aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAlex Shi <alex.shi@linaro.org>2018-02-01 12:02:38 +0800
committerAlex Shi <alex.shi@linaro.org>2018-02-01 12:02:38 +0800
commit59e35359ec360b74e9013ccab84c19ce53db38f9 (patch)
treef6c5cca3189d2140f23e7a71ee3f167c7e6f748e
parentc210bc406de6a7993b8d7f30c28436be80de7694 (diff)
parenta40f2a595adfe0be6ced06fdb4c4a24ae3291a91 (diff)
downloadlinux-linaro-stable-lsk-v4.4-18.02-android.tar.gz
Merge branch 'linux-linaro-lsk-v4.4' into linux-linaro-lsk-v4.4-androidlsk-v4.4-18.02-android
-rw-r--r--Documentation/kernel-parameters.txt28
-rw-r--r--Documentation/x86/pti.txt2
-rw-r--r--Makefile2
-rw-r--r--arch/arm/boot/dts/kirkwood-openblocks_a7.dts10
-rw-r--r--arch/arm64/kvm/handle_exit.c4
-rw-r--r--arch/mips/ar7/platform.c2
-rw-r--r--arch/um/Makefile2
-rw-r--r--arch/x86/Kconfig13
-rw-r--r--arch/x86/Makefile8
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S5
-rw-r--r--arch/x86/crypto/camellia-aesni-avx-asm_64.S3
-rw-r--r--arch/x86/crypto/camellia-aesni-avx2-asm_64.S3
-rw-r--r--arch/x86/crypto/crc32c-pcl-intel-asm_64.S3
-rw-r--r--arch/x86/entry/entry_32.S11
-rw-r--r--arch/x86/entry/entry_64.S16
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c7
-rw-r--r--arch/x86/include/asm/alternative.h4
-rw-r--r--arch/x86/include/asm/asm-prototypes.h41
-rw-r--r--arch/x86/include/asm/asm.h11
-rw-r--r--arch/x86/include/asm/cpufeature.h3
-rw-r--r--arch/x86/include/asm/intel-family.h68
-rw-r--r--arch/x86/include/asm/msr-index.h3
-rw-r--r--arch/x86/include/asm/nospec-branch.h198
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/switch_to.h38
-rw-r--r--arch/x86/include/asm/traps.h1
-rw-r--r--arch/x86/include/asm/vsyscall.h1
-rw-r--r--arch/x86/include/asm/xen/hypercall.h5
-rw-r--r--arch/x86/kernel/apic/io_apic.c2
-rw-r--r--arch/x86/kernel/apic/vector.c7
-rw-r--r--arch/x86/kernel/cpu/amd.c28
-rw-r--r--arch/x86/kernel/cpu/bugs.c202
-rw-r--r--arch/x86/kernel/cpu/common.c12
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c5
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c21
-rw-r--r--arch/x86/kernel/irq_32.c15
-rw-r--r--arch/x86/kernel/kprobes/opt.c23
-rw-r--r--arch/x86/kernel/mcount_64.S7
-rw-r--r--arch/x86/kernel/traps.c2
-rw-r--r--arch/x86/kernel/vmlinux.lds.S7
-rw-r--r--arch/x86/kvm/svm.c4
-rw-r--r--arch/x86/kvm/vmx.c4
-rw-r--r--arch/x86/lib/Makefile1
-rw-r--r--arch/x86/lib/checksum_32.S7
-rw-r--r--arch/x86/lib/delay.c7
-rw-r--r--arch/x86/lib/retpoline.S49
-rw-r--r--arch/x86/mm/kaiser.c2
-rw-r--r--drivers/acpi/acpi_processor.c9
-rw-r--r--drivers/acpi/acpica/nsutils.c23
-rw-r--r--drivers/acpi/glue.c12
-rw-r--r--drivers/acpi/processor_throttling.c9
-rw-r--r--drivers/ata/libata-core.c1
-rw-r--r--drivers/base/cacheinfo.c15
-rw-r--r--drivers/base/power/trace.c4
-rw-r--r--drivers/hv/hv.c11
-rw-r--r--drivers/input/misc/twl4030-vibra.c6
-rw-r--r--drivers/input/misc/twl6040-vibra.c2
-rw-r--r--drivers/input/mouse/trackpoint.c3
-rw-r--r--drivers/input/touchscreen/88pm860x-ts.c16
-rw-r--r--drivers/md/dm-thin-metadata.c6
-rw-r--r--drivers/md/persistent-data/dm-btree.c19
-rw-r--r--drivers/mmc/host/sdhci-of-esdhc.c10
-rw-r--r--drivers/net/can/usb/peak_usb/pcan_usb_fd.c21
-rw-r--r--drivers/net/ethernet/realtek/r8169.c9
-rw-r--r--drivers/net/ppp/pppoe.c11
-rw-r--r--drivers/net/usb/lan78xx.c1
-rw-r--r--drivers/net/vmxnet3/vmxnet3_drv.c2
-rw-r--r--drivers/pci/host/pci-layerscape.c22
-rw-r--r--drivers/phy/phy-core.c4
-rw-r--r--drivers/scsi/hpsa.c1
-rw-r--r--drivers/scsi/libiscsi.c2
-rw-r--r--drivers/scsi/sg.c30
-rw-r--r--drivers/usb/usbip/stub_dev.c3
-rw-r--r--drivers/usb/usbip/stub_rx.c46
-rw-r--r--drivers/usb/usbip/usbip_common.c15
-rw-r--r--drivers/usb/usbip/usbip_common.h1
-rw-r--r--drivers/usb/usbip/usbip_event.c5
-rw-r--r--drivers/usb/usbip/vhci_hcd.c90
-rw-r--r--drivers/usb/usbip/vhci_rx.c30
-rw-r--r--drivers/usb/usbip/vhci_sysfs.c44
-rw-r--r--drivers/usb/usbip/vhci_tx.c14
-rw-r--r--fs/ext2/acl.c36
-rw-r--r--fs/fcntl.c4
-rw-r--r--fs/nfsd/auth.c5
-rw-r--r--fs/pipe.c18
-rw-r--r--fs/reiserfs/bitmap.c14
-rw-r--r--fs/reiserfs/xattr_acl.c12
-rw-r--r--fs/select.c14
-rw-r--r--include/asm-generic/asm-prototypes.h7
-rw-r--r--include/asm-generic/export.h94
-rw-r--r--include/linux/cacheinfo.h1
-rw-r--r--include/linux/kconfig.h11
-rw-r--r--include/linux/ktime.h7
-rw-r--r--include/linux/netfilter/x_tables.h10
-rw-r--r--include/linux/sched.h1
-rw-r--r--include/linux/tcp.h7
-rw-r--r--include/net/arp.h3
-rw-r--r--include/net/ipv6.h1
-rw-r--r--include/net/net_namespace.h10
-rw-r--r--include/scsi/sg.h1
-rw-r--r--include/uapi/linux/eventpoll.h13
-rw-r--r--ipc/msg.c5
-rw-r--r--kernel/futex.c3
-rw-r--r--kernel/gcov/Kconfig1
-rw-r--r--kernel/sched/core.c2
-rw-r--r--kernel/sched/deadline.c100
-rw-r--r--kernel/time/hrtimer.c5
-rw-r--r--kernel/time/timer.c9
-rw-r--r--kernel/trace/trace_events.c16
-rw-r--r--mm/cma.c15
-rw-r--r--mm/memcontrol.c2
-rw-r--r--mm/memory-failure.c7
-rw-r--r--mm/mmap.c6
-rw-r--r--mm/page_alloc.c6
-rw-r--r--net/can/af_can.c22
-rw-r--r--net/core/dev.c19
-rw-r--r--net/core/flow_dissector.c3
-rw-r--r--net/core/neighbour.c4
-rw-r--r--net/dccp/ccids/ccid2.c3
-rw-r--r--net/ipv4/arp.c7
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/netfilter/arp_tables.c57
-rw-r--r--net/ipv4/netfilter/ip_tables.c51
-rw-r--r--net/ipv4/netfilter/nf_reject_ipv4.c2
-rw-r--r--net/ipv4/tcp.c3
-rw-r--r--net/ipv4/tcp_timer.c15
-rw-r--r--net/ipv6/ip6_output.c9
-rw-r--r--net/ipv6/ipv6_sockglue.c2
-rw-r--r--net/ipv6/netfilter/ip6_tables.c51
-rw-r--r--net/ipv6/netfilter/nf_dup_ipv6.c1
-rw-r--r--net/ipv6/netfilter/nf_reject_ipv6.c3
-rw-r--r--net/key/af_key.c8
-rw-r--r--net/netfilter/nf_conntrack_core.c7
-rw-r--r--net/netfilter/nf_conntrack_expect.c2
-rw-r--r--net/netfilter/nf_conntrack_sip.c5
-rw-r--r--net/netfilter/nfnetlink_cthelper.c10
-rw-r--r--net/netfilter/nfnetlink_queue.c6
-rw-r--r--net/netfilter/x_tables.c50
-rw-r--r--net/netfilter/xt_osf.c7
-rw-r--r--net/sctp/socket.c30
-rw-r--r--scripts/Makefile.build87
-rw-r--r--sound/core/pcm_lib.c1
-rw-r--r--sound/pci/hda/patch_cirrus.c1
-rw-r--r--sound/pci/hda/patch_realtek.c1
-rw-r--r--tools/usb/usbip/libsrc/usbip_common.c9
-rw-r--r--tools/usb/usbip/libsrc/usbip_host_driver.c27
-rw-r--r--tools/usb/usbip/libsrc/vhci_driver.c8
-rw-r--r--tools/usb/usbip/src/usbip.c2
149 files changed, 1875 insertions, 484 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 79af1716bf4d..9fee3a90deaa 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2458,6 +2458,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
nohugeiomap [KNL,x86] Disable kernel huge I/O mappings.
+ nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2
+ (indirect branch prediction) vulnerability. System may
+ allow data leaks with this option, which is equivalent
+ to spectre_v2=off.
+
noxsave [BUGS=X86] Disables x86 extended register state save
and restore using xsave. The kernel will fallback to
enabling legacy floating-point and sse state.
@@ -3604,6 +3609,29 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
sonypi.*= [HW] Sony Programmable I/O Control Device driver
See Documentation/laptops/sonypi.txt
+ spectre_v2= [X86] Control mitigation of Spectre variant 2
+ (indirect branch speculation) vulnerability.
+
+ on - unconditionally enable
+ off - unconditionally disable
+ auto - kernel detects whether your CPU model is
+ vulnerable
+
+ Selecting 'on' will, and 'auto' may, choose a
+ mitigation method at run time according to the
+ CPU, the available microcode, the setting of the
+ CONFIG_RETPOLINE configuration option, and the
+ compiler with which the kernel was built.
+
+ Specific mitigations can also be selected manually:
+
+ retpoline - replace indirect branches
+ retpoline,generic - google's original retpoline
+ retpoline,amd - AMD-specific minimal thunk
+
+ Not specifying this option is equivalent to
+ spectre_v2=auto.
+
spia_io_base= [HW,MTD]
spia_fio_base=
spia_pedr=
diff --git a/Documentation/x86/pti.txt b/Documentation/x86/pti.txt
index d11eff61fc9a..5cd58439ad2d 100644
--- a/Documentation/x86/pti.txt
+++ b/Documentation/x86/pti.txt
@@ -78,7 +78,7 @@ this protection comes at a cost:
non-PTI SYSCALL entry code, so requires mapping fewer
things into the userspace page tables. The downside is
that stacks must be switched at entry time.
- d. Global pages are disabled for all kernel structures not
+ c. Global pages are disabled for all kernel structures not
mapped into both kernel and userspace page tables. This
feature of the MMU allows different processes to share TLB
entries mapping the kernel. Losing the feature means more
diff --git a/Makefile b/Makefile
index bf1c908c5ac6..3c2bde6ea1d0 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 4
-SUBLEVEL = 112
+SUBLEVEL = 114
EXTRAVERSION =
NAME = Blurry Fish Butt
diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
index d5e3bc518968..d57f48543f76 100644
--- a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
+++ b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
@@ -53,7 +53,8 @@
};
pinctrl: pin-controller@10000 {
- pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>;
+ pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header
+ &pmx_gpio_header_gpo>;
pinctrl-names = "default";
pmx_uart0: pmx-uart0 {
@@ -85,11 +86,16 @@
* ground.
*/
pmx_gpio_header: pmx-gpio-header {
- marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28",
+ marvell,pins = "mpp17", "mpp29", "mpp28",
"mpp35", "mpp34", "mpp40";
marvell,function = "gpio";
};
+ pmx_gpio_header_gpo: pxm-gpio-header-gpo {
+ marvell,pins = "mpp7";
+ marvell,function = "gpo";
+ };
+
pmx_gpio_init: pmx-init {
marvell,pins = "mpp38";
marvell,function = "gpio";
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index e47f9bc71079..51abbd1d98e3 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -43,7 +43,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
ret = kvm_psci_call(vcpu);
if (ret < 0) {
- kvm_inject_undefined(vcpu);
+ vcpu_set_reg(vcpu, 0, ~0UL);
return 1;
}
@@ -52,7 +52,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
- kvm_inject_undefined(vcpu);
+ vcpu_set_reg(vcpu, 0, ~0UL);
return 1;
}
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index 3446b6fb3acb..9da4e2292fc7 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -576,7 +576,7 @@ static int __init ar7_register_uarts(void)
uart_port.type = PORT_AR7;
uart_port.uartclk = clk_get_rate(bus_clk) / 2;
uart_port.iotype = UPIO_MEM32;
- uart_port.flags = UPF_FIXED_TYPE;
+ uart_port.flags = UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF;
uart_port.regshift = 2;
uart_port.line = 0;
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/Kconfig b/arch/x86/Kconfig
index 09332bd6e05a..6151c916dab7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -395,6 +395,19 @@ config GOLDFISH
def_bool y
depends on X86_GOLDFISH
+config RETPOLINE
+ bool "Avoid speculative indirect branches in kernel"
+ default y
+ ---help---
+ Compile kernel with the retpoline compiler options to guard against
+ kernel-to-user data leaks by avoiding speculative indirect
+ branches. Requires a compiler with -mindirect-branch=thunk-extern
+ support for full protection. The kernel may run slower.
+
+ Without compiler support, at least indirect branches in assembler
+ code are eliminated. Since this includes the syscall entry path,
+ it is not entirely pointless.
+
if X86_32
config X86_EXTENDED_PLATFORM
bool "Support for extended (non-PC) x86 platforms"
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 0048d9886725..82fac1b62626 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -210,6 +210,14 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
KBUILD_CFLAGS += $(mflags-y)
KBUILD_AFLAGS += $(mflags-y)
+# Avoid indirect branches in kernel to deal with Spectre
+ifdef CONFIG_RETPOLINE
+ RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
+ ifneq ($(RETPOLINE_CFLAGS),)
+ KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
+ endif
+endif
+
archscripts: scripts_basic
$(Q)$(MAKE) $(build)=arch/x86/tools relocs
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 6bd2c6c95373..3f93dedb5a4d 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -31,6 +31,7 @@
#include <linux/linkage.h>
#include <asm/inst.h>
+#include <asm/nospec-branch.h>
/*
* The following macros are used to move an (un)aligned 16 byte value to/from
@@ -2714,7 +2715,7 @@ ENTRY(aesni_xts_crypt8)
pxor INC, STATE4
movdqu IV, 0x30(OUTP)
- call *%r11
+ CALL_NOSPEC %r11
movdqu 0x00(OUTP), INC
pxor INC, STATE1
@@ -2759,7 +2760,7 @@ ENTRY(aesni_xts_crypt8)
_aesni_gf128mul_x_ble()
movups IV, (IVP)
- call *%r11
+ CALL_NOSPEC %r11
movdqu 0x40(OUTP), INC
pxor INC, STATE1
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index ce71f9212409..5881756f78a2 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -16,6 +16,7 @@
*/
#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
#define CAMELLIA_TABLE_BYTE_LEN 272
@@ -1210,7 +1211,7 @@ camellia_xts_crypt_16way:
vpxor 14 * 16(%rax), %xmm15, %xmm14;
vpxor 15 * 16(%rax), %xmm15, %xmm15;
- call *%r9;
+ CALL_NOSPEC %r9;
addq $(16 * 16), %rsp;
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index 0e0b8863a34b..0d45b04b490a 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -11,6 +11,7 @@
*/
#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
#define CAMELLIA_TABLE_BYTE_LEN 272
@@ -1323,7 +1324,7 @@ camellia_xts_crypt_32way:
vpxor 14 * 32(%rax), %ymm15, %ymm14;
vpxor 15 * 32(%rax), %ymm15, %ymm15;
- call *%r9;
+ CALL_NOSPEC %r9;
addq $(16 * 32), %rsp;
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 4fe27e074194..48767520cbe0 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -45,6 +45,7 @@
#include <asm/inst.h>
#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
@@ -172,7 +173,7 @@ continue_block:
movzxw (bufp, %rax, 2), len
offset=crc_array-jump_table
lea offset(bufp, len, 1), bufp
- jmp *bufp
+ JMP_NOSPEC bufp
################################################################
## 2a) PROCESS FULL BLOCKS:
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index ae678ad128a9..d437f3871e53 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -44,6 +44,7 @@
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/smap.h>
+#include <asm/nospec-branch.h>
.section .entry.text, "ax"
@@ -226,7 +227,8 @@ ENTRY(ret_from_kernel_thread)
pushl $0x0202 # Reset kernel eflags
popfl
movl PT_EBP(%esp), %eax
- call *PT_EBX(%esp)
+ movl PT_EBX(%esp), %edx
+ CALL_NOSPEC %edx
movl $0, PT_EAX(%esp)
/*
@@ -861,7 +863,8 @@ trace:
movl 0x4(%ebp), %edx
subl $MCOUNT_INSN_SIZE, %eax
- call *ftrace_trace_function
+ movl ftrace_trace_function, %ecx
+ CALL_NOSPEC %ecx
popl %edx
popl %ecx
@@ -896,7 +899,7 @@ return_to_handler:
movl %eax, %ecx
popl %edx
popl %eax
- jmp *%ecx
+ JMP_NOSPEC %ecx
#endif
#ifdef CONFIG_TRACING
@@ -938,7 +941,7 @@ error_code:
movl %ecx, %es
TRACE_IRQS_OFF
movl %esp, %eax # pt_regs pointer
- call *%edi
+ CALL_NOSPEC %edi
jmp ret_from_exception
END(page_fault)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index db42a6766995..113de1592cc1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -36,6 +36,7 @@
#include <asm/smap.h>
#include <asm/pgtable_types.h>
#include <asm/kaiser.h>
+#include <asm/nospec-branch.h>
#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
@@ -184,7 +185,13 @@ entry_SYSCALL_64_fastpath:
#endif
ja 1f /* return -ENOSYS (already in pt_regs->ax) */
movq %r10, %rcx
+#ifdef CONFIG_RETPOLINE
+ movq sys_call_table(, %rax, 8), %rax
+ call __x86_indirect_thunk_rax
+#else
call *sys_call_table(, %rax, 8)
+#endif
+
movq %rax, RAX(%rsp)
1:
/*
@@ -276,7 +283,12 @@ tracesys_phase2:
#endif
