Merge branch 'WIP.x86/fpu' into x86/fpu, because it's ready
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt b/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt
index a135504..cac24ee 100644
--- a/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt
+++ b/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt
@@ -32,7 +32,7 @@
compatible = "st,stm32h743-rcc", "st,stm32-rcc";
reg = <0x58024400 0x400>;
#reset-cells = <1>;
- #clock-cells = <2>;
+ #clock-cells = <1>;
clocks = <&clk_hse>, <&clk_lse>, <&clk_i2s_ckin>;
st,syscfg = <&pwrcfg>;
diff --git a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt b/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt
index 3eca6de..a65d7b7 100644
--- a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt
+++ b/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt
@@ -8,6 +8,12 @@
the firmware event log
- linux,sml-size : size of the memory allocated for the firmware event log
+Optional properties:
+
+- powered-while-suspended: present when the TPM is left powered on between
+ suspend and resume (makes the suspend/resume
+ callbacks do nothing).
+
Example (for OpenPower Systems with Nuvoton TPM 2.0 on I2C)
----------------------------------------------------------
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 1ea1fd4..1afd298 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -3,8 +3,8 @@
This isn't an exhaustive list, but you should add new prefixes to it before
using them to avoid name-space collisions.
-abcn Abracon Corporation
abilis Abilis Systems
+abracon Abracon Corporation
actions Actions Semiconductor Co., Ltd.
active-semi Active-Semi International Inc
ad Avionic Design GmbH
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index b3345d0..77f4de5 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1680,6 +1680,9 @@
2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
link-local address has been found.
+ DAD operation and mode on a given interface will be selected according
+ to the maximum value of conf/{all,interface}/accept_dad.
+
force_tllao - BOOLEAN
Enable sending the target link-layer address option even when
responding to a unicast neighbor solicitation.
@@ -1727,16 +1730,23 @@
optimistic_dad - BOOLEAN
Whether to perform Optimistic Duplicate Address Detection (RFC 4429).
- 0: disabled (default)
- 1: enabled
+ 0: disabled (default)
+ 1: enabled
+
+ Optimistic Duplicate Address Detection for the interface will be enabled
+ if at least one of conf/{all,interface}/optimistic_dad is set to 1,
+ it will be disabled otherwise.
use_optimistic - BOOLEAN
If enabled, do not classify optimistic addresses as deprecated during
source address selection. Preferred addresses will still be chosen
before optimistic addresses, subject to other ranking in the source
address selection algorithm.
- 0: disabled (default)
- 1: enabled
+ 0: disabled (default)
+ 1: enabled
+
+ This will be enabled if at least one of
+ conf/{all,interface}/use_optimistic is set to 1, disabled otherwise.
stable_secret - IPv6 address
This IPv6 address will be used as a secret to generate IPv6
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
index 5e40e1f..82236a1 100644
--- a/Documentation/networking/switchdev.txt
+++ b/Documentation/networking/switchdev.txt
@@ -13,42 +13,42 @@
with SR-IOV or soft switches, such as OVS, are possible.
- User-space tools
+ User-space tools
- user space |
- +-------------------------------------------------------------------+
- kernel | Netlink
- |
- +--------------+-------------------------------+
- | Network stack |
- | (Linux) |
- | |
- +----------------------------------------------+
+ user space |
+ +-------------------------------------------------------------------+
+ kernel | Netlink
+ |
+ +--------------+-------------------------------+
+ | Network stack |
+ | (Linux) |
+ | |
+ +----------------------------------------------+
sw1p2 sw1p4 sw1p6
- sw1p1 + sw1p3 + sw1p5 + eth1
- + | + | + | +
- | | | | | | |
- +--+----+----+----+-+--+----+---+ +-----+-----+
- | Switch driver | | mgmt |
- | (this document) | | driver |
- | | | |
- +--------------+----------------+ +-----------+
- |
- kernel | HW bus (eg PCI)
- +-------------------------------------------------------------------+
- hardware |
- +--------------+---+------------+
- | Switch device (sw1) |
- | +----+ +--------+
- | | v offloaded data path | mgmt port
- | | | |
- +--|----|----+----+----+----+---+
- | | | | | |
- + + + + + +
- p1 p2 p3 p4 p5 p6
+ sw1p1 + sw1p3 + sw1p5 + eth1
+ + | + | + | +
+ | | | | | | |
+ +--+----+----+----+----+----+---+ +-----+-----+
+ | Switch driver | | mgmt |
+ | (this document) | | driver |
+ | | | |
+ +--------------+----------------+ +-----------+
+ |
+ kernel | HW bus (eg PCI)
+ +-------------------------------------------------------------------+
+ hardware |
+ +--------------+----------------+
+ | Switch device (sw1) |
+ | +----+ +--------+
+ | | v offloaded data path | mgmt port
+ | | | |
+ +--|----|----+----+----+----+---+
+ | | | | | |
+ + + + + + +
+ p1 p2 p3 p4 p5 p6
- front-panel ports
+ front-panel ports
Fig 1.
diff --git a/MAINTAINERS b/MAINTAINERS
index fa4e916..6671f37 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2865,7 +2865,6 @@
F: drivers/scsi/bnx2i/
BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-M: Yuval Mintz <Yuval.Mintz@cavium.com>
M: Ariel Elior <ariel.elior@cavium.com>
M: everest-linux-l2@cavium.com
L: netdev@vger.kernel.org
@@ -6655,8 +6654,8 @@
M: Stefan Schmidt <stefan@osg.samsung.com>
L: linux-wpan@vger.kernel.org
W: http://wpan.cakelab.org/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth.git
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan-next.git
S: Maintained
F: net/ieee802154/
F: net/mac802154/
@@ -11059,7 +11058,6 @@
F: drivers/scsi/qedi/
QLOGIC QL4xxx ETHERNET DRIVER
-M: Yuval Mintz <Yuval.Mintz@cavium.com>
M: Ariel Elior <Ariel.Elior@cavium.com>
M: everest-linux-l2@cavium.com
L: netdev@vger.kernel.org
diff --git a/Makefile b/Makefile
index 64cbc66..d111994 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 4
PATCHLEVEL = 14
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
NAME = Fearless Coyote
# *DOCUMENTATION*
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 1d468b5..776757d 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -139,11 +139,10 @@
#define TIF_NEED_RESCHED 1 /* rescheduling necessary */
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_UPROBE 3 /* breakpointed or singlestepping */
-#define TIF_FSCHECK 4 /* Check FS is USER_DS on return */
-#define TIF_SYSCALL_TRACE 5 /* syscall trace active */
-#define TIF_SYSCALL_AUDIT 6 /* syscall auditing active */
-#define TIF_SYSCALL_TRACEPOINT 7 /* syscall tracepoint instrumentation */
-#define TIF_SECCOMP 8 /* seccomp syscall filtering active */
+#define TIF_SYSCALL_TRACE 4 /* syscall trace active */
+#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
+#define TIF_SECCOMP 7 /* seccomp syscall filtering active */
#define TIF_NOHZ 12 /* in adaptive nohz mode */
#define TIF_USING_IWMMXT 17
@@ -154,7 +153,6 @@
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_UPROBE (1 << TIF_UPROBE)
-#define _TIF_FSCHECK (1 << TIF_FSCHECK)
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
@@ -168,9 +166,8 @@
/*
* Change these and you break ASM code in entry-common.S
*/
-#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
- _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- _TIF_FSCHECK)
+#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+ _TIF_NOTIFY_RESUME | _TIF_UPROBE)
#endif /* __KERNEL__ */
#endif /* __ASM_ARM_THREAD_INFO_H */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 87936dd..0bf2347 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -70,8 +70,6 @@
{
current_thread_info()->addr_limit = fs;
modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
- /* On user-mode return, check fs is correct */
- set_thread_flag(TIF_FSCHECK);
}
#define segment_eq(a, b) ((a) == (b))
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index ca3614d..99c9082 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -12,6 +12,7 @@
#include <asm/unistd.h>
#include <asm/ftrace.h>
#include <asm/unwind.h>
+#include <asm/memory.h>
#ifdef CONFIG_AEABI
#include <asm/unistd-oabi.h>
#endif
@@ -48,11 +49,13 @@
UNWIND(.fnstart )
UNWIND(.cantunwind )
disable_irq_notrace @ disable interrupts
+ ldr r2, [tsk, #TI_ADDR_LIMIT]
+ cmp r2, #TASK_SIZE
+ blne addr_limit_check_failed
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
- tst r1, #_TIF_SYSCALL_WORK
+ tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
bne fast_work_pending
- tst r1, #_TIF_WORK_MASK
- bne fast_work_pending
+
/* perform architecture specific actions before user return */
arch_ret_to_user r1, lr
@@ -76,16 +79,16 @@
UNWIND(.cantunwind )
str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
disable_irq_notrace @ disable interrupts
+ ldr r2, [tsk, #TI_ADDR_LIMIT]
+ cmp r2, #TASK_SIZE
+ blne addr_limit_check_failed
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
- tst r1, #_TIF_SYSCALL_WORK
- bne fast_work_pending
- tst r1, #_TIF_WORK_MASK
+ tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
beq no_work_pending
UNWIND(.fnend )
ENDPROC(ret_fast_syscall)
/* Slower path - fall through to work_pending */
-fast_work_pending:
#endif
tst r1, #_TIF_SYSCALL_WORK
@@ -111,6 +114,9 @@
ret_slow_syscall:
disable_irq_notrace @ disable interrupts
ENTRY(ret_to_user_from_irq)
+ ldr r2, [tsk, #TI_ADDR_LIMIT]
+ cmp r2, #TASK_SIZE
+ blne addr_limit_check_failed
ldr r1, [tsk, #TI_FLAGS]
tst r1, #_TIF_WORK_MASK
bne slow_work_pending
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index e2de50b..b67ae12 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -614,10 +614,6 @@
* Update the trace code with the current status.
*/
trace_hardirqs_off();
-
- /* Check valid user FS if needed */
- addr_limit_user_check();
-
do {
if (likely(thread_flags & _TIF_NEED_RESCHED)) {
schedule();
@@ -678,3 +674,9 @@
return page;
}
+
+/* Defer to generic check */
+asmlinkage void addr_limit_check_failed(void)
+{
+ addr_limit_user_check();
+}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index c45214f..0bdc96c 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -751,10 +751,10 @@
*/
trace_hardirqs_off();
- /* Check valid user FS if needed */
- addr_limit_user_check();
-
do {
+ /* Check valid user FS if needed */
+ addr_limit_user_check();
+
if (thread_flags & _TIF_NEED_RESCHED) {
schedule();
} else {
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 9d26abd..4f798aa 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -39,7 +39,7 @@
# Endianness selection
choice
prompt "Endianness selection"
- default CPU_BIG_ENDIAN
+ default CPU_LITTLE_ENDIAN
help
microblaze architectures can be configured for either little or
big endian formats. Be sure to select the appropriate mode.
diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild
index e77a596..06609ca 100644
--- a/arch/microblaze/include/uapi/asm/Kbuild
+++ b/arch/microblaze/include/uapi/asm/Kbuild
@@ -7,6 +7,7 @@
generic-y += ioctl.h
generic-y += ioctls.h
generic-y += ipcbuf.h
+generic-y += kvm_para.h
generic-y += mman.h
generic-y += msgbuf.h
generic-y += param.h
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index e45ada8..94700c5 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -165,7 +165,7 @@
unsigned long attrs)
{
#ifdef CONFIG_MMU
- unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+ unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
unsigned long pfn;
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index ba7b7dd..a57dedb 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -257,6 +257,18 @@
endchoice
+config PARISC_SELF_EXTRACT
+ bool "Build kernel as self-extracting executable"
+ default y
+ help
+ Say Y if you want to build the parisc kernel as a kind of
+ self-extracting executable.
+
+ If you say N here, the kernel will be compressed with gzip
+ which can be loaded by the palo bootloader directly too.
+
+ If you don't know what to do here, say Y.
+
config SMP
bool "Symmetric multi-processing support"
---help---
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 58fae5d..01946eb 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -129,8 +129,13 @@
bzImage: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+ifdef CONFIG_PARISC_SELF_EXTRACT
vmlinuz: bzImage
$(OBJCOPY) $(boot)/bzImage $@
+else
+vmlinuz: vmlinux
+ @gzip -cf -9 $< > $@
+endif
install:
$(CONFIG_SHELL) $(src)/arch/parisc/install.sh \
diff --git a/arch/parisc/boot/compressed/Makefile b/arch/parisc/boot/compressed/Makefile
index 5450a11..7d7e594 100644
--- a/arch/parisc/boot/compressed/Makefile
+++ b/arch/parisc/boot/compressed/Makefile
@@ -15,7 +15,7 @@
KBUILD_CFLAGS := -D__KERNEL__ -O2 -DBOOTLOADER
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks
-KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs
+KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs -Os
ifndef CONFIG_64BIT
KBUILD_CFLAGS += -mfast-indirect-calls
endif
diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c
index 13a4bf9..9345b44 100644
--- a/arch/parisc/boot/compressed/misc.c
+++ b/arch/parisc/boot/compressed/misc.c
@@ -24,7 +24,8 @@
/* Symbols defined by linker scripts */
extern char input_data[];
extern int input_len;
-extern __le32 output_len; /* at unaligned address, little-endian */
+/* output_len is inserted by the linker possibly at an unaligned address */
+extern __le32 output_len __aligned(1);
extern char _text, _end;
extern char _bss, _ebss;
extern char _startcode_end;
diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h
index 26b4455..510341f 100644
--- a/arch/parisc/include/asm/pdc.h
+++ b/arch/parisc/include/asm/pdc.h
@@ -280,6 +280,7 @@
/* wrapper-functions from pdc.c */
int pdc_add_valid(unsigned long address);
+int pdc_instr(unsigned int *instr);
int pdc_chassis_info(struct pdc_chassis_info *chassis_info, void *led_info, unsigned long len);
int pdc_chassis_disp(unsigned long disp);
int pdc_chassis_warn(unsigned long *warn);
diff --git a/arch/parisc/include/asm/smp.h b/arch/parisc/include/asm/smp.h
index a5dc906..ad9c9c3 100644
--- a/arch/parisc/include/asm/smp.h
+++ b/arch/parisc/include/asm/smp.h
@@ -1,6 +1,7 @@
#ifndef __ASM_SMP_H
#define __ASM_SMP_H
+extern int init_per_cpu(int cpuid);
#if defined(CONFIG_SMP)
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index ab80e5c..6d471c0 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -233,6 +233,26 @@
EXPORT_SYMBOL(pdc_add_valid);
/**
+ * pdc_instr - Get instruction that invokes PDCE_CHECK in HPMC handler.
+ * @instr: Pointer to variable which will get instruction opcode.
+ *
+ * The return value is PDC_OK (0) in case call succeeded.
+ */
+int __init pdc_instr(unsigned int *instr)
+{
+ int retval;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pdc_lock, flags);
+ retval = mem_pdc_call(PDC_INSTR, 0UL, __pa(pdc_result));
+ convert_to_wide(pdc_result);
+ *instr = pdc_result[0];
+ spin_unlock_irqrestore(&pdc_lock, flags);
+
+ return retval;
+}
+
+/**
* pdc_chassis_info - Return chassis information.
* @result: The return buffer.
