lkml.org 
[lkml]   [2018]   [Jan]   [31]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: Linux 4.4.114
diff --git a/Makefile b/Makefile
index 39019c9d205c..153440b1bbb0 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 4
-SUBLEVEL = 113
+SUBLEVEL = 114
EXTRAVERSION =
NAME = Blurry Fish Butt

diff --git a/arch/um/Makefile b/arch/um/Makefile
index e3abe6f3156d..9ccf462131c4 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -117,7 +117,7 @@ archheaders:
archprepare: include/generated/user_constants.h

LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
-LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib
+LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib $(call cc-option, -no-pie)

CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \
$(call cc-option, -fno-stack-protector,) \
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 112178b401a1..2d359991a273 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -46,6 +46,7 @@ static enum { EMULATE, NATIVE, NONE } vsyscall_mode =
#else
EMULATE;
#endif
+unsigned long vsyscall_pgprot = __PAGE_KERNEL_VSYSCALL;

static int __init vsyscall_setup(char *str)
{
@@ -336,11 +337,11 @@ void __init map_vsyscall(void)
extern char __vsyscall_page;
unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);

+ if (vsyscall_mode != NATIVE)
+ vsyscall_pgprot = __PAGE_KERNEL_VVAR;
if (vsyscall_mode != NONE)
__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
- vsyscall_mode == NATIVE
- ? PAGE_KERNEL_VSYSCALL
- : PAGE_KERNEL_VVAR);
+ __pgprot(vsyscall_pgprot));

BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
(unsigned long)VSYSCALL_ADDR);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 0fbc98568018..641f0f2c2982 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -199,6 +199,7 @@
#define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */
#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */

#define X86_FEATURE_RETPOLINE ( 7*32+29) /* Generic Retpoline mitigation for Spectre variant 2 */
#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* AMD Retpoline mitigation for Spectre variant 2 */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
new file mode 100644
index 000000000000..6999f7d01a0d
--- /dev/null
+++ b/arch/x86/include/asm/intel-family.h
@@ -0,0 +1,68 @@
+#ifndef _ASM_X86_INTEL_FAMILY_H
+#define _ASM_X86_INTEL_FAMILY_H
+
+/*
+ * "Big Core" Processors (Branded as Core, Xeon, etc...)
+ *
+ * The "_X" parts are generally the EP and EX Xeons, or the
+ * "Extreme" ones, like Broadwell-E.
+ *
+ * Things ending in "2" are usually because we have no better
+ * name for them. There's no processor called "WESTMERE2".
+ */
+
+#define INTEL_FAM6_CORE_YONAH 0x0E
+#define INTEL_FAM6_CORE2_MEROM 0x0F
+#define INTEL_FAM6_CORE2_MEROM_L 0x16
+#define INTEL_FAM6_CORE2_PENRYN 0x17
+#define INTEL_FAM6_CORE2_DUNNINGTON 0x1D
+
+#define INTEL_FAM6_NEHALEM 0x1E
+#define INTEL_FAM6_NEHALEM_EP 0x1A
+#define INTEL_FAM6_NEHALEM_EX 0x2E
+#define INTEL_FAM6_WESTMERE 0x25
+#define INTEL_FAM6_WESTMERE2 0x1F
+#define INTEL_FAM6_WESTMERE_EP 0x2C
+#define INTEL_FAM6_WESTMERE_EX 0x2F
+
+#define INTEL_FAM6_SANDYBRIDGE 0x2A
+#define INTEL_FAM6_SANDYBRIDGE_X 0x2D
+#define INTEL_FAM6_IVYBRIDGE 0x3A
+#define INTEL_FAM6_IVYBRIDGE_X 0x3E
+
+#define INTEL_FAM6_HASWELL_CORE 0x3C
+#define INTEL_FAM6_HASWELL_X 0x3F
+#define INTEL_FAM6_HASWELL_ULT 0x45
+#define INTEL_FAM6_HASWELL_GT3E 0x46
+
+#define INTEL_FAM6_BROADWELL_CORE 0x3D
+#define INTEL_FAM6_BROADWELL_XEON_D 0x56
+#define INTEL_FAM6_BROADWELL_GT3E 0x47
+#define INTEL_FAM6_BROADWELL_X 0x4F
+
+#define INTEL_FAM6_SKYLAKE_MOBILE 0x4E
+#define INTEL_FAM6_SKYLAKE_DESKTOP 0x5E
+#define INTEL_FAM6_SKYLAKE_X 0x55
+#define INTEL_FAM6_KABYLAKE_MOBILE 0x8E
+#define INTEL_FAM6_KABYLAKE_DESKTOP 0x9E
+
+/* "Small Core" Processors (Atom) */
+
+#define INTEL_FAM6_ATOM_PINEVIEW 0x1C
+#define INTEL_FAM6_ATOM_LINCROFT 0x26
+#define INTEL_FAM6_ATOM_PENWELL 0x27
+#define INTEL_FAM6_ATOM_CLOVERVIEW 0x35
+#define INTEL_FAM6_ATOM_CEDARVIEW 0x36
+#define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */
+#define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */
+#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */
+#define INTEL_FAM6_ATOM_MERRIFIELD1 0x4A /* Tangier */
+#define INTEL_FAM6_ATOM_MERRIFIELD2 0x5A /* Annidale */
+#define INTEL_FAM6_ATOM_GOLDMONT 0x5C
+#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */
+
+/* Xeon Phi */
+
+#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */
+
+#endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c124d6ab4bf9..86bccb4bd4dc 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -574,7 +574,7 @@ static inline void sync_core(void)
{
int tmp;

-#ifdef CONFIG_M486
+#ifdef CONFIG_X86_32
/*
* Do a CPUID if available, otherwise do a jump. The jump
* can conveniently enough be the jump around CPUID.
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 751bf4b7bf11..025ecfaba9c9 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -1,6 +1,8 @@
#ifndef _ASM_X86_SWITCH_TO_H
#define _ASM_X86_SWITCH_TO_H

+#include <asm/nospec-branch.h>
+
struct task_struct; /* one of the stranger aspects of C forward declarations */
__visible struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *next);
@@ -24,6 +26,23 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
#define __switch_canary_iparam
#endif /* CC_STACKPROTECTOR */

+#ifdef CONFIG_RETPOLINE
+ /*
+ * When switching from a shallower to a deeper call stack
+ * the RSB may either underflow or use entries populated
+ * with userspace addresses. On CPUs where those concerns
+ * exist, overwrite the RSB with entries which capture
+ * speculative execution to prevent attack.
+ */
+#define __retpoline_fill_return_buffer \
+ ALTERNATIVE("jmp 910f", \
+ __stringify(__FILL_RETURN_BUFFER(%%ebx, RSB_CLEAR_LOOPS, %%esp)),\
+ X86_FEATURE_RSB_CTXSW) \
+ "910:\n\t"
+#else
+#define __retpoline_fill_return_buffer
+#endif
+
/*
* Saving eflags is important. It switches not only IOPL between tasks,
* it also protects other tasks from NT leaking through sysenter etc.
@@ -46,6 +65,7 @@ do { \
"movl $1f,%[prev_ip]\n\t" /* save EIP */ \
"pushl %[next_ip]\n\t" /* restore EIP */ \
__switch_canary \
+ __retpoline_fill_return_buffer \
"jmp __switch_to\n" /* regparm call */ \
"1:\t" \
"popl %%ebp\n\t" /* restore EBP */ \
@@ -100,6 +120,23 @@ do { \
#define __switch_canary_iparam
#endif /* CC_STACKPROTECTOR */

+#ifdef CONFIG_RETPOLINE
+ /*
+ * When switching from a shallower to a deeper call stack
+ * the RSB may either underflow or use entries populated
+ * with userspace addresses. On CPUs where those concerns
+ * exist, overwrite the RSB with entries which capture
+ * speculative execution to prevent attack.
+ */
+#define __retpoline_fill_return_buffer \
+ ALTERNATIVE("jmp 910f", \
+ __stringify(__FILL_RETURN_BUFFER(%%r12, RSB_CLEAR_LOOPS, %%rsp)),\
+ X86_FEATURE_RSB_CTXSW) \
+ "910:\n\t"
+#else
+#define __retpoline_fill_return_buffer
+#endif
+
/*
* There is no need to save or restore flags, because flags are always
* clean in kernel mode, with the possible exception of IOPL. Kernel IOPL
@@ -112,6 +149,7 @@ do { \
"call __switch_to\n\t" \
"movq "__percpu_arg([current_task])",%%rsi\n\t" \
__switch_canary \
+ __retpoline_fill_return_buffer \
"movq %P[thread_info](%%rsi),%%r8\n\t" \
"movq %%rax,%%rdi\n\t" \
"testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 4865e10dbb55..9ee85066f407 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -13,6 +13,7 @@ extern void map_vsyscall(void);
*/
extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
extern bool vsyscall_enabled(void);
+extern unsigned long vsyscall_pgprot;
#else
static inline void map_vsyscall(void) {}
static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fc91c98bee01..fd945099fc95 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2592,8 +2592,8 @@ static struct resource * __init ioapic_setup_resources(void)
res[num].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i);
mem += IOAPIC_RESOURCE_NAME_SIZE;
+ ioapics[i].iomem_res = &res[num];
num++;
- ioapics[i].iomem_res = res;
}

ioapic_resources = res;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 49d25ddf0e9f..8cacf62ec458 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -22,6 +22,7 @@
#include <asm/alternative.h>
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
+#include <asm/intel-family.h>

static void __init spectre_v2_select_mitigation(void);

@@ -154,6 +155,23 @@ disable:
return SPECTRE_V2_CMD_NONE;
}

+/* Check for Skylake-like CPUs (for RSB handling) */
+static bool __init is_skylake_era(void)
+{
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+ boot_cpu_data.x86 == 6) {
+ switch (boot_cpu_data.x86_model) {
+ case INTEL_FAM6_SKYLAKE_MOBILE:
+ case INTEL_FAM6_SKYLAKE_DESKTOP:
+ case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_FAM6_KABYLAKE_MOBILE:
+ case INTEL_FAM6_KABYLAKE_DESKTOP:
+ return true;
+ }
+ }
+ return false;
+}
+
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -212,6 +230,24 @@ retpoline_auto:

spectre_v2_enabled = mode;
pr_info("%s\n", spectre_v2_strings[mode]);
+
+ /*
+ * If neither SMEP or KPTI are available, there is a risk of
+ * hitting userspace addresses in the RSB after a context switch
+ * from a shallow call stack to a deeper one. To prevent this fill
+ * the entire RSB, even when using IBRS.
+ *
+ * Skylake era CPUs have a separate issue with *underflow* of the
+ * RSB, when they will predict 'ret' targets from the generic BTB.
+ * The proper mitigation for this is IBRS. If IBRS is not supported
+ * or deactivated in favour of retpolines the RSB fill on context
+ * switch is required.
+ */
+ if ((!boot_cpu_has(X86_FEATURE_KAISER) &&
+ !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
+ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+ pr_info("Filling RSB on context switch\n");
+ }
}

#undef pr_fmt
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index e38d338a6447..b4ca91cf55b0 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -934,6 +934,8 @@ static int __populate_cache_leaves(unsigned int cpu)
ci_leaf_init(this_leaf++, &id4_regs);
__cache_cpumap_setup(cpu, idx, &id4_regs);
}
+ this_cpu_ci->cpu_map_populated = true;
+
return 0;
}

diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index b428a8174be1..2c76a1801393 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -39,6 +39,9 @@
#include <asm/setup.h>
#include <asm/msr.h>

+/* last level cache size per core */
+static int llc_size_per_core;
+
static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT];
static struct mc_saved_data {
unsigned int mc_saved_count;
@@ -996,15 +999,18 @@ static bool is_blacklisted(unsigned int cpu)

/*
* Late loading on model 79 with microcode revision less than 0x0b000021
- * may result in a system hang. This behavior is documented in item
- * BDF90, #334165 (Intel Xeon Processor E7-8800/4800 v4 Product Family).
+ * and LLC size per core bigger than 2.5MB may result in a system hang.
+ * This behavior is documented in item BDF90, #334165 (Intel Xeon
+ * Processor E7-8800/4800 v4 Product Family).
*/
if (c->x86 == 6 &&
c->x86_model == 79 &&
c->x86_mask == 0x01 &&
+ llc_size_per_core > 2621440 &&
c->microcode < 0x0b000021) {
pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode);
pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
+ return true;
}

return false;
@@ -1067,6 +1073,15 @@ static struct microcode_ops microcode_intel_ops = {
.microcode_fini_cpu = microcode_fini_cpu,
};

+static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c)
+{
+ u64 llc_size = c->x86_cache_size * 1024;
+
+ do_div(llc_size, c->x86_max_cores);
+
+ return (int)llc_size;
+}
+
struct microcode_ops * __init init_intel_microcode(void)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
@@ -1077,6 +1092,8 @@ struct microcode_ops * __init init_intel_microcode(void)
return NULL;
}

+ llc_size_per_core = calc_llc_size_per_core(c);
+
return &microcode_intel_ops;
}

diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index e912b2f6d36e..45772560aceb 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -93,6 +93,13 @@ static void delay_mwaitx(unsigned long __loops)
{
u64 start, end, delay, loops = __loops;

