644
--- a/include/scsi/scsi_devinfo.h
+++ b/include/scsi/scsi_devinfo.h
@@ -32,4 +32,7 @@
#define BLIST_ATTACH_PQ3 0x1000000 /* Scan: Attach to PQ3 devices */
#define BLIST_NO_DIF 0x2000000 /* Disable T10 PI (DIF) */
#define BLIST_SKIP_VPD_PAGES 0x4000000 /* Ignore SBC-3 VPD pages */
+#define BLIST_TRY_VPD_PAGES 0x10000000 /* Attempt to read VPD pages */
+#define BLIST_NO_RSOC 0x20000000 /* don't try to issue RSOC */
+
#endif
diff --git a/init/main.c b/init/main.c
index febc511..aca4f33 100644
--- a/init/main.c
+++ b/init/main.c
@@ -619,6 +619,10 @@ asmlinkage void __init start_kernel(void)
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_enter_virtual_mode();
#endif
+#ifdef CONFIG_X86_ESPFIX64
+ /* Should be run before the first non-init thread is created */
+ init_espfix_bsp();
+#endif
thread_info_cache_init();
cred_init();
fork_init(totalram_pages);
diff --git a/kernel/audit.c b/kernel/audit.c
index b64b367..013d900 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1516,7 +1516,7 @@ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap)
audit_log_format(ab, " %s=", prefix);
CAP_FOR_EACH_U32(i) {
audit_log_format(ab, "%08x",
- cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]);
+ cap->cap[CAP_LAST_U32 - i]);
}
}

diff --git a/kernel/capability.c b/kernel/capability.c
index 788653b..50fb74b 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -268,6 +268,10 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
i++;
}

+ effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+ permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+ inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+
new = prepare_creds();
if (!new)
return -ENOMEM;
diff --git a/kernel/smp.c b/kernel/smp.c
index bd9f940..cc2bbf7 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -657,7 +657,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
if (cond_func(cpu, info)) {
ret = smp_call_function_single(cpu, func,
info, wait);
- WARN_ON_ONCE(!ret);
+ WARN_ON_ONCE(ret);
}
preempt_enable();
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bca008f..572c8b8 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1978,7 +1978,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)

/**
* rb_update_event - update event type and data
- * @event: the even to update
+ * @event: the event to update
* @type: the type of event
* @length: the size of the event field in the ring buffer
*
@@ -3351,21 +3351,16 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;

/* Iterator usage is expected to have record disabled */
- if (list_empty(&cpu_buffer->reader_page->list)) {
- iter->head_page = rb_set_head_page(cpu_buffer);
- if (unlikely(!iter->head_page))
- return;
- iter->head = iter->head_page->read;
- } else {
- iter->head_page = cpu_buffer->reader_page;
- iter->head = cpu_buffer->reader_page->read;
- }
+ iter->head_page = cpu_buffer->reader_page;
+ iter->head = cpu_buffer->reader_page->read;
+
+ iter->cache_reader_page = iter->head_page;
+ iter->cache_read = iter->head;
+
if (iter->head)
iter->read_stamp = cpu_buffer->read_stamp;
else
iter->read_stamp = iter->head_page->page->time_stamp;
- iter->cache_reader_page = cpu_buffer->reader_page;
- iter->cache_read = cpu_buffer->read;
}

/**
@@ -3758,12 +3753,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
return NULL;

/*
- * We repeat when a time extend is encountered.
- * Since the time extend is always attached to a data event,
- * we should never loop more than once.
- * (We never hit the following condition more than twice).
+ * We repeat when a time extend is encountered or we hit
+ * the end of the page. Since the time extend is always attached
+ * to a data event, we should never loop more than three times.
+ * Once for going to next page, once on time extend, and
+ * finally once to get the event.
+ * (We never hit the following condition more than thrice).
*/
- if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2))
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3))
return NULL;

if (rb_per_cpu_empty(cpu_buffer))
diff --git a/mm/util.c b/mm/util.c
index 8636d3d..89abc97 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -276,17 +276,14 @@ pid_t vm_is_stack(struct task_struct *task,

if (in_group) {
struct task_struct *t;
- rcu_read_lock();
- if (!pid_alive(task))
- goto done;

- t = task;
- do {
+ rcu_read_lock();
+ for_each_thread(task, t) {
if (vm_is_stack_for_task(t, vma)) {
ret = t->pid;
goto done;
}
- } while_each_thread(task, t);
+ }
done:
rcu_read_unlock();
}
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index a674034..8a1d4b54 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -130,6 +130,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
{
struct batadv_frag_table_entry *chain;
struct batadv_frag_list_entry *frag_entry_new = NULL, *frag_entry_curr;
+ struct batadv_frag_list_entry *frag_entry_last = NULL;
struct batadv_frag_packet *frag_packet;
uint8_t bucket;
uint16_t seqno, hdr_size = sizeof(struct batadv_frag_packet);
@@ -182,11 +183,14 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
ret = true;
goto out;
}
+
+ /* store current entry because it could be the last in list */
+ frag_entry_last = frag_entry_curr;
}

- /* Reached the end of the list, so insert after 'frag_entry_curr'. */
- if (likely(frag_entry_curr)) {
- hlist_add_after(&frag_entry_curr->list, &frag_entry_new->list);
+ /* Reached the end of the list, so insert after 'frag_entry_last'. */
+ if (likely(frag_entry_last)) {
+ hlist_add_after(&frag_entry_last->list, &frag_entry_new->list);
chain->size += skb->len - hdr_size;
chain->timestamp = jiffies;
ret = true;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index c9e0915..eaa5ad5 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -978,7 +978,8 @@ static int l2cap_sock_shutdown(struct socket *sock, int how)
l2cap_chan_close(chan, 0);
lock_sock(sk);

- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+ !(current->flags & PF_EXITING))
err = bt_sock_wait_state(sk, BT_CLOSED,
sk->sk_lingertime);
}
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index facd8a7..b088651 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -1859,10 +1859,13 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s)
/* Get data directly from socket receive queue without copying it. */
while ((skb = skb_dequeue(&sk->sk_receive_queue))) {
skb_orphan(skb);
- if (!skb_linearize(skb))
+ if (!skb_linearize(skb)) {
s = rfcomm_recv_frame(s, skb);
- else
+ if (!s)
+ break;
+ } else {
kfree_skb(skb);
+ }
}

if (s && (sk->sk_state == BT_CLOSED))
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 3c2d3e4..a0050de 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -898,7 +898,8 @@ static int rfcomm_sock_shutdown(struct socket *sock, int how)
sk->sk_shutdown = SHUTDOWN_MASK;
__rfcomm_sock_close(sk);

- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+ !(current->flags & PF_EXITING))
err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
}
release_sock(sk);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 24fa396..316dd4e 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -909,7 +909,8 @@ static int sco_sock_shutdown(struct socket *sock, int how)
sco_sock_clear_timer(sk);
__sco_sock_close(sk);

- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+ !(current->flags & PF_EXITING))
err = bt_sock_wait_state(sk, BT_CLOSED,
sk->sk_lingertime);
}
@@ -929,7 +930,8 @@ static int sco_sock_release(struct socket *sock)

sco_sock_close(sk);

- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) {
+ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+ !(current->flags & PF_EXITING)) {
lock_sock(sk);
err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
release_sock(sk);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index ce83d07..94e21b9 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -904,7 +904,7 @@ static void ceph_msg_data_pages_cursor_init(struct ceph_msg_data_cursor *cursor,
BUG_ON(page_count > (int)USHRT_MAX);
cursor->page_count = (unsigned short)page_count;
BUG_ON(length > SIZE_MAX - cursor->page_offset);
- cursor->last_piece = (size_t)cursor->page_offset + length <= PAGE_SIZE;
+ cursor->last_piece = cursor->page_offset + cursor->resid <= PAGE_SIZE;
}

static struct page *
diff --git a/net/core/iovec.c b/net/core/iovec.c
index a9c46ba..26dc006 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -107,6 +107,10 @@ EXPORT_SYMBOL(memcpy_toiovecend);
int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
int offset, int len)
{
+ /* No data? Done! */
+ if (len == 0)
+ return 0;
+
/* Skip over the finished iovecs */
while (offset >= iov->iov_len) {
offset -= iov->iov_len;
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 897da56..ba71212 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
#endif

#ifdef CONFIG_INET
-__u32 secure_ip_id(__be32 daddr)
-{
- u32 hash[MD5_DIGEST_WORDS];
-
- net_secret_init();
- hash[0] = (__force __u32) daddr;
- hash[1] = net_secret[13];
- hash[2] = net_secret[14];
- hash[3] = net_secret[15];
-
- md5_transform(hash, net_secret);
-
- return hash[0];
-}
-
-__u32 secure_ipv6_id(const __be32 daddr[4])
-{
- __u32 hash[4];
-
- net_secret_init();
- memcpy(hash, daddr, 16);
- md5_transform(hash, net_secret);
-
- return hash[0];
-}

__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f7eca05..808a270 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2872,9 +2872,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
tail = nskb;