* @chassis_info: The memory buffer address.
diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c
index 05730a8..00aed08 100644
--- a/arch/parisc/kernel/pdt.c
+++ b/arch/parisc/kernel/pdt.c
@@ -15,6 +15,7 @@
#include <linux/memblock.h>
#include <linux/seq_file.h>
#include <linux/kthread.h>
+#include <linux/initrd.h>
#include <asm/pdc.h>
#include <asm/pdcpat.h>
@@ -216,8 +217,16 @@
}
for (i = 0; i < pdt_status.pdt_entries; i++) {
+ unsigned long addr;
+
report_mem_err(pdt_entry[i]);
+ addr = pdt_entry[i] & PDT_ADDR_PHYS_MASK;
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) &&
+ addr >= initrd_start && addr < initrd_end)
+ pr_crit("CRITICAL: initrd possibly broken "
+ "due to bad memory!\n");
+
/* mark memory page bad */
memblock_reserve(pdt_entry[i] & PAGE_MASK, PAGE_SIZE);
}
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index a778bd3..e120d63 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -317,7 +317,7 @@
*
* o Enable CPU profiling hooks.
*/
-int init_per_cpu(int cpunum)
+int __init init_per_cpu(int cpunum)
{
int ret;
struct pdc_coproc_cfg coproc_cfg;
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index dee6f9d..f7d0c3b3 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -38,6 +38,7 @@
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/clock.h>
+#include <linux/start_kernel.h>
#include <asm/processor.h>
#include <asm/sections.h>
@@ -48,6 +49,7 @@
#include <asm/io.h>
#include <asm/setup.h>
#include <asm/unwind.h>
+#include <asm/smp.h>
static char __initdata command_line[COMMAND_LINE_SIZE];
@@ -115,7 +117,6 @@
}
#endif
-extern int init_per_cpu(int cpuid);
extern void collect_boot_cpu_data(void);
void __init setup_arch(char **cmdline_p)
@@ -398,9 +399,8 @@
}
arch_initcall(parisc_init);
-void start_parisc(void)
+void __init start_parisc(void)
{
- extern void start_kernel(void);
extern void early_trap_init(void);
int ret, cpunum;
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 6336510..30c28ab 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -255,12 +255,11 @@
static void __init
smp_cpu_init(int cpunum)
{
- extern int init_per_cpu(int); /* arch/parisc/kernel/processor.c */
extern void init_IRQ(void); /* arch/parisc/kernel/irq.c */
extern void start_cpu_itimer(void); /* arch/parisc/kernel/time.c */
/* Set modes and Enable floating point coprocessor */
- (void) init_per_cpu(cpunum);
+ init_per_cpu(cpunum);
disable_sr_hashing();
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 991654c..23033315 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -817,7 +817,7 @@
u32 check = 0;
u32 *ivap;
u32 *hpmcp;
- u32 length;
+ u32 length, instr;
if (strcmp((const char *)iva, "cows can fly"))
panic("IVT invalid");
@@ -827,6 +827,14 @@
for (i = 0; i < 8; i++)
*ivap++ = 0;
+ /*
+ * Use PDC_INSTR firmware function to get instruction that invokes
+ * PDCE_CHECK in HPMC handler. See programming note at page 1-31 of
+ * the PA 1.1 Firmware Architecture document.
+ */
+ if (pdc_instr(&instr) == PDC_OK)
+ ivap[0] = instr;
+
/* Compute Checksum for HPMC handler */
length = os_hpmc_size;
ivap[7] = length;
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index 48dc7d4..caab39d 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -14,6 +14,7 @@
#include <linux/slab.h>
#include <linux/kallsyms.h>
#include <linux/sort.h>
+#include <linux/sched.h>
#include <linux/uaccess.h>
#include <asm/assembly.h>
@@ -279,6 +280,17 @@
info->prev_sp = sp - 64;
info->prev_ip = 0;
+
+ /* The stack is at the end inside the thread_union
+ * struct. If we reach data, we have reached the
+ * beginning of the stack and should stop unwinding. */
+ if (info->prev_sp >= (unsigned long) task_thread_info(info->t) &&
+ info->prev_sp < ((unsigned long) task_thread_info(info->t)
+ + THREAD_SZ_ALGN)) {
+ info->prev_sp = 0;
+ break;
+ }
+
if (get_user(tmp, (unsigned long *)(info->prev_sp - RP_OFFSET)))
break;
info->prev_ip = tmp;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 5b101f6..e247edb 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -17,6 +17,7 @@
#include <linux/interrupt.h>
#include <linux/extable.h>
#include <linux/uaccess.h>
+#include <linux/hugetlb.h>
#include <asm/traps.h>
@@ -261,7 +262,7 @@
struct task_struct *tsk;
struct mm_struct *mm;
unsigned long acc_type;
- int fault;
+ int fault = 0;
unsigned int flags;
if (faulthandler_disabled())
@@ -315,7 +316,8 @@
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
- else if (fault & VM_FAULT_SIGBUS)
+ else if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
+ VM_FAULT_HWPOISON_LARGE))
goto bad_area;
BUG();
}
@@ -352,8 +354,7 @@
if (user_mode(regs)) {
struct siginfo si;
-
- show_signal_msg(regs, code, address, tsk, vma);
+ unsigned int lsb = 0;
switch (code) {
case 15: /* Data TLB miss fault/Data page fault */
@@ -386,6 +387,30 @@
si.si_code = (code == 26) ? SEGV_ACCERR : SEGV_MAPERR;
break;
}
+
+#ifdef CONFIG_MEMORY_FAILURE
+ if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+ printk(KERN_ERR
+ "MCE: Killing %s:%d due to hardware memory corruption fault at %08lx\n",
+ tsk->comm, tsk->pid, address);
+ si.si_signo = SIGBUS;
+ si.si_code = BUS_MCEERR_AR;
+ }
+#endif
+
+ /*
+ * Either small page or large page may be poisoned.
+ * In other words, VM_FAULT_HWPOISON_LARGE and
+ * VM_FAULT_HWPOISON are mutually exclusive.
+ */
+ if (fault & VM_FAULT_HWPOISON_LARGE)
+ lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+ else if (fault & VM_FAULT_HWPOISON)
+ lsb = PAGE_SHIFT;
+ else
+ show_signal_msg(regs, code, address, tsk, vma);
+ si.si_addr_lsb = lsb;
+
si.si_errno = 0;
si.si_addr = (void __user *) address;
force_sig_info(si.si_signo, &si, current);
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 1b02038..c096624 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -218,10 +218,9 @@
#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \
output, input...) \
{ \
- register void *__sp asm(_ASM_SP); \
asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
"call %P[new2]", feature2) \
- : output, "+r" (__sp) \
+ : output, ASM_CALL_CONSTRAINT \
: [old] "i" (oldfunc), [new1] "i" (newfunc1), \
[new2] "i" (newfunc2), ## input); \
}
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 676ee58..c1eadba 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -132,4 +132,15 @@
/* 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 int __asm_call_sp asm("esp");
+#define ASM_CALL_CONSTRAINT "+r" (__asm_call_sp)
+#endif
+
#endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 7ae318c..c120b5d 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -286,6 +286,32 @@
return __pkru_allows_pkey(vma_pkey(vma), write);
}
+/*
+ * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
+ * bits. This serves two purposes. It prevents a nasty situation in
+ * which PCID-unaware code saves CR3, loads some other value (with PCID
+ * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
+ * the saved ASID was nonzero. It also means that any bugs involving
+ * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
+ * deterministically.
+ */
+
+static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
+{
+ if (static_cpu_has(X86_FEATURE_PCID)) {
+ VM_WARN_ON_ONCE(asid > 4094);
+ return __sme_pa(mm->pgd) | (asid + 1);
+ } else {
+ VM_WARN_ON_ONCE(asid != 0);
+ return __sme_pa(mm->pgd);
+ }
+}
+
+static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
+{
+ VM_WARN_ON_ONCE(asid > 4094);
+ return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
+}
/*
* This can be used from process context to figure out what the value of
@@ -296,10 +322,8 @@
*/
static inline unsigned long __get_current_cr3_fast(void)
{
- unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd);
-
- if (static_cpu_has(X86_FEATURE_PCID))
- cr3 |= this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+ unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+ this_cpu_read(cpu_tlbstate.loaded_mm_asid));
/* For now, be very restrictive about when this can be called. */
VM_WARN_ON(in_nmi() || preemptible());
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 63cc96f..738503e 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -179,7 +179,6 @@
u64 input_address = input ? virt_to_phys(input) : 0;
u64 output_address = output ? virt_to_phys(output) : 0;
u64 hv_status;
- register void *__sp asm(_ASM_SP);
#ifdef CONFIG_X86_64
if (!hv_hypercall_pg)
@@ -187,7 +186,7 @@
__asm__ __volatile__("mov %4, %%r8\n"
"call *%5"
- : "=a" (hv_status), "+r" (__sp),
+ : "=a" (hv_status), ASM_CALL_CONSTRAINT,
"+c" (control), "+d" (input_address)
: "r" (output_address), "m" (hv_hypercall_pg)
: "cc", "memory", "r8", "r9", "r10", "r11");
@@ -202,7 +201,7 @@
__asm__ __volatile__("call *%7"
: "=A" (hv_status),
- "+c" (input_address_lo), "+r" (__sp)
+ "+c" (input_address_lo), ASM_CALL_CONSTRAINT
: "A" (control),
"b" (input_address_hi),
"D"(output_address_hi), "S"(output_address_lo),
@@ -224,12 +223,11 @@
static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
{
u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
- register void *__sp asm(_ASM_SP);
#ifdef CONFIG_X86_64
{
__asm__ __volatile__("call *%4"
- : "=a" (hv_status), "+r" (__sp),
+ : "=a" (hv_status), ASM_CALL_CONSTRAINT,
"+c" (control), "+d" (input1)
: "m" (hv_hypercall_pg)
: "cc", "r8", "r9", "r10", "r11");
@@ -242,7 +240,7 @@
__asm__ __volatile__ ("call *%5"
: "=A"(hv_status),
"+c"(input1_lo),
- "+r"(__sp)
+ ASM_CALL_CONSTRAINT
: "A" (control),
"b" (input1_hi),
"m" (hv_hypercall_pg)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 42873ed..280d94c 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -459,8 +459,8 @@
*/
#ifdef CONFIG_X86_32
#define PVOP_VCALL_ARGS \
- unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; \
- register void *__sp asm("esp")
+ unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;
+
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x))
@@ -480,8 +480,8 @@
/* [re]ax isn't an arg, but the return val */
#define PVOP_VCALL_ARGS \
unsigned long __edi = __edi, __esi = __esi, \
- __edx = __edx, __ecx = __ecx, __eax = __eax; \
- register void *__sp asm("rsp")
+ __edx = __edx, __ecx = __ecx, __eax = __eax;
+
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x))
@@ -532,7 +532,7 @@
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr, "+r" (__sp) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
@@ -542,7 +542,7 @@
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr, "+r" (__sp) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
@@ -569,7 +569,7 @@
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr, "+r" (__sp) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index ec1f3c6..4f44505 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -100,19 +100,14 @@
#ifdef CONFIG_PREEMPT
extern asmlinkage void ___preempt_schedule(void);
-# define __preempt_schedule() \
-({ \
- register void *__sp asm(_ASM_SP); \
- asm volatile ("call ___preempt_schedule" : "+r"(__sp)); \
-})
+# define __preempt_schedule() \
+ asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT)
extern asmlinkage void preempt_schedule(void);
extern asmlinkage void ___preempt_schedule_notrace(void);
-# define __preempt_schedule_notrace() \
-({ \
- register void *__sp asm(_ASM_SP); \
- asm volatile ("call ___preempt_schedule_notrace" : "+r"(__sp)); \
-})
+# define __preempt_schedule_notrace() \
+ asm volatile ("call ___preempt_schedule_notrace" : ASM_CALL_CONSTRAINT)
+
extern asmlinkage void preempt_schedule_notrace(void);
#endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3fa26a6..b390ff7 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -677,8 +677,6 @@
* Like all of Linux's memory ordering operations, this is a
* compiler barrier as well.
*/
- register void *__sp asm(_ASM_SP);
-
#ifdef CONFIG_X86_32
asm volatile (
"pushfl\n\t"
@@ -686,7 +684,7 @@
"pushl $1f\n\t"
"iret\n\t"
"1:"
- : "+r" (__sp) : : "memory");
+ : ASM_CALL_CONSTRAINT : : "memory");
#else
unsigned int tmp;
@@ -703,7 +701,7 @@
"iretq\n\t"
UNWIND_HINT_RESTORE
"1:"
- : "=&r" (tmp), "+r" (__sp) : : "cc", "memory");
+ : "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
#endif
}
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index a34e0d4..7116b79 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -103,7 +103,6 @@
({ \
long tmp; \
struct rw_semaphore* ret; \
- register void *__sp asm(_ASM_SP); \
\
asm volatile("# beginning down_write\n\t" \
LOCK_PREFIX " xadd %1,(%4)\n\t" \
@@ -114,7 +113,8 @@
" call " slow_path "\n" \
"1:\n" \
"# ending down_write" \
- : "+m" (sem->count), "=d" (tmp), "=a" (ret), "+r" (__sp) \
+ : "+m" (sem->count), "=d" (tmp), \
+ "=a" (ret), ASM_CALL_CONSTRAINT \
: "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
: "memory", "cc"); \
ret; \
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 184eb98..78e8fcc 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -166,11 +166,11 @@
({ \
int __ret_gu; \
register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \
- register void *__sp asm(_ASM_SP); \
__chk_user_ptr(ptr); \
might_fault(); \
asm volatile("call __get_user_%P4" \
- : "=a" (__ret_gu), "=r" (__val_gu), "+r" (__sp) \
+ : "=a" (__ret_gu), "=r" (__val_gu), \
+ ASM_CALL_CONSTRAINT \
: "0" (ptr), "i" (sizeof(*(ptr)))); \
(x) = (__force __typeof__(*(ptr))) __val_gu; \
__builtin_expect(__ret_gu, 0); \
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 9606688..128a1a0 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -113,10 +113,9 @@
register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
- register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; \
- register void *__sp asm(_ASM_SP);
+ register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
-#define __HYPERCALL_0PARAM "=r" (__res), "+r" (__sp)
+#define __HYPERCALL_0PARAM "=r" (__res), ASM_CALL_CONSTRAINT
#define __HYPERCALL_1PARAM __HYPERCALL_0PARAM, "+r" (__arg1)
#define __HYPERCALL_2PARAM __HYPERCALL_1PARAM, "+r" (__arg2)
#define __HYPERCALL_3PARAM __HYPERCALL_2PARAM, "+r" (__arg3)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index db68488..0af86d9 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -21,14 +21,6 @@
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)) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 775f101..c9176ba 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -904,6 +904,14 @@
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
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/smpboot.c b/arch/x86/kernel/smpboot.c
index 0854ff1..ad59edd 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -232,12 +232,6 @@
*/
if (boot_cpu_has(X86_FEATURE_PCID))
__write_cr4(__read_cr4() | X86_CR4_PCIDE);
- cpu_init();
- x86_cpuinit.early_percpu_clock_init();
- preempt_disable();
- smp_callin();
-
- enable_start_cpu0 = 0;
#ifdef CONFIG_X86_32
/* switch away from the initial page table */
@@ -245,6 +239,13 @@
__flush_tlb_all();
#endif
+ cpu_init();
+ x86_cpuinit.early_percpu_clock_init();
+ preempt_disable();
+ smp_callin();
+
+ enable_start_cpu0 = 0;
+
/* otherwise gcc will move up smp_processor_id before the cpu_init */
barrier();
/*
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 15f527b..a36254c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -5298,7 +5298,6 @@
static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
{
- register void *__sp asm(_ASM_SP);
ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
if (!(ctxt->d & ByteOp))
@@ -5306,7 +5305,7 @@
asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
: "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
- [fastop]"+S"(fop), "+r"(__sp)
+ [fastop]"+S"(fop), ASM_CALL_CONSTRAINT
: "c"(ctxt->src2.val));
ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 0726ca7..6970249 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9045,7 +9045,6 @@
static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
{
u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
- register void *__sp asm(_ASM_SP);
if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) {
@@ -9074,7 +9073,7 @@
#ifdef CONFIG_X86_64
[sp]"=&r"(tmp),
#endif
- "+r"(__sp)
+ ASM_CALL_CONSTRAINT
:
[entry]"r"(entry),
[ss]"i"(__KERNEL_DS),
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b836a72..39567b5 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -806,7 +806,6 @@
if (is_vmalloc_addr((void *)address) &&
(((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
- register void *__sp asm("rsp");
unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
/*
* We're likely to be running with very little stack space
@@ -821,7 +820,7 @@
asm volatile ("movq %[stack], %%rsp\n\t"
"call handle_stack_overflow\n\t"
"1: jmp 1b"
- : "+r" (__sp)
+ : ASM_CALL_CONSTRAINT
: "D" ("kernel stack overflow (page fault)"),
"S" (regs), "d" (address),
[stack] "rm" (stack));
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 1ab3821..93fe97c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -126,8 +126,7 @@
* isn't free.