+ /*
+ * Timer value of 0 causes MWAITX to wait indefinitely, unless there
+ * is a store on the memory monitored by MONITORX.
+ */
+ if (loops == 0)
+ return;
+
start = rdtsc_ordered();

for (;;) {
diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c
index 8af98513d36c..2298434f7bdb 100644
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -345,7 +345,7 @@ void __init kaiser_init(void)
if (vsyscall_enabled())
kaiser_add_user_map_early((void *)VSYSCALL_ADDR,
PAGE_SIZE,
- __PAGE_KERNEL_VSYSCALL);
+ vsyscall_pgprot);

for_each_possible_cpu(cpu) {
void *percpu_vaddr = __per_cpu_user_mapped_start +
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 9f77943653fb..b63a173786d5 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -331,15 +331,6 @@ static int acpi_processor_get_info(struct acpi_device *device)
pr->throttling.duty_width = acpi_gbl_FADT.duty_width;

pr->pblk = object.processor.pblk_address;
-
- /*
- * We don't care about error returns - we just try to mark
- * these reserved so that nobody else is confused into thinking
- * that this region might be unused..
- *
- * (In particular, allocating the IO range for Cardbus)
- */
- request_region(pr->throttling.address, 6, "ACPI CPU throttle");
}

/*
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index de325ae04ce1..3b3c5b90bd20 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -593,25 +593,20 @@ struct acpi_namespace_node *acpi_ns_validate_handle(acpi_handle handle)
void acpi_ns_terminate(void)
{
acpi_status status;
+ union acpi_operand_object *prev;
+ union acpi_operand_object *next;

ACPI_FUNCTION_TRACE(ns_terminate);

-#ifdef ACPI_EXEC_APP
- {
- union acpi_operand_object *prev;
- union acpi_operand_object *next;
+ /* Delete any module-level code blocks */

- /* Delete any module-level code blocks */
-
- next = acpi_gbl_module_code_list;
- while (next) {
- prev = next;
- next = next->method.mutex;
- prev->method.mutex = NULL; /* Clear the Mutex (cheated) field */
- acpi_ut_remove_reference(prev);
- }
+ next = acpi_gbl_module_code_list;
+ while (next) {
+ prev = next;
+ next = next->method.mutex;
+ prev->method.mutex = NULL; /* Clear the Mutex (cheated) field */
+ acpi_ut_remove_reference(prev);
}
-#endif

/*
* Free the entire namespace -- all nodes and all objects
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 73c9c7fa9001..f06317d6fc38 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -99,13 +99,13 @@ static int find_child_checks(struct acpi_device *adev, bool check_children)
return -ENODEV;

/*
- * If the device has a _HID (or _CID) returning a valid ACPI/PNP
- * device ID, it is better to make it look less attractive here, so that
- * the other device with the same _ADR value (that may not have a valid
- * device ID) can be matched going forward. [This means a second spec
- * violation in a row, so whatever we do here is best effort anyway.]
+ * If the device has a _HID returning a valid ACPI/PNP device ID, it is
+ * better to make it look less attractive here, so that the other device
+ * with the same _ADR value (that may not have a valid device ID) can be
+ * matched going forward. [This means a second spec violation in a row,
+ * so whatever we do here is best effort anyway.]
*/
- return sta_present && list_empty(&adev->pnp.ids) ?
+ return sta_present && !adev->pnp.type.platform_id ?
FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
}

diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index f170d746336d..c72e64893d03 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -676,6 +676,15 @@ static int acpi_processor_get_throttling_fadt(struct acpi_processor *pr)
if (!pr->flags.throttling)
return -ENODEV;

+ /*
+ * We don't care about error returns - we just try to mark
+ * these reserved so that nobody else is confused into thinking
+ * that this region might be unused..
+ *
+ * (In particular, allocating the IO range for Cardbus)
+ */
+ request_region(pr->throttling.address, 6, "ACPI CPU throttle");
+
pr->throttling.state = 0;

duty_mask = pr->throttling.state_count - 1;
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index e9fd32e91668..70e13cf06ed0 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -16,6 +16,7 @@
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/acpi.h>
#include <linux/bitops.h>
#include <linux/cacheinfo.h>
#include <linux/compiler.h>
@@ -104,9 +105,16 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
struct cacheinfo *this_leaf, *sib_leaf;
unsigned int index;
- int ret;
+ int ret = 0;
+
+ if (this_cpu_ci->cpu_map_populated)
+ return 0;

- ret = cache_setup_of_node(cpu);
+ if (of_have_populated_dt())
+ ret = cache_setup_of_node(cpu);
+ else if (!acpi_disabled)
+ /* No cache property/hierarchy support yet in ACPI */
+ ret = -ENOTSUPP;
if (ret)
return ret;

@@ -203,8 +211,7 @@ static int detect_cache_attributes(unsigned int cpu)
*/
ret = cache_shared_cpu_map_setup(cpu);
if (ret) {
- pr_warn("Unable to detect cache hierarchy from DT for CPU %d\n",
- cpu);
+ pr_warn("Unable to detect cache hierarchy for CPU %d\n", cpu);
goto free_ci;
}
return 0;
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index a311cfa4c5bd..a6975795e7f3 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -166,14 +166,14 @@ void generate_pm_trace(const void *tracedata, unsigned int user)
}
EXPORT_SYMBOL(generate_pm_trace);

-extern char __tracedata_start, __tracedata_end;
+extern char __tracedata_start[], __tracedata_end[];
static int show_file_hash(unsigned int value)
{
int match;
char *tracedata;

match = 0;
- for (tracedata = &__tracedata_start ; tracedata < &__tracedata_end ;
+ for (tracedata = __tracedata_start ; tracedata < __tracedata_end ;
tracedata += 2 + sizeof(unsigned long)) {
unsigned short lineno = *(unsigned short *)tracedata;
const char *file = *(const char **)(tracedata + 2);
diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c
index 7e2dc5e56632..0b49f29bf0da 100644
--- a/drivers/input/mouse/trackpoint.c
+++ b/drivers/input/mouse/trackpoint.c
@@ -383,6 +383,9 @@ int trackpoint_detect(struct psmouse *psmouse, bool set_properties)
if (trackpoint_read(&psmouse->ps2dev, TP_EXT_BTN, &button_info)) {
psmouse_warn(psmouse, "failed to get extended button data, assuming 3 buttons\n");
button_info = 0x33;
+ } else if (!button_info) {
+ psmouse_warn(psmouse, "got 0 in extended button data, assuming 3 buttons\n");
+ button_info = 0x33;
}

psmouse->private = kzalloc(sizeof(struct trackpoint_data), GFP_KERNEL);
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 90e94a028a49..83b1226471c1 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -584,6 +584,8 @@ static int sdhci_esdhc_probe(struct platform_device *pdev)
{
struct sdhci_host *host;
struct device_node *np;
+ struct sdhci_pltfm_host *pltfm_host;
+ struct sdhci_esdhc *esdhc;
int ret;

np = pdev->dev.of_node;
@@ -600,6 +602,14 @@ static int sdhci_esdhc_probe(struct platform_device *pdev)

sdhci_get_of_property(pdev);

+ pltfm_host = sdhci_priv(host);
+ esdhc = pltfm_host->priv;
+ if (esdhc->vendor_ver == VENDOR_V_22)
+ host->quirks2 |= SDHCI_QUIRK2_HOST_NO_CMD23;
+
+ if (esdhc->vendor_ver > VENDOR_V_22)
+ host->quirks &= ~SDHCI_QUIRK_NO_BUSY_IRQ;
+
if (of_device_is_compatible(np, "fsl,p5040-esdhc") ||
of_device_is_compatible(np, "fsl,p5020-esdhc") ||
of_device_is_compatible(np, "fsl,p4080-esdhc") ||
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index c5ea1018cb47..24155380e43c 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2205,19 +2205,14 @@ static bool rtl8169_do_counters(struct net_device *dev, u32 counter_cmd)
void __iomem *ioaddr = tp->mmio_addr;
dma_addr_t paddr = tp->counters_phys_addr;
u32 cmd;
- bool ret;

RTL_W32(CounterAddrHigh, (u64)paddr >> 32);
+ RTL_R32(CounterAddrHigh);
cmd = (u64)paddr & DMA_BIT_MASK(32);
RTL_W32(CounterAddrLow, cmd);
RTL_W32(CounterAddrLow, cmd | counter_cmd);

- ret = rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
-
- RTL_W32(CounterAddrLow, 0);
- RTL_W32(CounterAddrHigh, 0);
-
- return ret;
+ return rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
}

static bool rtl8169_reset_counters(struct net_device *dev)
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 4e0068e775f9..b7b859c3a0c7 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -860,6 +860,7 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
struct pppoe_hdr *ph;
struct net_device *dev;
char *start;
+ int hlen;

lock_sock(sk);
if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) {
@@ -878,16 +879,16 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
if (total_len > (dev->mtu + dev->hard_header_len))
goto end;

-
- skb = sock_wmalloc(sk, total_len + dev->hard_header_len + 32,
- 0, GFP_KERNEL);
+ hlen = LL_RESERVED_SPACE(dev);
+ skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len +
+ dev->needed_tailroom, 0, GFP_KERNEL);
if (!skb) {
error = -ENOMEM;
goto end;
}

/* Reserve space for headers. */
- skb_reserve(skb, dev->hard_header_len);
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);

skb->dev = dev;
@@ -948,7 +949,7 @@ static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb)
/* Copy the data if there is no space for the header or if it's
* read-only.
*/
- if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len))
+ if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph)))
goto abort;

__skb_push(skb, sizeof(*ph));
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 41e9ebd7d0a6..ebdee8f01f65 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1859,6 +1859,7 @@ static int lan78xx_reset(struct lan78xx_net *dev)
buf = DEFAULT_BURST_CAP_SIZE / FS_USB_PKT_SIZE;
dev->rx_urb_size = DEFAULT_BURST_CAP_SIZE;
dev->rx_qlen = 4;
+ dev->tx_qlen = 4;
}

ret = lan78xx_write_reg(dev, BURST_CAP, buf);
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 0cbf520cea77..82bf85ae5d08 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1563,7 +1563,6 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
rq->rx_ring[i].basePA);
rq->rx_ring[i].base = NULL;
}
- rq->buf_info[i] = NULL;
}

if (rq->comp_ring.base) {
@@ -1578,6 +1577,7 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
(rq->rx_ring[0].size + rq->rx_ring[1].size);
dma_free_coherent(&adapter->pdev->dev, sz, rq->buf_info[0],
rq->buf_info_pa);
+ rq->buf_info[0] = rq->buf_info[1] = NULL;
}
}

diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c
index 3923bed93c7e..a21e229d95e0 100644
--- a/drivers/pci/host/pci-layerscape.c
+++ b/drivers/pci/host/pci-layerscape.c
@@ -77,6 +77,16 @@ static void ls_pcie_fix_class(struct ls_pcie *pcie)
iowrite16(PCI_CLASS_BRIDGE_PCI, pcie->dbi + PCI_CLASS_DEVICE);
}

+/* Drop MSG TLP except for Vendor MSG */
+static void ls_pcie_drop_msg_tlp(struct ls_pcie *pcie)
+{
+ u32 val;
+
+ val = ioread32(pcie->dbi + PCIE_STRFMR1);
+ val &= 0xDFFFFFFF;
+ iowrite32(val, pcie->dbi + PCIE_STRFMR1);
+}
+
static int ls1021_pcie_link_up(struct pcie_port *pp)
{
u32 state;
@@ -97,7 +107,7 @@ static int ls1021_pcie_link_up(struct pcie_port *pp)
static void ls1021_pcie_host_init(struct pcie_port *pp)
{
struct ls_pcie *pcie = to_ls_pcie(pp);
- u32 val, index[2];
+ u32 index[2];

pcie->scfg = syscon_regmap_lookup_by_phandle(pp->dev->of_node,
"fsl,pcie-scfg");
@@ -116,13 +126,7 @@ static void ls1021_pcie_host_init(struct pcie_port *pp)

dw_pcie_setup_rc(pp);

- /*
- * LS1021A Workaround for internal TKT228622
- * to fix the INTx hang issue
- */
- val = ioread32(pcie->dbi + PCIE_STRFMR1);
- val &= 0xffff;
- iowrite32(val, pcie->dbi + PCIE_STRFMR1);
+ ls_pcie_drop_msg_tlp(pcie);
}

static int ls_pcie_link_up(struct pcie_port *pp)
@@ -147,6 +151,7 @@ static void ls_pcie_host_init(struct pcie_port *pp)
iowrite32(1, pcie->dbi + PCIE_DBI_RO_WR_EN);
ls_pcie_fix_class(pcie);
ls_pcie_clear_multifunction(pcie);
+ ls_pcie_drop_msg_tlp(pcie);
iowrite32(0, pcie->dbi + PCIE_DBI_RO_WR_EN);
}