__copy_skb_header(nskb, head_skb);
- nskb->mac_len = head_skb->mac_len;

skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
+ skb_reset_mac_len(nskb);

skb_copy_from_linear_data_offset(head_skb, -tnl_hlen,
nskb->data - tnl_hlen,
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 667c1d4..d335b667 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -974,7 +974,7 @@ static int cipso_v4_map_cat_rbm_ntoh(const struct cipso_v4_doi *doi_def,
return -EPERM;
break;
}
- ret_val = netlbl_secattr_catmap_setbit(secattr->attr.mls.cat,
+ ret_val = netlbl_secattr_catmap_setbit(&secattr->attr.mls.cat,
host_spot,
GFP_ATOMIC);
if (ret_val != 0)
@@ -1076,7 +1076,7 @@ static int cipso_v4_map_cat_enum_ntoh(const struct cipso_v4_doi *doi_def,
u32 iter;

for (iter = 0; iter < net_cat_len; iter += 2) {
- ret_val = netlbl_secattr_catmap_setbit(secattr->attr.mls.cat,
+ ret_val = netlbl_secattr_catmap_setbit(&secattr->attr.mls.cat,
get_unaligned_be16(&net_cat[iter]),
GFP_ATOMIC);
if (ret_val != 0)
@@ -1218,7 +1218,7 @@ static int cipso_v4_map_cat_rng_ntoh(const struct cipso_v4_doi *doi_def,
else
cat_low = 0;

- ret_val = netlbl_secattr_catmap_setrng(secattr->attr.mls.cat,
+ ret_val = netlbl_secattr_catmap_setrng(&secattr->attr.mls.cat,
cat_low,
cat_high,
GFP_ATOMIC);
@@ -1336,11 +1336,6 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def,
secattr->flags |= NETLBL_SECATTR_MLS_LVL;

if (tag_len > 4) {
- secattr->attr.mls.cat =
- netlbl_secattr_catmap_alloc(GFP_ATOMIC);
- if (secattr->attr.mls.cat == NULL)
- return -ENOMEM;
-
ret_val = cipso_v4_map_cat_rbm_ntoh(doi_def,
&tag[4],
tag_len - 4,
@@ -1432,11 +1427,6 @@ static int cipso_v4_parsetag_enum(const struct cipso_v4_doi *doi_def,
secattr->flags |= NETLBL_SECATTR_MLS_LVL;

if (tag_len > 4) {
- secattr->attr.mls.cat =
- netlbl_secattr_catmap_alloc(GFP_ATOMIC);
- if (secattr->attr.mls.cat == NULL)
- return -ENOMEM;
-
ret_val = cipso_v4_map_cat_enum_ntoh(doi_def,
&tag[4],
tag_len - 4,
@@ -1527,11 +1517,6 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def,
secattr->flags |= NETLBL_SECATTR_MLS_LVL;

if (tag_len > 4) {
- secattr->attr.mls.cat =
- netlbl_secattr_catmap_alloc(GFP_ATOMIC);
- if (secattr->attr.mls.cat == NULL)
- return -ENOMEM;
-
ret_val = cipso_v4_map_cat_rng_ntoh(doi_def,
&tag[4],
tag_len - 4,
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 9fa5c09..94d40cc 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
pip->saddr = fl4.saddr;
pip->protocol = IPPROTO_IGMP;
pip->tot_len = 0; /* filled in later */
- ip_select_ident(skb, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
((u8 *)&pip[1])[0] = IPOPT_RA;
((u8 *)&pip[1])[1] = 4;
((u8 *)&pip[1])[2] = 0;
@@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
iph->daddr = dst;
iph->saddr = fl4.saddr;
iph->protocol = IPPROTO_IGMP;
- ip_select_ident(skb, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
((u8 *)&iph[1])[0] = IPOPT_RA;
((u8 *)&iph[1])[1] = 4;
((u8 *)&iph[1])[2] = 0;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 33d5537..67140ef 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -26,20 +26,7 @@
* Theory of operations.
* We keep one entry for each peer IP address. The nodes contains long-living
* information about the peer which doesn't depend on routes.
- * At this moment this information consists only of ID field for the next
- * outgoing IP packet. This field is incremented with each packet as encoded
- * in inet_getid() function (include/net/inetpeer.h).
- * At the moment of writing this notes identifier of IP packets is generated
- * to be unpredictable using this code only for packets subjected
- * (actually or potentially) to defragmentation. I.e. DF packets less than
- * PMTU in size when local fragmentation is disabled use a constant ID and do
- * not use this code (see ip_select_ident() in include/net/ip.h).
*
- * Route cache entries hold references to our nodes.
- * New cache entries get references via lookup by destination IP address in
- * the avl tree. The reference is grabbed only when it's needed i.e. only
- * when we try to output IP packet which needs an unpredictable ID (see
- * __ip_select_ident() in net/ipv4/route.c).
* Nodes are removed only when reference counter goes to 0.
* When it's happened the node may be removed when a sufficient amount of
* time has been passed since its last use. The less-recently-used entry can
@@ -62,7 +49,6 @@
* refcnt: atomically against modifications on other CPU;
* usually under some other lock to prevent node disappearing
* daddr: unchangeable
- * ip_id_count: atomic value (no lock needed)
*/

static struct kmem_cache *peer_cachep __read_mostly;
@@ -504,10 +490,6 @@ relookup:
p->daddr = *daddr;
atomic_set(&p->refcnt, 1);
atomic_set(&p->rid, 0);
- atomic_set(&p->ip_id_count,
- (daddr->family == AF_INET) ?
- secure_ip_id(daddr->addr.a4) :
- secure_ipv6_id(daddr->addr.a6));
p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
p->rate_tokens = 0;
/* 60*HZ is arbitrary, but chosen enough high so that the first
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index df18461..5352214 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
iph->saddr = saddr;
iph->protocol = sk->sk_protocol;
- ip_select_ident(skb, &rt->dst, sk);
+ ip_select_ident(skb, sk);

if (opt && opt->opt.optlen) {
iph->ihl += opt->opt.optlen>>2;
@@ -386,8 +386,7 @@ packet_routed:
ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
}

- ip_select_ident_more(skb, &rt->dst, sk,
- (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+ ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);

skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
@@ -1339,7 +1338,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
iph->ttl = ttl;
iph->protocol = sk->sk_protocol;
ip_copy_addrs(iph, fl4);
- ip_select_ident(skb, &rt->dst, sk);
+ ip_select_ident(skb, sk);

if (opt) {
iph->ihl += opt->optlen>>2;
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 42ffbc8..67bd005 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -74,7 +74,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
- __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+ __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);

err = ip_local_out(skb);
if (unlikely(net_xmit_eval(err)))
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 6fbf339..648ba5e 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1661,7 +1661,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr)
iph->protocol = IPPROTO_IPIP;
iph->ihl = 5;
iph->tot_len = htons(skb->len);
- ip_select_ident(skb, skb_dst(skb), NULL);
+ ip_select_ident(skb, NULL);
ip_send_check(iph);

memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 23c3e5b..3022aed 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -389,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
- ip_select_ident(skb, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);

iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 566bfa5..caadba0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -89,6 +89,7 @@
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <linux/slab.h>
+#include <linux/jhash.h>
#include <net/dst.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
@@ -465,39 +466,49 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
return neigh_create(&arp_tbl, pkey, dev);
}

-/*
- * Peer allocation may fail only in serious out-of-memory conditions. However
- * we still can generate some output.
- * Random ID selection looks a bit dangerous because we have no chances to
- * select ID being unique in a reasonable period of time.
- * But broken packet identifier may be better than no packet at all.
+#define IP_IDENTS_SZ 2048u
+struct ip_ident_bucket {
+ atomic_t id;
+ u32 stamp32;
+};
+
+static struct ip_ident_bucket *ip_idents __read_mostly;
+
+/* In order to protect privacy, we add a perturbation to identifiers
+ * if one generator is seldom used. This makes hard for an attacker
+ * to infer how many packets were sent between two points in time.
*/
-static void ip_select_fb_ident(struct iphdr *iph)
+u32 ip_idents_reserve(u32 hash, int segs)
{
- static DEFINE_SPINLOCK(ip_fb_id_lock);
- static u32 ip_fallback_id;
- u32 salt;
+ struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
+ u32 old = ACCESS_ONCE(bucket->stamp32);
+ u32 now = (u32)jiffies;
+ u32 delta = 0;
+
+ if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) {
+ u64 x = prandom_u32();
+
+ x *= (now - old);
+ delta = (u32)(x >> 32);
+ }

- spin_lock_bh(&ip_fb_id_lock);
- salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
- iph->id = htons(salt & 0xFFFF);
- ip_fallback_id = salt;
- spin_unlock_bh(&ip_fb_id_lock);
+ return atomic_add_return(segs + delta, &bucket->id) - segs;
}
+EXPORT_SYMBOL(ip_idents_reserve);

-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
+void __ip_select_ident(struct iphdr *iph, int segs)
{
- struct net *net = dev_net(dst->dev);
- struct inet_peer *peer;
+ static u32 ip_idents_hashrnd __read_mostly;
+ u32 hash, id;

- peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1);
- if (peer) {
- iph->id = htons(inet_getid(peer, more));
- inet_putpeer(peer);
- return;
- }
+ net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));

- ip_select_fb_ident(iph);
+ hash = jhash_3words((__force u32)iph->daddr,
+ (__force u32)iph->saddr,
+ iph->protocol,
+ ip_idents_hashrnd);
+ id = ip_idents_reserve(hash, segs);
+ iph->id = htons(id);
}
EXPORT_SYMBOL(__ip_select_ident);