ja 1f /* return -ENOSYS (already in pt_regs->ax) */
movq %r10, %rcx /* fixup for C */
+#ifdef CONFIG_RETPOLINE
+ movq sys_call_table(, %rax, 8), %rax
+ call __x86_indirect_thunk_rax
+#else
call *sys_call_table(, %rax, 8)
+#endif
movq %rax, RAX(%rsp)
1:
/* Use IRET because user could have changed pt_regs->foo */
@@ -491,7 +503,7 @@ ENTRY(ret_from_fork)
* nb: we depend on RESTORE_EXTRA_REGS above
*/
movq %rbp, %rdi
- call *%rbx
+ CALL_NOSPEC %rbx
movl $0, RAX(%rsp)
RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
@@ -1025,7 +1037,7 @@ idtentry async_page_fault do_async_page_fault has_error_code=1
#endif
#ifdef CONFIG_X86_MCE
-idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
+idtentry machine_check do_mce has_error_code=0 paranoid=1
#endif
/*
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/alternative.h b/arch/x86/include/asm/alternative.h
index d1cf17173b1b..215ea9214215 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -1,6 +1,8 @@
#ifndef _ASM_X86_ALTERNATIVE_H
#define _ASM_X86_ALTERNATIVE_H
+#ifndef __ASSEMBLY__
+
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/stringify.h>
@@ -271,4 +273,6 @@ extern void *text_poke(void *addr, const void *opcode, size_t len);
extern int poke_int3_handler(struct pt_regs *regs);
extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
new file mode 100644
index 000000000000..b15aa4083dfd
--- /dev/null
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -0,0 +1,41 @@
+#include <asm/ftrace.h>
+#include <asm/uaccess.h>
+#include <asm/string.h>
+#include <asm/page.h>
+#include <asm/checksum.h>
+
+#include <asm-generic/asm-prototypes.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/special_insns.h>
+#include <asm/preempt.h>
+#include <asm/asm.h>
+
+#ifndef CONFIG_X86_CMPXCHG64
+extern void cmpxchg8b_emu(void);
+#endif
+
+#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_X86_32
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void);
+#else
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void);
+INDIRECT_THUNK(8)
+INDIRECT_THUNK(9)
+INDIRECT_THUNK(10)
+INDIRECT_THUNK(11)
+INDIRECT_THUNK(12)
+INDIRECT_THUNK(13)
+INDIRECT_THUNK(14)
+INDIRECT_THUNK(15)
+#endif
+INDIRECT_THUNK(ax)
+INDIRECT_THUNK(bx)
+INDIRECT_THUNK(cx)
+INDIRECT_THUNK(dx)
+INDIRECT_THUNK(si)
+INDIRECT_THUNK(di)
+INDIRECT_THUNK(bp)
+INDIRECT_THUNK(sp)
+#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 1f16ec50abeb..817f67209568 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -106,4 +106,15 @@
/* For C file, we already have NOKPROBE_SYMBOL macro */
#endif
+#ifndef __ASSEMBLY__
+/*
+ * This output constraint should be used for any inline asm which has a "call"
+ * instruction. Otherwise the asm may be inserted before the frame pointer
+ * gets set up by the containing function. If you forget to do this, objtool
+ * may print a "call without frame pointer save/setup" warning.
+ */
+register unsigned long current_stack_pointer asm(_ASM_SP);
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
+#endif
+
#endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 142028afd049..641f0f2c2982 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -199,7 +199,10 @@
#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 */
/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
#define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
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/msr-index.h b/arch/x86/include/asm/msr-index.h
index 37db36fddc88..b8911aecf035 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -330,6 +330,9 @@
#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL
#define FAM10H_MMIO_CONF_BASE_SHIFT 20
#define MSR_FAM10H_NODE_ID 0xc001100c
+#define MSR_F10H_DECFG 0xc0011029
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
/* K8 MSRs */
#define MSR_K8_TOP_MEM1 0xc001001a
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
new file mode 100644
index 000000000000..492370b9b35b
--- /dev/null
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -0,0 +1,198 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __NOSPEC_BRANCH_H__
+#define __NOSPEC_BRANCH_H__
+
+#include <asm/alternative.h>
+#include <asm/alternative-asm.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Fill the CPU return stack buffer.
+ *
+ * Each entry in the RSB, if used for a speculative 'ret', contains an
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
+ *
+ * This is required in various cases for retpoline and IBRS-based
+ * mitigations for the Spectre variant 2 vulnerability. Sometimes to
+ * eliminate potentially bogus entries from the RSB, and sometimes
+ * purely to ensure that it doesn't get empty, which on some CPUs would
+ * allow predictions from other (unwanted!) sources to be used.
+ *
+ * We define a CPP macro such that it can be used from both .S files and
+ * inline assembly. It's possible to do a .macro and then include that
+ * from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
+ */
+
+#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */
+#define RSB_FILL_LOOPS 16 /* To avoid underflow */
+
+/*
+ * Google experimented with loop-unrolling and this turned out to be
+ * the optimal version — two calls, each with their own speculation
+ * trap should their return address end up getting used, in a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr, sp) \
+ mov $(nr/2), reg; \
+771: \
+ call 772f; \
+773: /* speculation trap */ \
+ pause; \
+ lfence; \
+ jmp 773b; \
+772: \
+ call 774f; \
+775: /* speculation trap */ \
+ pause; \
+ lfence; \
+ jmp 775b; \
+774: \
+ dec reg; \
+ jnz 771b; \
+ add $(BITS_PER_LONG/8) * nr, sp;
+
+#ifdef __ASSEMBLY__
+
+/*
+ * These are the bare retpoline primitives for indirect jmp and call.
+ * Do not use these directly; they only exist to make the ALTERNATIVE
+ * invocation below less ugly.
+ */
+.macro RETPOLINE_JMP reg:req
+ call .Ldo_rop_\@
+.Lspec_trap_\@:
+ pause
+ lfence
+ jmp .Lspec_trap_\@
+.Ldo_rop_\@:
+ mov \reg, (%_ASM_SP)
+ ret
+.endm
+
+/*
+ * This is a wrapper around RETPOLINE_JMP so the called function in reg
+ * returns to the instruction after the macro.
+ */
+.macro RETPOLINE_CALL reg:req
+ jmp .Ldo_call_\@
+.Ldo_retpoline_jmp_\@:
+ RETPOLINE_JMP \reg
+.Ldo_call_\@:
+ call .Ldo_retpoline_jmp_\@
+.endm
+
+/*
+ * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
+ * indirect jmp/call which may be susceptible to the Spectre variant 2
+ * attack.
+ */
+.macro JMP_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+ ALTERNATIVE_2 __stringify(jmp *\reg), \
+ __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \
+ __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+ jmp *\reg
+#endif
+.endm
+
+.macro CALL_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+ ALTERNATIVE_2 __stringify(call *\reg), \
+ __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
+ __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+ call *\reg
+#endif
+.endm
+
+ /*
+ * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
+ * monstrosity above, manually.
+ */
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
+#ifdef CONFIG_RETPOLINE
+ ALTERNATIVE "jmp .Lskip_rsb_\@", \
+ __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \
+ \ftr
+.Lskip_rsb_\@:
+#endif
+.endm
+
+#else /* __ASSEMBLY__ */
+
+#if defined(CONFIG_X86_64) && defined(RETPOLINE)
+
+/*
+ * Since the inline asm uses the %V modifier which is only in newer GCC,
+ * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE.
+ */
+# define CALL_NOSPEC \
+ ALTERNATIVE( \
+ "call *%[thunk_target]\n", \
+ "call __x86_indirect_thunk_%V[thunk_target]\n", \
+ X86_FEATURE_RETPOLINE)
+# define THUNK_TARGET(addr) [thunk_target] "r" (addr)
+
+#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE)
+/*
+ * For i386 we use the original ret-equivalent retpoline, because
+ * otherwise we'll run out of registers. We don't care about CET
+ * here, anyway.
+ */
+# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \
+ " jmp 904f;\n" \
+ " .align 16\n" \
+ "901: call 903f;\n" \
+ "902: pause;\n" \
+ " lfence;\n" \
+ " jmp 902b;\n" \
+ " .align 16\n" \
+ "903: addl $4, %%esp;\n" \
+ " pushl %[thunk_target];\n" \
+ " ret;\n" \
+ " .align 16\n" \
+ "904: call 901b;\n", \
+ X86_FEATURE_RETPOLINE)
+
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#else /* No retpoline for C / inline asm */
+# define CALL_NOSPEC "call *%[thunk_target]\n"
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#endif
+
+/* The Spectre V2 mitigation variants */
+enum spectre_v2_mitigation {
+ SPECTRE_V2_NONE,
+ SPECTRE_V2_RETPOLINE_MINIMAL,
+ SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
+ SPECTRE_V2_RETPOLINE_GENERIC,
+ SPECTRE_V2_RETPOLINE_AMD,
+ SPECTRE_V2_IBRS,
+};
+
+extern char __indirect_thunk_start[];
+extern char __indirect_thunk_end[];
+
+/*
+ * On VMEXIT we must ensure that no RSB predictions learned in the guest
+ * can be followed in the host, by overwriting the RSB completely. Both
+ * retpoline and IBRS mitigations for Spectre v2 need this; only on future
+ * CPUs with IBRS_ATT *might* it be avoided.