@@ -203,6 +208,7 @@ static const struct of_device_id ls_pcie_of_match[] = {
{ .compatible = "fsl,ls1021a-pcie", .data = &ls1021_drvdata },
{ .compatible = "fsl,ls1043a-pcie", .data = &ls1043_drvdata },
{ .compatible = "fsl,ls2080a-pcie", .data = &ls2080_drvdata },
+ { .compatible = "fsl,ls2085a-pcie", .data = &ls2080_drvdata },
{ },
};
MODULE_DEVICE_TABLE(of, ls_pcie_of_match);
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index c1ccf1ee99ea..efce04df2109 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1727,7 +1727,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)

if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) {
reason = FAILURE_SESSION_IN_RECOVERY;
- sc->result = DID_REQUEUE;
+ sc->result = DID_REQUEUE << 16;
goto fault;
}

diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index a3ec49bdc1e6..ec38370ffcab 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -163,8 +163,7 @@ static void stub_shutdown_connection(struct usbip_device *ud)
* step 1?
*/
if (ud->tcp_socket) {
- dev_dbg(&sdev->udev->dev, "shutdown tcp_socket %p\n",
- ud->tcp_socket);
+ dev_dbg(&sdev->udev->dev, "shutdown sockfd %d\n", ud->sockfd);
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}

diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
index 7de54a66044f..56cacb68040c 100644
--- a/drivers/usb/usbip/stub_rx.c
+++ b/drivers/usb/usbip/stub_rx.c
@@ -338,23 +338,26 @@ static struct stub_priv *stub_priv_alloc(struct stub_device *sdev,
return priv;
}

-static int get_pipe(struct stub_device *sdev, int epnum, int dir)
+static int get_pipe(struct stub_device *sdev, struct usbip_header *pdu)
{
struct usb_device *udev = sdev->udev;
struct usb_host_endpoint *ep;
struct usb_endpoint_descriptor *epd = NULL;
+ int epnum = pdu->base.ep;
+ int dir = pdu->base.direction;
+
+ if (epnum < 0 || epnum > 15)
+ goto err_ret;

if (dir == USBIP_DIR_IN)
ep = udev->ep_in[epnum & 0x7f];
else
ep = udev->ep_out[epnum & 0x7f];
- if (!ep) {
- dev_err(&sdev->interface->dev, "no such endpoint?, %d\n",
- epnum);
- BUG();
- }
+ if (!ep)
+ goto err_ret;

epd = &ep->desc;
+
if (usb_endpoint_xfer_control(epd)) {
if (dir == USBIP_DIR_OUT)
return usb_sndctrlpipe(udev, epnum);
@@ -377,15 +380,37 @@ static int get_pipe(struct stub_device *sdev, int epnum, int dir)
}

if (usb_endpoint_xfer_isoc(epd)) {
+ /* validate packet size and number of packets */
+ unsigned int maxp, packets, bytes;
+
+#define USB_EP_MAXP_MULT_SHIFT 11
+#define USB_EP_MAXP_MULT_MASK (3 << USB_EP_MAXP_MULT_SHIFT)
+#define USB_EP_MAXP_MULT(m) \
+ (((m) & USB_EP_MAXP_MULT_MASK) >> USB_EP_MAXP_MULT_SHIFT)
+
+ maxp = usb_endpoint_maxp(epd);
+ maxp *= (USB_EP_MAXP_MULT(
+ __le16_to_cpu(epd->wMaxPacketSize)) + 1);
+ bytes = pdu->u.cmd_submit.transfer_buffer_length;
+ packets = DIV_ROUND_UP(bytes, maxp);
+
+ if (pdu->u.cmd_submit.number_of_packets < 0 ||
+ pdu->u.cmd_submit.number_of_packets > packets) {
+ dev_err(&sdev->udev->dev,
+ "CMD_SUBMIT: isoc invalid num packets %d\n",
+ pdu->u.cmd_submit.number_of_packets);
+ return -1;
+ }
if (dir == USBIP_DIR_OUT)
return usb_sndisocpipe(udev, epnum);
else
return usb_rcvisocpipe(udev, epnum);
}

+err_ret:
/* NOT REACHED */
- dev_err(&sdev->interface->dev, "get pipe, epnum %d\n", epnum);
- return 0;
+ dev_err(&sdev->udev->dev, "CMD_SUBMIT: invalid epnum %d\n", epnum);
+ return -1;
}

static void masking_bogus_flags(struct urb *urb)
@@ -449,7 +474,10 @@ static void stub_recv_cmd_submit(struct stub_device *sdev,
struct stub_priv *priv;
struct usbip_device *ud = &sdev->ud;
struct usb_device *udev = sdev->udev;
- int pipe = get_pipe(sdev, pdu->base.ep, pdu->base.direction);
+ int pipe = get_pipe(sdev, pdu);
+
+ if (pipe == -1)
+ return;

priv = stub_priv_alloc(sdev, pdu);
if (!priv)
diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index 9752b93f754e..1838f1b2c2fa 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/drivers/usb/usbip/usbip_common.c
@@ -317,18 +317,14 @@ int usbip_recv(struct socket *sock, void *buf, int size)
struct msghdr msg;
struct kvec iov;
int total = 0;
-
/* for blocks of if (usbip_dbg_flag_xmit) */
char *bp = buf;
int osize = size;

- usbip_dbg_xmit("enter\n");
-
- if (!sock || !buf || !size) {
- pr_err("invalid arg, sock %p buff %p size %d\n", sock, buf,
- size);
+ if (!sock || !buf || !size)
return -EINVAL;
- }
+
+ usbip_dbg_xmit("enter\n");

do {
sock->sk->sk_allocation = GFP_NOIO;
@@ -341,11 +337,8 @@ int usbip_recv(struct socket *sock, void *buf, int size)
msg.msg_flags = MSG_NOSIGNAL;

result = kernel_recvmsg(sock, &msg, &iov, 1, size, MSG_WAITALL);
- if (result <= 0) {
- pr_debug("receive sock %p buf %p size %u ret %d total %d\n",
- sock, buf, size, result, total);
+ if (result <= 0)
goto err;
- }

size -= result;
buf += result;
diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h
index 86b08475c254..f875ccaa55f9 100644
--- a/drivers/usb/usbip/usbip_common.h
+++ b/drivers/usb/usbip/usbip_common.h
@@ -261,6 +261,7 @@ struct usbip_device {
/* lock for status */
spinlock_t lock;

+ int sockfd;
struct socket *tcp_socket;

struct task_struct *tcp_rx;
diff --git a/drivers/usb/usbip/usbip_event.c b/drivers/usb/usbip/usbip_event.c
index 64933b993d7a..2580a32bcdff 100644
--- a/drivers/usb/usbip/usbip_event.c
+++ b/drivers/usb/usbip/usbip_event.c
@@ -117,11 +117,12 @@ EXPORT_SYMBOL_GPL(usbip_event_add);
int usbip_event_happened(struct usbip_device *ud)
{
int happened = 0;
+ unsigned long flags;

- spin_lock(&ud->lock);
+ spin_lock_irqsave(&ud->lock, flags);
if (ud->event != 0)
happened = 1;
- spin_unlock(&ud->lock);
+ spin_unlock_irqrestore(&ud->lock, flags);

return happened;
}
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index f9af04d7f02f..00d68945548e 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -121,9 +121,11 @@ static void dump_port_status_diff(u32 prev_status, u32 new_status)

void rh_port_connect(int rhport, enum usb_device_speed speed)
{
+ unsigned long flags;
+
usbip_dbg_vhci_rh("rh_port_connect %d\n", rhport);

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);

the_controller->port_status[rhport] |= USB_PORT_STAT_CONNECTION
| (1 << USB_PORT_FEAT_C_CONNECTION);
@@ -139,22 +141,24 @@ void rh_port_connect(int rhport, enum usb_device_speed speed)
break;
}

- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

usb_hcd_poll_rh_status(vhci_to_hcd(the_controller));
}

static void rh_port_disconnect(int rhport)
{
+ unsigned long flags;
+
usbip_dbg_vhci_rh("rh_port_disconnect %d\n", rhport);

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);

the_controller->port_status[rhport] &= ~USB_PORT_STAT_CONNECTION;
the_controller->port_status[rhport] |=
(1 << USB_PORT_FEAT_C_CONNECTION);

- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
usb_hcd_poll_rh_status(vhci_to_hcd(the_controller));
}

@@ -182,13 +186,14 @@ static int vhci_hub_status(struct usb_hcd *hcd, char *buf)
int retval;
int rhport;
int changed = 0;
+ unsigned long flags;

retval = DIV_ROUND_UP(VHCI_NPORTS + 1, 8);
memset(buf, 0, retval);

vhci = hcd_to_vhci(hcd);

- spin_lock(&vhci->lock);
+ spin_lock_irqsave(&vhci->lock, flags);
if (!HCD_HW_ACCESSIBLE(hcd)) {
usbip_dbg_vhci_rh("hw accessible flag not on?\n");
goto done;
@@ -209,7 +214,7 @@ static int vhci_hub_status(struct usb_hcd *hcd, char *buf)
usb_hcd_resume_root_hub(hcd);

done:
- spin_unlock(&vhci->lock);
+ spin_unlock_irqrestore(&vhci->lock, flags);
return changed ? retval : 0;
}

@@ -236,6 +241,7 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
struct vhci_hcd *dum;
int retval = 0;
int rhport;
+ unsigned long flags;

u32 prev_port_status[VHCI_NPORTS];

@@ -254,7 +260,7 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,

dum = hcd_to_vhci(hcd);

- spin_lock(&dum->lock);
+ spin_lock_irqsave(&dum->lock, flags);

/* store old status and compare now and old later */
if (usbip_dbg_flag_vhci_rh) {
@@ -408,7 +414,7 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
}
usbip_dbg_vhci_rh(" bye\n");

- spin_unlock(&dum->lock);
+ spin_unlock_irqrestore(&dum->lock, flags);

return retval;
}
@@ -431,6 +437,7 @@ static void vhci_tx_urb(struct urb *urb)
{
struct vhci_device *vdev = get_vdev(urb->dev);
struct vhci_priv *priv;
+ unsigned long flags;

if (!vdev) {
pr_err("could not get virtual device");
@@ -443,7 +450,7 @@ static void vhci_tx_urb(struct urb *urb)
return;
}

- spin_lock(&vdev->priv_lock);
+ spin_lock_irqsave(&vdev->priv_lock, flags);

priv->seqnum = atomic_inc_return(&the_controller->seqnum);
if (priv->seqnum == 0xffff)
@@ -457,7 +464,7 @@ static void vhci_tx_urb(struct urb *urb)
list_add_tail(&priv->list, &vdev->priv_tx);

wake_up(&vdev->waitq_tx);
- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);
}

static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
@@ -466,15 +473,16 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
struct device *dev = &urb->dev->dev;
int ret = 0;
struct vhci_device *vdev;
+ unsigned long flags;

/* patch to usb_sg_init() is in 2.5.60 */
BUG_ON(!urb->transfer_buffer && urb->transfer_buffer_length);

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);

if (urb->status != -EINPROGRESS) {
dev_err(dev, "URB already unlinked!, status %d\n", urb->status);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
return urb->status;
}

@@ -486,7 +494,7 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
vdev->ud.status == VDEV_ST_ERROR) {
dev_err(dev, "enqueue for inactive port %d\n", vdev->rhport);
spin_unlock(&vdev->ud.lock);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
return -ENODEV;
}
spin_unlock(&vdev->ud.lock);
@@ -559,14 +567,14 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,

out:
vhci_tx_urb(urb);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

return 0;

no_need_xmit:
usb_hcd_unlink_urb_from_ep(hcd, urb);
no_need_unlink:
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
if (!ret)
usb_hcd_giveback_urb(vhci_to_hcd(the_controller),
urb, urb->status);
@@ -623,14 +631,15 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
{
struct vhci_priv *priv;
struct vhci_device *vdev;
+ unsigned long flags;

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);

priv = urb->hcpriv;
if (!priv) {
/* URB was never linked! or will be soon given back by
* vhci_rx. */
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
return -EIDRM;
}

@@ -639,7 +648,7 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)

ret = usb_hcd_check_unlink_urb(hcd, urb, status);
if (ret) {
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
return ret;
}
}
@@ -664,10 +673,10 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
*/
usb_hcd_unlink_urb_from_ep(hcd, urb);

- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
urb->status);
- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);

} else {
/* tcp connection is alive */
@@ -679,7 +688,7 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
unlink = kzalloc(sizeof(struct vhci_unlink), GFP_ATOMIC);
if (!unlink) {
spin_unlock(&vdev->priv_lock);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
usbip_event_add(&vdev->ud, VDEV_EVENT_ERROR_MALLOC);
return -ENOMEM;
}
@@ -698,7 +707,7 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
spin_unlock(&vdev->priv_lock);
}

- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

usbip_dbg_vhci_hc("leave\n");
return 0;
@@ -707,8 +716,9 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
static void vhci_device_unlink_cleanup(struct vhci_device *vdev)
{
struct vhci_unlink *unlink, *tmp;
+ unsigned long flags;

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);
spin_lock(&vdev->priv_lock);

list_for_each_entry_safe(unlink, tmp, &vdev->unlink_tx, list) {
@@ -742,19 +752,19 @@ static void vhci_device_unlink_cleanup(struct vhci_device *vdev)
list_del(&unlink->list);

spin_unlock(&vdev->priv_lock);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
urb->status);

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);
spin_lock(&vdev->priv_lock);

kfree(unlink);
}

spin_unlock(&vdev->priv_lock);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
}

/*
@@ -768,7 +778,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud)