@@ -2716,6 +2727,12 @@ int __init ip_rt_init(void)
{
int rc = 0;

+ ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
+ if (!ip_idents)
+ panic("IP: failed to allocate ip_idents\n");
+
+ prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
+
#ifdef CONFIG_IP_ROUTE_CLASSID
ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
if (!ip_rt_acct)
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 06cae62..6b1a5fd 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -219,7 +219,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked,
* This is:
* (actual rate in segments) * baseRTT
*/
- target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt;
+ target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT;
+ do_div(target_cwnd, rtt);

/* Calculate the difference between the window we had,
* and the window we would like to have. This quantity
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 326475a..603ad49 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -145,7 +145,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked,

rtt = veno->minrtt;

- target_cwnd = (tp->snd_cwnd * veno->basertt);
+ target_cwnd = (u64)tp->snd_cwnd * veno->basertt;
target_cwnd <<= V_PARAM_SHIFT;
do_div(target_cwnd, rtt);

diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 31b1815..1f564a1 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -117,12 +117,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)

top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
- ip_select_ident(skb, dst->child, NULL);

top_iph->ttl = ip4_dst_hoplimit(dst->child);

top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
+ ip_select_ident(skb, NULL);

return 0;
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e86c22e..6622e14 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -516,6 +516,20 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
skb_copy_secmark(to, from);
}

+static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+ static u32 ip6_idents_hashrnd __read_mostly;
+ u32 hash, id;
+
+ net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+ hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+ hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
+
+ id = ip_idents_reserve(hash, 1);
+ fhdr->identification = htonl(id);
+}
+
int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
struct sk_buff *frag;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index b31a012..798eb0f 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -7,29 +7,6 @@
#include <net/ip6_fib.h>
#include <net/addrconf.h>

-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
- static atomic_t ipv6_fragmentation_id;
- int ident;
-
-#if IS_ENABLED(CONFIG_IPV6)
- if (rt && !(rt->dst.flags & DST_NOPEER)) {
- struct inet_peer *peer;
- struct net *net;
-
- net = dev_net(rt->dst.dev);
- peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
- if (peer) {
- fhdr->identification = htonl(inet_getid(peer, 0));
- inet_putpeer(peer);
- return;
- }
- }
-#endif
- ident = atomic_inc_return(&ipv6_fragmentation_id);
- fhdr->identification = htonl(ident);
-}
-EXPORT_SYMBOL(ipv6_select_ident);

int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
{
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index c47444e..7f0e1cf 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = old_iph->ttl;
- ip_select_ident(skb, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);

/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index dce1beb..929bfc6 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -406,6 +406,70 @@ out_entry:
* Security Attribute Functions
*/

+#define _CM_F_NONE 0x00000000
+#define _CM_F_ALLOC 0x00000001
+#define _CM_F_WALK 0x00000002
+
+/**
+ * _netlbl_secattr_catmap_getnode - Get a individual node from a catmap
+ * @catmap: pointer to the category bitmap
+ * @offset: the requested offset
+ * @cm_flags: catmap flags, see _CM_F_*
+ * @gfp_flags: memory allocation flags
+ *
+ * Description:
+ * Iterate through the catmap looking for the node associated with @offset.
+ * If the _CM_F_ALLOC flag is set in @cm_flags and there is no associated node,
+ * one will be created and inserted into the catmap. If the _CM_F_WALK flag is
+ * set in @cm_flags and there is no associated node, the next highest node will
+ * be returned. Returns a pointer to the node on success, NULL on failure.
+ *
+ */
+static struct netlbl_lsm_secattr_catmap *_netlbl_secattr_catmap_getnode(
+ struct netlbl_lsm_secattr_catmap **catmap,
+ u32 offset,
+ unsigned int cm_flags,
+ gfp_t gfp_flags)
+{
+ struct netlbl_lsm_secattr_catmap *iter = *catmap;
+ struct netlbl_lsm_secattr_catmap *prev = NULL;
+
+ if (iter == NULL)
+ goto secattr_catmap_getnode_alloc;
+ if (offset < iter->startbit)
+ goto secattr_catmap_getnode_walk;
+ while (iter && offset >= (iter->startbit + NETLBL_CATMAP_SIZE)) {
+ prev = iter;
+ iter = iter->next;
+ }
+ if (iter == NULL || offset < iter->startbit)
+ goto secattr_catmap_getnode_walk;
+
+ return iter;
+
+secattr_catmap_getnode_walk:
+ if (cm_flags & _CM_F_WALK)
+ return iter;
+secattr_catmap_getnode_alloc:
+ if (!(cm_flags & _CM_F_ALLOC))
+ return NULL;
+
+ iter = netlbl_secattr_catmap_alloc(gfp_flags);
+ if (iter == NULL)
+ return NULL;
+ iter->startbit = offset & ~(NETLBL_CATMAP_SIZE - 1);
+
+ if (prev == NULL) {
+ iter->next = *catmap;
+ *catmap = iter;
+ } else {
+ iter->next = prev->next;
+ prev->next = iter;
+ }
+
+ return iter;
+}
+
/**
* netlbl_secattr_catmap_walk - Walk a LSM secattr catmap looking for a bit
* @catmap: the category bitmap
@@ -420,43 +484,41 @@ int netlbl_secattr_catmap_walk(struct netlbl_lsm_secattr_catmap *catmap,
u32 offset)
{
struct netlbl_lsm_secattr_catmap *iter = catmap;
- u32 node_idx;
- u32 node_bit;
+ u32 idx;
+ u32 bit;
NETLBL_CATMAP_MAPTYPE bitmap;

+ iter = _netlbl_secattr_catmap_getnode(&catmap, offset, _CM_F_WALK, 0);
+ if (iter == NULL)
+ return -ENOENT;
if (offset > iter->startbit) {
- while (offset >= (iter->startbit + NETLBL_CATMAP_SIZE)) {
- iter = iter->next;
- if (iter == NULL)
- return -ENOENT;
- }
- node_idx = (offset - iter->startbit) / NETLBL_CATMAP_MAPSIZE;
- node_bit = offset - iter->startbit -
- (NETLBL_CATMAP_MAPSIZE * node_idx);
+ offset -= iter->startbit;
+ idx = offset / NETLBL_CATMAP_MAPSIZE;
+ bit = offset % NETLBL_CATMAP_MAPSIZE;
} else {
- node_idx = 0;
- node_bit = 0;
+ idx = 0;
+ bit = 0;
}
- bitmap = iter->bitmap[node_idx] >> node_bit;
+ bitmap = iter->bitmap[idx] >> bit;

for (;;) {
if (bitmap != 0) {
while ((bitmap & NETLBL_CATMAP_BIT) == 0) {
bitmap >>= 1;
- node_bit++;
+ bit++;
}
return iter->startbit +
- (NETLBL_CATMAP_MAPSIZE * node_idx) + node_bit;
+ (NETLBL_CATMAP_MAPSIZE * idx) + bit;
}
- if (++node_idx >= NETLBL_CATMAP_MAPCNT) {
+ if (++idx >= NETLBL_CATMAP_MAPCNT) {
if (iter->next != NULL) {
iter = iter->next;
- node_idx = 0;
+ idx = 0;
} else
return -ENOENT;
}
- bitmap = iter->bitmap[node_idx];
- node_bit = 0;
+ bitmap = iter->bitmap[idx];
+ bit = 0;
}

return -ENOENT;
@@ -476,54 +538,103 @@ int netlbl_secattr_catmap_walk(struct netlbl_lsm_secattr_catmap *catmap,
int netlbl_secattr_catmap_walk_rng(struct netlbl_lsm_secattr_catmap *catmap,
u32 offset)
{
- struct netlbl_lsm_secattr_catmap *iter = catmap;
- u32 node_idx;
- u32 node_bit;
+ struct netlbl_lsm_secattr_catmap *iter;
+ struct netlbl_lsm_secattr_catmap *prev = NULL;
+ u32 idx;
+ u32 bit;
NETLBL_CATMAP_MAPTYPE bitmask;
NETLBL_CATMAP_MAPTYPE bitmap;

+ iter = _netlbl_secattr_catmap_getnode(&catmap, offset, _CM_F_WALK, 0);
+ if (iter == NULL)
+ return -ENOENT;
if (offset > iter->startbit) {
- while (offset >= (iter->startbit + NETLBL_CATMAP_SIZE)) {
- iter = iter->next;
- if (iter == NULL)
- return -ENOENT;
- }
- node_idx = (offset - iter->startbit) / NETLBL_CATMAP_MAPSIZE;
- node_bit = offset - iter->startbit -
- (NETLBL_CATMAP_MAPSIZE * node_idx);
+ offset -= iter->startbit;
+ idx = offset / NETLBL_CATMAP_MAPSIZE;
+ bit = offset % NETLBL_CATMAP_MAPSIZE;
} else {
- node_idx = 0;
- node_bit = 0;
+ idx = 0;
+ bit = 0;
}
- bitmask = NETLBL_CATMAP_BIT << node_bit;
+ bitmask = NETLBL_CATMAP_BIT << bit;

for (;;) {
- bitmap = iter->bitmap[node_idx];
+ bitmap = iter->bitmap[idx];
while (bitmask != 0 && (bitmap & bitmask) != 0) {
bitmask <<= 1;
- node_bit++;
+ bit++;
}