*/
#ifdef CONFIG_DEBUG_VM
- if (WARN_ON_ONCE(__read_cr3() !=
- (__sme_pa(real_prev->pgd) | prev_asid))) {
+ if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) {
/*
* If we were to BUG here, we'd be very likely to kill
* the system so hard that we don't see the call trace.
@@ -172,7 +171,7 @@
*/
this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen,
next_tlb_gen);
- write_cr3(__sme_pa(next->pgd) | prev_asid);
+ write_cr3(build_cr3(next, prev_asid));
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
TLB_FLUSH_ALL);
}
@@ -216,12 +215,12 @@
if (need_flush) {
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- write_cr3(__sme_pa(next->pgd) | new_asid);
+ write_cr3(build_cr3(next, new_asid));
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
- write_cr3(__sme_pa(next->pgd) | new_asid | CR3_NOFLUSH);
+ write_cr3(build_cr3_noflush(next, new_asid));
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
}
@@ -265,7 +264,7 @@
!(cr4_read_shadow() & X86_CR4_PCIDE));
/* Force ASID 0 and force a TLB flush. */
- write_cr3(cr3 & ~CR3_PCID_MASK);
+ write_cr3(build_cr3(mm, 0));
/* Reinitialize tlbstate. */
this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
diff --git a/block/blk-core.c b/block/blk-core.c
index aebe676..048be4a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -854,6 +854,9 @@
kobject_init(&q->kobj, &blk_queue_ktype);
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+ mutex_init(&q->blk_trace_mutex);
+#endif
mutex_init(&q->sysfs_lock);
spin_lock_init(&q->__queue_lock);
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index c82408c..dbddff8 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -154,7 +154,6 @@
failjob_rls_rqst_payload:
kfree(job->request_payload.sg_list);
failjob_rls_job:
- kfree(job);
return -ENOMEM;
}
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 86e8fe1..88c555d 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -112,7 +112,7 @@
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
- struct request_queue *q = dev_to_disk(dev)->queue;
+ struct request_queue *q = part_to_disk(p)->queue;
unsigned int inflight[2];
int cpu;
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index bbd0d18..2d7178f 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -342,7 +342,7 @@
if (!brd)
return -ENODEV;
- page = brd_insert_page(brd, PFN_PHYS(pgoff) / 512);
+ page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT);
if (!page)
return -ENOSPC;
*kaddr = page_address(page);
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index f68c1d5..1f39567 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -67,10 +67,8 @@
struct loop_cmd {
struct kthread_work work;
struct request *rq;
- union {
- bool use_aio; /* use AIO interface to handle I/O */
- atomic_t ref; /* only for aio */
- };
+ bool use_aio; /* use AIO interface to handle I/O */
+ atomic_t ref; /* only for aio */
long ret;
struct kiocb iocb;
struct bio_vec *bvec;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 2aa87cb..3684e21 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1194,6 +1194,12 @@
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ /* The block layer will pass back some non-nbd ioctls in case we have
+ * special handling for them, but we don't so just return an error.
+ */
+ if (_IOC_TYPE(cmd) != 0xab)
+ return -EINVAL;
+
mutex_lock(&nbd->config_lock);
/* Don't allow ioctl operations on a nbd device that was created with
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index fe597e6..1d6729b 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -455,7 +455,7 @@
goto out;
}
- msleep(TPM_TIMEOUT); /* CHECK */
+ tpm_msleep(TPM_TIMEOUT);
rmb();
} while (time_before(jiffies, stop));
@@ -970,7 +970,7 @@
dev_info(
&chip->dev, HW_ERR
"TPM command timed out during continue self test");
- msleep(delay_msec);
+ tpm_msleep(delay_msec);
continue;
}
@@ -985,7 +985,7 @@
}
if (rc != TPM_WARN_DOING_SELFTEST)
return rc;
- msleep(delay_msec);
+ tpm_msleep(delay_msec);
} while (--loops > 0);
return rc;
@@ -1085,7 +1085,7 @@
}
} else {
do {
- msleep(TPM_TIMEOUT);
+ tpm_msleep(TPM_TIMEOUT);
status = chip->ops->status(chip);
if ((status & mask) == mask)
return 0;
@@ -1150,7 +1150,7 @@
*/
if (rc != TPM_WARN_RETRY)
break;
- msleep(TPM_TIMEOUT_RETRY);
+ tpm_msleep(TPM_TIMEOUT_RETRY);
}
if (rc)
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 04fbff2..2d5466a 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -50,7 +50,8 @@
enum tpm_timeout {
TPM_TIMEOUT = 5, /* msecs */
- TPM_TIMEOUT_RETRY = 100 /* msecs */
+ TPM_TIMEOUT_RETRY = 100, /* msecs */
+ TPM_TIMEOUT_RANGE_US = 300 /* usecs */
};
/* TPM addresses */
@@ -527,6 +528,12 @@
int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout,
wait_queue_head_t *queue, bool check_cancel);
+static inline void tpm_msleep(unsigned int delay_msec)
+{
+ usleep_range(delay_msec * 1000,
+ (delay_msec * 1000) + TPM_TIMEOUT_RANGE_US);
+};
+
struct tpm_chip *tpm_chip_find_get(int chip_num);
__must_check int tpm_try_get_ops(struct tpm_chip *chip);
void tpm_put_ops(struct tpm_chip *chip);
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index f7f34b2a..e1a41b7 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -899,7 +899,7 @@
if (rc != TPM2_RC_TESTING)
break;
- msleep(delay_msec);
+ tpm_msleep(delay_msec);
}
return rc;
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index a4ac63a..8f0a98d 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -665,7 +665,7 @@
SET_RUNTIME_PM_OPS(crb_pm_runtime_suspend, crb_pm_runtime_resume, NULL)
};
-static struct acpi_device_id crb_device_ids[] = {
+static const struct acpi_device_id crb_device_ids[] = {
{"MSFT0101", 0},
{"", 0},
};
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index f01d083..25f6e26 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -32,26 +32,70 @@
static const char tpm_ibmvtpm_driver_name[] = "tpm_ibmvtpm";
-static struct vio_device_id tpm_ibmvtpm_device_table[] = {
+static const struct vio_device_id tpm_ibmvtpm_device_table[] = {
{ "IBM,vtpm", "IBM,vtpm"},
{ "", "" }
};
MODULE_DEVICE_TABLE(vio, tpm_ibmvtpm_device_table);
/**
+ *
+ * ibmvtpm_send_crq_word - Send a CRQ request
+ * @vdev: vio device struct
+ * @w1: pre-constructed first word of tpm crq (second word is reserved)
+ *
+ * Return:
+ * 0 - Success
+ * Non-zero - Failure
+ */
+static int ibmvtpm_send_crq_word(struct vio_dev *vdev, u64 w1)
+{
+ return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, 0);
+}
+
+/**
+ *
* ibmvtpm_send_crq - Send a CRQ request
*
* @vdev: vio device struct
- * @w1: first word
- * @w2: second word
+ * @valid: Valid field
+ * @msg: Type field
+ * @len: Length field
+ * @data: Data field
+ *
+ * The ibmvtpm crq is defined as follows:
+ *
+ * Byte | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7
+ * -----------------------------------------------------------------------
+ * Word0 | Valid | Type | Length | Data
+ * -----------------------------------------------------------------------
+ * Word1 | Reserved
+ * -----------------------------------------------------------------------
+ *
+ * Which matches the following structure (on bigendian host):
+ *
+ * struct ibmvtpm_crq {
+ * u8 valid;
+ * u8 msg;
+ * __be16 len;
+ * __be32 data;
+ * __be64 reserved;
+ * } __attribute__((packed, aligned(8)));
+ *
+ * However, the value is passed in a register so just compute the numeric value
+ * to load into the register avoiding byteswap altogether. Endian only affects
+ * memory loads and stores - registers are internally represented the same.
*
* Return:
- * 0 -Sucess
+ * 0 (H_SUCCESS) - Success
* Non-zero - Failure
*/
-static int ibmvtpm_send_crq(struct vio_dev *vdev, u64 w1, u64 w2)
+static int ibmvtpm_send_crq(struct vio_dev *vdev,
+ u8 valid, u8 msg, u16 len, u32 data)
{
- return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, w2);
+ u64 w1 = ((u64)valid << 56) | ((u64)msg << 48) | ((u64)len << 32) |
+ (u64)data;
+ return ibmvtpm_send_crq_word(vdev, w1);
}
/**
@@ -109,8 +153,6 @@
static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
{
struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
- struct ibmvtpm_crq crq;
- __be64 *word = (__be64 *)&crq;
int rc, sig;
if (!ibmvtpm->rtce_buf) {
@@ -137,10 +179,6 @@
spin_lock(&ibmvtpm->rtce_lock);
ibmvtpm->res_len = 0;
memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count);
- crq.valid = (u8)IBMVTPM_VALID_CMD;
- crq.msg = (u8)VTPM_TPM_COMMAND;
- crq.len = cpu_to_be16(count);
- crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle);
/*
* set the processing flag before the Hcall, since we may get the
@@ -148,8 +186,9 @@
*/
ibmvtpm->tpm_processing_cmd = true;
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]),
- be64_to_cpu(word[1]));
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+ IBMVTPM_VALID_CMD, VTPM_TPM_COMMAND,
+ count, ibmvtpm->rtce_dma_handle);
if (rc != H_SUCCESS) {
dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc);
rc = 0;
@@ -182,15 +221,10 @@
*/
static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm)
{
- struct ibmvtpm_crq crq;
- u64 *buf = (u64 *) &crq;
int rc;
- crq.valid = (u8)IBMVTPM_VALID_CMD;
- crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE;
-
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
- cpu_to_be64(buf[1]));
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+ IBMVTPM_VALID_CMD, VTPM_GET_RTCE_BUFFER_SIZE, 0, 0);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc);
@@ -210,15 +244,10 @@
*/
static int ibmvtpm_crq_get_version(struct ibmvtpm_dev *ibmvtpm)
{
- struct ibmvtpm_crq crq;
- u64 *buf = (u64 *) &crq;
int rc;
- crq.valid = (u8)IBMVTPM_VALID_CMD;
- crq.msg = (u8)VTPM_GET_VERSION;
-
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
- cpu_to_be64(buf[1]));
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+ IBMVTPM_VALID_CMD, VTPM_GET_VERSION, 0, 0);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_get_version failed rc=%d\n", rc);
@@ -238,7 +267,7 @@
{
int rc;
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_COMP_CMD, 0);
+ rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_COMP_CMD);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_send_init_complete failed rc=%d\n", rc);
@@ -258,7 +287,7 @@
{
int rc;
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_CMD, 0);
+ rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_send_init failed rc=%d\n", rc);
@@ -340,15 +369,10 @@
{
struct tpm_chip *chip = dev_get_drvdata(dev);
struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
- struct ibmvtpm_crq crq;
- u64 *buf = (u64 *) &crq;
int rc = 0;
- crq.valid = (u8)IBMVTPM_VALID_CMD;
- crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND;
-
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
- cpu_to_be64(buf[1]));
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+ IBMVTPM_VALID_CMD, VTPM_PREPARE_TO_SUSPEND, 0, 0);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"tpm_ibmvtpm_suspend failed rc=%d\n", rc);
diff --git a/drivers/char/tpm/tpm_infineon.c b/drivers/char/tpm/tpm_infineon.c
index 3b1b9f9..d8f1004 100644
--- a/drivers/char/tpm/tpm_infineon.c
+++ b/drivers/char/tpm/tpm_infineon.c
@@ -191,7 +191,7 @@
/* check the status-register if wait_for_bit is set */
if (status & 1 << wait_for_bit)
break;
- msleep(TPM_MSLEEP_TIME);
+ tpm_msleep(TPM_MSLEEP_TIME);
}
if (i == TPM_MAX_TRIES) { /* timeout occurs */
if (wait_for_bit == STAT_XFE)
@@ -226,7 +226,7 @@
wait_and_send(chip, TPM_CTRL_WTX);
wait_and_send(chip, 0x00);
wait_and_send(chip, 0x00);
- msleep(TPM_WTX_MSLEEP_TIME);
+ tpm_msleep(TPM_WTX_MSLEEP_TIME);
}
static void tpm_wtx_abort(struct tpm_chip *chip)
@@ -237,7 +237,7 @@
wait_and_send(chip, 0x00);
wait_and_send(chip, 0x00);
number_of_wtx = 0;
- msleep(TPM_WTX_MSLEEP_TIME);
+ tpm_msleep(TPM_WTX_MSLEEP_TIME);
}
static int tpm_inf_recv(struct tpm_chip *chip, u8 * buf, size_t count)
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index b617b2e..63bc6c3 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -51,7 +51,7 @@
if (access & TPM_ACCESS_VALID)
return 0;
- msleep(TPM_TIMEOUT);
+ tpm_msleep(TPM_TIMEOUT);
} while (time_before(jiffies, stop));
return -1;
}
@@ -117,7 +117,7 @@
do {
if (check_locality(chip, l))
return l;
- msleep(TPM_TIMEOUT);
+ tpm_msleep(TPM_TIMEOUT);
} while (time_before(jiffies, stop));
}
return -1;
@@ -164,7 +164,7 @@
burstcnt = (value >> 8) & 0xFFFF;
if (burstcnt)
return burstcnt;
- msleep(TPM_TIMEOUT);
+ tpm_msleep(TPM_TIMEOUT);
} while (time_before(jiffies, stop));
return -EBUSY;
}
@@ -396,7 +396,7 @@
priv->irq = irq;
chip->flags |= TPM_CHIP_FLAG_IRQ;
if (!priv->irq_tested)
- msleep(1);
+ tpm_msleep(1);
if (!priv->irq_tested)
disable_interrupts(chip);
priv->irq_tested = true;
diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c
index 2ff64d9..62d2469 100644
--- a/drivers/clocksource/timer-integrator-ap.c
+++ b/drivers/clocksource/timer-integrator-ap.c
@@ -36,8 +36,8 @@
return -readl(sched_clk_base + TIMER_VALUE);
}
-static int integrator_clocksource_init(unsigned long inrate,
- void __iomem *base)
+static int __init integrator_clocksource_init(unsigned long inrate,
+ void __iomem *base)
{
u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC;
unsigned long rate = inrate;
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index ee9e27d..de57d6c 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1646,7 +1646,7 @@
*/
if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) {
if (attr.qp_state >= IB_QPS_INIT) {
- if (qp->device->get_link_layer(qp->device, attr.port_num) !=
+ if (rdma_port_get_link_layer(qp->device, attr.port_num) !=
IB_LINK_LAYER_INFINIBAND)
return true;
goto lid_check;
@@ -1655,7 +1655,7 @@
/* Can't get a quick answer, iterate over all ports */
for (port = 0; port < qp->device->phys_port_cnt; port++)
- if (qp->device->get_link_layer(qp->device, port) !=
+ if (rdma_port_get_link_layer(qp->device, port) !=
IB_LINK_LAYER_INFINIBAND)
num_eth_ports++;
diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index b3ad37f..ecbac91 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -93,11 +93,13 @@
struct ib_device ibdev;
struct list_head list;
unsigned long flags;
-#define BNXT_RE_FLAG_NETDEV_REGISTERED 0
-#define BNXT_RE_FLAG_IBDEV_REGISTERED 1
-#define BNXT_RE_FLAG_GOT_MSIX 2
-#define BNXT_RE_FLAG_RCFW_CHANNEL_EN 8
-#define BNXT_RE_FLAG_QOS_WORK_REG 16
+#define BNXT_RE_FLAG_NETDEV_REGISTERED 0
+#define BNXT_RE_FLAG_IBDEV_REGISTERED 1
+#define BNXT_RE_FLAG_GOT_MSIX 2
+#define BNXT_RE_FLAG_HAVE_L2_REF 3
+#define BNXT_RE_FLAG_RCFW_CHANNEL_EN 4
+#define BNXT_RE_FLAG_QOS_WORK_REG 5
+#define BNXT_RE_FLAG_TASK_IN_PROG 6
struct net_device *netdev;
unsigned int version, major, minor;
struct bnxt_en_dev *en_dev;
@@ -108,6 +110,8 @@
struct delayed_work worker;
u8 cur_prio_map;
+ u8 active_speed;
+ u8 active_width;
/* FP Notification Queue (CQ & SRQ) */
struct tasklet_struct nq_task;
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 01eee15..0d89621 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -259,14 +259,9 @@
port_attr->sm_sl = 0;
port_attr->subnet_timeout = 0;
port_attr->init_type_reply = 0;
- /* call the underlying netdev's ethtool hooks to query speed settings
- * for which we acquire rtnl_lock _only_ if it's registered with
- * IB stack to avoid race in the NETDEV_UNREG path
- */
- if (test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
- if (ib_get_eth_speed(ibdev, port_num, &port_attr->active_speed,
- &port_attr->active_width))
- return -EINVAL;
+ port_attr->active_speed = rdev->active_speed;
+ port_attr->active_width = rdev->active_width;
+
return 0;
}
@@ -319,6 +314,7 @@
struct bnxt_re_gid_ctx *ctx, **ctx_tbl;
struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+ struct bnxt_qplib_gid *gid_to_del;
/* Delete the entry from the hardware */
ctx = *context;
@@ -328,11 +324,25 @@
if (sgid_tbl && sgid_tbl->active) {
if (ctx->idx >= sgid_tbl->max)
return -EINVAL;
+ gid_to_del = &sgid_tbl->tbl[ctx->idx];
+ /* DEL_GID is called in WQ context(netdevice_event_work_handler)
+ * or via the ib_unregister_device path. In the former case QP1
+ * may not be destroyed yet, in which case just return as FW
+ * needs that entry to be present and will fail it's deletion.