/* need this? see stub_dev.c */
if (ud->tcp_socket) {
- pr_debug("shutdown tcp_socket %p\n", ud->tcp_socket);
+ pr_debug("shutdown sockfd %d\n", ud->sockfd);
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}

@@ -821,8 +831,9 @@ static void vhci_shutdown_connection(struct usbip_device *ud)
static void vhci_device_reset(struct usbip_device *ud)
{
struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
+ unsigned long flags;

- spin_lock(&ud->lock);
+ spin_lock_irqsave(&ud->lock, flags);

vdev->speed = 0;
vdev->devid = 0;
@@ -836,14 +847,16 @@ static void vhci_device_reset(struct usbip_device *ud)
}
ud->status = VDEV_ST_NULL;

- spin_unlock(&ud->lock);
+ spin_unlock_irqrestore(&ud->lock, flags);
}

static void vhci_device_unusable(struct usbip_device *ud)
{
- spin_lock(&ud->lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&ud->lock, flags);
ud->status = VDEV_ST_ERROR;
- spin_unlock(&ud->lock);
+ spin_unlock_irqrestore(&ud->lock, flags);
}

static void vhci_device_init(struct vhci_device *vdev)
@@ -933,12 +946,13 @@ static int vhci_get_frame_number(struct usb_hcd *hcd)
static int vhci_bus_suspend(struct usb_hcd *hcd)
{
struct vhci_hcd *vhci = hcd_to_vhci(hcd);
+ unsigned long flags;

dev_dbg(&hcd->self.root_hub->dev, "%s\n", __func__);

- spin_lock(&vhci->lock);
+ spin_lock_irqsave(&vhci->lock, flags);
hcd->state = HC_STATE_SUSPENDED;
- spin_unlock(&vhci->lock);
+ spin_unlock_irqrestore(&vhci->lock, flags);

return 0;
}
@@ -947,15 +961,16 @@ static int vhci_bus_resume(struct usb_hcd *hcd)
{
struct vhci_hcd *vhci = hcd_to_vhci(hcd);
int rc = 0;
+ unsigned long flags;

dev_dbg(&hcd->self.root_hub->dev, "%s\n", __func__);

- spin_lock(&vhci->lock);
+ spin_lock_irqsave(&vhci->lock, flags);
if (!HCD_HW_ACCESSIBLE(hcd))
rc = -ESHUTDOWN;
else
hcd->state = HC_STATE_RUNNING;
- spin_unlock(&vhci->lock);
+ spin_unlock_irqrestore(&vhci->lock, flags);

return rc;
}
@@ -1053,17 +1068,18 @@ static int vhci_hcd_suspend(struct platform_device *pdev, pm_message_t state)
int rhport = 0;
int connected = 0;
int ret = 0;
+ unsigned long flags;

hcd = platform_get_drvdata(pdev);

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);

for (rhport = 0; rhport < VHCI_NPORTS; rhport++)
if (the_controller->port_status[rhport] &
USB_PORT_STAT_CONNECTION)
connected += 1;

- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

if (connected > 0) {
dev_info(&pdev->dev,
diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c
index bc4eb0855314..323aa7789989 100644
--- a/drivers/usb/usbip/vhci_rx.c
+++ b/drivers/usb/usbip/vhci_rx.c
@@ -71,10 +71,11 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
{
struct usbip_device *ud = &vdev->ud;
struct urb *urb;
+ unsigned long flags;

- spin_lock(&vdev->priv_lock);
+ spin_lock_irqsave(&vdev->priv_lock, flags);
urb = pickup_urb_and_free_priv(vdev, pdu->base.seqnum);
- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);

if (!urb) {
pr_err("cannot find a urb of seqnum %u max seqnum %d\n",
@@ -103,9 +104,9 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,

usbip_dbg_vhci_rx("now giveback urb %u\n", pdu->base.seqnum);

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);
usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status);

@@ -116,8 +117,9 @@ static struct vhci_unlink *dequeue_pending_unlink(struct vhci_device *vdev,
struct usbip_header *pdu)
{
struct vhci_unlink *unlink, *tmp;
+ unsigned long flags;

- spin_lock(&vdev->priv_lock);
+ spin_lock_irqsave(&vdev->priv_lock, flags);

list_for_each_entry_safe(unlink, tmp, &vdev->unlink_rx, list) {
pr_info("unlink->seqnum %lu\n", unlink->seqnum);
@@ -126,12 +128,12 @@ static struct vhci_unlink *dequeue_pending_unlink(struct vhci_device *vdev,
unlink->seqnum);
list_del(&unlink->list);

- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);
return unlink;
}
}

- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);

return NULL;
}
@@ -141,6 +143,7 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
{
struct vhci_unlink *unlink;
struct urb *urb;
+ unsigned long flags;

usbip_dump_header(pdu);

@@ -151,9 +154,9 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
return;
}

- spin_lock(&vdev->priv_lock);
+ spin_lock_irqsave(&vdev->priv_lock, flags);
urb = pickup_urb_and_free_priv(vdev, unlink->unlink_seqnum);
- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);

if (!urb) {
/*
@@ -170,9 +173,9 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
urb->status = pdu->u.ret_unlink.status;
pr_info("urb->status %d\n", urb->status);

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);
usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
urb->status);
@@ -184,10 +187,11 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
static int vhci_priv_tx_empty(struct vhci_device *vdev)
{
int empty = 0;
+ unsigned long flags;

- spin_lock(&vdev->priv_lock);
+ spin_lock_irqsave(&vdev->priv_lock, flags);
empty = list_empty(&vdev->priv_rx);
- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);

return empty;
}
diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c
index 211f43f67ea2..1c7f41a65565 100644
--- a/drivers/usb/usbip/vhci_sysfs.c
+++ b/drivers/usb/usbip/vhci_sysfs.c
@@ -32,23 +32,28 @@ static ssize_t status_show(struct device *dev, struct device_attribute *attr,
{
char *s = out;
int i = 0;
+ unsigned long flags;

BUG_ON(!the_controller || !out);

- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);

/*
* output example:
- * prt sta spd dev socket local_busid
- * 000 004 000 000 c5a7bb80 1-2.3
- * 001 004 000 000 d8cee980 2-3.4
+ * port sta spd dev sockfd local_busid
+ * 0000 004 000 00000000 000003 1-2.3
+ * 0001 004 000 00000000 000004 2-3.4
*
- * IP address can be retrieved from a socket pointer address by looking
- * up /proc/net/{tcp,tcp6}. Also, a userland program may remember a
- * port number and its peer IP address.
+ * Output includes socket fd instead of socket pointer address to
+ * avoid leaking kernel memory address in:
+ * /sys/devices/platform/vhci_hcd.0/status and in debug output.
+ * The socket pointer address is not used at the moment and it was
+ * made visible as a convenient way to find IP address from socket
+ * pointer address by looking up /proc/net/{tcp,tcp6}. As this opens
+ * a security hole, the change is made to use sockfd instead.
*/
out += sprintf(out,
- "prt sta spd bus dev socket local_busid\n");
+ "prt sta spd bus dev sockfd local_busid\n");

for (i = 0; i < VHCI_NPORTS; i++) {
struct vhci_device *vdev = port_to_vdev(i);
@@ -60,17 +65,17 @@ static ssize_t status_show(struct device *dev, struct device_attribute *attr,
out += sprintf(out, "%03u %08x ",
vdev->speed, vdev->devid);
out += sprintf(out, "%16p ", vdev->ud.tcp_socket);
+ out += sprintf(out, "%06u", vdev->ud.sockfd);
out += sprintf(out, "%s", dev_name(&vdev->udev->dev));

- } else {
- out += sprintf(out, "000 000 000 0000000000000000 0-0");
- }
+ } else
+ out += sprintf(out, "000 000 000 000000 0-0");

out += sprintf(out, "\n");
spin_unlock(&vdev->ud.lock);
}

- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

return out - s;
}
@@ -80,11 +85,12 @@ static DEVICE_ATTR_RO(status);
static int vhci_port_disconnect(__u32 rhport)
{
struct vhci_device *vdev;
+ unsigned long flags;

usbip_dbg_vhci_sysfs("enter\n");

/* lock */
- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);

vdev = port_to_vdev(rhport);

@@ -94,14 +100,14 @@ static int vhci_port_disconnect(__u32 rhport)

/* unlock */
spin_unlock(&vdev->ud.lock);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

return -EINVAL;
}

/* unlock */
spin_unlock(&vdev->ud.lock);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

usbip_event_add(&vdev->ud, VDEV_EVENT_DOWN);

@@ -177,6 +183,7 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr,
int sockfd = 0;
__u32 rhport = 0, devid = 0, speed = 0;
int err;
+ unsigned long flags;

/*
* @rhport: port number of vhci_hcd
@@ -202,14 +209,14 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr,
/* now need lock until setting vdev status as used */

/* begin a lock */
- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);
vdev = port_to_vdev(rhport);
spin_lock(&vdev->ud.lock);

if (vdev->ud.status != VDEV_ST_NULL) {
/* end of the lock */
spin_unlock(&vdev->ud.lock);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);

sockfd_put(socket);

@@ -223,11 +230,12 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr,

vdev->devid = devid;
vdev->speed = speed;
+ vdev->ud.sockfd = sockfd;
vdev->ud.tcp_socket = socket;
vdev->ud.status = VDEV_ST_NOTASSIGNED;

spin_unlock(&vdev->ud.lock);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
/* end the lock */

vdev->ud.tcp_rx = kthread_get_run(vhci_rx_loop, &vdev->ud, "vhci_rx");
diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c
index 3c5796c8633a..a9a663a578b6 100644
--- a/drivers/usb/usbip/vhci_tx.c
+++ b/drivers/usb/usbip/vhci_tx.c
@@ -47,16 +47,17 @@ static void setup_cmd_submit_pdu(struct usbip_header *pdup, struct urb *urb)
static struct vhci_priv *dequeue_from_priv_tx(struct vhci_device *vdev)
{
struct vhci_priv *priv, *tmp;
+ unsigned long flags;

- spin_lock(&vdev->priv_lock);
+ spin_lock_irqsave(&vdev->priv_lock, flags);

list_for_each_entry_safe(priv, tmp, &vdev->priv_tx, list) {
list_move_tail(&priv->list, &vdev->priv_rx);
- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);
return priv;
}

- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);

return NULL;
}
@@ -137,16 +138,17 @@ static int vhci_send_cmd_submit(struct vhci_device *vdev)
static struct vhci_unlink *dequeue_from_unlink_tx(struct vhci_device *vdev)
{
struct vhci_unlink *unlink, *tmp;
+ unsigned long flags;

- spin_lock(&vdev->priv_lock);
+ spin_lock_irqsave(&vdev->priv_lock, flags);

list_for_each_entry_safe(unlink, tmp, &vdev->unlink_tx, list) {
list_move_tail(&unlink->list, &vdev->unlink_rx);
- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);
return unlink;
}

- spin_unlock(&vdev->priv_lock);
+ spin_unlock_irqrestore(&vdev->priv_lock, flags);

return NULL;
}
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index d6aeb84e90b6..d882d873c5a3 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -178,11 +178,8 @@ ext2_get_acl(struct inode *inode, int type)
return acl;
}

-/*
- * inode->i_mutex: down
- */
-int
-ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+static int
+__ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
int name_index;
void *value = NULL;
@@ -192,13 +189,6 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
switch(type) {
case ACL_TYPE_ACCESS:
name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
- if (acl) {
- error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
- if (error)
- return error;
- inode->i_ctime = CURRENT_TIME_SEC;
- mark_inode_dirty(inode);
- }
break;

case ACL_TYPE_DEFAULT:
@@ -224,6 +214,24 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
return error;
}

+/*
+ * inode->i_mutex: down
+ */
+int
+ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+ int error;
+
+ if (type == ACL_TYPE_ACCESS && acl) {
+ error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+ if (error)
+ return error;
+ inode->i_ctime = CURRENT_TIME_SEC;
+ mark_inode_dirty(inode);
+ }
+ return __ext2_set_acl(inode, acl, type);
+}
+
/*
* Initialize the ACLs of a new inode. Called from ext2_new_inode.
*
@@ -241,12 +249,12 @@ ext2_init_acl(struct inode *inode, struct inode *dir)
return error;

if (default_acl) {
- error = ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+ error = __ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
posix_acl_release(default_acl);
}
if (acl) {
if (!error)
- error = ext2_set_acl(inode, acl, ACL_TYPE_ACCESS);
+ error = __ext2_set_acl(inode, acl, ACL_TYPE_ACCESS);
posix_acl_release(acl);
}
return error;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 62376451bbce..5df914943d96 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -113,6 +113,10 @@ void f_setown(struct file *filp, unsigned long arg, int force)
int who = arg;
type = PIDTYPE_PID;
if (who < 0) {
+ /* avoid overflow below */
+ if (who == INT_MIN)
+ return;
+
type = PIDTYPE_PGID;
who = -who;
}
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index a260060042ad..67eb154af881 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -60,9 +60,10 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
else
GROUP_AT(gi, i) = GROUP_AT(rqgi, i);