- if (bitmask != 0)
+ if (prev && idx == 0 && bit == 0)
+ return prev->startbit + NETLBL_CATMAP_SIZE - 1;
+ else if (bitmask != 0)
return iter->startbit +
- (NETLBL_CATMAP_MAPSIZE * node_idx) +
- node_bit - 1;
- else if (++node_idx >= NETLBL_CATMAP_MAPCNT) {
+ (NETLBL_CATMAP_MAPSIZE * idx) + bit - 1;
+ else if (++idx >= NETLBL_CATMAP_MAPCNT) {
if (iter->next == NULL)
- return iter->startbit + NETLBL_CATMAP_SIZE - 1;
+ return iter->startbit + NETLBL_CATMAP_SIZE - 1;
+ prev = iter;
iter = iter->next;
- node_idx = 0;
+ idx = 0;
}
bitmask = NETLBL_CATMAP_BIT;
- node_bit = 0;
+ bit = 0;
}

return -ENOENT;
}

/**
+ * netlbl_secattr_catmap_getlong - Export an unsigned long bitmap
+ * @catmap: pointer to the category bitmap
+ * @offset: pointer to the requested offset
+ * @bitmap: the exported bitmap
+ *
+ * Description:
+ * Export a bitmap with an offset greater than or equal to @offset and return
+ * it in @bitmap. The @offset must be aligned to an unsigned long and will be
+ * updated on return if different from what was requested; if the catmap is
+ * empty at the requested offset and beyond, the @offset is set to (u32)-1.
+ * Returns zero on sucess, negative values on failure.
+ *
+ */
+int netlbl_secattr_catmap_getlong(struct netlbl_lsm_secattr_catmap *catmap,
+ u32 *offset,
+ unsigned long *bitmap)
+{
+ struct netlbl_lsm_secattr_catmap *iter;
+ u32 off = *offset;
+ u32 idx;
+
+ /* only allow aligned offsets */
+ if ((off & (BITS_PER_LONG - 1)) != 0)
+ return -EINVAL;
+
+ if (off < catmap->startbit) {
+ off = catmap->startbit;
+ *offset = off;
+ }
+ iter = _netlbl_secattr_catmap_getnode(&catmap, off, _CM_F_NONE, 0);
+ if (iter == NULL) {
+ *offset = (u32)-1;
+ return 0;
+ }
+
+ if (off < iter->startbit) {
+ off = iter->startbit;
+ *offset = off;
+ } else
+ off -= iter->startbit;
+
+ idx = off / NETLBL_CATMAP_MAPSIZE;
+ *bitmap = iter->bitmap[idx] >> (off % NETLBL_CATMAP_SIZE);
+
+ return 0;
+}
+
+/**
* netlbl_secattr_catmap_setbit - Set a bit in a LSM secattr catmap
- * @catmap: the category bitmap
+ * @catmap: pointer to the category bitmap
* @bit: the bit to set
* @flags: memory allocation flags
*
@@ -532,36 +643,27 @@ int netlbl_secattr_catmap_walk_rng(struct netlbl_lsm_secattr_catmap *catmap,
* negative values on failure.
*
*/
-int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap *catmap,
+int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap **catmap,
u32 bit,
gfp_t flags)
{
- struct netlbl_lsm_secattr_catmap *iter = catmap;
- u32 node_bit;
- u32 node_idx;
+ struct netlbl_lsm_secattr_catmap *iter;
+ u32 idx;

- while (iter->next != NULL &&
- bit >= (iter->startbit + NETLBL_CATMAP_SIZE))
- iter = iter->next;
- if (bit >= (iter->startbit + NETLBL_CATMAP_SIZE)) {
- iter->next = netlbl_secattr_catmap_alloc(flags);
- if (iter->next == NULL)
- return -ENOMEM;
- iter = iter->next;
- iter->startbit = bit & ~(NETLBL_CATMAP_SIZE - 1);
- }
+ iter = _netlbl_secattr_catmap_getnode(catmap, bit, _CM_F_ALLOC, flags);
+ if (iter == NULL)
+ return -ENOMEM;

- /* gcc always rounds to zero when doing integer division */
- node_idx = (bit - iter->startbit) / NETLBL_CATMAP_MAPSIZE;
- node_bit = bit - iter->startbit - (NETLBL_CATMAP_MAPSIZE * node_idx);
- iter->bitmap[node_idx] |= NETLBL_CATMAP_BIT << node_bit;
+ bit -= iter->startbit;
+ idx = bit / NETLBL_CATMAP_MAPSIZE;
+ iter->bitmap[idx] |= NETLBL_CATMAP_BIT << (bit % NETLBL_CATMAP_MAPSIZE);

return 0;
}

/**
* netlbl_secattr_catmap_setrng - Set a range of bits in a LSM secattr catmap
- * @catmap: the category bitmap
+ * @catmap: pointer to the category bitmap
* @start: the starting bit
* @end: the last bit in the string
* @flags: memory allocation flags
@@ -571,36 +673,66 @@ int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap *catmap,
* on success, negative values on failure.
*
*/
-int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap *catmap,
+int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap **catmap,
u32 start,
u32 end,
gfp_t flags)
{
- int ret_val = 0;
- struct netlbl_lsm_secattr_catmap *iter = catmap;
- u32 iter_max_spot;
- u32 spot;
+ int rc = 0;
+ u32 spot = start;
+
+ while (rc == 0 && spot <= end) {
+ if (((spot & (BITS_PER_LONG - 1)) != 0) &&
+ ((end - spot) > BITS_PER_LONG)) {
+ rc = netlbl_secattr_catmap_setlong(catmap,
+ spot,
+ (unsigned long)-1,
+ flags);
+ spot += BITS_PER_LONG;
+ } else
+ rc = netlbl_secattr_catmap_setbit(catmap,
+ spot++,
+ flags);
+ }

- /* XXX - This could probably be made a bit faster by combining writes
- * to the catmap instead of setting a single bit each time, but for
- * right now skipping to the start of the range in the catmap should
- * be a nice improvement over calling the individual setbit function
- * repeatedly from a loop. */
+ return rc;
+}

- while (iter->next != NULL &&
- start >= (iter->startbit + NETLBL_CATMAP_SIZE))
- iter = iter->next;
- iter_max_spot = iter->startbit + NETLBL_CATMAP_SIZE;
+/**
+ * netlbl_secattr_catmap_setlong - Import an unsigned long bitmap
+ * @catmap: pointer to the category bitmap
+ * @offset: offset to the start of the imported bitmap
+ * @bitmap: the bitmap to import
+ * @flags: memory allocation flags
+ *
+ * Description:
+ * Import the bitmap specified in @bitmap into @catmap, using the offset
+ * in @offset. The offset must be aligned to an unsigned long. Returns zero
+ * on success, negative values on failure.
+ *
+ */
+int netlbl_secattr_catmap_setlong(struct netlbl_lsm_secattr_catmap **catmap,
+ u32 offset,
+ unsigned long bitmap,
+ gfp_t flags)
+{
+ struct netlbl_lsm_secattr_catmap *iter;
+ u32 idx;

- for (spot = start; spot <= end && ret_val == 0; spot++) {
- if (spot >= iter_max_spot && iter->next != NULL) {
- iter = iter->next;
- iter_max_spot = iter->startbit + NETLBL_CATMAP_SIZE;
- }
- ret_val = netlbl_secattr_catmap_setbit(iter, spot, flags);
- }
+ /* only allow aligned offsets */
+ if ((offset & (BITS_PER_LONG - 1)) != 0)
+ return -EINVAL;

- return ret_val;
+ iter = _netlbl_secattr_catmap_getnode(catmap,
+ offset, _CM_F_ALLOC, flags);
+ if (iter == NULL)
+ return -ENOMEM;
+
+ offset -= iter->startbit;
+ idx = offset / NETLBL_CATMAP_MAPSIZE;
+ iter->bitmap[idx] |= bitmap << (offset % NETLBL_CATMAP_MAPSIZE);
+
+ return 0;
}

/*
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 6524fa8..6a4c5a7 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1197,6 +1197,7 @@ void sctp_assoc_update(struct sctp_association *asoc,
asoc->c = new->c;
asoc->peer.rwnd = new->peer.rwnd;
asoc->peer.sack_needed = new->peer.sack_needed;
+ asoc->peer.auth_capable = new->peer.auth_capable;
asoc->peer.i = new->peer.i;
sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
asoc->peer.i.initial_tsn, GFP_ATOMIC);
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 0fb140f..e867326 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -601,7 +601,7 @@ out:
return err;
no_route:
kfree_skb(nskb);
- IP_INC_STATS_BH(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);

/* FIXME: Returning the 'err' will effect all the associations
* associated with a socket, although only one of the paths of the
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 1eebf22..154c504 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -541,8 +541,7 @@ static void warn_gssd(void)
unsigned long now = jiffies;

if (time_after(now, ratelimit)) {
- printk(KERN_WARNING "RPC: AUTH_GSS upcall timed out.\n"
- "Please check user daemon is running.\n");
+ pr_warn("RPC: AUTH_GSS upcall failed. Please check user daemon is running.\n");
ratelimit = now + 15*HZ;
}
}
@@ -605,7 +604,6 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
struct rpc_pipe *pipe;
struct rpc_cred *cred = &gss_cred->gc_base;
struct gss_upcall_msg *gss_msg;
- unsigned long timeout;
DEFINE_WAIT(wait);
int err;