+ * We could get invoked again after QP1 is destroyed OR get an
+ * ADD_GID call with a different GID value for the same index
+ * where we issue MODIFY_GID cmd to update the GID entry -- TBD
+ */
+ if (ctx->idx == 0 &&
+ rdma_link_local_addr((struct in6_addr *)gid_to_del) &&
+ ctx->refcnt == 1 && rdev->qp1_sqp) {
+ dev_dbg(rdev_to_dev(rdev),
+ "Trying to delete GID0 while QP1 is alive\n");
+ return -EFAULT;
+ }
ctx->refcnt--;
if (!ctx->refcnt) {
- rc = bnxt_qplib_del_sgid(sgid_tbl,
- &sgid_tbl->tbl[ctx->idx],
- true);
+ rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, true);
if (rc) {
dev_err(rdev_to_dev(rdev),
"Failed to remove GID: %#x", rc);
@@ -816,6 +826,8 @@
kfree(rdev->sqp_ah);
kfree(rdev->qp1_sqp);
+ rdev->qp1_sqp = NULL;
+ rdev->sqp_ah = NULL;
}
if (!IS_ERR_OR_NULL(qp->rumem))
@@ -1436,11 +1448,14 @@
qp->qplib_qp.modify_flags |=
CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu);
+ qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu);
} else if (qp_attr->qp_state == IB_QPS_RTR) {
qp->qplib_qp.modify_flags |=
CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
qp->qplib_qp.path_mtu =
__from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu));
+ qp->qplib_qp.mtu =
+ ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu));
}
if (qp_attr_mask & IB_QP_TIMEOUT) {
@@ -1551,43 +1566,46 @@
{
struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
struct bnxt_re_dev *rdev = qp->rdev;
- struct bnxt_qplib_qp qplib_qp;
+ struct bnxt_qplib_qp *qplib_qp;
int rc;
- memset(&qplib_qp, 0, sizeof(struct bnxt_qplib_qp));
- qplib_qp.id = qp->qplib_qp.id;
- qplib_qp.ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index;
+ qplib_qp = kzalloc(sizeof(*qplib_qp), GFP_KERNEL);
+ if (!qplib_qp)
+ return -ENOMEM;
- rc = bnxt_qplib_query_qp(&rdev->qplib_res, &qplib_qp);
+ qplib_qp->id = qp->qplib_qp.id;
+ qplib_qp->ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index;
+
+ rc = bnxt_qplib_query_qp(&rdev->qplib_res, qplib_qp);
if (rc) {
dev_err(rdev_to_dev(rdev), "Failed to query HW QP");
- return rc;
+ goto out;
}
- qp_attr->qp_state = __to_ib_qp_state(qplib_qp.state);
- qp_attr->en_sqd_async_notify = qplib_qp.en_sqd_async_notify ? 1 : 0;
- qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp.access);
- qp_attr->pkey_index = qplib_qp.pkey_index;
- qp_attr->qkey = qplib_qp.qkey;
+ qp_attr->qp_state = __to_ib_qp_state(qplib_qp->state);
+ qp_attr->en_sqd_async_notify = qplib_qp->en_sqd_async_notify ? 1 : 0;
+ qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp->access);
+ qp_attr->pkey_index = qplib_qp->pkey_index;
+ qp_attr->qkey = qplib_qp->qkey;
qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
- rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp.ah.flow_label,
- qplib_qp.ah.host_sgid_index,
- qplib_qp.ah.hop_limit,
- qplib_qp.ah.traffic_class);
- rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp.ah.dgid.data);
- rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp.ah.sl);
- ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp.ah.dmac);
- qp_attr->path_mtu = __to_ib_mtu(qplib_qp.path_mtu);
- qp_attr->timeout = qplib_qp.timeout;
- qp_attr->retry_cnt = qplib_qp.retry_cnt;
- qp_attr->rnr_retry = qplib_qp.rnr_retry;
- qp_attr->min_rnr_timer = qplib_qp.min_rnr_timer;
- qp_attr->rq_psn = qplib_qp.rq.psn;
- qp_attr->max_rd_atomic = qplib_qp.max_rd_atomic;
- qp_attr->sq_psn = qplib_qp.sq.psn;
- qp_attr->max_dest_rd_atomic = qplib_qp.max_dest_rd_atomic;
- qp_init_attr->sq_sig_type = qplib_qp.sig_type ? IB_SIGNAL_ALL_WR :
- IB_SIGNAL_REQ_WR;
- qp_attr->dest_qp_num = qplib_qp.dest_qpn;
+ rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp->ah.flow_label,
+ qplib_qp->ah.host_sgid_index,
+ qplib_qp->ah.hop_limit,
+ qplib_qp->ah.traffic_class);
+ rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp->ah.dgid.data);
+ rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp->ah.sl);
+ ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp->ah.dmac);
+ qp_attr->path_mtu = __to_ib_mtu(qplib_qp->path_mtu);
+ qp_attr->timeout = qplib_qp->timeout;
+ qp_attr->retry_cnt = qplib_qp->retry_cnt;
+ qp_attr->rnr_retry = qplib_qp->rnr_retry;
+ qp_attr->min_rnr_timer = qplib_qp->min_rnr_timer;
+ qp_attr->rq_psn = qplib_qp->rq.psn;
+ qp_attr->max_rd_atomic = qplib_qp->max_rd_atomic;
+ qp_attr->sq_psn = qplib_qp->sq.psn;
+ qp_attr->max_dest_rd_atomic = qplib_qp->max_dest_rd_atomic;
+ qp_init_attr->sq_sig_type = qplib_qp->sig_type ? IB_SIGNAL_ALL_WR :
+ IB_SIGNAL_REQ_WR;
+ qp_attr->dest_qp_num = qplib_qp->dest_qpn;
qp_attr->cap.max_send_wr = qp->qplib_qp.sq.max_wqe;
qp_attr->cap.max_send_sge = qp->qplib_qp.sq.max_sge;
@@ -1596,7 +1614,9 @@
qp_attr->cap.max_inline_data = qp->qplib_qp.max_inline_data;
qp_init_attr->cap = qp_attr->cap;
- return 0;
+out:
+ kfree(qplib_qp);
+ return rc;
}
/* Routine for sending QP1 packets for RoCE V1 an V2
@@ -1908,6 +1928,7 @@
switch (wr->opcode) {
case IB_WR_ATOMIC_CMP_AND_SWP:
wqe->type = BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP;
+ wqe->atomic.cmp_data = atomic_wr(wr)->compare_add;
wqe->atomic.swap_data = atomic_wr(wr)->swap;
break;
case IB_WR_ATOMIC_FETCH_AND_ADD:
@@ -3062,7 +3083,7 @@
return rc;
}
- if (mr->npages && mr->pages) {
+ if (mr->pages) {
rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res,
&mr->qplib_frpl);
kfree(mr->pages);
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 82d1cbc..e7450ea 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -1161,6 +1161,8 @@
}
}
set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags);
+ ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+ &rdev->active_width);
bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_PORT_ACTIVE);
bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_GID_CHANGE);
@@ -1255,10 +1257,14 @@
else if (netif_carrier_ok(rdev->netdev))
bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1,
IB_EVENT_PORT_ACTIVE);
+ ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+ &rdev->active_width);
break;
default:
break;
}
+ smp_mb__before_atomic();
+ clear_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags);
kfree(re_work);
}
@@ -1317,6 +1323,11 @@
break;
case NETDEV_UNREGISTER:
+ /* netdev notifier will call NETDEV_UNREGISTER again later since
+ * we are still holding the reference to the netdev
+ */
+ if (test_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags))
+ goto exit;
bnxt_re_ib_unreg(rdev, false);
bnxt_re_remove_one(rdev);
bnxt_re_dev_unreg(rdev);
@@ -1335,6 +1346,7 @@
re_work->vlan_dev = (real_dev == netdev ?