- /* Each thread allocates its own gi, no race */
- groups_sort(gi);
}
+
+ /* Each thread allocates its own gi, no race */
+ groups_sort(gi);
} else {
gi = get_group_info(rqgi);
}
diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c
index dc198bc64c61..edc8ef78b63f 100644
--- a/fs/reiserfs/bitmap.c
+++ b/fs/reiserfs/bitmap.c
@@ -513,9 +513,17 @@ static void __discard_prealloc(struct reiserfs_transaction_handle *th,
"inode has negative prealloc blocks count.");
#endif
while (ei->i_prealloc_count > 0) {
- reiserfs_free_prealloc_block(th, inode, ei->i_prealloc_block);
- ei->i_prealloc_block++;
+ b_blocknr_t block_to_free;
+
+ /*
+ * reiserfs_free_prealloc_block can drop the write lock,
+ * which could allow another caller to free the same block.
+ * We can protect against it by modifying the prealloc
+ * state before calling it.
+ */
+ block_to_free = ei->i_prealloc_block++;
ei->i_prealloc_count--;
+ reiserfs_free_prealloc_block(th, inode, block_to_free);
dirty = 1;
}
if (dirty)
@@ -1128,7 +1136,7 @@ static int determine_prealloc_size(reiserfs_blocknr_hint_t * hint)
hint->prealloc_size = 0;

if (!hint->formatted_node && hint->preallocate) {
- if (S_ISREG(hint->inode->i_mode)
+ if (S_ISREG(hint->inode->i_mode) && !IS_PRIVATE(hint->inode)
&& hint->inode->i_size >=
REISERFS_SB(hint->th->t_super)->s_alloc_options.
preallocmin * hint->inode->i_sb->s_blocksize)
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 9b1824f35501..91b036902a17 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -37,7 +37,14 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
error = journal_begin(&th, inode->i_sb, jcreate_blocks);
reiserfs_write_unlock(inode->i_sb);
if (error == 0) {
+ if (type == ACL_TYPE_ACCESS && acl) {
+ error = posix_acl_update_mode(inode, &inode->i_mode,
+ &acl);
+ if (error)
+ goto unlock;
+ }
error = __reiserfs_set_acl(&th, inode, type, acl);
+unlock:
reiserfs_write_lock(inode->i_sb);
error2 = journal_end(&th);
reiserfs_write_unlock(inode->i_sb);
@@ -245,11 +252,6 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode,
switch (type) {
case ACL_TYPE_ACCESS:
name = POSIX_ACL_XATTR_ACCESS;
- if (acl) {
- error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
- if (error)
- return error;
- }
break;
case ACL_TYPE_DEFAULT:
name = POSIX_ACL_XATTR_DEFAULT;
diff --git a/fs/select.c b/fs/select.c
index 015547330e88..f4dd55fc638c 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -29,6 +29,7 @@
#include <linux/sched/rt.h>
#include <linux/freezer.h>
#include <net/busy_poll.h>
+#include <linux/vmalloc.h>

#include <asm/uaccess.h>

@@ -550,7 +551,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
fd_set_bits fds;
void *bits;
int ret, max_fds;
- unsigned int size;
+ size_t size, alloc_size;
struct fdtable *fdt;
/* Allocate small arguments on the stack to save memory and be faster */
long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
@@ -577,7 +578,14 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
if (size > sizeof(stack_fds) / 6) {
/* Not enough space in on-stack array; must use kmalloc */
ret = -ENOMEM;
- bits = kmalloc(6 * size, GFP_KERNEL);
+ if (size > (SIZE_MAX / 6))
+ goto out_nofds;
+
+ alloc_size = 6 * size;
+ bits = kmalloc(alloc_size, GFP_KERNEL|__GFP_NOWARN);
+ if (!bits && alloc_size > PAGE_SIZE)
+ bits = vmalloc(alloc_size);
+
if (!bits)
goto out_nofds;
}
@@ -614,7 +622,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,

out:
if (bits != stack_fds)
- kfree(bits);
+ kvfree(bits);
out_nofds:
return ret;
}
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 2189935075b4..a951fd10aaaa 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -71,6 +71,7 @@ struct cpu_cacheinfo {
struct cacheinfo *info_list;
unsigned int num_levels;
unsigned int num_leaves;
+ bool cpu_map_populated;
};

/*
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 2b6a204bd8d4..3ffc69ebe967 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -63,6 +63,13 @@ static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs)
#define ktime_add(lhs, rhs) \
({ (ktime_t){ .tv64 = (lhs).tv64 + (rhs).tv64 }; })

+/*
+ * Same as ktime_add(), but avoids undefined behaviour on overflow; however,
+ * this means that you must check the result for overflow yourself.
+ */
+#define ktime_add_unsafe(lhs, rhs) \
+ ({ (ktime_t){ .tv64 = (u64) (lhs).tv64 + (rhs).tv64 }; })
+
/*
* Add a ktime_t variable and a scalar nanosecond value.
* res = kt + nsval:
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 04078e8a4803..d6c53fce006b 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -243,6 +243,10 @@ int xt_check_entry_offsets(const void *base, const char *elems,
unsigned int target_offset,
unsigned int next_offset);

+unsigned int *xt_alloc_entry_offsets(unsigned int size);
+bool xt_find_jump_offset(const unsigned int *offsets,
+ unsigned int target, unsigned int size);
+
int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
bool inv_proto);
int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
@@ -377,16 +381,16 @@ static inline unsigned long ifname_compare_aligned(const char *_a,
* allows us to return 0 for single core systems without forcing
* callers to deal with SMP vs. NONSMP issues.
*/
-static inline u64 xt_percpu_counter_alloc(void)
+static inline unsigned long xt_percpu_counter_alloc(void)
{
if (nr_cpu_ids > 1) {
void __percpu *res = __alloc_percpu(sizeof(struct xt_counters),
sizeof(struct xt_counters));

if (res == NULL)
- return (u64) -ENOMEM;
+ return -ENOMEM;

- return (u64) (__force unsigned long) res;
+ return (__force unsigned long) res;
}

return 0;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e887c8d6f395..90bea398e5e0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1313,6 +1313,7 @@ struct sched_dl_entity {
u64 dl_deadline; /* relative deadline of each instance */
u64 dl_period; /* separation of two instances (period) */
u64 dl_bw; /* dl_runtime / dl_deadline */
+ u64 dl_density; /* dl_runtime / dl_deadline */

/*
* Actual scheduling parameters. Initialized with the values above,
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 318c24612458..2260f92f1492 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -29,9 +29,14 @@ static inline struct tcphdr *tcp_hdr(const struct sk_buff *skb)
return (struct tcphdr *)skb_transport_header(skb);
}

+static inline unsigned int __tcp_hdrlen(const struct tcphdr *th)
+{
+ return th->doff * 4;
+}
+
static inline unsigned int tcp_hdrlen(const struct sk_buff *skb)
{
- return tcp_hdr(skb)->doff * 4;
+ return __tcp_hdrlen(tcp_hdr(skb));
}

static inline struct tcphdr *inner_tcp_hdr(const struct sk_buff *skb)
diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h
index a3d04934aa96..6f8fbcf10dfb 100644
--- a/include/linux/vermagic.h
+++ b/include/linux/vermagic.h
@@ -24,16 +24,10 @@
#ifndef MODULE_ARCH_VERMAGIC
#define MODULE_ARCH_VERMAGIC ""
#endif
-#ifdef RETPOLINE
-#define MODULE_VERMAGIC_RETPOLINE "retpoline "
-#else
-#define MODULE_VERMAGIC_RETPOLINE ""
-#endif

#define VERMAGIC_STRING \
UTS_RELEASE " " \
MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \
MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \
- MODULE_ARCH_VERMAGIC \
- MODULE_VERMAGIC_RETPOLINE
+ MODULE_ARCH_VERMAGIC

diff --git a/include/net/arp.h b/include/net/arp.h
index 5e0f891d476c..1b3f86981757 100644
--- a/include/net/arp.h
+++ b/include/net/arp.h
@@ -19,6 +19,9 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32

static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
{
+ if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+ key = INADDR_ANY;
+
return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev);
}

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 7a8066b90289..84f0d0602433 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -281,6 +281,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
int flags);
int ip6_flowlabel_init(void);
void ip6_flowlabel_cleanup(void);
+bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np);

static inline void fl6_sock_release(struct ip6_flowlabel *fl)
{
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 2dcea635ecce..93328c61934a 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -209,6 +209,11 @@ int net_eq(const struct net *net1, const struct net *net2)
return net1 == net2;
}

+static inline int check_net(const struct net *net)
+{
+ return atomic_read(&net->count) != 0;
+}
+
void net_drop_ns(void *);

#else
@@ -233,6 +238,11 @@ int net_eq(const struct net *net1, const struct net *net2)
return 1;
}

+static inline int check_net(const struct net *net)
+{
+ return 1;
+}
+
#define net_drop_ns NULL
#endif

diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h
index bc81fb2e1f0e..6f04cb419115 100644
--- a/include/uapi/linux/eventpoll.h
+++ b/include/uapi/linux/eventpoll.h
@@ -26,6 +26,19 @@
#define EPOLL_CTL_DEL 2
#define EPOLL_CTL_MOD 3

+/* Epoll event masks */
+#define EPOLLIN 0x00000001
+#define EPOLLPRI 0x00000002
+#define EPOLLOUT 0x00000004
+#define EPOLLERR 0x00000008
+#define EPOLLHUP 0x00000010
+#define EPOLLRDNORM 0x00000040
+#define EPOLLRDBAND 0x00000080
+#define EPOLLWRNORM 0x00000100
+#define EPOLLWRBAND 0x00000200
+#define EPOLLMSG 0x00000400
+#define EPOLLRDHUP 0x00002000
+
/*
* Request the handling of system wakeup events so as to prevent system suspends
* from happening while those events are being processed.
diff --git a/ipc/msg.c b/ipc/msg.c
index c6521c205cb4..f993f441f852 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -742,7 +742,10 @@ static inline int convert_mode(long *msgtyp, int msgflg)
if (*msgtyp == 0)
return SEARCH_ANY;
if (*msgtyp < 0) {
- *msgtyp = -*msgtyp;
+ if (*msgtyp == LONG_MIN) /* -LONG_MIN is undefined */
+ *msgtyp = LONG_MAX;
+ else
+ *msgtyp = -*msgtyp;
return SEARCH_LESSEQUAL;
}
if (msgflg & MSG_EXCEPT)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9d6b3d869592..e6d1173a2046 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2109,6 +2109,7 @@ void __dl_clear_params(struct task_struct *p)
dl_se->dl_period = 0;
dl_se->flags = 0;
dl_se->dl_bw = 0;
+ dl_se->dl_density = 0;

dl_se->dl_throttled = 0;
dl_se->dl_new = 1;
@@ -3647,6 +3648,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
dl_se->flags = attr->sched_flags;
dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+ dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);

/*
* Changing the parameters of a task is 'tricky' and we're not doing
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6be2afd9bfd6..e12b0a4df891 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -480,13 +480,84 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
}

/*
- * When a -deadline entity is queued back on the runqueue, its runtime and
- * deadline might need updating.
+ * Revised wakeup rule [1]: For self-suspending tasks, rather then
+ * re-initializing task's runtime and deadline, the revised wakeup
+ * rule adjusts the task's runtime to avoid the task to overrun its
+ * density.
*
- * The policy here is that we update the deadline of the entity only if:
- * - the current deadline is in the past,
- * - using the remaining runtime with the current deadline would make
- * the entity exceed its bandwidth.
+ * Reasoning: a task may overrun the density if:
+ * runtime / (deadline - t) > dl_runtime / dl_deadline
+ *
+ * Therefore, runtime can be adjusted to:
+ * runtime = (dl_runtime / dl_deadline) * (deadline - t)
+ *
+ * In such way that runtime will be equal to the maximum density
+ * the task can use without breaking any rule.
+ *
+ * [1] Luca Abeni, Giuseppe Lipari, and Juri Lelli. 2015. Constant
+ * bandwidth server revisited. SIGBED Rev. 11, 4 (January 2015), 19-24.
+ */
+static void
+update_dl_revised_wakeup(struct sched_dl_entity *dl_se, struct rq *rq)
+{
+ u64 laxity = dl_se->deadline - rq_clock(rq);
+
+ /*
+ * If the task has deadline < period, and the deadline is in the past,
+ * it should already be throttled before this check.
+ *
+ * See update_dl_entity() comments for further details.
+ */
+ WARN_ON(dl_time_before(dl_se->deadline, rq_clock(rq)));
+
+ dl_se->runtime = (dl_se->dl_density * laxity) >> 20;
+}
+
+/*
+ * Regarding the deadline, a task with implicit deadline has a relative
+ * deadline == relative period. A task with constrained deadline has a
+ * relative deadline <= relative period.
+ *
+ * We support constrained deadline tasks. However, there are some restrictions
+ * applied only for tasks which do not have an implicit deadline. See
+ * update_dl_entity() to know more about such restrictions.
+ *
+ * The dl_is_implicit() returns true if the task has an implicit deadline.
+ */
+static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
+{
+ return dl_se->dl_deadline == dl_se->dl_period;
+}
+
+/*
+ * When a deadline entity is placed in the runqueue, its runtime and deadline
+ * might need to be updated. This is done by a CBS wake up rule. There are two
+ * different rules: 1) the original CBS; and 2) the Revisited CBS.
+ *
+ * When the task is starting a new period, the Original CBS is used. In this
+ * case, the runtime is replenished and a new absolute deadline is set.
+ *
+ * When a task is queued before the begin of the next period, using the
+ * remaining runtime and deadline could make the entity to overflow, see
+ * dl_entity_overflow() to find more about runtime overflow. When such case
+ * is detected, the runtime and deadline need to be updated.
+ *
+ * If the task has an implicit deadline, i.e., deadline == period, the Original
+ * CBS is applied. the runtime is replenished and a new absolute deadline is
+ * set, as in the previous cases.
+ *
+ * However, the Original CBS does not work properly for tasks with
+ * deadline < period, which are said to have a constrained deadline. By
+ * applying the Original CBS, a constrained deadline task would be able to run
+ * runtime/deadline in a period. With deadline < period, the task would
+ * overrun the runtime/period allowed bandwidth, breaking the admission test.
+ *
+ * In order to prevent this misbehave, the Revisited CBS is used for
+ * constrained deadline tasks when a runtime overflow is detected. In the
+ * Revisited CBS, rather than replenishing & setting a new absolute deadline,
+ * the remaining runtime of the task is reduced to avoid runtime overflow.
+ * Please refer to the comments update_dl_revised_wakeup() function to find
+ * more about the Revised CBS rule.
*/
static void update_dl_entity(struct sched_dl_entity *dl_se,
struct sched_dl_entity *pi_se)
@@ -505,6 +576,14 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,

if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+
+ if (unlikely(!dl_is_implicit(dl_se) &&
+ !dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+ !dl_se->dl_boosted)){
+ update_dl_revised_wakeup(dl_se, rq);
+ return;
+ }
+
dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
dl_se->runtime = pi_se->dl_runtime;
}
@@ -991,11 +1070,6 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
__dequeue_dl_entity(dl_se);
}