@@ -613,17 +611,16 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
__func__, from_kuid(&init_user_ns, cred->cr_uid));
retry:
err = 0;
- /* Default timeout is 15s unless we know that gssd is not running */
- timeout = 15 * HZ;
- if (!sn->gssd_running)
- timeout = HZ >> 2;
+ /* if gssd is down, just skip upcalling altogether */
+ if (!gssd_running(net)) {
+ warn_gssd();
+ return -EACCES;
+ }
gss_msg = gss_setup_upcall(gss_auth, cred);
if (PTR_ERR(gss_msg) == -EAGAIN) {
err = wait_event_interruptible_timeout(pipe_version_waitqueue,
- sn->pipe_version >= 0, timeout);
+ sn->pipe_version >= 0, 15 * HZ);
if (sn->pipe_version < 0) {
- if (err == 0)
- sn->gssd_running = 0;
warn_gssd();
err = -EACCES;
}
diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h
index 3a260e4..df58268 100644
--- a/net/sunrpc/netns.h
+++ b/net/sunrpc/netns.h
@@ -14,6 +14,7 @@ struct sunrpc_net {
struct cache_detail *rsi_cache;

struct super_block *pipefs_sb;
+ struct rpc_pipe *gssd_dummy;
struct mutex pipefs_sb_lock;

struct list_head all_clients;
@@ -31,8 +32,6 @@ struct sunrpc_net {
int pipe_version;
atomic_t pipe_users;
struct proc_dir_entry *use_gssp_proc;
-
- unsigned int gssd_running;
};

extern int sunrpc_net_id;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index bf04b30..5cd7ad1 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -38,7 +38,7 @@
#define NET_NAME(net) ((net == &init_net) ? " (init_net)" : "")

static struct file_system_type rpc_pipe_fs_type;
-
+static const struct rpc_pipe_ops gssd_dummy_pipe_ops;

static struct kmem_cache *rpc_inode_cachep __read_mostly;

@@ -216,14 +216,11 @@ rpc_destroy_inode(struct inode *inode)
static int
rpc_pipe_open(struct inode *inode, struct file *filp)
{
- struct net *net = inode->i_sb->s_fs_info;
- struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
struct rpc_pipe *pipe;
int first_open;
int res = -ENXIO;

mutex_lock(&inode->i_mutex);
- sn->gssd_running = 1;
pipe = RPC_I(inode)->pipe;
if (pipe == NULL)
goto out;
@@ -1159,6 +1156,7 @@ enum {
RPCAUTH_nfsd4_cb,
RPCAUTH_cache,
RPCAUTH_nfsd,
+ RPCAUTH_gssd,
RPCAUTH_RootEOF
};

@@ -1195,6 +1193,10 @@ static const struct rpc_filelist files[] = {
.name = "nfsd",
.mode = S_IFDIR | S_IRUGO | S_IXUGO,
},
+ [RPCAUTH_gssd] = {
+ .name = "gssd",
+ .mode = S_IFDIR | S_IRUGO | S_IXUGO,
+ },
};

/*
@@ -1208,13 +1210,24 @@ struct dentry *rpc_d_lookup_sb(const struct super_block *sb,
}
EXPORT_SYMBOL_GPL(rpc_d_lookup_sb);

-void rpc_pipefs_init_net(struct net *net)
+int rpc_pipefs_init_net(struct net *net)
{
struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);

+ sn->gssd_dummy = rpc_mkpipe_data(&gssd_dummy_pipe_ops, 0);
+ if (IS_ERR(sn->gssd_dummy))
+ return PTR_ERR(sn->gssd_dummy);
+
mutex_init(&sn->pipefs_sb_lock);
- sn->gssd_running = 1;
sn->pipe_version = -1;
+ return 0;
+}
+
+void rpc_pipefs_exit_net(struct net *net)
+{
+ struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+
+ rpc_destroy_pipe_data(sn->gssd_dummy);
}

/*
@@ -1244,11 +1257,73 @@ void rpc_put_sb_net(const struct net *net)
}
EXPORT_SYMBOL_GPL(rpc_put_sb_net);

+static const struct rpc_filelist gssd_dummy_clnt_dir[] = {
+ [0] = {
+ .name = "clntXX",
+ .mode = S_IFDIR | S_IRUGO | S_IXUGO,
+ },
+};
+
+static ssize_t
+dummy_downcall(struct file *filp, const char __user *src, size_t len)
+{
+ return -EINVAL;
+}
+
+static const struct rpc_pipe_ops gssd_dummy_pipe_ops = {
+ .upcall = rpc_pipe_generic_upcall,
+ .downcall = dummy_downcall,
+};
+
+/**
+ * rpc_gssd_dummy_populate - create a dummy gssd pipe
+ * @root: root of the rpc_pipefs filesystem
+ * @pipe_data: pipe data created when netns is initialized
+ *
+ * Create a dummy set of directories and a pipe that gssd can hold open to
+ * indicate that it is up and running.
+ */
+static struct dentry *
+rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
+{
+ int ret = 0;
+ struct dentry *gssd_dentry;
+ struct dentry *clnt_dentry = NULL;
+ struct dentry *pipe_dentry = NULL;
+ struct qstr q = QSTR_INIT(files[RPCAUTH_gssd].name,
+ strlen(files[RPCAUTH_gssd].name));
+
+ /* We should never get this far if "gssd" doesn't exist */
+ gssd_dentry = d_hash_and_lookup(root, &q);
+ if (!gssd_dentry)
+ return ERR_PTR(-ENOENT);
+
+ ret = rpc_populate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1, NULL);
+ if (ret) {
+ pipe_dentry = ERR_PTR(ret);
+ goto out;
+ }
+
+ q.name = gssd_dummy_clnt_dir[0].name;
+ q.len = strlen(gssd_dummy_clnt_dir[0].name);
+ clnt_dentry = d_hash_and_lookup(gssd_dentry, &q);
+ if (!clnt_dentry) {
+ pipe_dentry = ERR_PTR(-ENOENT);
+ goto out;
+ }
+
+ pipe_dentry = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data);
+out:
+ dput(clnt_dentry);
+ dput(gssd_dentry);
+ return pipe_dentry;
+}
+
static int
rpc_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode *inode;
- struct dentry *root;
+ struct dentry *root, *gssd_dentry;
struct net *net = data;
struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
int err;
@@ -1266,6 +1341,13 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
return -ENOMEM;
if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL))
return -ENOMEM;
+
+ gssd_dentry = rpc_gssd_dummy_populate(root, sn->gssd_dummy);
+ if (IS_ERR(gssd_dentry)) {
+ __rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF);
+ return PTR_ERR(gssd_dentry);
+ }
+
dprintk("RPC: sending pipefs MOUNT notification for net %p%s\n",
net, NET_NAME(net));
mutex_lock(&sn->pipefs_sb_lock);
@@ -1280,6 +1362,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
return 0;

err_depopulate:
+ dput(gssd_dentry);
blocking_notifier_call_chain(&rpc_pipefs_notifier_list,
RPC_PIPEFS_UMOUNT,
sb);
@@ -1289,6 +1372,16 @@ err_depopulate:
return err;
}

+bool
+gssd_running(struct net *net)
+{
+ struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+ struct rpc_pipe *pipe = sn->gssd_dummy;
+
+ return pipe->nreaders || pipe->nwriters;
+}
+EXPORT_SYMBOL_GPL(gssd_running);
+
static struct dentry *
rpc_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index 3d6498a..cd30120 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -44,12 +44,17 @@ static __net_init int sunrpc_init_net(struct net *net)
if (err)
goto err_unixgid;

- rpc_pipefs_init_net(net);
+ err = rpc_pipefs_init_net(net);
+ if (err)
+ goto err_pipefs;
+
INIT_LIST_HEAD(&sn->all_clients);
spin_lock_init(&sn->rpc_client_lock);
spin_lock_init(&sn->rpcb_clnt_lock);
return 0;

+err_pipefs:
+ unix_gid_cache_destroy(net);
err_unixgid:
ip_map_cache_destroy(net);
err_ipmap:
@@ -60,6 +65,7 @@ err_proc:

static __net_exit void sunrpc_exit_net(struct net *net)
{
+ rpc_pipefs_exit_net(net);
unix_gid_cache_destroy(net);
ip_map_cache_destroy(net);
rpc_proc_exit(net);
diff --git a/security/commoncap.c b/security/commoncap.c
index b9d613e..963dc59 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -421,6 +421,9 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable);
}

+ cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+ cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+
return 0;
}

diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c
index 820313a..842deca 100644
--- a/security/selinux/ss/ebitmap.c
+++ b/security/selinux/ss/ebitmap.c
@@ -89,48 +89,33 @@ int ebitmap_netlbl_export(struct ebitmap *ebmap,
struct netlbl_lsm_secattr_catmap **catmap)
{
struct ebitmap_node *e_iter = ebmap->node;
- struct netlbl_lsm_secattr_catmap *c_iter;
- u32 cmap_idx, cmap_sft;
- int i;
-
- /* NetLabel's NETLBL_CATMAP_MAPTYPE is defined as an array of u64,
- * however, it is not always compatible with an array of unsigned long
- * in ebitmap_node.
- * In addition, you should pay attention the following implementation
- * assumes unsigned long has a width equal with or less than 64-bit.
- */
+ unsigned long e_map;
+ u32 offset;
+ unsigned int iter;
+ int rc;

if (e_iter == NULL) {
*catmap = NULL;
return 0;
}

- c_iter = netlbl_secattr_catmap_alloc(GFP_ATOMIC);
- if (c_iter == NULL)
- return -ENOMEM;
- *catmap = c_iter;
- c_iter->startbit = e_iter->startbit & ~(NETLBL_CATMAP_SIZE - 1);
+ if (*catmap != NULL)
+ netlbl_secattr_catmap_free(*catmap);
+ *catmap = NULL;

while (e_iter) {
- for (i = 0; i < EBITMAP_UNIT_NUMS; i++) {
- unsigned int delta, e_startbit, c_endbit;
-
- e_startbit = e_iter->startbit + i * EBITMAP_UNIT_SIZE;
- c_endbit = c_iter->startbit + NETLBL_CATMAP_SIZE;
- if (e_startbit >= c_endbit) {
- c_iter->next
- = netlbl_secattr_catmap_alloc(GFP_ATOMIC);
- if (c_iter->next == NULL)
+ offset = e_iter->startbit;
+ for (iter = 0; iter < EBITMAP_UNIT_NUMS; iter++) {
+ e_map = e_iter->maps[iter];
+ if (e_map != 0) {
+ rc = netlbl_secattr_catmap_setlong(catmap,
+ offset,
+ e_map,
+ GFP_ATOMIC);
+ if (rc != 0)
goto netlbl_export_failure;
- c_iter = c_iter->next;
- c_iter->startbit
- = e_startbit & ~(NETLBL_CATMAP_SIZE - 1);
}
- delta = e_startbit - c_iter->startbit;
- cmap_idx = delta / NETLBL_CATMAP_MAPSIZE;
- cmap_sft = delta % NETLBL_CATMAP_MAPSIZE;
- c_iter->bitmap[cmap_idx]
- |= e_iter->maps[i] << cmap_sft;
+ offset += EBITMAP_UNIT_SIZE;
}
e_iter = e_iter->next;
}
@@ -155,56 +140,42 @@ netlbl_export_failure:
int ebitmap_netlbl_import(struct ebitmap *ebmap,
struct netlbl_lsm_secattr_catmap *catmap)
{
+ int rc;
struct ebitmap_node *e_iter = NULL;
- struct ebitmap_node *emap_prev = NULL;
- struct netlbl_lsm_secattr_catmap *c_iter = catmap;
- u32 c_idx, c_pos, e_idx, e_sft;
-
- /* NetLabel's NETLBL_CATMAP_MAPTYPE is defined as an array of u64,
- * however, it is not always compatible with an array of unsigned long
- * in ebitmap_node.
- * In addition, you should pay attention the following implementation
- * assumes unsigned long has a width equal with or less than 64-bit.
- */
-
- do {
- for (c_idx = 0; c_idx < NETLBL_CATMAP_MAPCNT; c_idx++) {
- unsigned int delta;
- u64 map = c_iter->bitmap[c_idx];
-
- if (!map)
- continue;
+ struct ebitmap_node *e_prev = NULL;
+ u32 offset = 0, idx;
+ unsigned long bitmap;
+
+ for (;;) {
+ rc = netlbl_secattr_catmap_getlong(catmap, &offset, &bitmap);
+ if (rc < 0)
+ goto netlbl_import_failure;
+ if (offset == (u32)-1)
+ return 0;

- c_pos = c_iter->startbit
- + c_idx * NETLBL_CATMAP_MAPSIZE;
- if (!e_iter
- || c_pos >= e_iter->startbit + EBITMAP_SIZE) {
- e_iter = kzalloc(sizeof(*e_iter), GFP_ATOMIC);
- if (!e_iter)
- goto netlbl_import_failure;
- e_iter->startbit
- = c_pos - (c_pos % EBITMAP_SIZE);
- if (emap_prev == NULL)
- ebmap->node = e_iter;
- else
- emap_prev->next = e_iter;
- emap_prev = e_iter;
- }
- delta = c_pos - e_iter->startbit;
- e_idx = delta / EBITMAP_UNIT_SIZE;
- e_sft = delta % EBITMAP_UNIT_SIZE;
- while (map) {
- e_iter->maps[e_idx++] |= map & (-1UL);
- map = EBITMAP_SHIFT_UNIT_SIZE(map);
- }
+ if (e_iter == NULL ||
+ offset >= e_iter->startbit + EBITMAP_SIZE) {
+ e_prev = e_iter;
+ e_iter = kzalloc(sizeof(*e_iter), GFP_ATOMIC);
+ if (e_iter == NULL)
+ goto netlbl_import_failure;
+ e_iter->startbit = offset & ~(EBITMAP_SIZE - 1);
+ if (e_prev == NULL)
+ ebmap->node = e_iter;
+ else
+ e_prev->next = e_iter;
+ ebmap->highbit = e_iter->startbit + EBITMAP_SIZE;
}
- c_iter = c_iter->next;
- } while (c_iter);
- if (e_iter != NULL)
- ebmap->highbit = e_iter->startbit + EBITMAP_SIZE;
- else
- ebitmap_destroy(ebmap);

+ /* offset will always be aligned to an unsigned long */
+ idx = EBITMAP_NODE_INDEX(e_iter, offset);
+ e_iter->maps[idx] = bitmap;
+
+ /* next */
+ offset += EBITMAP_UNIT_SIZE;
+ }
+
+ /* NOTE: we should never reach this return */
return 0;

netlbl_import_failure:
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c
index 14293cd..ea1bc50 100644
--- a/security/smack/smack_access.c
+++ b/security/smack/smack_access.c
@@ -435,16 +435,13 @@ int smk_netlbl_mls(int level, char *catset, struct netlbl_lsm_secattr *sap,

sap->flags |= NETLBL_SECATTR_MLS_CAT;
sap->attr.mls.lvl = level;
- sap->attr.mls.cat = netlbl_secattr_catmap_alloc(GFP_ATOMIC);
- if (!sap->attr.mls.cat)
- return -ENOMEM;
- sap->attr.mls.cat->startbit = 0;
+ sap->attr.mls.cat = NULL;

for (cat = 1, cp = catset, byte = 0; byte < len; cp++, byte++)
for (m = 0x80; m != 0; m >>= 1, cat++) {
if ((m & *cp) == 0)
continue;
- rc = netlbl_secattr_catmap_setbit(sap->attr.mls.cat,
+ rc = netlbl_secattr_catmap_setbit(&sap->attr.mls.cat,
cat, GFP_ATOMIC);
if (rc < 0) {
netlbl_secattr_catmap_free(sap->attr.mls.cat);
diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig
index cc9fd67..be6277c 100644
--- a/sound/pci/Kconfig
+++ b/sound/pci/Kconfig
@@ -858,8 +858,8 @@ config SND_VIRTUOSO
select SND_JACK if INPUT=y || INPUT=SND
help
Say Y here to include support for sound cards based on the
- Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS,
- Essence ST (Deluxe), and Essence STX.
+ Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, DSX,
+ Essence ST (Deluxe), and Essence STX (II).
Support for the HDAV1.3 (Deluxe) and HDAV1.3 Slim is experimental;
for the Xense, missing.

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 46ecdbb..d5843da 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -4379,6 +4379,9 @@ static void ca0132_download_dsp(struct hda_codec *codec)
return; /* NOP */
#endif

+ if (spec->dsp_state == DSP_DOWNLOAD_FAILED)
+ return; /* don't retry failures */
+
chipio_enable_clocks(codec);
spec->dsp_state = DSP_DOWNLOADING;
if (!ca0132_download_dsp_images(codec))
@@ -4555,7 +4558,8 @@ static int ca0132_init(struct hda_codec *codec)
struct auto_pin_cfg *cfg = &spec->autocfg;
int i;

- spec->dsp_state = DSP_DOWNLOAD_INIT;
+ if (spec->dsp_state != DSP_DOWNLOAD_FAILED)
+ spec->dsp_state = DSP_DOWNLOAD_INIT;
spec->curr_chip_addx = INVALID_CHIP_ADDRESS;

snd_hda_power_up(codec);
@@ -4666,6 +4670,7 @@ static int patch_ca0132(struct hda_codec *codec)
codec->spec = spec;
spec->codec = codec;

+ spec->dsp_state = DSP_DOWNLOAD_INIT;
spec->num_mixers = 1;
spec->mixers[0] = ca0132_mixer;

diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 0f28aa2..c7b0ba6 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -84,6 +84,7 @@ enum {
STAC_DELL_EQ,
STAC_ALIENWARE_M17X,
STAC_92HD89XX_HP_FRONT_JACK,
+ STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK,
STAC_92HD73XX_MODELS
};

@@ -1785,6 +1786,11 @@ static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = {
{}
};

+static const struct hda_pintbl stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs[] = {
+ { 0x0e, 0x400000f0 },
+ {}
+};
+
static void stac92hd73xx_fixup_ref(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -1907,6 +1913,10 @@ static const struct hda_fixup stac92hd73xx_fixups[] = {
[STAC_92HD89XX_HP_FRONT_JACK] = {
.type = HDA_FIXUP_PINS,
.v.pins = stac92hd89xx_hp_front_jack_pin_configs,
+ },
+ [STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs,
}
};