NULL : netdev);
INIT_WORK(&re_work->work, bnxt_re_task);
+ set_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags);
queue_work(bnxt_re_wq, &re_work->work);
}
}
@@ -1375,6 +1387,22 @@
static void __exit bnxt_re_mod_exit(void)
{
+ struct bnxt_re_dev *rdev;
+ LIST_HEAD(to_be_deleted);
+
+ mutex_lock(&bnxt_re_dev_lock);
+ /* Free all adapter allocated resources */
+ if (!list_empty(&bnxt_re_dev_list))
+ list_splice_init(&bnxt_re_dev_list, &to_be_deleted);
+ mutex_unlock(&bnxt_re_dev_lock);
+
+ list_for_each_entry(rdev, &to_be_deleted, list) {
+ dev_info(rdev_to_dev(rdev), "Unregistering Device");
+ bnxt_re_dev_stop(rdev);
+ bnxt_re_ib_unreg(rdev, true);
+ bnxt_re_remove_one(rdev);
+ bnxt_re_dev_unreg(rdev);
+ }
unregister_netdevice_notifier(&bnxt_re_netdev_notifier);
if (bnxt_re_wq)
destroy_workqueue(bnxt_re_wq);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 391bb70..2bdb156 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -107,6 +107,9 @@
return -EINVAL;
}
+ if (test_bit(FIRMWARE_TIMED_OUT, &rcfw->flags))
+ return -ETIMEDOUT;
+
/* Cmdq are in 16-byte units, each request can consume 1 or more
* cmdqe
*/
@@ -226,6 +229,7 @@
/* timed out */
dev_err(&rcfw->pdev->dev, "QPLIB: cmdq[%#x]=%#x timedout (%d)msec",
cookie, opcode, RCFW_CMD_WAIT_TIME_MS);
+ set_bit(FIRMWARE_TIMED_OUT, &rcfw->flags);
return rc;
}
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 0ed312f..85b16da 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -162,8 +162,9 @@
unsigned long *cmdq_bitmap;
u32 bmap_size;
unsigned long flags;
-#define FIRMWARE_INITIALIZED_FLAG 1
+#define FIRMWARE_INITIALIZED_FLAG BIT(0)
#define FIRMWARE_FIRST_FLAG BIT(31)
+#define FIRMWARE_TIMED_OUT BIT(3)
wait_queue_head_t waitq;
int (*aeq_handler)(struct bnxt_qplib_rcfw *,
struct creq_func_event *);
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index ceaa2fa..daf7a56 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2333,9 +2333,14 @@
unsigned int stid = GET_TID(rpl);
struct c4iw_listen_ep *ep = get_ep_from_stid(dev, stid);
+ if (!ep) {
+ pr_debug("%s stid %d lookup failure!\n", __func__, stid);
+ goto out;
+ }
pr_debug("%s ep %p\n", __func__, ep);
c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
c4iw_put_ep(&ep->com);
+out:
return 0;
}
@@ -2594,9 +2599,9 @@
c4iw_put_ep(&child_ep->com);
reject:
reject_cr(dev, hwtid, skb);
+out:
if (parent_ep)
c4iw_put_ep(&parent_ep->com);
-out:
return 0;
}
@@ -3457,7 +3462,7 @@
cm_id->provider_data = ep;
goto out;
}
-
+ remove_handle(ep->com.dev, &ep->com.dev->stid_idr, ep->stid);
cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid,
ep->com.local_addr.ss_family);
fail2:
diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h
index 9b15664..a65e4cbd 100644
--- a/drivers/infiniband/hw/i40iw/i40iw.h
+++ b/drivers/infiniband/hw/i40iw/i40iw.h
@@ -201,7 +201,6 @@
CEQ_CREATED,
ILQ_CREATED,
IEQ_CREATED,
- INET_NOTIFIER,
IP_ADDR_REGISTERED,
RDMA_DEV_REGISTERED
};
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 14f36ba..5230dd3 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -1504,23 +1504,40 @@
}
/**
- * listen_port_in_use - determine if port is in use
- * @port: Listen port number
+ * i40iw_port_in_use - determine if port is in use
+ * @port: port number
+ * @active_side: flag for listener side vs active side
*/
-static bool i40iw_listen_port_in_use(struct i40iw_cm_core *cm_core, u16 port)
+static bool i40iw_port_in_use(struct i40iw_cm_core *cm_core, u16 port, bool active_side)
{
struct i40iw_cm_listener *listen_node;
+ struct i40iw_cm_node *cm_node;
unsigned long flags;
bool ret = false;
- spin_lock_irqsave(&cm_core->listen_list_lock, flags);
- list_for_each_entry(listen_node, &cm_core->listen_nodes, list) {
- if (listen_node->loc_port == port) {
- ret = true;
- break;
+ if (active_side) {
+ /* search connected node list */
+ spin_lock_irqsave(&cm_core->ht_lock, flags);
+ list_for_each_entry(cm_node, &cm_core->connected_nodes, list) {
+ if (cm_node->loc_port == port) {
+ ret = true;
+ break;
+ }
}
+ if (!ret)
+ clear_bit(port, cm_core->active_side_ports);
+ spin_unlock_irqrestore(&cm_core->ht_lock, flags);
+ } else {
+ spin_lock_irqsave(&cm_core->listen_list_lock, flags);
+ list_for_each_entry(listen_node, &cm_core->listen_nodes, list) {
+ if (listen_node->loc_port == port) {
+ ret = true;
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
}
- spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
+
return ret;
}
@@ -1868,7 +1885,7 @@
spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
if (listener->iwdev) {
- if (apbvt_del && !i40iw_listen_port_in_use(cm_core, listener->loc_port))
+ if (apbvt_del && !i40iw_port_in_use(cm_core, listener->loc_port, false))
i40iw_manage_apbvt(listener->iwdev,
listener->loc_port,
I40IW_MANAGE_APBVT_DEL);
@@ -2247,21 +2264,21 @@
if (cm_node->listener) {
i40iw_dec_refcnt_listen(cm_core, cm_node->listener, 0, true);
} else {
- if (!i40iw_listen_port_in_use(cm_core, cm_node->loc_port) &&
- cm_node->apbvt_set) {
+ if (!i40iw_port_in_use(cm_core, cm_node->loc_port, true) && cm_node->apbvt_set) {
i40iw_manage_apbvt(cm_node->iwdev,
cm_node->loc_port,
I40IW_MANAGE_APBVT_DEL);
- i40iw_get_addr_info(cm_node, &nfo);
- if (cm_node->qhash_set) {
- i40iw_manage_qhash(cm_node->iwdev,
- &nfo,
- I40IW_QHASH_TYPE_TCP_ESTABLISHED,
- I40IW_QHASH_MANAGE_TYPE_DELETE,
- NULL,
- false);
- cm_node->qhash_set = 0;
- }
+ cm_node->apbvt_set = 0;
+ }
+ i40iw_get_addr_info(cm_node, &nfo);
+ if (cm_node->qhash_set) {
+ i40iw_manage_qhash(cm_node->iwdev,
+ &nfo,
+ I40IW_QHASH_TYPE_TCP_ESTABLISHED,
+ I40IW_QHASH_MANAGE_TYPE_DELETE,
+ NULL,
+ false);
+ cm_node->qhash_set = 0;
}
}
@@ -3255,7 +3272,8 @@
tcp_info->snd_mss = cpu_to_le32(((u32)cm_node->tcp_cntxt.mss));
if (cm_node->vlan_id < VLAN_TAG_PRESENT) {
tcp_info->insert_vlan_tag = true;
- tcp_info->vlan_tag = cpu_to_le16(cm_node->vlan_id);
+ tcp_info->vlan_tag = cpu_to_le16(((u16)cm_node->user_pri << I40IW_VLAN_PRIO_SHIFT) |
+ cm_node->vlan_id);
}
if (cm_node->ipv4) {
tcp_info->src_port = cpu_to_le16(cm_node->loc_port);
@@ -3737,10 +3755,8 @@
struct sockaddr_in *raddr;
struct sockaddr_in6 *laddr6;
struct sockaddr_in6 *raddr6;
- bool qhash_set = false;
- int apbvt_set = 0;
- int err = 0;
- enum i40iw_status_code status;
+ int ret = 0;
+ unsigned long flags;
ibqp = i40iw_get_qp(cm_id->device, conn_param->qpn);
if (!ibqp)
@@ -3789,32 +3805,6 @@
cm_info.user_pri = rt_tos2priority(cm_id->tos);
i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_DCB, "%s TOS:[%d] UP:[%d]\n",
__func__, cm_id->tos, cm_info.user_pri);
- if ((cm_info.ipv4 && (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr)) ||
- (!cm_info.ipv4 && memcmp(laddr6->sin6_addr.in6_u.u6_addr32,
- raddr6->sin6_addr.in6_u.u6_addr32,
- sizeof(laddr6->sin6_addr.in6_u.u6_addr32)))) {
- status = i40iw_manage_qhash(iwdev,
- &cm_info,
- I40IW_QHASH_TYPE_TCP_ESTABLISHED,
- I40IW_QHASH_MANAGE_TYPE_ADD,
- NULL,
- true);
- if (status)
- return -EINVAL;
- qhash_set = true;
- }
- status = i40iw_manage_apbvt(iwdev, cm_info.loc_port, I40IW_MANAGE_APBVT_ADD);
- if (status) {
- i40iw_manage_qhash(iwdev,
- &cm_info,
- I40IW_QHASH_TYPE_TCP_ESTABLISHED,
- I40IW_QHASH_MANAGE_TYPE_DELETE,
- NULL,
- false);
- return -EINVAL;
- }
-
- apbvt_set = 1;
cm_id->add_ref(cm_id);
cm_node = i40iw_create_cm_node(&iwdev->cm_core, iwdev,
conn_param->private_data_len,
@@ -3822,17 +3812,40 @@
&cm_info);
if (IS_ERR(cm_node)) {
- err = PTR_ERR(cm_node);
- goto err_out;
+ ret = PTR_ERR(cm_node);
+ cm_id->rem_ref(cm_id);
+ return ret;
}
+ if ((cm_info.ipv4 && (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr)) ||
+ (!cm_info.ipv4 && memcmp(laddr6->sin6_addr.in6_u.u6_addr32,
+ raddr6->sin6_addr.in6_u.u6_addr32,
+ sizeof(laddr6->sin6_addr.in6_u.u6_addr32)))) {
+ if (i40iw_manage_qhash(iwdev, &cm_info, I40IW_QHASH_TYPE_TCP_ESTABLISHED,
+ I40IW_QHASH_MANAGE_TYPE_ADD, NULL, true)) {
+ ret = -EINVAL;
+ goto err;
+ }
+ cm_node->qhash_set = true;
+ }
+
+ spin_lock_irqsave(&iwdev->cm_core.ht_lock, flags);
+ if (!test_and_set_bit(cm_info.loc_port, iwdev->cm_core.active_side_ports)) {
+ spin_unlock_irqrestore(&iwdev->cm_core.ht_lock, flags);
+ if (i40iw_manage_apbvt(iwdev, cm_info.loc_port, I40IW_MANAGE_APBVT_ADD)) {
+ ret = -EINVAL;
+ goto err;
+ }
+ } else {
+ spin_unlock_irqrestore(&iwdev->cm_core.ht_lock, flags);
+ }
+
+ cm_node->apbvt_set = true;
i40iw_record_ird_ord(cm_node, (u16)conn_param->ird, (u16)conn_param->ord);
if (cm_node->send_rdma0_op == SEND_RDMA_READ_ZERO &&
!cm_node->ord_size)
cm_node->ord_size = 1;
- cm_node->apbvt_set = apbvt_set;
- cm_node->qhash_set = qhash_set;
iwqp->cm_node = cm_node;
cm_node->iwqp = iwqp;
iwqp->cm_id = cm_id;
@@ -3840,11 +3853,9 @@
if (cm_node->state != I40IW_CM_STATE_OFFLOADED) {
cm_node->state = I40IW_CM_STATE_SYN_SENT;
- err = i40iw_send_syn(cm_node, 0);
- if (err) {
- i40iw_rem_ref_cm_node(cm_node);
- goto err_out;
- }
+ ret = i40iw_send_syn(cm_node, 0);
+ if (ret)
+ goto err;
}
i40iw_debug(cm_node->dev,
@@ -3853,9 +3864,10 @@
cm_node->rem_port,
cm_node,
cm_node->cm_id);
+
return 0;
-err_out:
+err:
if (cm_info.ipv4)
i40iw_debug(&iwdev->sc_dev,
I40IW_DEBUG_CM,
@@ -3867,22 +3879,10 @@
"Api - connect() FAILED: dest addr=%pI6",
cm_info.rem_addr);
- if (qhash_set)
- i40iw_manage_qhash(iwdev,
- &cm_info,
- I40IW_QHASH_TYPE_TCP_ESTABLISHED,
- I40IW_QHASH_MANAGE_TYPE_DELETE,
- NULL,
- false);
-
- if (apbvt_set && !i40iw_listen_port_in_use(&iwdev->cm_core,
- cm_info.loc_port))
- i40iw_manage_apbvt(iwdev,
- cm_info.loc_port,
- I40IW_MANAGE_APBVT_DEL);
+ i40iw_rem_ref_cm_node(cm_node);
cm_id->rem_ref(cm_id);
iwdev->cm_core.stats_connect_errs++;
- return err;
+ return ret;
}
/**
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.h b/drivers/infiniband/hw/i40iw/i40iw_cm.h
index 2e52e38..45abef7 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.h
@@ -71,6 +71,9 @@
#define I40IW_HW_IRD_SETTING_32 32
#define I40IW_HW_IRD_SETTING_64 64
+#define MAX_PORTS 65536
+#define I40IW_VLAN_PRIO_SHIFT 13
+
enum ietf_mpa_flags {
IETF_MPA_FLAGS_MARKERS = 0x80, /* receive Markers */
IETF_MPA_FLAGS_CRC = 0x40, /* receive Markers */
@@ -411,6 +414,8 @@
spinlock_t ht_lock; /* manage hash table */
spinlock_t listen_list_lock; /* listen list */
+ unsigned long active_side_ports[BITS_TO_LONGS(MAX_PORTS)];
+
u64 stats_nodes_created;
u64 stats_nodes_destroyed;
u64 stats_listen_created;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index cc742c3..27590ae 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -99,8 +99,6 @@
.notifier_call = i40iw_net_event
};
-static atomic_t i40iw_notifiers_registered;
-
/**
* i40iw_find_i40e_handler - find a handler given a client info
* @ldev: pointer to a client info
@@ -1376,11 +1374,20 @@
*/
static void i40iw_register_notifiers(void)
{
- if (atomic_inc_return(&i40iw_notifiers_registered) == 1) {
- register_inetaddr_notifier(&i40iw_inetaddr_notifier);
- register_inet6addr_notifier(&i40iw_inetaddr6_notifier);
- register_netevent_notifier(&i40iw_net_notifier);
- }
+ register_inetaddr_notifier(&i40iw_inetaddr_notifier);
+ register_inet6addr_notifier(&i40iw_inetaddr6_notifier);
+ register_netevent_notifier(&i40iw_net_notifier);
+}
+
+/**
+ * i40iw_unregister_notifiers - unregister tcp ip notifiers
+ */
+
+static void i40iw_unregister_notifiers(void)
+{
+ unregister_netevent_notifier(&i40iw_net_notifier);
+ unregister_inetaddr_notifier(&i40iw_inetaddr_notifier);
+ unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier);
}
/**
@@ -1400,6 +1407,11 @@
u32 i;
u32 size;
+ if (!ldev->msix_count) {
+ i40iw_pr_err("No MSI-X vectors\n");
+ return I40IW_ERR_CONFIG;
+ }
+
iwdev->msix_count = ldev->msix_count;
size = sizeof(struct i40iw_msix_vector) * iwdev->msix_count;
@@ -1462,12 +1474,6 @@
if (!iwdev->reset)
i40iw_del_macip_entry(iwdev, (u8)iwdev->mac_ip_table_idx);
/* fallthrough */
- case INET_NOTIFIER:
- if (!atomic_dec_return(&i40iw_notifiers_registered)) {
- unregister_netevent_notifier(&i40iw_net_notifier);
- unregister_inetaddr_notifier(&i40iw_inetaddr_notifier);
- unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier);
- }
/* fallthrough */
case PBLE_CHUNK_MEM:
i40iw_destroy_pble_pool(dev, iwdev->pble_rsrc);
@@ -1550,7 +1556,7 @@
status = i40iw_save_msix_info(iwdev, ldev);
if (status)
- goto exit;
+ return status;
iwdev->hw.dev_context = (void *)ldev->pcidev;
iwdev->hw.hw_addr = ldev->hw_addr;
status = i40iw_allocate_dma_mem(&iwdev->hw,
@@ -1667,8 +1673,6 @@
break;
iwdev->init_state = PBLE_CHUNK_MEM;
iwdev->virtchnl_wq = alloc_ordered_workqueue("iwvch", WQ_MEM_RECLAIM);
- i40iw_register_notifiers();
- iwdev->init_state = INET_NOTIFIER;
status = i40iw_add_mac_ip(iwdev);
if (status)
break;
@@ -2018,6 +2022,8 @@
i40iw_client.type = I40E_CLIENT_IWARP;
spin_lock_init(&i40iw_handler_lock);
ret = i40e_register_client(&i40iw_client);
+ i40iw_register_notifiers();
+
return ret;
}
@@ -2029,6 +2035,7 @@
*/
static void __exit i40iw_exit_module(void)
{
+ i40iw_unregister_notifiers();
i40e_unregister_client(&i40iw_client);
}
diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c
index 62f1f45..e52dbbb 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_utils.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c
@@ -160,7 +160,7 @@
return NOTIFY_DONE;
iwdev = &hdl->device;
- if (iwdev->init_state < INET_NOTIFIER)
+ if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing)
return NOTIFY_DONE;
netdev = iwdev->ldev->netdev;
@@ -217,7 +217,7 @@
return NOTIFY_DONE;
iwdev = &hdl->device;
- if (iwdev->init_state < INET_NOTIFIER)
+ if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing)
return NOTIFY_DONE;
netdev = iwdev->ldev->netdev;
@@ -266,7 +266,7 @@
if (!iwhdl)
return NOTIFY_DONE;
iwdev = &iwhdl->device;
- if (iwdev->init_state < INET_NOTIFIER)
+ if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing)
return NOTIFY_DONE;
p = (__be32 *)neigh->primary_key;
i40iw_copy_ip_ntohl(local_ipaddr, p);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 1aa4110..28b3d02 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -1027,7 +1027,19 @@
iwqp->hw_tcp_state = I40IW_TCP_STATE_CLOSED;
iwqp->last_aeq = I40IW_AE_RESET_SENT;
spin_unlock_irqrestore(&iwqp->lock, flags);
+ i40iw_cm_disconn(iwqp);
}
+ } else {
+ spin_lock_irqsave(&iwqp->lock, flags);
+ if (iwqp->cm_id) {
+ if (atomic_inc_return(&iwqp->close_timer_started) == 1) {
+ iwqp->cm_id->add_ref(iwqp->cm_id);
+ i40iw_schedule_cm_timer(iwqp->cm_node,
+ (struct i40iw_puda_buf *)iwqp,
+ I40IW_TIMER_TYPE_CLOSE, 1, 0);
+ }
+ }
+ spin_unlock_irqrestore(&iwqp->lock, flags);
}
}
return 0;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index ab3c562..05fb4bd 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3837,11 +3837,13 @@
if (!dbg)
return -ENOMEM;
+ dev->delay_drop.dbg = dbg;
+
dbg->dir_debugfs =
debugfs_create_dir("delay_drop",
dev->mdev->priv.dbg_root);
if (!dbg->dir_debugfs)
- return -ENOMEM;
+ goto out_debugfs;
dbg->events_cnt_debugfs =
debugfs_create_atomic_t("num_timeout_events", 0400,
@@ -3865,8 +3867,6 @@
if (!dbg->timeout_debugfs)
goto out_debugfs;
- dev->delay_drop.dbg = dbg;
-
return 0;
out_debugfs:
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index dcb5942..65b166c 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -252,7 +252,10 @@
case OCRDMA_MBX_ADDI_STATUS_INSUFFICIENT_RESOURCES:
err_num = -EAGAIN;
break;
+ default:
+ err_num = -EFAULT;
}
+ break;
default:
err_num = -EFAULT;
}
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 663a0c3..984aa34 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -416,9 +416,34 @@
return (enum ib_wc_status)status;
}
-static inline int pvrdma_wc_opcode_to_ib(int opcode)
+static inline int pvrdma_wc_opcode_to_ib(unsigned int opcode)
{
- return opcode;
+ switch (opcode) {
+ case PVRDMA_WC_SEND:
+ return IB_WC_SEND;
+ case PVRDMA_WC_RDMA_WRITE:
+ return IB_WC_RDMA_WRITE;
+ case PVRDMA_WC_RDMA_READ:
+ return IB_WC_RDMA_READ;
+ case PVRDMA_WC_COMP_SWAP:
+ return IB_WC_COMP_SWAP;
+ case PVRDMA_WC_FETCH_ADD:
+ return IB_WC_FETCH_ADD;
+ case PVRDMA_WC_LOCAL_INV:
+ return IB_WC_LOCAL_INV;
+ case PVRDMA_WC_FAST_REG_MR:
+ return IB_WC_REG_MR;
+ case PVRDMA_WC_MASKED_COMP_SWAP:
+ return IB_WC_MASKED_COMP_SWAP;
+ case PVRDMA_WC_MASKED_FETCH_ADD:
+ return IB_WC_MASKED_FETCH_ADD;
+ case PVRDMA_WC_RECV:
+ return IB_WC_RECV;
+ case PVRDMA_WC_RECV_RDMA_WITH_IMM:
+ return IB_WC_RECV_RDMA_WITH_IMM;
+ default:
+ return IB_WC_SEND;
+ }
}
static inline int pvrdma_wc_flags_to_ib(int flags)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 14b62f7..7774654 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -823,12 +823,18 @@
wc->status != IB_WC_WR_FLUSH_ERR) {
struct ipoib_neigh *neigh;
- if (wc->status != IB_WC_RNR_RETRY_EXC_ERR)
- ipoib_warn(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n",
- wc->status, wr_id, wc->vendor_err);
+ /* IB_WC[_RNR]_RETRY_EXC_ERR error is part of the life cycle,
+ * so don't make waves.