-static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
-{
- return dl_se->dl_deadline < dl_se->dl_period;
-}
-
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
struct task_struct *pi_task = rt_mutex_get_top_task(p);
@@ -1027,7 +1101,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
* If that is the case, the task will be throttled and
* the replenishment timer will be set to the next period.
*/
- if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+ if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl))
dl_check_constrained_dl(&p->dl);

/*
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 17f7bcff1e02..323282e63865 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -312,7 +312,7 @@ EXPORT_SYMBOL_GPL(__ktime_divns);
*/
ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
{
- ktime_t res = ktime_add(lhs, rhs);
+ ktime_t res = ktime_add_unsafe(lhs, rhs);

/*
* We use KTIME_SEC_MAX here, the maximum timeout which we can
@@ -669,7 +669,9 @@ static void hrtimer_reprogram(struct hrtimer *timer,
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
{
base->expires_next.tv64 = KTIME_MAX;
+ base->hang_detected = 0;
base->hres_active = 0;
+ base->next_timer = NULL;
}

/*
@@ -1615,6 +1617,7 @@ static void init_hrtimers_cpu(int cpu)
timerqueue_init_head(&cpu_base->clock_base[i].active);
}

+ cpu_base->active_bases = 0;
cpu_base->cpu = cpu;
hrtimer_init_hres(cpu_base);
}
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 125407144c01..3d7588a2e97c 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -764,8 +764,15 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
__acquires(timer->base->lock)
{
for (;;) {
- u32 tf = timer->flags;
struct tvec_base *base;
+ u32 tf;
+
+ /*
+ * We need to use READ_ONCE() here, otherwise the compiler
+ * might re-read @tf between the check for TIMER_MIGRATING
+ * and spin_lock().
+ */
+ tf = READ_ONCE(timer->flags);

if (!(tf & TIMER_MIGRATING)) {
base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK);
diff --git a/mm/cma.c b/mm/cma.c
index bd0e1412475e..43f4a122e969 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -54,7 +54,7 @@ unsigned long cma_get_size(const struct cma *cma)
}

static unsigned long cma_bitmap_aligned_mask(const struct cma *cma,
- int align_order)
+ unsigned int align_order)
{
if (align_order <= cma->order_per_bit)
return 0;
@@ -62,17 +62,14 @@ static unsigned long cma_bitmap_aligned_mask(const struct cma *cma,
}

/*
- * Find a PFN aligned to the specified order and return an offset represented in
- * order_per_bits.
+ * Find the offset of the base PFN from the specified align_order.
+ * The value returned is represented in order_per_bits.
*/
static unsigned long cma_bitmap_aligned_offset(const struct cma *cma,
- int align_order)
+ unsigned int align_order)
{
- if (align_order <= cma->order_per_bit)
- return 0;
-
- return (ALIGN(cma->base_pfn, (1UL << align_order))
- - cma->base_pfn) >> cma->order_per_bit;
+ return (cma->base_pfn & ((1UL << align_order) - 1))
+ >> cma->order_per_bit;
}

static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e25b93a4267d..55a9facb8e8d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5576,7 +5576,7 @@ static void uncharge_list(struct list_head *page_list)
next = page->lru.next;

VM_BUG_ON_PAGE(PageLRU(page), page);
- VM_BUG_ON_PAGE(page_count(page), page);
+ VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);

if (!page->mem_cgroup)
continue;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 091fe9b06663..92a647957f91 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -539,6 +539,13 @@ static int delete_from_lru_cache(struct page *p)
*/
ClearPageActive(p);
ClearPageUnevictable(p);
+
+ /*
+ * Poisoned page might never drop its ref count to 0 so we have
+ * to uncharge it manually from its memcg.
+ */
+ mem_cgroup_uncharge(p);
+
/*
* drop the page count elevated by isolate_lru_page()
*/
diff --git a/mm/mmap.c b/mm/mmap.c
index eaa460ddcaf9..cc84b97ca250 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2188,7 +2188,8 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
gap_addr = TASK_SIZE;

next = vma->vm_next;
- if (next && next->vm_start < gap_addr) {
+ if (next && next->vm_start < gap_addr &&
+ (next->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) {
if (!(next->vm_flags & VM_GROWSUP))
return -ENOMEM;
/* Check that both stack segments have the same anon_vma? */
@@ -2273,7 +2274,8 @@ int expand_downwards(struct vm_area_struct *vma,
if (gap_addr > address)
return -ENOMEM;
prev = vma->vm_prev;
- if (prev && prev->vm_end > gap_addr) {
+ if (prev && prev->vm_end > gap_addr &&
+ (prev->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) {
if (!(prev->vm_flags & VM_GROWSDOWN))
return -ENOMEM;
/* Check that both stack segments have the same anon_vma? */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3c70f03d91ec..a4c9cd80c7b6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2468,9 +2468,6 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
if (!area->nr_free)
continue;

- if (alloc_harder)
- return true;
-
for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
if (!list_empty(&area->free_list[mt]))
return true;
@@ -2482,6 +2479,9 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
return true;
}
#endif
+ if (alloc_harder &&
+ !list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+ return true;
}
return false;
}
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 928f58064098..c866e761651a 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -722,13 +722,12 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev,
if (unlikely(!net_eq(dev_net(dev), &init_net)))
goto drop;

- if (WARN_ONCE(dev->type != ARPHRD_CAN ||
- skb->len != CAN_MTU ||
- cfd->len > CAN_MAX_DLEN,
- "PF_CAN: dropped non conform CAN skbuf: "
- "dev type %d, len %d, datalen %d\n",
- dev->type, skb->len, cfd->len))
+ if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU ||
+ cfd->len > CAN_MAX_DLEN)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n",
+ dev->type, skb->len, cfd->len);
goto drop;
+ }

can_receive(skb, dev);
return NET_RX_SUCCESS;
@@ -746,13 +745,12 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
if (unlikely(!net_eq(dev_net(dev), &init_net)))
goto drop;

- if (WARN_ONCE(dev->type != ARPHRD_CAN ||
- skb->len != CANFD_MTU ||
- cfd->len > CANFD_MAX_DLEN,
- "PF_CAN: dropped non conform CAN FD skbuf: "
- "dev type %d, len %d, datalen %d\n",
- dev->type, skb->len, cfd->len))
+ if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU ||
+ cfd->len > CANFD_MAX_DLEN)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n",
+ dev->type, skb->len, cfd->len);
goto drop;
+ }

can_receive(skb, dev);
return NET_RX_SUCCESS;
diff --git a/net/core/dev.c b/net/core/dev.c
index 3b67c1e5756f..cb58ba15d51e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2889,10 +2889,21 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
hdr_len = skb_transport_header(skb) - skb_mac_header(skb);

/* + transport layer */
- if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
- hdr_len += tcp_hdrlen(skb);
- else
- hdr_len += sizeof(struct udphdr);
+ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
+ const struct tcphdr *th;
+ struct tcphdr _tcphdr;
+
+ th = skb_header_pointer(skb, skb_transport_offset(skb),
+ sizeof(_tcphdr), &_tcphdr);
+ if (likely(th))
+ hdr_len += __tcp_hdrlen(th);
+ } else {
+ struct udphdr _udphdr;
+
+ if (skb_header_pointer(skb, skb_transport_offset(skb),
+ sizeof(_udphdr), &_udphdr))
+ hdr_len += sizeof(struct udphdr);
+ }

if (shinfo->gso_type & SKB_GSO_DODGY)
gso_segs = DIV_ROUND_UP(skb->len - hdr_len,
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index ee9082792530..4d14908afaec 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -492,8 +492,8 @@ ip_proto_again:
out_good:
ret = true;

- key_control->thoff = (u16)nhoff;
out:
+ key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
key_basic->n_proto = proto;
key_basic->ip_proto = ip_proto;

@@ -501,7 +501,6 @@ out:

out_bad:
ret = false;
- key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
goto out;
}
EXPORT_SYMBOL(__skb_flow_dissect);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ae92131c4f89..253c86b78ff0 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -496,7 +496,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
if (atomic_read(&tbl->entries) > (1 << nht->hash_shift))
nht = neigh_hash_grow(tbl, nht->hash_shift + 1);

- hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
+ hash_val = tbl->hash(n->primary_key, dev, nht->hash_rnd) >> (32 - nht->hash_shift);

if (n->parms->dead) {
rc = ERR_PTR(-EINVAL);
@@ -508,7 +508,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
n1 != NULL;
n1 = rcu_dereference_protected(n1->next,
lockdep_is_held(&tbl->lock))) {
- if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) {
+ if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) {
if (want_ref)
neigh_hold(n1);
rc = n1;
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 5e3a7302f774..7753681195c1 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -140,6 +140,9 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)

ccid2_pr_debug("RTO_EXPIRE\n");

+ if (sk->sk_state == DCCP_CLOSED)
+ goto out;
+
/* back-off timer */
hc->tx_rto <<= 1;
if (hc->tx_rto > DCCP_RTO_MAX)
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 711b4dfa17c3..cb5eb649ad5f 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -223,11 +223,16 @@ static bool arp_key_eq(const struct neighbour *neigh, const void *pkey)

static int arp_constructor(struct neighbour *neigh)
{
- __be32 addr = *(__be32 *)neigh->primary_key;
+ __be32 addr;
struct net_device *dev = neigh->dev;
struct in_device *in_dev;
struct neigh_parms *parms;
+ u32 inaddr_any = INADDR_ANY;

+ if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+ memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len);
+
+ addr = *(__be32 *)neigh->primary_key;
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
if (!in_dev) {
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index b60106d34346..8212ed80da48 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -338,7 +338,7 @@ static __be32 igmpv3_get_srcaddr(struct net_device *dev,
return htonl(INADDR_ANY);

for_ifa(in_dev) {
- if (inet_ifa_match(fl4->saddr, ifa))
+ if (fl4->saddr == ifa->ifa_local)
return fl4->saddr;
} endfor_ifa(in_dev);

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 6e3e0e8b1ce3..4cfcc22f7430 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -367,23 +367,12 @@ static inline bool unconditional(const struct arpt_entry *e)
memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
}

-static bool find_jump_target(const struct xt_table_info *t,
- const struct arpt_entry *target)
-{
- struct arpt_entry *iter;
-
- xt_entry_foreach(iter, t->entries, t->size) {
- if (iter == target)
- return true;
- }
- return false;
-}
-
/* Figures out from what hook each rule can be called: returns 0 if
* there are loops. Puts hook bitmask in comefrom.
*/
static int mark_source_chains(const struct xt_table_info *newinfo,
- unsigned int valid_hooks, void *entry0)
+ unsigned int valid_hooks, void *entry0,
+ unsigned int *offsets)
{
unsigned int hook;

@@ -472,10 +461,11 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
/* This a jump; chase it. */
duprintf("Jump rule %u -> %u\n",
pos, newpos);
+ if (!xt_find_jump_offset(offsets, newpos,
+ newinfo->number))
+ return 0;
e = (struct arpt_entry *)
(entry0 + newpos);
- if (!find_jump_target(newinfo, e))
- return 0;
} else {
/* ... this is a fallthru */
newpos = pos + e->next_offset;
@@ -521,11 +511,13 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
{
struct xt_entry_target *t;
struct xt_target *target;
+ unsigned long pcnt;
int ret;

- e->counters.pcnt = xt_percpu_counter_alloc();
- if (IS_ERR_VALUE(e->counters.pcnt))
+ pcnt = xt_percpu_counter_alloc();
+ if (IS_ERR_VALUE(pcnt))
return -ENOMEM;
+ e->counters.pcnt = pcnt;

t = arpt_get_target(e);
target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,
@@ -642,6 +634,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
const struct arpt_replace *repl)
{
struct arpt_entry *iter;
+ unsigned int *offsets;
unsigned int i;
int ret = 0;