+ */
+static inline void vmexit_fill_RSB(void)
+{
+#ifdef CONFIG_RETPOLINE
+ unsigned long loops;
+
+ asm volatile (ALTERNATIVE("jmp 910f",
+ __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
+ X86_FEATURE_RETPOLINE)
+ "910:"
+ : "=r" (loops), ASM_CALL_CONSTRAINT
+ : : "memory" );
+#endif
+}
+
+#endif /* __ASSEMBLY__ */
+#endif /* __NOSPEC_BRANCH_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/traps.h b/arch/x86/include/asm/traps.h
index c3496619740a..156959ca49ce 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -92,6 +92,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *, long);
#endif
+dotraplinkage void do_mce(struct pt_regs *, long);
static inline int get_si_code(unsigned long condition)
{
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/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 85133b2b8e99..0977e7607046 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -44,6 +44,7 @@
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/smap.h>
+#include <asm/nospec-branch.h>
#include <xen/interface/xen.h>
#include <xen/interface/sched.h>
@@ -215,9 +216,9 @@ privcmd_call(unsigned call,
__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
stac();
- asm volatile("call *%[call]"
+ asm volatile(CALL_NOSPEC
: __HYPERCALL_5PARAM
- : [call] "a" (&hypercall_page[call])
+ : [thunk_target] "a" (&hypercall_page[call])
: __HYPERCALL_CLOBBER5);
clac();
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/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 0988e204f1e3..a41e523536a2 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -359,14 +359,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
irq_data->chip_data = data;
irq_data->hwirq = virq + i;
err = assign_irq_vector_policy(virq + i, node, data, info);
- if (err)
+ if (err) {
+ irq_data->chip_data = NULL;
+ free_apic_chip_data(data);
goto error;
+ }
}
return 0;
error:
- x86_vector_free_irqs(domain, virq, i + 1);
+ x86_vector_free_irqs(domain, virq, i);
return err;
}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e2defc7593a4..4bf9e77f3e05 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -746,8 +746,32 @@ static void init_amd(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_K8);
if (cpu_has_xmm2) {
- /* MFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+ unsigned long long val;
+ int ret;
+
+ /*
+ * A serializing LFENCE has less overhead than MFENCE, so
+ * use it for execution serialization. On families which
+ * don't have that MSR, LFENCE is already serializing.
+ * msr_set_bit() uses the safe accessors, too, even if the MSR
+ * is not present.
+ */
+ msr_set_bit(MSR_F10H_DECFG,
+ MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+
+ /*
+ * Verify that the MSR write was successful (could be running
+ * under a hypervisor) and only then assume that LFENCE is
+ * serializing.
+ */
+ ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
+ if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
+ /* A serializing LFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+ } else {
+ /* MFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+ }
}
/*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index cd46f9039119..8cacf62ec458 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -10,6 +10,9 @@
#include <linux/init.h>
#include <linux/utsname.h>
#include <linux/cpu.h>
+
+#include <asm/nospec-branch.h>
+#include <asm/cmdline.h>
#include <asm/bugs.h>
#include <asm/processor.h>
#include <asm/processor-flags.h>
@@ -19,17 +22,12 @@
#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);
void __init check_bugs(void)
{
-#ifdef CONFIG_X86_32
- /*
- * Regardless of whether PCID is enumerated, the SDM says
- * that it can't be enabled in 32-bit mode.
- */
- setup_clear_cpu_cap(X86_FEATURE_PCID);
-#endif
-
identify_boot_cpu();
if (!IS_ENABLED(CONFIG_SMP)) {
@@ -37,6 +35,9 @@ void __init check_bugs(void)
print_cpu_info(&boot_cpu_data);
}
+ /* Select the proper spectre mitigation before patching alternatives */
+ spectre_v2_select_mitigation();
+
#ifdef CONFIG_X86_32
/*
* Check whether we are able to run this kernel safely on SMP.
@@ -69,6 +70,188 @@ void __init check_bugs(void)
#endif
}
+/* The kernel command line selection */
+enum spectre_v2_mitigation_cmd {
+ SPECTRE_V2_CMD_NONE,
+ SPECTRE_V2_CMD_AUTO,
+ SPECTRE_V2_CMD_FORCE,
+ SPECTRE_V2_CMD_RETPOLINE,
+ SPECTRE_V2_CMD_RETPOLINE_GENERIC,
+ SPECTRE_V2_CMD_RETPOLINE_AMD,
+};
+
+static const char *spectre_v2_strings[] = {
+ [SPECTRE_V2_NONE] = "Vulnerable",
+ [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline",
+ [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline",
+ [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline",
+ [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline",
+};
+
+#undef pr_fmt
+#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt
+
+static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+
+static void __init spec2_print_if_insecure(const char *reason)
+{
+ if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+ pr_info("%s\n", reason);
+}
+
+static void __init spec2_print_if_secure(const char *reason)
+{
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+ pr_info("%s\n", reason);
+}
+
+static inline bool retp_compiler(void)
+{
+ return __is_defined(RETPOLINE);
+}
+
+static inline bool match_option(const char *arg, int arglen, const char *opt)
+{
+ int len = strlen(opt);
+
+ return len == arglen && !strncmp(arg, opt, len);
+}
+
+static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
+{
+ char arg[20];
+ int ret;
+
+ ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
+ sizeof(arg));
+ if (ret > 0) {
+ if (match_option(arg, ret, "off")) {
+ goto disable;
+ } else if (match_option(arg, ret, "on")) {
+ spec2_print_if_secure("force enabled on command line.");
+ return SPECTRE_V2_CMD_FORCE;
+ } else if (match_option(arg, ret, "retpoline")) {
+ spec2_print_if_insecure("retpoline selected on command line.");
+ return SPECTRE_V2_CMD_RETPOLINE;
+ } else if (match_option(arg, ret, "retpoline,amd")) {
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+ pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
+ return SPECTRE_V2_CMD_AUTO;
+ }
+ spec2_print_if_insecure("AMD retpoline selected on command line.");
+ return SPECTRE_V2_CMD_RETPOLINE_AMD;
+ } else if (match_option(arg, ret, "retpoline,generic")) {
+ spec2_print_if_insecure("generic retpoline selected on command line.");
+ return SPECTRE_V2_CMD_RETPOLINE_GENERIC;
+ } else if (match_option(arg, ret, "auto")) {
+ return SPECTRE_V2_CMD_AUTO;
+ }
+ }
+
+ if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+ return SPECTRE_V2_CMD_AUTO;
+disable:
+ spec2_print_if_insecure("disabled on command line.");
+ 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();
+ enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
+
+ /*
+ * If the CPU is not affected and the command line mode is NONE or AUTO
+ * then nothing to do.
+ */
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
+ (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO))
+ return;
+
+ switch (cmd) {
+ case SPECTRE_V2_CMD_NONE:
+ return;
+
+ case SPECTRE_V2_CMD_FORCE:
+ /* FALLTRHU */
+ case SPECTRE_V2_CMD_AUTO:
+ goto retpoline_auto;
+
+ case SPECTRE_V2_CMD_RETPOLINE_AMD:
+ if (IS_ENABLED(CONFIG_RETPOLINE))
+ goto retpoline_amd;
+ break;
+ case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
+ if (IS_ENABLED(CONFIG_RETPOLINE))
+ goto retpoline_generic;
+ break;
+ case SPECTRE_V2_CMD_RETPOLINE:
+ if (IS_ENABLED(CONFIG_RETPOLINE))
+ goto retpoline_auto;
+ break;
+ }
+ pr_err("kernel not compiled with retpoline; no mitigation available!");
+ return;
+
+retpoline_auto:
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ retpoline_amd:
+ if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
+ pr_err("LFENCE not serializing. Switching to generic retpoline\n");
+ goto retpoline_generic;
+ }
+ mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
+ SPECTRE_V2_RETPOLINE_MINIMAL_AMD;
+ setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);
+ setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+ } else {
+ retpoline_generic:
+ mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC :
+ SPECTRE_V2_RETPOLINE_MINIMAL;
+ setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+ }
+
+ 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
+
#ifdef CONFIG_SYSFS
ssize_t cpu_show_meltdown(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -93,6 +276,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
{
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
return sprintf(buf, "Not affected\n");
- return sprintf(buf, "Vulnerable\n");
+
+ return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]);
}
#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index dc4dfad66a70..f7f2ad3687ee 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -831,13 +831,21 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
- /* Assume for now that ALL x86 CPUs are insecure */
- setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+ if (c->x86_vendor != X86_VENDOR_AMD)
+ setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
fpu__init_system(c);
+
+#ifdef CONFIG_X86_32
+ /*
+ * Regardless of whether PCID is enumerated, the SDM says
+ * that it can't be enabled in 32-bit mode.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
+#endif
}
void __init early_cpu_init(void)
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/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7e8a736d09db..364fbad72e60 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1672,6 +1672,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code)
void (*machine_check_vector)(struct pt_regs *, long error_code) =
unexpected_machine_check;
+dotraplinkage void do_mce(struct pt_regs *regs, long error_code)
+{
+ machine_check_vector(regs, error_code);
+}
+
/*
* Called for each booted CPU to set up machine checks.