+ */
+ if (wc->status == IB_WC_RNR_RETRY_EXC_ERR ||
+ wc->status == IB_WC_RETRY_EXC_ERR)
+ ipoib_dbg(priv,
+ "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n",
+ __func__, wc->status, wr_id, wc->vendor_err);
else
- ipoib_dbg(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n",
- wc->status, wr_id, wc->vendor_err);
+ ipoib_warn(priv,
+ "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n",
+ __func__, wc->status, wr_id, wc->vendor_err);
spin_lock_irqsave(&priv->lock, flags);
neigh = tx->neigh;
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 519149e..b5df99c 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1042,7 +1042,7 @@
{
const __be32 *cell;
u64 hwid;
- int i;
+ int cpu;
cell = of_get_property(dn, "reg", NULL);
if (!cell)
@@ -1056,9 +1056,9 @@
if (hwid & ~MPIDR_HWID_BITMASK)
return -1;
- for (i = 0; i < num_possible_cpus(); i++)
- if (cpu_logical_map(i) == hwid)
- return i;
+ for_each_possible_cpu(cpu)
+ if (cpu_logical_map(cpu) == hwid)
+ return cpu;
return -1;
}
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 2370e6d..cd0bcc3 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -173,7 +173,9 @@
{
struct its_cmd_info info = {
.cmd_type = MAP_VLPI,
- .map = map,
+ {
+ .map = map,
+ },
};
/*
@@ -189,7 +191,9 @@
{
struct its_cmd_info info = {
.cmd_type = GET_VLPI,
- .map = map,
+ {
+ .map = map,
+ },
};
return irq_set_vcpu_affinity(irq, &info);
@@ -205,7 +209,9 @@
{
struct its_cmd_info info = {
.cmd_type = inv ? PROP_UPDATE_AND_INV_VLPI : PROP_UPDATE_VLPI,
- .config = config,
+ {
+ .config = config,
+ },
};
return irq_set_vcpu_affinity(irq, &info);
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 6e52a88..40159ac 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -169,7 +169,7 @@
{
unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq);
- write_gic_rmask(BIT(intr));
+ write_gic_rmask(intr);
gic_clear_pcpu_masks(intr);
}
@@ -179,7 +179,7 @@
unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq);
unsigned int cpu;
- write_gic_smask(BIT(intr));
+ write_gic_smask(intr);
gic_clear_pcpu_masks(intr);
cpu = cpumask_first_and(affinity, cpu_online_mask);
@@ -767,7 +767,7 @@
for (i = 0; i < gic_shared_intrs; i++) {
change_gic_pol(i, GIC_POL_ACTIVE_HIGH);
change_gic_trig(i, GIC_TRIG_LEVEL);
- write_gic_rmask(BIT(i));
+ write_gic_rmask(i);
}
for (i = 0; i < gic_vpes; i++) {
diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 6c44609..cd2b3c6 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -825,7 +825,6 @@
isdn_net_local *lp;
struct ippp_struct *is;
int proto;
- unsigned char protobuf[4];
is = file->private_data;
@@ -839,24 +838,28 @@
if (!lp)
printk(KERN_DEBUG "isdn_ppp_write: lp == NULL\n");
else {
- /*
- * Don't reset huptimer for
- * LCP packets. (Echo requests).
- */
- if (copy_from_user(protobuf, buf, 4))
- return -EFAULT;
- proto = PPP_PROTOCOL(protobuf);
- if (proto != PPP_LCP)
- lp->huptimer = 0;
+ if (lp->isdn_device < 0 || lp->isdn_channel < 0) {
+ unsigned char protobuf[4];
+ /*
+ * Don't reset huptimer for
+ * LCP packets. (Echo requests).
+ */
+ if (copy_from_user(protobuf, buf, 4))
+ return -EFAULT;
- if (lp->isdn_device < 0 || lp->isdn_channel < 0)
+ proto = PPP_PROTOCOL(protobuf);
+ if (proto != PPP_LCP)
+ lp->huptimer = 0;
+
return 0;
+ }
if ((dev->drv[lp->isdn_device]->flags & DRV_FLAG_RUNNING) &&
lp->dialstate == 0 &&
(lp->flags & ISDN_NET_CONNECTED)) {
unsigned short hl;
struct sk_buff *skb;
+ unsigned char *cpy_buf;
/*
* we need to reserve enough space in front of
* sk_buff. old call to dev_alloc_skb only reserved
@@ -869,11 +872,21 @@
return count;
}
skb_reserve(skb, hl);
- if (copy_from_user(skb_put(skb, count), buf, count))
+ cpy_buf = skb_put(skb, count);
+ if (copy_from_user(cpy_buf, buf, count))
{
kfree_skb(skb);
return -EFAULT;
}
+
+ /*
+ * Don't reset huptimer for
+ * LCP packets. (Echo requests).
+ */
+ proto = PPP_PROTOCOL(cpy_buf);
+ if (proto != PPP_LCP)
+ lp->huptimer = 0;
+
if (is->debug & 0x40) {
printk(KERN_DEBUG "ppp xmit: len %d\n", (int) skb->len);
isdn_ppp_frame_log("xmit", skb->data, skb->len, 32, is->unit, lp->ppp_slot);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index c3c53f6..83eec9a 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -432,6 +432,27 @@
netif_dbg(priv, hw, priv->netdev, "updated MIB counters\n");
}
+static void bcm_sysport_update_tx_stats(struct bcm_sysport_priv *priv,
+ u64 *tx_bytes, u64 *tx_packets)
+{
+ struct bcm_sysport_tx_ring *ring;
+ u64 bytes = 0, packets = 0;
+ unsigned int start;
+ unsigned int q;
+
+ for (q = 0; q < priv->netdev->num_tx_queues; q++) {
+ ring = &priv->tx_rings[q];
+ do {
+ start = u64_stats_fetch_begin_irq(&priv->syncp);
+ bytes = ring->bytes;
+ packets = ring->packets;
+ } while (u64_stats_fetch_retry_irq(&priv->syncp, start));
+
+ *tx_bytes += bytes;
+ *tx_packets += packets;
+ }
+}
+
static void bcm_sysport_get_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
@@ -439,11 +460,16 @@
struct bcm_sysport_stats64 *stats64 = &priv->stats64;
struct u64_stats_sync *syncp = &priv->syncp;
struct bcm_sysport_tx_ring *ring;
+ u64 tx_bytes = 0, tx_packets = 0;
unsigned int start;
int i, j;
- if (netif_running(dev))
+ if (netif_running(dev)) {
bcm_sysport_update_mib_counters(priv);
+ bcm_sysport_update_tx_stats(priv, &tx_bytes, &tx_packets);
+ stats64->tx_bytes = tx_bytes;
+ stats64->tx_packets = tx_packets;
+ }
for (i = 0, j = 0; i < BCM_SYSPORT_STATS_LEN; i++) {
const struct bcm_sysport_stats *s;
@@ -461,12 +487,13 @@
continue;
p += s->stat_offset;
- if (s->stat_sizeof == sizeof(u64))
+ if (s->stat_sizeof == sizeof(u64) &&
+ s->type == BCM_SYSPORT_STAT_NETDEV64) {
do {
start = u64_stats_fetch_begin_irq(syncp);
data[i] = *(u64 *)p;
} while (u64_stats_fetch_retry_irq(syncp, start));
- else
+ } else
data[i] = *(u32 *)p;
j++;
}
@@ -1716,27 +1743,12 @@
{
struct bcm_sysport_priv *priv = netdev_priv(dev);
struct bcm_sysport_stats64 *stats64 = &priv->stats64;
- struct bcm_sysport_tx_ring *ring;
- u64 tx_packets = 0, tx_bytes = 0;
unsigned int start;
- unsigned int q;
netdev_stats_to_stats64(stats, &dev->stats);
- for (q = 0; q < dev->num_tx_queues; q++) {
- ring = &priv->tx_rings[q];
- do {
- start = u64_stats_fetch_begin_irq(&priv->syncp);
- tx_bytes = ring->bytes;
- tx_packets = ring->packets;
- } while (u64_stats_fetch_retry_irq(&priv->syncp, start));
-
- stats->tx_bytes += tx_bytes;
- stats->tx_packets += tx_packets;
- }
-
- stats64->tx_bytes = stats->tx_bytes;
- stats64->tx_packets = stats->tx_packets;
+ bcm_sysport_update_tx_stats(priv, &stats->tx_bytes,
+ &stats->tx_packets);
do {
start = u64_stats_fetch_begin_irq(&priv->syncp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index ccd699f..7dd3d13 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -750,6 +750,10 @@
{
int rc = 0;
+ if (!is_classid_clsact_ingress(cls_flower->common.classid) ||
+ cls_flower->common.chain_index)
+ return -EOPNOTSUPP;
+
switch (cls_flower->command) {
case TC_CLSFLOWER_REPLACE:
rc = bnxt_tc_add_flow(bp, src_fid, cls_flower);
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 38c7b21..ede1876 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -374,8 +374,8 @@
#define FEC_ENET_TS_AVAIL ((uint)0x00010000)
#define FEC_ENET_TS_TIMER ((uint)0x00008000)
-#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII | FEC_ENET_TS_TIMER)
-#define FEC_NAPI_IMASK (FEC_ENET_MII | FEC_ENET_TS_TIMER)
+#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII)
+#define FEC_NAPI_IMASK FEC_ENET_MII
#define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
/* ENET interrupt coalescing macro define */
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 56f56d6..3dc2d77 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1559,14 +1559,14 @@
if (int_events == 0)
return false;
- if (int_events & FEC_ENET_RXF)
+ if (int_events & FEC_ENET_RXF_0)
fep->work_rx |= (1 << 2);
if (int_events & FEC_ENET_RXF_1)
fep->work_rx |= (1 << 0);
if (int_events & FEC_ENET_RXF_2)
fep->work_rx |= (1 << 1);
- if (int_events & FEC_ENET_TXF)
+ if (int_events & FEC_ENET_TXF_0)
fep->work_tx |= (1 << 2);
if (int_events & FEC_ENET_TXF_1)
fep->work_tx |= (1 << 0);
@@ -1604,8 +1604,8 @@
}
if (fep->ptp_clock)
- fec_ptp_check_pps_event(fep);
-
+ if (fec_ptp_check_pps_event(fep))
+ ret = IRQ_HANDLED;
return ret;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 59efbd6..5bcb223 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -37,20 +37,15 @@
}
static int hnae3_match_n_instantiate(struct hnae3_client *client,
- struct hnae3_ae_dev *ae_dev,
- bool is_reg, bool *matched)
+ struct hnae3_ae_dev *ae_dev, bool is_reg)
{
int ret;
- *matched = false;
-
/* check if this client matches the type of ae_dev */
if (!(hnae3_client_match(client->type, ae_dev->dev_type) &&
hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
return 0;
}
- /* there is a match of client and dev */
- *matched = true;
/* now, (un-)instantiate client by calling lower layer */
if (is_reg) {
@@ -69,7 +64,6 @@
{
struct hnae3_client *client_tmp;
struct hnae3_ae_dev *ae_dev;
- bool matched;
int ret = 0;
mutex_lock(&hnae3_common_lock);
@@ -86,7 +80,7 @@
/* if the client could not be initialized on current port, for
* any error reasons, move on to next available port
*/
- ret = hnae3_match_n_instantiate(client, ae_dev, true, &matched);
+ ret = hnae3_match_n_instantiate(client, ae_dev, true);
if (ret)
dev_err(&ae_dev->pdev->dev,
"match and instantiation failed for port\n");
@@ -102,12 +96,11 @@
void hnae3_unregister_client(struct hnae3_client *client)
{
struct hnae3_ae_dev *ae_dev;
- bool matched;
mutex_lock(&hnae3_common_lock);
/* un-initialize the client on every matched port */
list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
- hnae3_match_n_instantiate(client, ae_dev, false, &matched);
+ hnae3_match_n_instantiate(client, ae_dev, false);
}
list_del(&client->node);
@@ -124,7 +117,6 @@