@@ -655,6 +648,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
}

duprintf("translate_table: size %u\n", newinfo->size);
+ offsets = xt_alloc_entry_offsets(newinfo->number);
+ if (!offsets)
+ return -ENOMEM;
i = 0;

/* Walk through entries, checking offsets. */
@@ -665,7 +661,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
repl->underflow,
repl->valid_hooks);
if (ret != 0)
- break;
+ goto out_free;
+ if (i < repl->num_entries)
+ offsets[i] = (void *)iter - entry0;
++i;
if (strcmp(arpt_get_target(iter)->u.user.name,
XT_ERROR_TARGET) == 0)
@@ -673,12 +671,13 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
}
duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret);
if (ret != 0)
- return ret;
+ goto out_free;

+ ret = -EINVAL;
if (i != repl->num_entries) {
duprintf("translate_table: %u not %u entries\n",
i, repl->num_entries);
- return -EINVAL;
+ goto out_free;
}

/* Check hooks all assigned */
@@ -689,17 +688,20 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
duprintf("Invalid hook entry %u %u\n",
i, repl->hook_entry[i]);
- return -EINVAL;
+ goto out_free;
}
if (newinfo->underflow[i] == 0xFFFFFFFF) {
duprintf("Invalid underflow %u %u\n",
i, repl->underflow[i]);
- return -EINVAL;
+ goto out_free;
}
}

- if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
- return -ELOOP;
+ if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+ ret = -ELOOP;
+ goto out_free;
+ }
+ kvfree(offsets);

/* Finally, each sanity check must pass */
i = 0;
@@ -719,6 +721,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
return ret;
}

+ return ret;
+ out_free:
+ kvfree(offsets);
return ret;
}

@@ -1336,8 +1341,8 @@ static int translate_compat_table(struct xt_table_info **pinfo,

newinfo->number = compatr->num_entries;
for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
- newinfo->hook_entry[i] = info->hook_entry[i];
- newinfo->underflow[i] = info->underflow[i];
+ newinfo->hook_entry[i] = compatr->hook_entry[i];
+ newinfo->underflow[i] = compatr->underflow[i];
}
entry1 = newinfo->entries;
pos = entry1;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index a399c5419622..a98173d1ea97 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -443,23 +443,12 @@ ipt_do_table(struct sk_buff *skb,
#endif
}

-static bool find_jump_target(const struct xt_table_info *t,
- const struct ipt_entry *target)
-{
- struct ipt_entry *iter;
-
- xt_entry_foreach(iter, t->entries, t->size) {
- if (iter == target)
- return true;
- }
- return false;
-}
-
/* Figures out from what hook each rule can be called: returns 0 if
there are loops. Puts hook bitmask in comefrom. */
static int
mark_source_chains(const struct xt_table_info *newinfo,
- unsigned int valid_hooks, void *entry0)
+ unsigned int valid_hooks, void *entry0,
+ unsigned int *offsets)
{
unsigned int hook;

@@ -552,10 +541,11 @@ mark_source_chains(const struct xt_table_info *newinfo,
/* This a jump; chase it. */
duprintf("Jump rule %u -> %u\n",
pos, newpos);
+ if (!xt_find_jump_offset(offsets, newpos,
+ newinfo->number))
+ return 0;
e = (struct ipt_entry *)
(entry0 + newpos);
- if (!find_jump_target(newinfo, e))
- return 0;
} else {
/* ... this is a fallthru */
newpos = pos + e->next_offset;
@@ -663,10 +653,12 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
unsigned int j;
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
+ unsigned long pcnt;

- e->counters.pcnt = xt_percpu_counter_alloc();
- if (IS_ERR_VALUE(e->counters.pcnt))
+ pcnt = xt_percpu_counter_alloc();
+ if (IS_ERR_VALUE(pcnt))
return -ENOMEM;
+ e->counters.pcnt = pcnt;

j = 0;
mtpar.net = net;
@@ -811,6 +803,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
const struct ipt_replace *repl)
{
struct ipt_entry *iter;
+ unsigned int *offsets;
unsigned int i;
int ret = 0;

@@ -824,6 +817,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
}

duprintf("translate_table: size %u\n", newinfo->size);
+ offsets = xt_alloc_entry_offsets(newinfo->number);
+ if (!offsets)
+ return -ENOMEM;
i = 0;
/* Walk through entries, checking offsets. */
xt_entry_foreach(iter, entry0, newinfo->size) {
@@ -833,17 +829,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
repl->underflow,
repl->valid_hooks);
if (ret != 0)
- return ret;
+ goto out_free;
+ if (i < repl->num_entries)
+ offsets[i] = (void *)iter - entry0;
++i;
if (strcmp(ipt_get_target(iter)->u.user.name,
XT_ERROR_TARGET) == 0)
++newinfo->stacksize;
}

+ ret = -EINVAL;
if (i != repl->num_entries) {
duprintf("translate_table: %u not %u entries\n",
i, repl->num_entries);
- return -EINVAL;
+ goto out_free;
}

/* Check hooks all assigned */
@@ -854,17 +853,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
duprintf("Invalid hook entry %u %u\n",
i, repl->hook_entry[i]);
- return -EINVAL;
+ goto out_free;
}
if (newinfo->underflow[i] == 0xFFFFFFFF) {
duprintf("Invalid underflow %u %u\n",
i, repl->underflow[i]);
- return -EINVAL;
+ goto out_free;
}
}

- if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
- return -ELOOP;
+ if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+ ret = -ELOOP;
+ goto out_free;
+ }
+ kvfree(offsets);

/* Finally, each sanity check must pass */
i = 0;
@@ -884,6 +886,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
return ret;
}

+ return ret;
+ out_free:
+ kvfree(offsets);
return ret;
}

diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index c747b2d9eb77..d4acf38b60fd 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -124,6 +124,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));

+ nskb->mark = IP4_REPLY_MARK(net, oldskb->mark);
+
skb_reserve(nskb, LL_MAX_HEADER);
niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
ip4_dst_hoplimit(skb_dst(nskb)));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5597120c8ffd..37e8966a457b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2176,6 +2176,9 @@ adjudge_to_death:
tcp_send_active_reset(sk, GFP_ATOMIC);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPABORTONMEMORY);
+ } else if (!check_net(sock_net(sk))) {
+ /* Not possible to send reset; just close */
+ tcp_set_state(sk, TCP_CLOSE);
}
}

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 1ec12a4f327e..35f638cfc675 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -46,11 +46,19 @@ static void tcp_write_err(struct sock *sk)
* to prevent DoS attacks. It is called when a retransmission timeout
* or zero probe timeout occurs on orphaned socket.
*
+ * Also close if our net namespace is exiting; in that case there is no
+ * hope of ever communicating again since all netns interfaces are already
+ * down (or about to be down), and we need to release our dst references,
+ * which have been moved to the netns loopback interface, so the namespace
+ * can finish exiting. This condition is only possible if we are a kernel
+ * socket, as those do not hold references to the namespace.
+ *
* Criteria is still not confirmed experimentally and may change.
* We kill the socket, if:
* 1. If number of orphaned sockets exceeds an administratively configured
* limit.
* 2. If we have strong memory pressure.
+ * 3. If our net namespace is exiting.
*/
static int tcp_out_of_resources(struct sock *sk, bool do_reset)
{
@@ -79,6 +87,13 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
return 1;
}
+
+ if (!check_net(sock_net(sk))) {
+ /* Not possible to send reset; just close */
+ tcp_done(sk);
+ return 1;
+ }
+
return 0;
}

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b809958f7388..3ef81c387923 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -148,7 +148,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
}

-static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
{
if (!np->autoflowlabel_set)
return ip6_default_np_autolabel(net);
@@ -1246,14 +1246,16 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
v6_cork->tclass = tclass;
if (rt->dst.flags & DST_XFRM_TUNNEL)
mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
- rt->dst.dev->mtu : dst_mtu(&rt->dst);
+ READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
else
mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
- rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+ READ_ONCE(rt->dst.dev->mtu) : dst_mtu(rt->dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
+ if (mtu < IPV6_MIN_MTU)
+ return -EINVAL;
cork->base.fragsize = mtu;
if (dst_allfrag(rt->dst.path))
cork->base.flags |= IPCORK_ALLFRAG;
@@ -1783,6 +1785,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
cork.base.flags = 0;
cork.base.addr = 0;
cork.base.opt = NULL;
+ cork.base.dst = NULL;
v6_cork.opt = NULL;
err = ip6_setup_cork(sk, &cork, &v6_cork, hlimit, tclass, opt, rt, fl6);
if (err) {
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 435e26210587..9011176c8387 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1313,7 +1313,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
break;

case IPV6_AUTOFLOWLABEL:
- val = np->autoflowlabel;
+ val = ip6_autoflowlabel(sock_net(sk), np);
break;

default:
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 22f39e00bef3..bb1b5453a7a1 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -455,23 +455,12 @@ ip6t_do_table(struct sk_buff *skb,
#endif
}

-static bool find_jump_target(const struct xt_table_info *t,
- const struct ip6t_entry *target)
-{
- struct ip6t_entry *iter;
-
- xt_entry_foreach(iter, t->entries, t->size) {
- if (iter == target)
- return true;
- }
- return false;
-}
-
/* Figures out from what hook each rule can be called: returns 0 if
there are loops. Puts hook bitmask in comefrom. */
static int
mark_source_chains(const struct xt_table_info *newinfo,
- unsigned int valid_hooks, void *entry0)
+ unsigned int valid_hooks, void *entry0,
+ unsigned int *offsets)
{
unsigned int hook;

@@ -564,10 +553,11 @@ mark_source_chains(const struct xt_table_info *newinfo,
/* This a jump; chase it. */
duprintf("Jump rule %u -> %u\n",
pos, newpos);
+ if (!xt_find_jump_offset(offsets, newpos,
+ newinfo->number))
+ return 0;
e = (struct ip6t_entry *)
(entry0 + newpos);
- if (!find_jump_target(newinfo, e))
- return 0;
} else {
/* ... this is a fallthru */
newpos = pos + e->next_offset;
@@ -676,10 +666,12 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
unsigned int j;
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
+ unsigned long pcnt;

- e->counters.pcnt = xt_percpu_counter_alloc();
- if (IS_ERR_VALUE(e->counters.pcnt))
+ pcnt = xt_percpu_counter_alloc();
+ if (IS_ERR_VALUE(pcnt))
return -ENOMEM;
+ e->counters.pcnt = pcnt;

j = 0;
mtpar.net = net;
@@ -823,6 +815,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
const struct ip6t_replace *repl)
{
struct ip6t_entry *iter;
+ unsigned int *offsets;
unsigned int i;
int ret = 0;

@@ -836,6 +829,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
}

duprintf("translate_table: size %u\n", newinfo->size);
+ offsets = xt_alloc_entry_offsets(newinfo->number);
+ if (!offsets)
+ return -ENOMEM;
i = 0;
/* Walk through entries, checking offsets. */
xt_entry_foreach(iter, entry0, newinfo->size) {
@@ -845,17 +841,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
repl->underflow,
repl->valid_hooks);
if (ret != 0)
- return ret;
+ goto out_free;
+ if (i < repl->num_entries)
+ offsets[i] = (void *)iter - entry0;
++i;
if (strcmp(ip6t_get_target(iter)->u.user.name,
XT_ERROR_TARGET) == 0)
++newinfo->stacksize;
}

+ ret = -EINVAL;
if (i != repl->num_entries) {
duprintf("translate_table: %u not %u entries\n",
i, repl->num_entries);
- return -EINVAL;
+ goto out_free;
}

/* Check hooks all assigned */
@@ -866,17 +865,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
duprintf("Invalid hook entry %u %u\n",
i, repl->hook_entry[i]);
- return -EINVAL;
+ goto out_free;
}
if (newinfo->underflow[i] == 0xFFFFFFFF) {
duprintf("Invalid underflow %u %u\n",
i, repl->underflow[i]);
- return -EINVAL;
+ goto out_free;
}
}

- if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
- return -ELOOP;
+ if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+ ret = -ELOOP;
+ goto out_free;
+ }
+ kvfree(offsets);

/* Finally, each sanity check must pass */
i = 0;
@@ -896,6 +898,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
return ret;
}

+ return ret;
+ out_free:
+ kvfree(offsets);
return ret;
}

diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index 6989c70ae29f..4a84b5ad9ecb 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -33,6 +33,7 @@ static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb,
fl6.daddr = *gw;
fl6.flowlabel = (__force __be32)(((iph->flow_lbl[0] & 0xF) << 16) |
(iph->flow_lbl[1] << 8) | iph->flow_lbl[2]);
+ fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
dst_release(dst);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index e0f922b777e3..7117e5bef412 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -157,6 +157,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
fl6.daddr = oip6h->saddr;
fl6.fl6_sport = otcph->dest;
fl6.fl6_dport = otcph->source;
+ fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark);
security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
dst = ip6_route_output(net, NULL, &fl6);
if (dst == NULL || dst->error) {
@@ -180,6 +181,8 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)

skb_dst_set(nskb, dst);