@@ -1967,6 +1977,8 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = {
"Alienware M17x", STAC_ALIENWARE_M17X),
SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490,
"Alienware M17x R3", STAC_DELL_EQ),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1927,
+ "HP Z1 G2", STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17,
"unknown HP", STAC_92HD89XX_HP_FRONT_JACK),
{} /* terminator */
diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c
index 64b9fda..dbbbacf 100644
--- a/sound/pci/oxygen/virtuoso.c
+++ b/sound/pci/oxygen/virtuoso.c
@@ -53,6 +53,7 @@ static DEFINE_PCI_DEVICE_TABLE(xonar_ids) = {
{ OXYGEN_PCI_SUBID(0x1043, 0x835e) },
{ OXYGEN_PCI_SUBID(0x1043, 0x838e) },
{ OXYGEN_PCI_SUBID(0x1043, 0x8522) },
+ { OXYGEN_PCI_SUBID(0x1043, 0x85f4) },
{ OXYGEN_PCI_SUBID_BROKEN_EEPROM },
{ }
};
diff --git a/sound/pci/oxygen/xonar_pcm179x.c b/sound/pci/oxygen/xonar_pcm179x.c
index c8c7f2c..e026059 100644
--- a/sound/pci/oxygen/xonar_pcm179x.c
+++ b/sound/pci/oxygen/xonar_pcm179x.c
@@ -100,8 +100,8 @@
*/

/*
- * Xonar Essence ST (Deluxe)/STX
- * -----------------------------
+ * Xonar Essence ST (Deluxe)/STX (II)
+ * ----------------------------------
*
* CMI8788:
*
@@ -1138,6 +1138,14 @@ int get_xonar_pcm179x_model(struct oxygen *chip,
chip->model.resume = xonar_stx_resume;
chip->model.set_dac_params = set_pcm1796_params;
break;
+ case 0x85f4:
+ chip->model = model_xonar_st;
+ /* TODO: daughterboard support */
+ chip->model.shortname = "Xonar STX II";
+ chip->model.init = xonar_stx_init;
+ chip->model.resume = xonar_stx_resume;
+ chip->model.set_dac_params = set_pcm1796_params;
+ break;
default:
return -EINVAL;
}
diff --git a/sound/soc/blackfin/bf5xx-i2s-pcm.c b/sound/soc/blackfin/bf5xx-i2s-pcm.c
index 2a5b434..8cbcbf0 100644
--- a/sound/soc/blackfin/bf5xx-i2s-pcm.c
+++ b/sound/soc/blackfin/bf5xx-i2s-pcm.c
@@ -293,19 +293,19 @@ static int bf5xx_pcm_silence(struct snd_pcm_substream *substream,
unsigned int sample_size = runtime->sample_bits / 8;
void *buf = runtime->dma_area;
struct bf5xx_i2s_pcm_data *dma_data;
- unsigned int offset, size;
+ unsigned int offset, samples;

dma_data = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream);

if (dma_data->tdm_mode) {
offset = pos * 8 * sample_size;
- size = count * 8 * sample_size;
+ samples = count * 8;
} else {
offset = frames_to_bytes(runtime, pos);
- size = frames_to_bytes(runtime, count);
+ samples = count * runtime->channels;
}

- snd_pcm_format_set_silence(runtime->format, buf + offset, size);
+ snd_pcm_format_set_silence(runtime->format, buf + offset, samples);

return 0;
}
diff --git a/sound/soc/codecs/adau1701.c b/sound/soc/codecs/adau1701.c
index adee866..56bfc67 100644
--- a/sound/soc/codecs/adau1701.c
+++ b/sound/soc/codecs/adau1701.c
@@ -230,8 +230,10 @@ static int adau1701_reg_read(void *context, unsigned int reg,

*value = 0;

- for (i = 0; i < size; i++)
- *value |= recv_buf[i] << (i * 8);
+ for (i = 0; i < size; i++) {
+ *value <<= 8;
+ *value |= recv_buf[i];
+ }

return 0;
}
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 9ad8f01..764d0ea 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -2250,7 +2250,7 @@ static int max98090_probe(struct snd_soc_codec *codec)
/* Register for interrupts */
dev_dbg(codec->dev, "irq = %d\n", max98090->irq);

- ret = request_threaded_irq(max98090->irq, NULL,
+ ret = devm_request_threaded_irq(codec->dev, max98090->irq, NULL,
max98090_interrupt, IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
"max98090_interrupt", codec);
if (ret < 0) {
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 86426a1..c9ce977 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -3492,6 +3492,7 @@ static irqreturn_t wm8994_mic_irq(int irq, void *data)
return IRQ_HANDLED;
}

+/* Should be called with accdet_lock held */
static void wm1811_micd_stop(struct snd_soc_codec *codec)
{
struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
@@ -3499,14 +3500,10 @@ static void wm1811_micd_stop(struct snd_soc_codec *codec)
if (!wm8994->jackdet)
return;

- mutex_lock(&wm8994->accdet_lock);
-
snd_soc_update_bits(codec, WM8958_MIC_DETECT_1, WM8958_MICD_ENA, 0);

wm1811_jackdet_set_mode(codec, WM1811_JACKDET_MODE_JACK);

- mutex_unlock(&wm8994->accdet_lock);
-
if (wm8994->wm8994->pdata.jd_ext_cap)
snd_soc_dapm_disable_pin(&codec->dapm,
"MICBIAS2");
@@ -3547,10 +3544,10 @@ static void wm8958_open_circuit_work(struct work_struct *work)
open_circuit_work.work);
struct device *dev = wm8994->wm8994->dev;

- wm1811_micd_stop(wm8994->hubs.codec);
-
mutex_lock(&wm8994->accdet_lock);

+ wm1811_micd_stop(wm8994->hubs.codec);
+
dev_dbg(dev, "Reporting open circuit\n");

wm8994->jack_mic = false;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 4fbcab6..07c99e8 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1702,3 +1702,5 @@ int wm_adsp2_init(struct wm_adsp *adsp, bool dvfs)
return 0;
}
EXPORT_SYMBOL_GPL(wm_adsp2_init);
+
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index a5cbdb4..27ca0aa 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -915,11 +915,9 @@ static int i2s_suspend(struct snd_soc_dai *dai)
{
struct i2s_dai *i2s = to_info(dai);

- if (dai->active) {
- i2s->suspend_i2smod = readl(i2s->addr + I2SMOD);
- i2s->suspend_i2scon = readl(i2s->addr + I2SCON);
- i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR);
- }
+ i2s->suspend_i2smod = readl(i2s->addr + I2SMOD);
+ i2s->suspend_i2scon = readl(i2s->addr + I2SCON);
+ i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR);

return 0;
}
@@ -928,11 +926,9 @@ static int i2s_resume(struct snd_soc_dai *dai)
{
struct i2s_dai *i2s = to_info(dai);

- if (dai->active) {
- writel(i2s->suspend_i2scon, i2s->addr + I2SCON);
- writel(i2s->suspend_i2smod, i2s->addr + I2SMOD);
- writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR);
- }
+ writel(i2s->suspend_i2scon, i2s->addr + I2SCON);
+ writel(i2s->suspend_i2smod, i2s->addr + I2SMOD);
+ writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR);

return 0;
}
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 891b9a9..e683959 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1908,6 +1908,7 @@ int soc_dpcm_runtime_update(struct snd_soc_card *card)
dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
}