const struct pci_device_id *id;
struct hnae3_ae_dev *ae_dev;
struct hnae3_client *client;
- bool matched;
int ret = 0;
mutex_lock(&hnae3_common_lock);
@@ -151,13 +143,10 @@
* initialize the figure out client instance
*/
list_for_each_entry(client, &hnae3_client_list, node) {
- ret = hnae3_match_n_instantiate(client, ae_dev, true,
- &matched);
+ ret = hnae3_match_n_instantiate(client, ae_dev, true);
if (ret)
dev_err(&ae_dev->pdev->dev,
"match and instantiation failed\n");
- if (matched)
- break;
}
}
@@ -175,7 +164,6 @@
const struct pci_device_id *id;
struct hnae3_ae_dev *ae_dev;
struct hnae3_client *client;
- bool matched;
mutex_lock(&hnae3_common_lock);
/* Check if there are matched ae_dev */
@@ -187,12 +175,8 @@
/* check the client list for the match with this ae_dev type and
* un-initialize the figure out client instance
*/
- list_for_each_entry(client, &hnae3_client_list, node) {
- hnae3_match_n_instantiate(client, ae_dev, false,
- &matched);
- if (matched)
- break;
- }
+ list_for_each_entry(client, &hnae3_client_list, node)
+ hnae3_match_n_instantiate(client, ae_dev, false);
ae_algo->ops->uninit_ae_dev(ae_dev);
hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
@@ -212,7 +196,6 @@
const struct pci_device_id *id;
struct hnae3_ae_algo *ae_algo;
struct hnae3_client *client;
- bool matched;
int ret = 0;
mutex_lock(&hnae3_common_lock);
@@ -246,13 +229,10 @@
* initialize the figure out client instance
*/
list_for_each_entry(client, &hnae3_client_list, node) {
- ret = hnae3_match_n_instantiate(client, ae_dev, true,
- &matched);
+ ret = hnae3_match_n_instantiate(client, ae_dev, true);
if (ret)
dev_err(&ae_dev->pdev->dev,
"match and instantiation failed\n");
- if (matched)
- break;
}
out_err:
@@ -270,7 +250,6 @@
const struct pci_device_id *id;
struct hnae3_ae_algo *ae_algo;
struct hnae3_client *client;
- bool matched;
mutex_lock(&hnae3_common_lock);
/* Check if there are matched ae_algo */
@@ -279,12 +258,8 @@
if (!id)
continue;
- list_for_each_entry(client, &hnae3_client_list, node) {
- hnae3_match_n_instantiate(client, ae_dev, false,
- &matched);
- if (matched)
- break;
- }
+ list_for_each_entry(client, &hnae3_client_list, node)
+ hnae3_match_n_instantiate(client, ae_dev, false);
ae_algo->ops->uninit_ae_dev(ae_dev);
hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index b2f28ae..1a01cad 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -49,7 +49,17 @@
#define HNAE3_CLASS_NAME_SIZE 16
#define HNAE3_DEV_INITED_B 0x0
-#define HNAE_DEV_SUPPORT_ROCE_B 0x1
+#define HNAE3_DEV_SUPPORT_ROCE_B 0x1
+#define HNAE3_DEV_SUPPORT_DCB_B 0x2
+
+#define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\
+ BIT(HNAE3_DEV_SUPPORT_ROCE_B))
+
+#define hnae3_dev_roce_supported(hdev) \
+ hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
+
+#define hnae3_dev_dcb_supported(hdev) \
+ hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
#define ring_ptr_move_fw(ring, p) \
((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
@@ -366,12 +376,12 @@
struct hnae3_tc_info {
u16 tqp_offset; /* TQP offset from base TQP */
u16 tqp_count; /* Total TQPs */
- u8 up; /* user priority */
u8 tc; /* TC index */
bool enable; /* If this TC is enable or not */
};
#define HNAE3_MAX_TC 8
+#define HNAE3_MAX_USER_PRIO 8
struct hnae3_knic_private_info {
struct net_device *netdev; /* Set by KNIC client when init instance */
u16 rss_size; /* Allocated RSS queues */
@@ -379,6 +389,7 @@
u16 num_desc;
u8 num_tc; /* Total number of enabled TCs */
+ u8 prio_tc[HNAE3_MAX_USER_PRIO]; /* TC indexed by prio */
struct hnae3_tc_info tc_info[HNAE3_MAX_TC]; /* Idx of array is HW TC */
u16 num_tqps; /* total number of TQPs in this handle */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 91ae013..758cf39 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -238,7 +238,7 @@
u8 rsv[18];
};
-#define HCLGE_VECTOR_ELEMENTS_PER_CMD 11
+#define HCLGE_VECTOR_ELEMENTS_PER_CMD 10
enum hclge_int_type {
HCLGE_INT_TX,
@@ -252,8 +252,12 @@
#define HCLGE_INT_TYPE_S 0
#define HCLGE_INT_TYPE_M 0x3
#define HCLGE_TQP_ID_S 2
-#define HCLGE_TQP_ID_M (0x3fff << HCLGE_TQP_ID_S)
+#define HCLGE_TQP_ID_M (0x7ff << HCLGE_TQP_ID_S)
+#define HCLGE_INT_GL_IDX_S 13
+#define HCLGE_INT_GL_IDX_M (0x3 << HCLGE_INT_GL_IDX_S)
__le16 tqp_type_and_id[HCLGE_VECTOR_ELEMENTS_PER_CMD];
+ u8 vfid;
+ u8 rsv;
};
#define HCLGE_TC_NUM 8
@@ -266,7 +270,8 @@
struct hclge_rx_priv_buff {
__le16 buf_num[HCLGE_TC_NUM];
- u8 rsv[8];
+ __le16 shared_buf;
+ u8 rsv[6];
};
struct hclge_query_version {
@@ -684,6 +689,7 @@
#define HCLGE_DEFAULT_TX_BUF 0x4000 /* 16k bytes */
#define HCLGE_TOTAL_PKT_BUF 0x108000 /* 1.03125M bytes */
#define HCLGE_DEFAULT_DV 0xA000 /* 40k byte */
+#define HCLGE_DEFAULT_NON_DCB_DV 0x7800 /* 30K byte */
#define HCLGE_TYPE_CRQ 0
#define HCLGE_TYPE_CSQ 1
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index bb45365..e0685e6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -46,17 +46,7 @@
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
- /* Required last entry */
- {0, }
-};
-
-static const struct pci_device_id roce_pci_tbl[] = {
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
- /* Required last entry */
+ /* required last entry */
{0, }
};
@@ -894,7 +884,7 @@
hdev->num_tqps = __le16_to_cpu(req->tqp_num);
hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
- if (hnae_get_bit(hdev->ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B)) {
+ if (hnae3_dev_roce_supported(hdev)) {
hdev->num_roce_msix =
hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number),
HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
@@ -1063,9 +1053,9 @@
hdev->base_tqp_pid = 0;
hdev->rss_size_max = 1;
hdev->rx_buf_len = cfg.rx_buf_len;
- for (i = 0; i < ETH_ALEN; i++)
- hdev->hw.mac.mac_addr[i] = cfg.mac_addr[i];
+ ether_addr_copy(hdev->hw.mac.mac_addr, cfg.mac_addr);
hdev->hw.mac.media_type = cfg.media_type;
+ hdev->hw.mac.phy_addr = cfg.phy_addr;
hdev->num_desc = cfg.tqp_desc_num;
hdev->tm_info.num_pg = 1;
hdev->tm_info.num_tc = cfg.tc_num;
@@ -1454,7 +1444,11 @@
tc_num = hclge_get_tc_num(hdev);
pfc_enable_num = hclge_get_pfc_enalbe_num(hdev);
- shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV;
+ if (hnae3_dev_dcb_supported(hdev))
+ shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV;
+ else
+ shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_NON_DCB_DV;
+
shared_buf_tc = pfc_enable_num * hdev->mps +
(tc_num - pfc_enable_num) * hdev->mps / 2 +
hdev->mps;
@@ -1495,6 +1489,16 @@
struct hclge_priv_buf *priv;
int i;
+ /* When DCB is not supported, rx private
+ * buffer is not allocated.
+ */
+ if (!hnae3_dev_dcb_supported(hdev)) {
+ if (!hclge_is_rx_buf_ok(hdev, rx_all))
+ return -ENOMEM;
+
+ return 0;
+ }
+
/* step 1, try to alloc private buffer for all enabled tc */
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
priv = &hdev->priv_buf[i];
@@ -1510,6 +1514,11 @@
priv->wl.high = 2 * hdev->mps;
priv->buf_size = priv->wl.high;
}
+ } else {
+ priv->enable = 0;
+ priv->wl.low = 0;
+ priv->wl.high = 0;
+ priv->buf_size = 0;
}
}
@@ -1522,8 +1531,15 @@
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
priv = &hdev->priv_buf[i];
- if (hdev->hw_tc_map & BIT(i))
- priv->enable = 1;
+ priv->enable = 0;
+ priv->wl.low = 0;
+ priv->wl.high = 0;
+ priv->buf_size = 0;
+
+ if (!(hdev->hw_tc_map & BIT(i)))
+ continue;
+
+ priv->enable = 1;
if (hdev->tm_info.hw_pfc_map & BIT(i)) {
priv->wl.low = 128;
@@ -1616,6 +1632,10 @@
cpu_to_le16(true << HCLGE_TC0_PRI_BUF_EN_B);
}
+ req->shared_buf =
+ cpu_to_le16((hdev->s_buf.buf_size >> HCLGE_BUF_UNIT_S) |
+ (1 << HCLGE_TC0_PRI_BUF_EN_B));
+
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
dev_err(&hdev->pdev->dev,
@@ -1782,18 +1802,22 @@
return ret;
}
- ret = hclge_rx_priv_wl_config(hdev);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "could not configure rx private waterline %d\n", ret);
- return ret;
- }
+ if (hnae3_dev_dcb_supported(hdev)) {
+ ret = hclge_rx_priv_wl_config(hdev);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "could not configure rx private waterline %d\n",
+ ret);
+ return ret;
+ }
- ret = hclge_common_thrd_config(hdev);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "could not configure common threshold %d\n", ret);
- return ret;
+ ret = hclge_common_thrd_config(hdev);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "could not configure common threshold %d\n",
+ ret);
+ return ret;
+ }
}
ret = hclge_common_wl_config(hdev);
@@ -2582,6 +2606,7 @@
u16 tc_valid[HCLGE_MAX_TC_NUM];
u16 tc_size[HCLGE_MAX_TC_NUM];
u32 *rss_indir = NULL;
+ u16 rss_size = 0, roundup_size;
const u8 *key;
int i, ret, j;
@@ -2596,7 +2621,13 @@
for (j = 0; j < hdev->num_vmdq_vport + 1; j++) {
for (i = 0; i < HCLGE_RSS_IND_TBL_SIZE; i++) {
vport[j].rss_indirection_tbl[i] =
- i % hdev->rss_size_max;
+ i % vport[j].alloc_rss_size;
+
+ /* vport 0 is for PF */
+ if (j != 0)
+ continue;
+
+ rss_size = vport[j].alloc_rss_size;
rss_indir[i] = vport[j].rss_indirection_tbl[i];
}
}
@@ -2613,42 +2644,31 @@
if (ret)
goto err;
- for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
- if (hdev->hw_tc_map & BIT(i))
- tc_valid[i] = 1;
- else
- tc_valid[i] = 0;
-
- switch (hdev->rss_size_max) {
- case HCLGE_RSS_TC_SIZE_0:
- tc_size[i] = 0;
- break;
- case HCLGE_RSS_TC_SIZE_1:
- tc_size[i] = 1;
- break;
- case HCLGE_RSS_TC_SIZE_2:
- tc_size[i] = 2;
- break;
- case HCLGE_RSS_TC_SIZE_3:
- tc_size[i] = 3;
- break;
- case HCLGE_RSS_TC_SIZE_4:
- tc_size[i] = 4;
- break;
- case HCLGE_RSS_TC_SIZE_5:
- tc_size[i] = 5;
- break;
- case HCLGE_RSS_TC_SIZE_6:
- tc_size[i] = 6;
- break;
- case HCLGE_RSS_TC_SIZE_7:
- tc_size[i] = 7;
- break;
- default:
- break;
- }
- tc_offset[i] = hdev->rss_size_max * i;
+ /* Each TC have the same queue size, and tc_size set to hardware is
+ * the log2 of roundup power of two of rss_size, the acutal queue
+ * size is limited by indirection table.