+ nskb->mark = fl6.flowi6_mark;
+
skb_reserve(nskb, hh_len + dst->header_len);
ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
ip6_dst_hoplimit(dst));
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 86a3c6f0c871..5f747089024f 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -719,6 +719,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
* least once for the stats anyway.
*/
rcu_read_lock_bh();
+ begin:
hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (ct != ignored_conntrack &&
@@ -730,6 +731,12 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
}
NF_CT_STAT_INC(net, searched);
}
+
+ if (get_nulls_value(n) != hash) {
+ NF_CT_STAT_INC(net, search_restart);
+ goto begin;
+ }
+
rcu_read_unlock_bh();

return 0;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 7f16d19d6198..a91f8bd51d05 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -560,7 +560,7 @@ static int exp_seq_show(struct seq_file *s, void *v)
helper = rcu_dereference(nfct_help(expect->master)->helper);
if (helper) {
seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name);
- if (helper->expect_policy[expect->class].name)
+ if (helper->expect_policy[expect->class].name[0])
seq_printf(s, "/%s",
helper->expect_policy[expect->class].name);
}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 885b4aba3695..1665c2159e4b 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1434,9 +1434,12 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff,
handler = &sip_handlers[i];
if (handler->request == NULL)
continue;
- if (*datalen < handler->len ||
+ if (*datalen < handler->len + 2 ||
strncasecmp(*dptr, handler->method, handler->len))
continue;
+ if ((*dptr)[handler->len] != ' ' ||
+ !isalpha((*dptr)[handler->len+1]))
+ continue;

if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CSEQ,
&matchoff, &matchlen) <= 0) {
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 8d34a488efc0..ac143ae4f7b6 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -17,6 +17,7 @@
#include <linux/types.h>
#include <linux/list.h>
#include <linux/errno.h>
+#include <linux/capability.h>
#include <net/netlink.h>
#include <net/sock.h>

@@ -392,6 +393,9 @@ nfnl_cthelper_new(struct sock *nfnl, struct sk_buff *skb,
struct nfnl_cthelper *nlcth;
int ret = 0;

+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE])
return -EINVAL;

@@ -595,6 +599,9 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb,
struct nfnl_cthelper *nlcth;
bool tuple_set = false;

+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = nfnl_cthelper_dump_table,
@@ -661,6 +668,9 @@ nfnl_cthelper_del(struct sock *nfnl, struct sk_buff *skb,
struct nfnl_cthelper *nlcth, *n;
int j = 0, ret;

+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
if (tb[NFCTH_NAME])
helper_name = nla_data(tb[NFCTH_NAME]);

diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index f6837f9b6d6c..c14d2e8eaec3 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1053,10 +1053,8 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb,
struct net *net = sock_net(ctnl);
struct nfnl_queue_net *q = nfnl_queue_pernet(net);

- queue = instance_lookup(q, queue_num);
- if (!queue)
- queue = verdict_instance_lookup(q, queue_num,
- NETLINK_CB(skb).portid);
+ queue = verdict_instance_lookup(q, queue_num,
+ NETLINK_CB(skb).portid);
if (IS_ERR(queue))
return PTR_ERR(queue);

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 2fc6ca9d1286..7b42b0ad3f9b 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -701,6 +701,56 @@ int xt_check_entry_offsets(const void *base,
}
EXPORT_SYMBOL(xt_check_entry_offsets);

+/**
+ * xt_alloc_entry_offsets - allocate array to store rule head offsets
+ *
+ * @size: number of entries
+ *
+ * Return: NULL or kmalloc'd or vmalloc'd array
+ */
+unsigned int *xt_alloc_entry_offsets(unsigned int size)
+{
+ unsigned int *off;
+
+ off = kcalloc(size, sizeof(unsigned int), GFP_KERNEL | __GFP_NOWARN);
+
+ if (off)
+ return off;
+
+ if (size < (SIZE_MAX / sizeof(unsigned int)))
+ off = vmalloc(size * sizeof(unsigned int));
+
+ return off;
+}
+EXPORT_SYMBOL(xt_alloc_entry_offsets);
+
+/**
+ * xt_find_jump_offset - check if target is a valid jump offset
+ *
+ * @offsets: array containing all valid rule start offsets of a rule blob
+ * @target: the jump target to search for
+ * @size: entries in @offset
+ */
+bool xt_find_jump_offset(const unsigned int *offsets,
+ unsigned int target, unsigned int size)
+{
+ int m, low = 0, hi = size;
+
+ while (hi > low) {
+ m = (low + hi) / 2u;
+
+ if (offsets[m] > target)
+ hi = m;
+ else if (offsets[m] < target)
+ low = m + 1;
+ else
+ return true;
+ }
+
+ return false;
+}
+EXPORT_SYMBOL(xt_find_jump_offset);
+
int xt_check_target(struct xt_tgchk_param *par,
unsigned int size, u_int8_t proto, bool inv_proto)
{
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index df8801e02a32..7eae0d0af89a 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -19,6 +19,7 @@
#include <linux/module.h>
#include <linux/kernel.h>

+#include <linux/capability.h>
#include <linux/if.h>
#include <linux/inetdevice.h>
#include <linux/ip.h>
@@ -69,6 +70,9 @@ static int xt_osf_add_callback(struct sock *ctnl, struct sk_buff *skb,
struct xt_osf_finger *kf = NULL, *sf;
int err = 0;

+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
if (!osf_attrs[OSF_ATTR_FINGER])
return -EINVAL;

@@ -112,6 +116,9 @@ static int xt_osf_remove_callback(struct sock *ctnl, struct sk_buff *skb,
struct xt_osf_finger *sf;
int err = -ENOENT;

+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
if (!osf_attrs[OSF_ATTR_FINGER])
return -EINVAL;

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index a870d27ca778..e9851198a850 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -83,7 +83,7 @@
static int sctp_writeable(struct sock *sk);
static void sctp_wfree(struct sk_buff *skb);
static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
- size_t msg_len, struct sock **orig_sk);
+ size_t msg_len);
static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p);
static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p);
static int sctp_wait_for_accept(struct sock *sk, long timeo);
@@ -332,16 +332,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt,
if (len < sizeof (struct sockaddr))
return NULL;

+ if (!opt->pf->af_supported(addr->sa.sa_family, opt))
+ return NULL;
+
/* V4 mapped address are really of AF_INET family */
if (addr->sa.sa_family == AF_INET6 &&
- ipv6_addr_v4mapped(&addr->v6.sin6_addr)) {
- if (!opt->pf->af_supported(AF_INET, opt))
- return NULL;
- } else {
- /* Does this PF support this AF? */
- if (!opt->pf->af_supported(addr->sa.sa_family, opt))
- return NULL;
- }
+ ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
+ !opt->pf->af_supported(AF_INET, opt))
+ return NULL;

/* If we get this far, af is valid. */
af = sctp_get_af_specific(addr->sa.sa_family);
@@ -1954,7 +1952,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
if (!sctp_wspace(asoc)) {
/* sk can be changed by peel off when waiting for buf. */
- err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len, &sk);
+ err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
if (err) {
if (err == -ESRCH) {
/* asoc is already dead. */
@@ -6976,12 +6974,12 @@ void sctp_sock_rfree(struct sk_buff *skb)

/* Helper function to wait for space in the sndbuf. */
static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
- size_t msg_len, struct sock **orig_sk)
+ size_t msg_len)
{
struct sock *sk = asoc->base.sk;
- int err = 0;
long current_timeo = *timeo_p;
DEFINE_WAIT(wait);
+ int err = 0;

pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc,
*timeo_p, msg_len);
@@ -7010,17 +7008,13 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
release_sock(sk);
current_timeo = schedule_timeout(current_timeo);
lock_sock(sk);
- if (sk != asoc->base.sk) {
- release_sock(sk);
- sk = asoc->base.sk;
- lock_sock(sk);
- }
+ if (sk != asoc->base.sk)
+ goto do_error;

*timeo_p = current_timeo;
}

out:
- *orig_sk = sk;
finish_wait(&asoc->wait, &wait);

/* Release the association's refcnt. */
diff --git a/tools/usb/usbip/libsrc/usbip_common.c b/tools/usb/usbip/libsrc/usbip_common.c
index ac73710473de..8000445ff884 100644
--- a/tools/usb/usbip/libsrc/usbip_common.c
+++ b/tools/usb/usbip/libsrc/usbip_common.c
@@ -215,9 +215,16 @@ int read_usb_interface(struct usbip_usb_device *udev, int i,
struct usbip_usb_interface *uinf)
{
char busid[SYSFS_BUS_ID_SIZE];
+ int size;
struct udev_device *sif;

- sprintf(busid, "%s:%d.%d", udev->busid, udev->bConfigurationValue, i);
+ size = snprintf(busid, sizeof(busid), "%s:%d.%d",
+ udev->busid, udev->bConfigurationValue, i);
+ if (size < 0 || (unsigned int)size >= sizeof(busid)) {
+ err("busid length %i >= %lu or < 0", size,
+ (unsigned long)sizeof(busid));
+ return -1;
+ }

sif = udev_device_new_from_subsystem_sysname(udev_context, "usb", busid);
if (!sif) {
diff --git a/tools/usb/usbip/libsrc/usbip_host_driver.c b/tools/usb/usbip/libsrc/usbip_host_driver.c
index bef08d5c44e8..071b9ce99420 100644
--- a/tools/usb/usbip/libsrc/usbip_host_driver.c
+++ b/tools/usb/usbip/libsrc/usbip_host_driver.c
@@ -39,13 +39,19 @@ struct udev *udev_context;
static int32_t read_attr_usbip_status(struct usbip_usb_device *udev)
{
char status_attr_path[SYSFS_PATH_MAX];
+ int size;
int fd;
int length;
char status;
int value = 0;

- snprintf(status_attr_path, SYSFS_PATH_MAX, "%s/usbip_status",
- udev->path);
+ size = snprintf(status_attr_path, SYSFS_PATH_MAX, "%s/usbip_status",
+ udev->path);
+ if (size < 0 || (unsigned int)size >= sizeof(status_attr_path)) {
+ err("usbip_status path length %i >= %lu or < 0", size,
+ (unsigned long)sizeof(status_attr_path));
+ return -1;
+ }

fd = open(status_attr_path, O_RDONLY);
if (fd < 0) {
@@ -225,6 +231,7 @@ int usbip_host_export_device(struct usbip_exported_device *edev, int sockfd)
{
char attr_name[] = "usbip_sockfd";
char sockfd_attr_path[SYSFS_PATH_MAX];
+ int size;
char sockfd_buff[30];
int ret;

@@ -244,10 +251,20 @@ int usbip_host_export_device(struct usbip_exported_device *edev, int sockfd)
}

/* only the first interface is true */
- snprintf(sockfd_attr_path, sizeof(sockfd_attr_path), "%s/%s",
- edev->udev.path, attr_name);
+ size = snprintf(sockfd_attr_path, sizeof(sockfd_attr_path), "%s/%s",
+ edev->udev.path, attr_name);
+ if (size < 0 || (unsigned int)size >= sizeof(sockfd_attr_path)) {
+ err("exported device path length %i >= %lu or < 0", size,
+ (unsigned long)sizeof(sockfd_attr_path));
+ return -1;
+ }

- snprintf(sockfd_buff, sizeof(sockfd_buff), "%d\n", sockfd);
+ size = snprintf(sockfd_buff, sizeof(sockfd_buff), "%d\n", sockfd);
+ if (size < 0 || (unsigned int)size >= sizeof(sockfd_buff)) {
+ err("socket length %i >= %lu or < 0", size,
+ (unsigned long)sizeof(sockfd_buff));
+ return -1;
+ }

ret = write_sysfs_attribute(sockfd_attr_path, sockfd_buff,
strlen(sockfd_buff));
diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c
index ad9204773533..1274f326242c 100644
--- a/tools/usb/usbip/libsrc/vhci_driver.c
+++ b/tools/usb/usbip/libsrc/vhci_driver.c
@@ -55,12 +55,12 @@ static int parse_status(const char *value)

while (*c != '\0') {
int port, status, speed, devid;
- unsigned long socket;
+ int sockfd;
char lbusid[SYSFS_BUS_ID_SIZE];

- ret = sscanf(c, "%d %d %d %x %lx %31s\n",
+ ret = sscanf(c, "%d %d %d %x %u %31s\n",
&port, &status, &speed,
- &devid, &socket, lbusid);
+ &devid, &sockfd, lbusid);

if (ret < 5) {
dbg("sscanf failed: %d", ret);
@@ -69,7 +69,7 @@ static int parse_status(const char *value)

dbg("port %d status %d speed %d devid %x",
port, status, speed, devid);
- dbg("socket %lx lbusid %s", socket, lbusid);
+ dbg("sockfd %u lbusid %s", sockfd, lbusid);


/* if a device is connected, look at it */
diff --git a/tools/usb/usbip/src/usbip.c b/tools/usb/usbip/src/usbip.c
index d7599d943529..73d8eee8130b 100644
--- a/tools/usb/usbip/src/usbip.c
+++ b/tools/usb/usbip/src/usbip.c
@@ -176,6 +176,8 @@ int main(int argc, char *argv[])
break;
case '?':
printf("usbip: invalid option\n");
+ /* Terminate after printing error */
+ /* FALLTHRU */
default:
usbip_usage();
goto out;
\
 
 \ /
  Last update: 2018-01-31 16:27    [W:0.120 / U:0.044 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site