* Must be called with preempt off:
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/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 38da8f29a9c8..528b7aa1780d 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -20,6 +20,7 @@
#include <linux/mm.h>
#include <asm/apic.h>
+#include <asm/nospec-branch.h>
#ifdef CONFIG_DEBUG_STACKOVERFLOW
@@ -55,17 +56,17 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
static void call_on_stack(void *func, void *stack)
{
asm volatile("xchgl %%ebx,%%esp \n"
- "call *%%edi \n"
+ CALL_NOSPEC
"movl %%ebx,%%esp \n"
: "=b" (stack)
: "0" (stack),
- "D"(func)
+ [thunk_target] "D"(func)
: "memory", "cc", "edx", "ecx", "eax");
}
static inline void *current_stack(void)
{
- return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+ return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
}
static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
@@ -89,17 +90,17 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
/* Save the next esp at the bottom of the stack */
prev_esp = (u32 *)irqstk;
- *prev_esp = current_stack_pointer();
+ *prev_esp = current_stack_pointer;
if (unlikely(overflow))
call_on_stack(print_stack_overflow, isp);
asm volatile("xchgl %%ebx,%%esp \n"
- "call *%%edi \n"
+ CALL_NOSPEC
"movl %%ebx,%%esp \n"
: "=a" (arg1), "=b" (isp)
: "0" (desc), "1" (isp),
- "D" (desc->handle_irq)
+ [thunk_target] "D" (desc->handle_irq)
: "memory", "cc", "ecx");
return 1;
}
@@ -142,7 +143,7 @@ void do_softirq_own_stack(void)
/* Push the previous esp onto the stack */
prev_esp = (u32 *)irqstk;
- *prev_esp = current_stack_pointer();
+ *prev_esp = current_stack_pointer;
call_on_stack(__do_softirq, isp);
}
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index c9d488f3e4cd..ea8e2b846101 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -36,6 +36,7 @@
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/debugreg.h>
+#include <asm/nospec-branch.h>
#include "common.h"
@@ -191,7 +192,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
}
/* Check whether insn is indirect jump */
-static int insn_is_indirect_jump(struct insn *insn)
+static int __insn_is_indirect_jump(struct insn *insn)
{
return ((insn->opcode.bytes[0] == 0xff &&
(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
@@ -225,6 +226,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
return (start <= target && target <= start + len);
}
+static int insn_is_indirect_jump(struct insn *insn)
+{
+ int ret = __insn_is_indirect_jump(insn);
+
+#ifdef CONFIG_RETPOLINE
+ /*
+ * Jump to x86_indirect_thunk_* is treated as an indirect jump.
+ * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with
+ * older gcc may use indirect jump. So we add this check instead of
+ * replace indirect-jump check.
+ */
+ if (!ret)
+ ret = insn_jump_into_range(insn,
+ (unsigned long)__indirect_thunk_start,
+ (unsigned long)__indirect_thunk_end -
+ (unsigned long)__indirect_thunk_start);
+#endif
+ return ret;
+}
+
/* Decode whole function to ensure any instructions don't jump into target */
static int can_optimize(unsigned long paddr)
{
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 5d9afbcb6074..09284cfab86f 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -7,7 +7,7 @@
#include <linux/linkage.h>
#include <asm/ptrace.h>
#include <asm/ftrace.h>
-
+#include <asm/nospec-branch.h>
.code64
.section .entry.text, "ax"
@@ -285,8 +285,9 @@ trace:
* ip and parent ip are used and the list function is called when
* function tracing is enabled.
*/
- call *ftrace_trace_function
+ movq ftrace_trace_function, %r8
+ CALL_NOSPEC %r8
restore_mcount_regs
jmp fgraph_trace
@@ -329,5 +330,5 @@ GLOBAL(return_to_handler)
movq 8(%rsp), %rdx
movq (%rsp), %rax
addq $24, %rsp
- jmp *%rdi
+ JMP_NOSPEC %rdi
#endif
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 679302c312f8..22b81f35c500 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -166,7 +166,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
* from double_fault.
*/
BUG_ON((unsigned long)(current_top_of_stack() -
- current_stack_pointer()) >= THREAD_SIZE);
+ current_stack_pointer) >= THREAD_SIZE);
preempt_enable_no_resched();
}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 1d0e36f909eb..31355fb1a2cc 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -104,6 +104,13 @@ SECTIONS
SOFTIRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
+
+#ifdef CONFIG_RETPOLINE
+ __indirect_thunk_start = .;
+ *(.text.__x86.indirect_thunk)
+ __indirect_thunk_end = .;
+#endif
+
/* End of text section */
_etext = .;
} :text = 0x9090
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 900ffb6c28b5..2038e5bacce6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -37,6 +37,7 @@
#include <asm/desc.h>
#include <asm/debugreg.h>
#include <asm/kvm_para.h>
+#include <asm/nospec-branch.h>
#include <asm/virtext.h>
#include "trace.h"
@@ -3904,6 +3905,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
#endif
);
+ /* Eliminate branch target predictions from guest mode */
+ vmexit_fill_RSB();
+
#ifdef CONFIG_X86_64
wrmsrl(MSR_GS_BASE, svm->host.gs_base);
#else
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c26255f19603..75d60e40c389 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -47,6 +47,7 @@
#include <asm/kexec.h>
#include <asm/apic.h>
#include <asm/irq_remapping.h>
+#include <asm/nospec-branch.h>
#include "trace.h"
#include "pmu.h"
@@ -8701,6 +8702,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
#endif
);
+ /* Eliminate branch target predictions from guest mode */
+ vmexit_fill_RSB();
+
/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
if (debugctlmsr)
update_debugctlmsr(debugctlmsr);
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 2b6561d97a46..7f46ea66eeb6 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -24,6 +24,7 @@ lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
+lib-$(CONFIG_RETPOLINE) += retpoline.o
obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index c1e623209853..90353a26ed95 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -28,7 +28,8 @@
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/asm.h>
-
+#include <asm/nospec-branch.h>
+
/*
* computes a partial checksum, e.g. for TCP/UDP fragments
*/
@@ -155,7 +156,7 @@ ENTRY(csum_partial)
negl %ebx
lea 45f(%ebx,%ebx,2), %ebx
testl %esi, %esi
- jmp *%ebx
+ JMP_NOSPEC %ebx
# Handle 2-byte-aligned regions
20: addw (%esi), %ax
@@ -437,7 +438,7 @@ ENTRY(csum_partial_copy_generic)
andl $-32,%edx
lea 3f(%ebx,%ebx), %ebx
testl %esi, %esi
- jmp *%ebx
+ JMP_NOSPEC %ebx
1: addl $64,%esi
addl $64,%edi
SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl)
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/lib/retpoline.S b/arch/x86/lib/retpoline.S
new file mode 100644
index 000000000000..e611a124c442
--- /dev/null
+++ b/arch/x86/lib/retpoline.S
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/stringify.h>
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
+#include <asm-generic/export.h>
+#include <asm/nospec-branch.h>
+
+.macro THUNK reg
+ .section .text.__x86.indirect_thunk
+
+ENTRY(__x86_indirect_thunk_\reg)
+ CFI_STARTPROC
+ JMP_NOSPEC %\reg
+ CFI_ENDPROC
+ENDPROC(__x86_indirect_thunk_\reg)
+.endm
+
+/*
+ * Despite being an assembler file we can't just use .irp here
+ * because __KSYM_DEPS__ only uses the C preprocessor and would
+ * only see one instance of "__x86_indirect_thunk_\reg" rather
+ * than one per register with the correct names. So we do it
+ * the simple and nasty way...
+ */
+#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
+#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
+#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
+
+GENERATE_THUNK(_ASM_AX)
+GENERATE_THUNK(_ASM_BX)
+GENERATE_THUNK(_ASM_CX)
+GENERATE_THUNK(_ASM_DX)
+GENERATE_THUNK(_ASM_SI)
+GENERATE_THUNK(_ASM_DI)
+GENERATE_THUNK(_ASM_BP)
+GENERATE_THUNK(_ASM_SP)
+#ifdef CONFIG_64BIT
+GENERATE_THUNK(r8)
+GENERATE_THUNK(r9)
+GENERATE_THUNK(r10)
+GENERATE_THUNK(r11)
+GENERATE_THUNK(r12)
+GENERATE_THUNK(r13)
+GENERATE_THUNK(r14)
+GENERATE_THUNK(r15)
+#endif
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/ata/libata-core.c b/drivers/ata/libata-core.c
index b0b77b61c40c..69ec1c5d7152 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4143,6 +4143,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
* https://bugzilla.kernel.org/show_bug.cgi?id=121671
*/
{ "LITEON CX1-JB*-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 },
+ { "LITEON EP1-*", NULL, ATA_HORKAGE_MAX_SEC_1024 },
/* Devices we expect to fail diagnostics */
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/hv/hv.c b/drivers/hv/hv.c
index 8ce1f2e22912..d415a804fd26 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -31,6 +31,7 @@
#include <linux/clockchips.h>
#include <asm/hyperv.h>
#include <asm/mshyperv.h>
+#include <asm/nospec-branch.h>
#include "hyperv_vmbus.h"
/* The one and only */
@@ -103,9 +104,10 @@ static u64 do_hypercall(u64 control, void *input, void *output)
return (u64)ULLONG_MAX;
__asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8");
- __asm__ __volatile__("call *%3" : "=a" (hv_status) :
+ __asm__ __volatile__(CALL_NOSPEC :
+ "=a" (hv_status) :
"c" (control), "d" (input_address),
- "m" (hypercall_page));
+ THUNK_TARGET(hypercall_page));