+ dpcm_path_put(&list);
capture:
/* skip if FE doesn't have capture capability */
if (!fe->cpu_dai->driver->capture.channels_min)
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index f5f0595..0e52836 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -1582,6 +1582,64 @@ YAMAHA_DEVICE(0x7010, "UB99"),
}
},
{
+ /* BOSS ME-25 */
+ USB_DEVICE(0x0582, 0x0113),
+ .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+ .ifnum = QUIRK_ANY_INTERFACE,
+ .type = QUIRK_COMPOSITE,
+ .data = (const struct snd_usb_audio_quirk[]) {
+ {
+ .ifnum = 0,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ {
+ .ifnum = 1,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ {
+ .ifnum = 2,
+ .type = QUIRK_MIDI_FIXED_ENDPOINT,
+ .data = & (const struct snd_usb_midi_endpoint_info) {
+ .out_cables = 0x0001,
+ .in_cables = 0x0001
+ }
+ },
+ {
+ .ifnum = -1
+ }
+ }
+ }
+},
+{
+ /* BOSS ME-25 */
+ USB_DEVICE(0x0582, 0x0113),
+ .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+ .ifnum = QUIRK_ANY_INTERFACE,
+ .type = QUIRK_COMPOSITE,
+ .data = (const struct snd_usb_audio_quirk[]) {
+ {
+ .ifnum = 0,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ {
+ .ifnum = 1,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ {
+ .ifnum = 2,
+ .type = QUIRK_MIDI_FIXED_ENDPOINT,
+ .data = & (const struct snd_usb_midi_endpoint_info) {
+ .out_cables = 0x0001,
+ .in_cables = 0x0001
+ }
+ },
+ {
+ .ifnum = -1
+ }
+ }
+ }
+},
+{
/* only 44.1 kHz works at the moment */
USB_DEVICE(0x0582, 0x0120),
.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 9f3eae2..2d9ab94 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -4,6 +4,7 @@ TARGETS += efivarfs
TARGETS += kcmp
TARGETS += memory-hotplug
TARGETS += mqueue
+TARGETS += mount
TARGETS += net
TARGETS += ptrace
TARGETS += timers
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
new file mode 100644
index 0000000..337d853
--- /dev/null
+++ b/tools/testing/selftests/mount/Makefile
@@ -0,0 +1,17 @@
+# Makefile for mount selftests.
+
+all: unprivileged-remount-test
+
+unprivileged-remount-test: unprivileged-remount-test.c
+ gcc -Wall -O2 unprivileged-remount-test.c -o unprivileged-remount-test
+
+# Allow specific tests to be selected.
+test_unprivileged_remount: unprivileged-remount-test
+ @if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi
+
+run_tests: all test_unprivileged_remount
+
+clean:
+ rm -f unprivileged-remount-test
+
+.PHONY: all test_unprivileged_remount
diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
new file mode 100644
index 0000000..1b3ff2f
--- /dev/null
+++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
@@ -0,0 +1,242 @@
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <stdbool.h>
+#include <stdarg.h>
+
+#ifndef CLONE_NEWNS
+# define CLONE_NEWNS 0x00020000
+#endif
+#ifndef CLONE_NEWUTS
+# define CLONE_NEWUTS 0x04000000
+#endif
+#ifndef CLONE_NEWIPC
+# define CLONE_NEWIPC 0x08000000
+#endif
+#ifndef CLONE_NEWNET
+# define CLONE_NEWNET 0x40000000
+#endif
+#ifndef CLONE_NEWUSER
+# define CLONE_NEWUSER 0x10000000
+#endif
+#ifndef CLONE_NEWPID
+# define CLONE_NEWPID 0x20000000
+#endif
+
+#ifndef MS_RELATIME
+#define MS_RELATIME (1 << 21)
+#endif
+#ifndef MS_STRICTATIME
+#define MS_STRICTATIME (1 << 24)
+#endif
+
+static void die(char *fmt, ...)
+{
+ va_list ap;
+ va_start(ap, fmt);
+ vfprintf(stderr, fmt, ap);
+ va_end(ap);
+ exit(EXIT_FAILURE);
+}
+
+static void write_file(char *filename, char *fmt, ...)
+{
+ char buf[4096];
+ int fd;
+ ssize_t written;
+ int buf_len;
+ va_list ap;
+
+ va_start(ap, fmt);
+ buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
+ va_end(ap);
+ if (buf_len < 0) {
+ die("vsnprintf failed: %s\n",
+ strerror(errno));
+ }
+ if (buf_len >= sizeof(buf)) {
+ die("vsnprintf output truncated\n");
+ }
+
+ fd = open(filename, O_WRONLY);
+ if (fd < 0) {
+ die("open of %s failed: %s\n",
+ filename, strerror(errno));
+ }
+ written = write(fd, buf, buf_len);
+ if (written != buf_len) {
+ if (written >= 0) {
+ die("short write to %s\n", filename);
+ } else {
+ die("write to %s failed: %s\n",
+ filename, strerror(errno));
+ }
+ }
+ if (close(fd) != 0) {
+ die("close of %s failed: %s\n",
+ filename, strerror(errno));
+ }
+}
+
+static void create_and_enter_userns(void)
+{
+ uid_t uid;
+ gid_t gid;
+
+ uid = getuid();
+ gid = getgid();
+
+ if (unshare(CLONE_NEWUSER) !=0) {
+ die("unshare(CLONE_NEWUSER) failed: %s\n",
+ strerror(errno));
+ }
+
+ write_file("/proc/self/uid_map", "0 %d 1", uid);
+ write_file("/proc/self/gid_map", "0 %d 1", gid);
+
+ if (setgroups(0, NULL) != 0) {
+ die("setgroups failed: %s\n",
+ strerror(errno));
+ }
+ if (setgid(0) != 0) {
+ die ("setgid(0) failed %s\n",
+ strerror(errno));
+ }
+ if (setuid(0) != 0) {
+ die("setuid(0) failed %s\n",
+ strerror(errno));
+ }
+}
+
+static
+bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
+{
+ pid_t child;
+
+ child = fork();
+ if (child == -1) {
+ die("fork failed: %s\n",
+ strerror(errno));
+ }
+ if (child != 0) { /* parent */
+ pid_t pid;
+ int status;
+ pid = waitpid(child, &status, 0);
+ if (pid == -1) {
+ die("waitpid failed: %s\n",
+ strerror(errno));
+ }
+ if (pid != child) {
+ die("waited for %d got %d\n",
+ child, pid);
+ }
+ if (!WIFEXITED(status)) {
+ die("child did not terminate cleanly\n");
+ }
+ return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+ }
+
+ create_and_enter_userns();
+ if (unshare(CLONE_NEWNS) != 0) {
+ die("unshare(CLONE_NEWNS) failed: %s\n",
+ strerror(errno));
+ }
+
+ if (mount("testing", "/tmp", "ramfs", mount_flags, NULL) != 0) {
+ die("mount of /tmp failed: %s\n",
+ strerror(errno));
+ }
+
+ create_and_enter_userns();
+
+ if (unshare(CLONE_NEWNS) != 0) {
+ die("unshare(CLONE_NEWNS) failed: %s\n",
+ strerror(errno));
+ }
+
+ if (mount("/tmp", "/tmp", "none",
+ MS_REMOUNT | MS_BIND | remount_flags, NULL) != 0) {
+ /* system("cat /proc/self/mounts"); */
+ die("remount of /tmp failed: %s\n",
+ strerror(errno));
+ }
+
+ if (mount("/tmp", "/tmp", "none",
+ MS_REMOUNT | MS_BIND | invalid_flags, NULL) == 0) {
+ /* system("cat /proc/self/mounts"); */
+ die("remount of /tmp with invalid flags "
+ "succeeded unexpectedly\n");
+ }
+ exit(EXIT_SUCCESS);
+}
+
+static bool test_unpriv_remount_simple(int mount_flags)
+{
+ return test_unpriv_remount(mount_flags, mount_flags, 0);
+}
+
+static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags)
+{
+ return test_unpriv_remount(mount_flags, mount_flags, invalid_flags);
+}
+
+int main(int argc, char **argv)
+{
+ if (!test_unpriv_remount_simple(MS_RDONLY|MS_NODEV)) {
+ die("MS_RDONLY malfunctions\n");
+ }
+ if (!test_unpriv_remount_simple(MS_NODEV)) {
+ die("MS_NODEV malfunctions\n");
+ }
+ if (!test_unpriv_remount_simple(MS_NOSUID|MS_NODEV)) {
+ die("MS_NOSUID malfunctions\n");
+ }
+ if (!test_unpriv_remount_simple(MS_NOEXEC|MS_NODEV)) {
+ die("MS_NOEXEC malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODEV,
+ MS_NOATIME|MS_NODEV))
+ {
+ die("MS_RELATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODEV,
+ MS_NOATIME|MS_NODEV))
+ {
+ die("MS_STRICTATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODEV,
+ MS_STRICTATIME|MS_NODEV))
+ {
+ die("MS_RELATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME|MS_NODEV,
+ MS_NOATIME|MS_NODEV))
+ {
+ die("MS_RELATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME|MS_NODEV,
+ MS_NOATIME|MS_NODEV))
+ {
+ die("MS_RELATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME|MS_NODEV,
+ MS_STRICTATIME|MS_NODEV))
+ {
+ die("MS_RELATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount(MS_STRICTATIME|MS_NODEV, MS_NODEV,
+ MS_NOATIME|MS_NODEV))
+ {
+ die("Default atime malfunctions\n");
+ }
+ return EXIT_SUCCESS;
+}
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 39dc5bc..5eaf18f 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -203,10 +203,9 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
spin_lock(&ioapic->lock);
for (index = 0; index < IOAPIC_NUM_PINS; index++) {
e = &ioapic->redirtbl[index];
- if (!e->fields.mask &&
- (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
- kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC,
- index) || index == RTC_GSI)) {
+ if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+ kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
+ index == RTC_GSI) {
if (kvm_apic_match_dest(vcpu, NULL, 0,
e->fields.dest_id, e->fields.dest_mode)) {
__set_bit(e->fields.vector,
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 0df7d4b..714b949 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -61,6 +61,14 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
return pfn;
}

+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+ unsigned long i;
+
+ for (i = 0; i < npages; ++i)
+ kvm_release_pfn_clean(pfn + i);
+}
+
int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
{
gfn_t gfn, end_gfn;
@@ -123,6 +131,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
if (r) {
printk(KERN_ERR "kvm_iommu_map_address:"
"iommu failed to map pfn=%llx\n", pfn);
+ kvm_unpin_pages(kvm, pfn, page_size);
goto unmap_pages;
}

@@ -134,7 +143,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
return 0;

unmap_pages:
- kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
+ kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
return r;
}

@@ -266,14 +275,6 @@ out_unlock:
return r;
}

-static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
-{
- unsigned long i;
-
- for (i = 0; i < npages; ++i)
- kvm_release_pfn_clean(pfn + i);
-}
-
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages)
{
--
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: Theodore Ts'o: "Re: [PATCH 1/1 linux-next] jbd2: Fix sparse context imbalance warning"
Previous message: Kamal Mostafa: "[3.13.y.z extended stable] Linux 3.13.11.7"
In reply to: Kamal Mostafa: "[3.13.y.z extended stable] Linux 3.13.11.7"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]