return hv_status;
@@ -123,11 +125,12 @@ static u64 do_hypercall(u64 control, void *input, void *output)
if (!hypercall_page)
return (u64)ULLONG_MAX;
- __asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi),
+ __asm__ __volatile__ (CALL_NOSPEC : "=d"(hv_status_hi),
"=a"(hv_status_lo) : "d" (control_hi),
"a" (control_lo), "b" (input_address_hi),
"c" (input_address_lo), "D"(output_address_hi),
- "S"(output_address_lo), "m" (hypercall_page));
+ "S"(output_address_lo),
+ THUNK_TARGET(hypercall_page));
return hv_status_lo | ((u64)hv_status_hi << 32);
#endif /* !x86_64 */
diff --git a/drivers/input/misc/twl4030-vibra.c b/drivers/input/misc/twl4030-vibra.c
index 10c4e3d462f1..7233db002588 100644
--- a/drivers/input/misc/twl4030-vibra.c
+++ b/drivers/input/misc/twl4030-vibra.c
@@ -178,12 +178,14 @@ static SIMPLE_DEV_PM_OPS(twl4030_vibra_pm_ops,
twl4030_vibra_suspend, twl4030_vibra_resume);
static bool twl4030_vibra_check_coexist(struct twl4030_vibra_data *pdata,
- struct device_node *node)
+ struct device_node *parent)
{
+ struct device_node *node;
+
if (pdata && pdata->coexist)
return true;
- node = of_find_node_by_name(node, "codec");
+ node = of_get_child_by_name(parent, "codec");
if (node) {
of_node_put(node);
return true;
diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c
index ea63fad48de6..1e968ae37f60 100644
--- a/drivers/input/misc/twl6040-vibra.c
+++ b/drivers/input/misc/twl6040-vibra.c
@@ -262,7 +262,7 @@ static int twl6040_vibra_probe(struct platform_device *pdev)
int vddvibr_uV = 0;
int error;
- twl6040_core_node = of_find_node_by_name(twl6040_core_dev->of_node,
+ twl6040_core_node = of_get_child_by_name(twl6040_core_dev->of_node,
"vibra");
if (!twl6040_core_node) {
dev_err(&pdev->dev, "parent of node is missing?\n");
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/input/touchscreen/88pm860x-ts.c b/drivers/input/touchscreen/88pm860x-ts.c
index 251ff2aa0633..7a0dbce4dae9 100644
--- a/drivers/input/touchscreen/88pm860x-ts.c
+++ b/drivers/input/touchscreen/88pm860x-ts.c
@@ -126,7 +126,7 @@ static int pm860x_touch_dt_init(struct platform_device *pdev,
int data, n, ret;
if (!np)
return -ENODEV;
- np = of_find_node_by_name(np, "touch");
+ np = of_get_child_by_name(np, "touch");
if (!np) {
dev_err(&pdev->dev, "Can't find touch node\n");
return -EINVAL;
@@ -144,13 +144,13 @@ static int pm860x_touch_dt_init(struct platform_device *pdev,
if (data) {
ret = pm860x_reg_write(i2c, PM8607_GPADC_MISC1, data);
if (ret < 0)
- return -EINVAL;
+ goto err_put_node;
}
/* set tsi prebias time */
if (!of_property_read_u32(np, "marvell,88pm860x-tsi-prebias", &data)) {
ret = pm860x_reg_write(i2c, PM8607_TSI_PREBIAS, data);
if (ret < 0)
- return -EINVAL;
+ goto err_put_node;
}
/* set prebias & prechg time of pen detect */
data = 0;
@@ -161,10 +161,18 @@ static int pm860x_touch_dt_init(struct platform_device *pdev,
if (data) {
ret = pm860x_reg_write(i2c, PM8607_PD_PREBIAS, data);
if (ret < 0)
- return -EINVAL;
+ goto err_put_node;
}
of_property_read_u32(np, "marvell,88pm860x-resistor-X", res_x);
+
+ of_node_put(np);
+
return 0;
+
+err_put_node:
+ of_node_put(np);
+
+ return -EINVAL;
}
#else
#define pm860x_touch_dt_init(x, y, z) (-1)
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 3b67afda430b..e339f4288e8f 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -81,10 +81,14 @@
#define SECTOR_TO_BLOCK_SHIFT 3
/*
+ * For btree insert:
* 3 for btree insert +
* 2 for btree lookup used within space map
+ * For btree remove:
+ * 2 for shadow spine +
+ * 4 for rebalance 3 child node
*/
-#define THIN_MAX_CONCURRENT_LOCKS 5
+#define THIN_MAX_CONCURRENT_LOCKS 6
/* This should be plenty */
#define SPACE_MAP_ROOT_SIZE 128
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index a1a68209bd36..880b7dee9c52 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -671,23 +671,8 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
pn->keys[1] = rn->keys[0];
memcpy_disk(value_ptr(pn, 1), &val, sizeof(__le64));
- /*
- * rejig the spine. This is ugly, since it knows too
- * much about the spine
- */
- if (s->nodes[0] != new_parent) {
- unlock_block(s->info, s->nodes[0]);
- s->nodes[0] = new_parent;
- }
- if (key < le64_to_cpu(rn->keys[0])) {
- unlock_block(s->info, right);
- s->nodes[1] = left;
- } else {
- unlock_block(s->info, left);
- s->nodes[1] = right;
- }
- s->count = 2;
-
+ unlock_block(s->info, left);
+ unlock_block(s->info, right);
return 0;
}
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/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index ce44a033f63b..64cc86a82b2d 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -184,7 +184,7 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail)
void *cmd_head = pcan_usb_fd_cmd_buffer(dev);
int err = 0;
u8 *packet_ptr;
- int i, n = 1, packet_len;
+ int packet_len;
ptrdiff_t cmd_len;
/* usb device unregistered? */
@@ -201,17 +201,13 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail)
}
packet_ptr = cmd_head;
+ packet_len = cmd_len;
/* firmware is not able to re-assemble 512 bytes buffer in full-speed */
- if ((dev->udev->speed != USB_SPEED_HIGH) &&
- (cmd_len > PCAN_UFD_LOSPD_PKT_SIZE)) {
- packet_len = PCAN_UFD_LOSPD_PKT_SIZE;
- n += cmd_len / packet_len;
- } else {
- packet_len = cmd_len;
- }
+ if (unlikely(dev->udev->speed != USB_SPEED_HIGH))
+ packet_len = min(packet_len, PCAN_UFD_LOSPD_PKT_SIZE);
- for (i = 0; i < n; i++) {
+ do {
err = usb_bulk_msg(dev->udev,
usb_sndbulkpipe(dev->udev,
PCAN_USBPRO_EP_CMDOUT),
@@ -224,7 +220,12 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail)
}
packet_ptr += packet_len;
- }
+ cmd_len -= packet_len;
+
+ if (cmd_len < PCAN_UFD_LOSPD_PKT_SIZE)
+ packet_len = cmd_len;
+
+ } while (packet_len > 0);
return err;
}
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/phy/phy-core.c b/drivers/phy/phy-core.c
index e7e574dc667a..be1f0276ab23 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -365,6 +365,10 @@ static struct phy *_of_phy_get(struct device_node *np, int index)
if (ret)
return ERR_PTR(-ENODEV);
+ /* This phy type handled by the usb-phy subsystem for now */
+ if (of_device_is_compatible(args.np, "usb-nop-xceiv"))
+ return ERR_PTR(-ENODEV);
+
mutex_lock(&phy_provider_mutex);
phy_provider = of_phy_provider_lookup(args.np);
if (IS_ERR(phy_provider) || !try_module_get(phy_provider->owner)) {
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 0c87f341fed4..910b795fc5eb 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -3638,6 +3638,7 @@ static int hpsa_update_device_info(struct ctlr_info *h,
if (h->fw_support & MISC_FW_RAID_OFFLOAD_BASIC)
hpsa_get_ioaccel_status(h, scsi3addr, this_device);
volume_offline = hpsa_volume_offline(h, scsi3addr);
+ this_device->volume_offline = volume_offline;
if (volume_offline == HPSA_LV_FAILED) {
rc = HPSA_LV_FAILED;
dev_err(&h->pdev->dev,
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/scsi/sg.c b/drivers/scsi/sg.c
index 38f77e127349..0f0ff75755e0 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -160,7 +160,6 @@ typedef struct sg_fd { /* holds the state of a file descriptor */
struct list_head rq_list; /* head of request list */
struct fasync_struct *async_qp; /* used by asynchronous notification */
Sg_request req_arr[SG_MAX_QUEUE]; /* used as singly-linked list */
- char low_dma; /* as in parent but possibly overridden to 1 */
char force_packid; /* 1 -> pack_id input to read(), 0 -> ignored */
char cmd_q; /* 1 -> allow command queuing, 0 -> don't */
unsigned char next_cmd_len; /* 0: automatic, >0: use on next write() */
@@ -932,24 +931,14 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
/* strange ..., for backward compatibility */
return sfp->timeout_user;
case SG_SET_FORCE_LOW_DMA:
- result = get_user(val, ip);
- if (result)
- return result;
- if (val) {
- sfp->low_dma = 1;
- if ((0 == sfp->low_dma) && !sfp->res_in_use) {
- val = (int) sfp->reserve.bufflen;
- sg_remove_scat(sfp, &sfp->reserve);
- sg_build_reserve(sfp, val);
- }
- } else {
- if (atomic_read(&sdp->detaching))
- return -ENODEV;
- sfp->low_dma = sdp->device->host->unchecked_isa_dma;
- }
+ /*
+ * N.B. This ioctl never worked properly, but failed to
+ * return an error value. So returning '0' to keep compability
+ * with legacy applications.
+ */
return 0;
case SG_GET_LOW_DMA:
- return put_user((int) sfp->low_dma, ip);
+ return put_user((int) sdp->device->host->unchecked_isa_dma, ip);
case SG_GET_SCSI_ID:
if (!access_ok(VERIFY_WRITE, p, sizeof (sg_scsi_id_t)))
return -EFAULT;
@@ -1870,6 +1859,7 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
int sg_tablesize = sfp->parentdp->sg_tablesize;
int blk_size = buff_size, order;
gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN;
+ struct sg_device *sdp = sfp->parentdp;
if (blk_size < 0)
return -EFAULT;
@@ -1895,7 +1885,7 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
scatter_elem_sz_prev = num;
}
- if (sfp->low_dma)
+ if (sdp->device->host->unchecked_isa_dma)
gfp_mask |= GFP_DMA;
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
@@ -2158,8 +2148,6 @@ sg_add_sfp(Sg_device * sdp)
sfp->timeout = SG_DEFAULT_TIMEOUT;
sfp->timeout_user = SG_DEFAULT_TIMEOUT_USER;
sfp->force_packid = SG_DEF_FORCE_PACK_ID;
- sfp->low_dma = (SG_DEF_FORCE_LOW_DMA == 0) ?
- sdp->device->host->unchecked_isa_dma : 1;
sfp->cmd_q = SG_DEF_COMMAND_Q;
sfp->keep_orphan = SG_DEF_KEEP_ORPHAN;
sfp->parentdp = sdp;
@@ -2618,7 +2606,7 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
jiffies_to_msecs(fp->timeout),
fp->reserve.bufflen,
(int) fp->reserve.k_use_sg,
- (int) fp->low_dma);
+ (int) sdp->device->host->unchecked_isa_dma);
seq_printf(s, " cmd_q=%d f_packid=%d k_orphan=%d closed=0\n",
(int) fp->cmd_q, (int) fp->force_packid,
(int) fp->keep_orphan);
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:
@@ -225,6 +215,24 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
}
/*
+ * 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.
*
* dir->i_mutex: down
@@ -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/pipe.c b/fs/pipe.c
index ab8dad3ccb6a..39eff9a67253 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1001,6 +1001,9 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
{
struct pipe_buffer *bufs;
+ if (!nr_pages)
+ return -EINVAL;
+
/*
* We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't
* expect a lot of shrink+grow operations, just free and allocate
@@ -1045,13 +1048,19 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
/*
* Currently we rely on the pipe array holding a power-of-2 number
- * of pages.
+ * of pages. Returns 0 on error.
*/
static inline unsigned int round_pipe_size(unsigned int size)
{
unsigned long nr_pages;
+ if (size < pipe_min_size)
+ size = pipe_min_size;
+
nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (nr_pages == 0)
+ return 0;
+
return roundup_pow_of_two(nr_pages) << PAGE_SHIFT;
}
@@ -1062,13 +1071,18 @@ static inline unsigned int round_pipe_size(unsigned int size)
int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf,
size_t *lenp, loff_t *ppos)
{
+ unsigned int rounded_pipe_max_size;
int ret;
ret = proc_dointvec_minmax(table, write, buf, lenp, ppos);
if (ret < 0 || !write)
return ret;
- pipe_max_size = round_pipe_size(pipe_max_size);
+ rounded_pipe_max_size = round_pipe_size(pipe_max_size);
+ if (rounded_pipe_max_size == 0)
+ return -EINVAL;
+
+ pipe_max_size = rounded_pipe_max_size;
return ret;
}
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 09e71a00a9b8..3d38808dbcb6 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/asm-generic/asm-prototypes.h b/include/asm-generic/asm-prototypes.h
new file mode 100644
index 000000000000..df13637e4017
--- /dev/null
+++ b/include/asm-generic/asm-prototypes.h
@@ -0,0 +1,7 @@
+#include <linux/bitops.h>
+extern void *__memset(void *, int, __kernel_size_t);
+extern void *__memcpy(void *, const void *, __kernel_size_t);
+extern void *__memmove(void *, const void *, __kernel_size_t);
+extern void *memset(void *, int, __kernel_size_t);
+extern void *memcpy(void *, const void *, __kernel_size_t);
+extern void *memmove(void *, const void *, __kernel_size_t);
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
new file mode 100644
index 000000000000..43199a049da5
--- /dev/null
+++ b/include/asm-generic/export.h
@@ -0,0 +1,94 @@
+#ifndef __ASM_GENERIC_EXPORT_H
+#define __ASM_GENERIC_EXPORT_H
+
+#ifndef KSYM_FUNC
+#define KSYM_FUNC(x) x
+#endif
+#ifdef CONFIG_64BIT
+#define __put .quad
+#ifndef KSYM_ALIGN
+#define KSYM_ALIGN 8
+#endif
+#ifndef KCRC_ALIGN
+#define KCRC_ALIGN 8
+#endif
+#else
+#define __put .long
+#ifndef KSYM_ALIGN
+#define KSYM_ALIGN 4
+#endif
+#ifndef KCRC_ALIGN
+#define KCRC_ALIGN 4
+#endif
+#endif
+
+#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
+#define KSYM(name) _##name
+#else
+#define KSYM(name) name
+#endif
+
+/*
+ * note on .section use: @progbits vs %progbits nastiness doesn't matter,
+ * since we immediately emit into those sections anyway.
+ */
+.macro ___EXPORT_SYMBOL name,val,sec
+#ifdef CONFIG_MODULES
+ .globl KSYM(__ksymtab_\name)
+ .section ___ksymtab\sec+\name,"a"
+ .balign KSYM_ALIGN
+KSYM(__ksymtab_\name):
+ __put \val, KSYM(__kstrtab_\name)
+ .previous
+ .section __ksymtab_strings,"a"
+KSYM(__kstrtab_\name):
+#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
+ .asciz "_\name"
+#else
+ .asciz "\name"
+#endif
+ .previous
+#ifdef CONFIG_MODVERSIONS
+ .section ___kcrctab\sec+\name,"a"
+ .balign KCRC_ALIGN
+KSYM(__kcrctab_\name):
+ __put KSYM(__crc_\name)
+ .weak KSYM(__crc_\name)
+ .previous
+#endif
+#endif
+.endm
+#undef __put
+
+#if defined(__KSYM_DEPS__)
+
+#define __EXPORT_SYMBOL(sym, val, sec) === __KSYM_##sym ===
+
+#elif defined(CONFIG_TRIM_UNUSED_KSYMS)
+
+#include <linux/kconfig.h>
+#include <generated/autoksyms.h>
+
+#define __EXPORT_SYMBOL(sym, val, sec) \
+ __cond_export_sym(sym, val, sec, config_enabled(__KSYM_##sym))
+#define __cond_export_sym(sym, val, sec, conf) \
+ ___cond_export_sym(sym, val, sec, conf)
+#define ___cond_export_sym(sym, val, sec, enabled) \
+ __cond_export_sym_##enabled(sym, val, sec)
+#define __cond_export_sym_1(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
+#define __cond_export_sym_0(sym, val, sec) /* nothing */
+
+#else
+#define __EXPORT_SYMBOL(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
+#endif
+
+#define EXPORT_SYMBOL(name) \
+ __EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)),)
+#define EXPORT_SYMBOL_GPL(name) \
+ __EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)), _gpl)
+#define EXPORT_DATA_SYMBOL(name) \
+ __EXPORT_SYMBOL(name, KSYM(name),)
+#define EXPORT_DATA_SYMBOL_GPL(name) \
+ __EXPORT_SYMBOL(name, KSYM(name),_gpl)
+
+#endif
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/kconfig.h b/include/linux/kconfig.h
index b33c7797eb57..a94b5bf57f51 100644
--- a/include/linux/kconfig.h
+++ b/include/linux/kconfig.h
@@ -17,10 +17,11 @@
* the last step cherry picks the 2nd arg, we get a zero.
*/
#define __ARG_PLACEHOLDER_1 0,
-#define config_enabled(cfg) _config_enabled(cfg)
-#define _config_enabled(value) __config_enabled(__ARG_PLACEHOLDER_##value)
-#define __config_enabled(arg1_or_junk) ___config_enabled(arg1_or_junk 1, 0)
-#define ___config_enabled(__ignored, val, ...) val
+#define config_enabled(cfg) ___is_defined(cfg)
+#define __is_defined(x) ___is_defined(x)
+#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0)
+#define __take_second_arg(__ignored, val, ...) val
/*
* IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
@@ -42,7 +43,7 @@
* built-in code when CONFIG_FOO is set to 'm'.
*/
#define IS_REACHABLE(option) (config_enabled(option) || \
- (config_enabled(option##_MODULE) && config_enabled(MODULE)))
+ (config_enabled(option##_MODULE) && __is_defined(MODULE)))
/*
* IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm',
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
@@ -64,6 +64,13 @@ static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs)
({ (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 de6b3edd835b..4645017c6a24 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1456,6 +1456,7 @@ 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/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/scsi/sg.h b/include/scsi/sg.h
index 3afec7032448..20bc71c3e0b8 100644
--- a/include/scsi/sg.h
+++ b/include/scsi/sg.h
@@ -197,7 +197,6 @@ typedef struct sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */
#define SG_DEFAULT_RETRIES 0
/* Defaults, commented if they differ from original sg driver */
-#define SG_DEF_FORCE_LOW_DMA 0 /* was 1 -> memory below 16MB on i386 */
#define SG_DEF_FORCE_PACK_ID 0
#define SG_DEF_KEEP_ORPHAN 0
#define SG_DEF_RESERVED_SIZE SG_SCATTER_SZ /* load time option */
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/futex.c b/kernel/futex.c
index d3e7120f1c33..a09c1dd1f659 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1621,6 +1621,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
struct futex_q *this, *next;
WAKE_Q(wake_q);
+ if (nr_wake < 0 || nr_requeue < 0)
+ return -EINVAL;
+
if (requeue_pi) {
/*
* Requeue PI only works on two distinct uaddrs. This
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index c92e44855ddd..1276aabaab55 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -37,6 +37,7 @@ config ARCH_HAS_GCOV_PROFILE_ALL
config GCOV_PROFILE_ALL
bool "Profile entire Kernel"
+ depends on !COMPILE_TEST
depends on GCOV_KERNEL
depends on ARCH_HAS_GCOV_PROFILE_ALL
default n
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6681abbf2c18..fcb7887dacea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2158,6 +2158,7 @@ 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;
@@ -3767,6 +3768,7 @@ __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 0d0c8e954861..5c6ffddcafcd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -500,13 +500,84 @@ 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)
@@ -528,6 +599,14 @@ 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;
}
@@ -755,6 +834,8 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
return;
dl_se->dl_throttled = 1;
+ if (dl_se->runtime > 0)
+ dl_se->runtime = 0;
}
}
@@ -1015,11 +1096,6 @@ 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);
@@ -1051,7 +1127,7 @@ 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 405536b22c0c..227ea8166a83 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 f575785c7cd8..523fe1669d4c 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/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 996f0fd34312..ba5392807912 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2300,6 +2300,7 @@ void trace_event_enum_update(struct trace_enum_map **map, int len)
{
struct trace_event_call *call, *p;
const char *last_system = NULL;
+ bool first = false;
int last_i;
int i;
@@ -2307,15 +2308,28 @@ void trace_event_enum_update(struct trace_enum_map **map, int len)
list_for_each_entry_safe(call, p, &ftrace_events, list) {
/* events are usually grouped together with systems */
if (!last_system || call->class->system != last_system) {
+ first = true;
last_i = 0;
last_system = call->class->system;
}
+ /*
+ * Since calls are grouped by systems, the likelyhood that the
+ * next call in the iteration belongs to the same system as the
+ * previous call is high. As an optimization, we skip seaching
+ * for a map[] that matches the call's system if the last call
+ * was from the same system. That's what last_i is for. If the
+ * call has the same system as the previous call, then last_i
+ * will be the index of the first map[] that has a matching
+ * system.
+ */
for (i = last_i; i < len; i++) {
if (call->class->system == map[i]->system) {
/* Save the first system if need be */
- if (!last_i)
+ if (first) {
last_i = i;
+ first = false;
+ }
update_event_printk(call, map[i]);
}
}
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 a399f3056ad7..9c9ae859fbbb 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2209,7 +2209,8 @@ 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? */
@@ -2294,7 +2295,8 @@ 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 692c0377ac77..15d86c744f97 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2473,9 +2473,6 @@ 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;
@@ -2487,6 +2484,9 @@ 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;
@@ -720,6 +722,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
}
return ret;
+ out_free:
+ kvfree(offsets);
+ return ret;
}
static void get_counters(const struct xt_table_info *t,
@@ -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;
@@ -885,6 +887,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
}
return ret;
+ out_free:
+ kvfree(offsets);
+ return ret;
}
static void
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 34b5bf9e7406..11133e63cd77 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;
@@ -897,6 +899,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
}
return ret;
+ out_free:
+ kvfree(offsets);
+ return ret;
}
static void
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/key/af_key.c b/net/key/af_key.c
index 94bf810ad242..6482b001f19a 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -401,6 +401,11 @@ static int verify_address_len(const void *p)
#endif
int len;
+ if (sp->sadb_address_len <
+ DIV_ROUND_UP(sizeof(*sp) + offsetofend(typeof(*addr), sa_family),
+ sizeof(uint64_t)))
+ return -EINVAL;
+
switch (addr->sa_family) {
case AF_INET:
len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t));
@@ -511,6 +516,9 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void *
uint16_t ext_type;
int ext_len;
+ if (len < sizeof(*ehdr))
+ return -EINVAL;
+
ext_len = ehdr->sadb_ext_len;
ext_len *= sizeof(uint64_t);
ext_type = ehdr->sadb_ext_type;
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/scripts/Makefile.build b/scripts/Makefile.build
index 411281c36898..42aef001dfdd 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -158,7 +158,8 @@ cmd_cc_i_c = $(CPP) $(c_flags) -o $@ $<
$(obj)/%.i: $(src)/%.c FORCE
$(call if_changed_dep,cc_i_c)
-cmd_gensymtypes = \
+# These mirror gensymtypes_S and co below, keep them in synch.
+cmd_gensymtypes_c = \
$(CPP) -D__GENKSYMS__ $(c_flags) $< | \
$(GENKSYMS) $(if $(1), -T $(2)) \
$(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \
@@ -168,7 +169,7 @@ cmd_gensymtypes = \
quiet_cmd_cc_symtypes_c = SYM $(quiet_modtag) $@
cmd_cc_symtypes_c = \
set -e; \
- $(call cmd_gensymtypes,true,$@) >/dev/null; \
+ $(call cmd_gensymtypes_c,true,$@) >/dev/null; \
test -s $@ || rm -f $@
$(obj)/%.symtypes : $(src)/%.c FORCE
@@ -205,9 +206,10 @@ else
# the actual value of the checksum generated by genksyms
cmd_cc_o_c = $(CC) $(c_flags) -c -o $(@D)/.tmp_$(@F) $<
-cmd_modversions = \
+
+cmd_modversions_c = \
if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \
- $(call cmd_gensymtypes,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \
+ $(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \
> $(@D)/.tmp_$(@F:.o=.ver); \
\
$(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) \
@@ -252,7 +254,7 @@ endif
define rule_cc_o_c
$(call echo-cmd,checksrc) $(cmd_checksrc) \
$(call echo-cmd,cc_o_c) $(cmd_cc_o_c); \
- $(cmd_modversions) \
+ $(cmd_modversions_c) \
$(call echo-cmd,record_mcount) \
$(cmd_record_mcount) \
scripts/basic/fixdep $(depfile) $@ '$(call make-cmd,cc_o_c)' > \
@@ -261,6 +263,15 @@ define rule_cc_o_c
mv -f $(dot-target).tmp $(dot-target).cmd
endef
+define rule_as_o_S
+ $(call echo-cmd,as_o_S) $(cmd_as_o_S); \
+ scripts/basic/fixdep $(depfile) $@ '$(call make-cmd,as_o_S)' > \
+ $(dot-target).tmp; \
+ $(cmd_modversions_S) \
+ rm -f $(depfile); \
+ mv -f $(dot-target).tmp $(dot-target).cmd
+endef
+
# Built-in and composite module parts
$(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE
$(call cmd,force_checksrc)
@@ -289,6 +300,38 @@ modkern_aflags := $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL)
$(real-objs-m) : modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE)
$(real-objs-m:.o=.s): modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE)
+# .S file exports must have their C prototypes defined in asm/asm-prototypes.h
+# or a file that it includes, in order to get versioned symbols. We build a
+# dummy C file that includes asm-prototypes and the EXPORT_SYMBOL lines from
+# the .S file (with trailing ';'), and run genksyms on that, to extract vers.
+#
+# This is convoluted. The .S file must first be preprocessed to run guards and
+# expand names, then the resulting exports must be constructed into plain
+# EXPORT_SYMBOL(symbol); to build our dummy C file, and that gets preprocessed
+# to make the genksyms input.
+#
+# These mirror gensymtypes_c and co above, keep them in synch.
+cmd_gensymtypes_S = \
+ (echo "\#include <linux/kernel.h>" ; \
+ echo "\#include <asm/asm-prototypes.h>" ; \
+ $(CPP) $(a_flags) $< | \
+ grep "\<___EXPORT_SYMBOL\>" | \
+ sed 's/.*___EXPORT_SYMBOL[[:space:]]*\([a-zA-Z0-9_]*\)[[:space:]]*,.*/EXPORT_SYMBOL(\1);/' ) | \
+ $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | \
+ $(GENKSYMS) $(if $(1), -T $(2)) \
+ $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \
+ $(if $(KBUILD_PRESERVE),-p) \
+ -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null))
+
+quiet_cmd_cc_symtypes_S = SYM $(quiet_modtag) $@
+cmd_cc_symtypes_S = \
+ set -e; \
+ $(call cmd_gensymtypes_S,true,$@) >/dev/null; \
+ test -s $@ || rm -f $@
+
+$(obj)/%.symtypes : $(src)/%.S FORCE
+ $(call cmd,cc_symtypes_S)
+
quiet_cmd_as_s_S = CPP $(quiet_modtag) $@
cmd_as_s_S = $(CPP) $(a_flags) -o $@ $<
@@ -296,10 +339,40 @@ $(obj)/%.s: $(src)/%.S FORCE
$(call if_changed_dep,as_s_S)
quiet_cmd_as_o_S = AS $(quiet_modtag) $@
-cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $<
+
+ifndef CONFIG_MODVERSIONS
+cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $<
+
+else
+
+ASM_PROTOTYPES := $(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/asm-prototypes.h)
+
+ifeq ($(ASM_PROTOTYPES),)
+cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $<
+
+else
+
+# versioning matches the C process described above, with difference that
+# we parse asm-prototypes.h C header to get function definitions.
+
+cmd_as_o_S = $(CC) $(a_flags) -c -o $(@D)/.tmp_$(@F) $<
+
+cmd_modversions_S = \
+ if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \
+ $(call cmd_gensymtypes_S,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \
+ > $(@D)/.tmp_$(@F:.o=.ver); \
+ \
+ $(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) \
+ -T $(@D)/.tmp_$(@F:.o=.ver); \
+ rm -f $(@D)/.tmp_$(@F) $(@D)/.tmp_$(@F:.o=.ver); \
+ else \
+ mv -f $(@D)/.tmp_$(@F) $@; \
+ fi;
+endif
+endif
$(obj)/%.o: $(src)/%.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
targets += $(real-objs-y) $(real-objs-m) $(lib-y)
targets += $(extra-y) $(MAKECMDGOALS) $(always)
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 7b805766306e..4c145d6bccd4 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -578,7 +578,6 @@ static inline unsigned int muldiv32(unsigned int a, unsigned int b,
{
u_int64_t n = (u_int64_t) a * b;
if (c == 0) {
- snd_BUG_ON(!n);
*r = 0;
return UINT_MAX;
}
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 80bbadc83721..d6e079f4ec09 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -408,6 +408,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = {
/*SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),*/
/* codec SSID */
+ SND_PCI_QUIRK(0x106b, 0x0600, "iMac 14,1", CS420X_IMAC27_122),
SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81),
SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122),
SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 5875a08d555e..f14c1f288443 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5600,6 +5600,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
+ SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
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;