+ */
+ if (rss_size > HCLGE_RSS_TC_SIZE_7 || rss_size == 0) {
+ dev_err(&hdev->pdev->dev,
+ "Configure rss tc size failed, invalid TC_SIZE = %d\n",
+ rss_size);
+ return -EINVAL;
}
+
+ roundup_size = roundup_pow_of_two(rss_size);
+ roundup_size = ilog2(roundup_size);
+
+ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
+ tc_valid[i] = 0;
+
+ if (!(hdev->hw_tc_map & BIT(i)))
+ continue;
+
+ tc_valid[i] = 1;
+ tc_size[i] = roundup_size;
+ tc_offset[i] = rss_size * i;
+ }
+
ret = hclge_set_rss_tc_mode(hdev, tc_valid, tc_size, tc_offset);
err:
@@ -2679,7 +2699,11 @@
hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M,
HCLGE_TQP_ID_S, node->tqp_index);
+ hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M,
+ HCLGE_INT_GL_IDX_S,
+ hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]);
+ req->vfid = vport->vport_id;
if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD;
@@ -2763,8 +2787,12 @@
hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M,
HCLGE_TQP_ID_S, node->tqp_index);
+ hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M,
+ HCLGE_INT_GL_IDX_S,
+ hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]);
+ req->vfid = vport->vport_id;
if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD;
@@ -2778,7 +2806,7 @@
}
i = 0;
hclge_cmd_setup_basic_desc(&desc,
- HCLGE_OPC_ADD_RING_TO_VECTOR,
+ HCLGE_OPC_DEL_RING_TO_VECTOR,
false);
req->int_vector_id = vector_id;
}
@@ -3665,6 +3693,7 @@
{
#define HCLGE_VLAN_TYPE_VF_TABLE 0
#define HCLGE_VLAN_TYPE_PORT_TABLE 1
+ struct hnae3_handle *handle;
int ret;
ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_VF_TABLE,
@@ -3674,8 +3703,11 @@
ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_PORT_TABLE,
true);
+ if (ret)
+ return ret;
- return ret;
+ handle = &hdev->vport[0].nic;
+ return hclge_set_port_vlan_filter(handle, htons(ETH_P_8021Q), 0, false);
}
static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
@@ -3920,8 +3952,7 @@
goto err;
if (hdev->roce_client &&
- hnae_get_bit(hdev->ae_dev->flag,
- HNAE_DEV_SUPPORT_ROCE_B)) {
+ hnae3_dev_roce_supported(hdev)) {
struct hnae3_client *rc = hdev->roce_client;
ret = hclge_init_roce_base_info(vport);
@@ -3944,8 +3975,7 @@
break;
case HNAE3_CLIENT_ROCE:
- if (hnae_get_bit(hdev->ae_dev->flag,
- HNAE_DEV_SUPPORT_ROCE_B)) {
+ if (hnae3_dev_roce_supported(hdev)) {
hdev->roce_client = client;
vport->roce.client = client;
}
@@ -4057,7 +4087,6 @@
static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
{
struct pci_dev *pdev = ae_dev->pdev;
- const struct pci_device_id *id;
struct hclge_dev *hdev;
int ret;
@@ -4072,10 +4101,6 @@
hdev->ae_dev = ae_dev;
ae_dev->priv = hdev;
- id = pci_match_id(roce_pci_tbl, ae_dev->pdev);
- if (id)
- hnae_set_bit(ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B, 1);
-
ret = hclge_pci_init(hdev);
if (ret) {
dev_err(&pdev->dev, "PCI init failed\n");
@@ -4138,12 +4163,6 @@
return ret;
}
- ret = hclge_rss_init_hw(hdev);
- if (ret) {
- dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret);
- return ret;
- }
-
ret = hclge_init_vlan_config(hdev);
if (ret) {
dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret);
@@ -4156,6 +4175,12 @@
return ret;
}
+ ret = hclge_rss_init_hw(hdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret);
+ return ret;
+ }
+
setup_timer(&hdev->service_timer, hclge_service_timer,
(unsigned long)hdev);
INIT_WORK(&hdev->service_task, hclge_service_task);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index edb10ad..9fcfd93 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -176,7 +176,6 @@
struct hclge_tc_info {
u8 tc_id;
u8 tc_sch_mode; /* 0: sp; 1: dwrr */
- u8 up;
u8 pgid;
u32 bw_limit;
};
@@ -197,6 +196,7 @@
u8 num_tc;
u8 num_pg; /* It must be 1 if vNET-Base schd */
u8 pg_dwrr[HCLGE_PG_NUM];
+ u8 prio_tc[HNAE3_MAX_USER_PRIO];
struct hclge_pg_info pg_info[HCLGE_PG_NUM];
struct hclge_tc_info tc_info[HNAE3_MAX_TC];
enum hclge_fc_mode fc_mode;
@@ -477,6 +477,7 @@
u8 rss_hash_key[HCLGE_RSS_KEY_SIZE]; /* User configured hash keys */
/* User configured lookup table entries */
u8 rss_indirection_tbl[HCLGE_RSS_IND_TBL_SIZE];
+ u16 alloc_rss_size;
u16 qs_offset;
u16 bw_limit; /* VSI BW Limit (0 = disabled) */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 1c577d2..73a75d7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -128,9 +128,7 @@
{
u8 tc;
- for (tc = 0; tc < hdev->tm_info.num_tc; tc++)
- if (hdev->tm_info.tc_info[tc].up == pri_id)
- break;
+ tc = hdev->tm_info.prio_tc[pri_id];
if (tc >= hdev->tm_info.num_tc)
return -EINVAL;
@@ -158,7 +156,7 @@
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, false);
- for (pri_id = 0; pri_id < hdev->tm_info.num_tc; pri_id++) {
+ for (pri_id = 0; pri_id < HNAE3_MAX_USER_PRIO; pri_id++) {
ret = hclge_fill_pri_array(hdev, pri, pri_id);
if (ret)
return ret;
@@ -280,11 +278,11 @@
shap_cfg_cmd->pg_id = pg_id;
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b);
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u);
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s);
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b);
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s);
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
@@ -307,11 +305,11 @@
shap_cfg_cmd->pri_id = pri_id;
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b);
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u);
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s);
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b);
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s);
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
@@ -397,6 +395,7 @@
kinfo->num_tqps / kinfo->num_tc);
vport->qs_offset = hdev->tm_info.num_tc * vport->vport_id;
vport->dwrr = 100; /* 100 percent as init */
+ vport->alloc_rss_size = kinfo->rss_size;
for (i = 0; i < kinfo->num_tc; i++) {
if (hdev->hw_tc_map & BIT(i)) {
@@ -404,16 +403,17 @@
kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size;
kinfo->tc_info[i].tqp_count = kinfo->rss_size;
kinfo->tc_info[i].tc = i;
- kinfo->tc_info[i].up = hdev->tm_info.tc_info[i].up;
} else {
/* Set to default queue if TC is disable */
kinfo->tc_info[i].enable = false;
kinfo->tc_info[i].tqp_offset = 0;
kinfo->tc_info[i].tqp_count = 1;
kinfo->tc_info[i].tc = 0;
- kinfo->tc_info[i].up = 0;
}
}
+
+ memcpy(kinfo->prio_tc, hdev->tm_info.prio_tc,
+ FIELD_SIZEOF(struct hnae3_knic_private_info, prio_tc));
}
static void hclge_tm_vport_info_update(struct hclge_dev *hdev)
@@ -435,12 +435,15 @@
for (i = 0; i < hdev->tm_info.num_tc; i++) {
hdev->tm_info.tc_info[i].tc_id = i;
hdev->tm_info.tc_info[i].tc_sch_mode = HCLGE_SCH_MODE_DWRR;
- hdev->tm_info.tc_info[i].up = i;
hdev->tm_info.tc_info[i].pgid = 0;
hdev->tm_info.tc_info[i].bw_limit =
hdev->tm_info.pg_info[0].bw_limit;
}
+ for (i = 0; i < HNAE3_MAX_USER_PRIO; i++)
+ hdev->tm_info.prio_tc[i] =
+ (i >= hdev->tm_info.num_tc) ? 0 : i;
+
hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
}
@@ -976,6 +979,10 @@
if (ret)
return ret;
+ /* Only DCB-supported dev supports qset back pressure setting */
+ if (!hnae3_dev_dcb_supported(hdev))
+ return 0;
+
for (i = 0; i < hdev->tm_info.num_tc; i++) {
ret = hclge_tm_qs_bp_cfg(hdev, i);
if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 7e67337..85158b0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -94,10 +94,10 @@
u32 rsvd1;
};
-#define hclge_tm_set_feild(dest, string, val) \
+#define hclge_tm_set_field(dest, string, val) \
hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
(HCLGE_TM_SHAP_##string##_LSH), val)
-#define hclge_tm_get_feild(src, string) \
+#define hclge_tm_get_field(src, string) \
hnae_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \
(HCLGE_TM_SHAP_##string##_LSH))
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
index 1c3e294..35369e1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
@@ -41,11 +41,16 @@
static const struct pci_device_id hns3_pci_tbl[] = {
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_GE), 0},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
/* required last entry */
{0, }
};
@@ -1348,6 +1353,7 @@
}
ae_dev->pdev = pdev;
+ ae_dev->flag = ent->driver_data;
ae_dev->dev_type = HNAE3_DEV_KNIC;
pci_set_drvdata(pdev, ae_dev);
@@ -2705,10 +2711,11 @@
eth_hw_addr_random(netdev);
dev_warn(priv->dev, "using random MAC address %pM\n",
netdev->dev_addr);
- /* Also copy this new MAC address into hdev */
- if (h->ae_algo->ops->set_mac_addr)
- h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr);
}
+
+ if (h->ae_algo->ops->set_mac_addr)
+ h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr);
+
}
static void hns3_nic_set_priv_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index 2c74baa..fff09dc 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -402,7 +402,7 @@
unsigned long flags;
MAL_DBG2(mal, "poll(%d)" NL, budget);
- again:
+
/* Process TX skbs */
list_for_each(l, &mal->poll_list) {
struct mal_commac *mc =
@@ -451,7 +451,6 @@
spin_lock_irqsave(&mal->lock, flags);
mal_disable_eob_irq(mal);
spin_unlock_irqrestore(&mal->lock, flags);
- goto again;
}
mc->ops->poll_tx(mc->dev);
}
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c
index bbe2463..c8c6231 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c
@@ -88,6 +88,8 @@
static int emac_get_sset_count(struct net_device *netdev, int sset)
{
switch (sset) {
+ case ETH_SS_PRIV_FLAGS:
+ return 1;
case ETH_SS_STATS:
return EMAC_STATS_LEN;
default:
@@ -100,6 +102,10 @@
unsigned int i;
switch (stringset) {
+ case ETH_SS_PRIV_FLAGS:
+ strcpy(data, "single-pause-mode");
+ break;
+
case ETH_SS_STATS:
for (i = 0; i < EMAC_STATS_LEN; i++) {
strlcpy(data, emac_ethtool_stat_strings[i],
@@ -230,6 +236,27 @@
return EMAC_MAX_REG_SIZE * sizeof(u32);
}
+#define EMAC_PRIV_ENABLE_SINGLE_PAUSE BIT(0)
+
+static int emac_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+ struct emac_adapter *adpt = netdev_priv(netdev);
+
+ adpt->single_pause_mode = !!(flags & EMAC_PRIV_ENABLE_SINGLE_PAUSE);
+
+ if (netif_running(netdev))
+ return emac_reinit_locked(adpt);
+
+ return 0;
+}
+
+static u32 emac_get_priv_flags(struct net_device *netdev)
+{
+ struct emac_adapter *adpt = netdev_priv(netdev);
+
+ return adpt->single_pause_mode ? EMAC_PRIV_ENABLE_SINGLE_PAUSE : 0;
+}
+
static const struct ethtool_ops emac_ethtool_ops = {
.get_link_ksettings = phy_ethtool_get_link_ksettings,
.set_link_ksettings = phy_ethtool_set_link_ksettings,
@@ -253,6 +280,9 @@
.get_regs_len = emac_get_regs_len,
.get_regs = emac_get_regs,
+
+ .set_priv_flags = emac_set_priv_flags,
+ .get_priv_flags = emac_get_priv_flags,
};
void emac_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index bcd4708..0ea3ca0 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -551,6 +551,28 @@
mac &= ~(HUGEN | VLAN_STRIP | TPAUSE | SIMR | HUGE | MULTI_ALL |
DEBUG_MODE | SINGLE_PAUSE_MODE);
+ /* Enable single-pause-frame mode if requested.
+ *
+ * If enabled, the EMAC will send a single pause frame when the RX
+ * queue is full. This normally leads to packet loss because
+ * the pause frame disables the remote MAC only for 33ms (the quanta),
+ * and then the remote MAC continues sending packets even though
+ * the RX queue is still full.
+ *
+ * If disabled, the EMAC sends a pause frame every 31ms until the RX
+ * queue is no longer full. Normally, this is the preferred
+ * method of operation. However, when the system is hung (e.g.
+ * cores are halted), the EMAC interrupt handler is never called
+ * and so the RX queue fills up quickly and stays full. The resuling
+ * non-stop "flood" of pause frames sometimes has the effect of
+ * disabling nearby switches. In some cases, other nearby switches
+ * are also affected, shutting down the entire network.
+ *
+ * The user can enable or disable single-pause-frame mode
+ * via ethtool.
+ */
+ mac |= adpt->single_pause_mode ? SINGLE_PAUSE_MODE : 0;
+
writel_relaxed(csr1, adpt->csr + EMAC_EMAC_WRAPPER_CSR1);
writel_relaxed(mac, adpt->base + EMAC_MAC_CTRL);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 60850bf..7595435 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -443,6 +443,9 @@
/* default to automatic flow control */
adpt->automatic = true;
+
+ /* Disable single-pause-frame mode by default */
+ adpt->single_pause_mode = false;
}
/* Get the clock */
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.h b/drivers/net/ethernet/qualcomm/emac/emac.h
index 8ee4ec6..d7c9f44 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.h
+++ b/drivers/net/ethernet/qualcomm/emac/emac.h
@@ -363,6 +363,9 @@
bool tx_flow_control;
bool rx_flow_control;
+ /* True == use single-pause-frame mode. */
+ bool single_pause_mode;
+
/* Ring parameter */
u8 tpd_burst;
u8 rfd_burst;
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index ca22f28..d24b47b 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2135,11 +2135,12 @@
if (likely(RTL_R16(IntrStatus) & RxAckBits))
work_done += rtl8139_rx(dev, tp, budget);
- if (work_done < budget && napi_complete_done(napi, work_done)) {
+ if (work_done < budget) {
unsigned long flags;
spin_lock_irqsave(&tp->lock, flags);
- RTL_W16_F(IntrMask, rtl8139_intr_mask);
+ if (napi_complete_done(napi, work_done))
+ RTL_W16_F(IntrMask, rtl8139_intr_mask);
spin_unlock_irqrestore(&tp->lock, flags);
}
spin_unlock(&tp->rx_lock);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index a366b37..8a280b4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -315,6 +315,7 @@
{ .compatible = "allwinner,sun8i-h3-emac" },
{ .compatible = "allwinner,sun8i-v3s-emac" },
{ .compatible = "allwinner,sun50i-a64-emac" },
+ {},
};
/* If phy-handle property is passed from DT, use it as the PHY */
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index d98cdfb..5176be7 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -150,6 +150,8 @@
u32 num_chn;
u32 send_sections;
u32 recv_sections;
+ u32 send_section_size;
+ u32 recv_section_size;
};
enum rndis_device_state {
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index a5511b7..8d5077f 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -76,9 +76,6 @@
net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
- net_device->recv_section_size = NETVSC_RECV_SECTION_SIZE;
- net_device->send_section_size = NETVSC_SEND_SECTION_SIZE;
-
init_completion(&net_device->channel_init_wait);
init_waitqueue_head(&net_device->subchan_open);
INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
@@ -262,7 +259,7 @@
int ret = 0;
/* Get receive buffer area. */
- buf_size = device_info->recv_sections * net_device->recv_section_size;
+ buf_size = device_info->recv_sections * device_info->recv_section_size;
buf_size = roundup(buf_size, PAGE_SIZE);
net_device->recv_buf = vzalloc(buf_size);
@@ -344,7 +341,7 @@
goto cleanup;
/* Now setup the send buffer. */
- buf_size = device_info->send_sections * net_device->send_section_size;
+ buf_size = device_info->send_sections * device_info->send_section_size;
buf_size = round_up(buf_size, PAGE_SIZE);
net_device->send_buf = vzalloc(buf_size);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index d4902ee5f..a32ae02 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -848,7 +848,9 @@
device_info.num_chn = count;
device_info.ring_size = ring_size;
device_info.send_sections = nvdev->send_section_cnt;
+ device_info.send_section_size = nvdev->send_section_size;
device_info.recv_sections = nvdev->recv_section_cnt;
+ device_info.recv_section_size = nvdev->recv_section_size;
rndis_filter_device_remove(dev, nvdev);
@@ -963,7 +965,9 @@
device_info.ring_size = ring_size;
device_info.num_chn = nvdev->num_chn;
device_info.send_sections = nvdev->send_section_cnt;
+ device_info.send_section_size = nvdev->send_section_size;
device_info.recv_sections = nvdev->recv_section_cnt;
+ device_info.recv_section_size = nvdev->recv_section_size;
rndis_filter_device_remove(hdev, nvdev);
@@ -1485,7 +1489,9 @@
device_info.num_chn = nvdev->num_chn;
device_info.ring_size = ring_size;
device_info.send_sections = new_tx;
+ device_info.send_section_size = nvdev->send_section_size;
device_info.recv_sections = new_rx;
+ device_info.recv_section_size = nvdev->recv_section_size;
netif_device_detach(ndev);
was_opened = rndis_filter_opened(nvdev);
@@ -1934,7 +1940,9 @@
device_info.ring_size = ring_size;
device_info.num_chn = VRSS_CHANNEL_DEFAULT;
device_info.send_sections = NETVSC_DEFAULT_TX;
+ device_info.send_section_size = NETVSC_SEND_SECTION_SIZE;
device_info.recv_sections = NETVSC_DEFAULT_RX;
+ device_info.recv_section_size = NETVSC_RECV_SECTION_SIZE;
nvdev = rndis_filter_device_add(dev, &device_info);
if (IS_ERR(nvdev)) {
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index a9d16a3..cd931cf 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -160,15 +160,6 @@
endif
-menuconfig PHYLIB
- tristate "PHY Device support and infrastructure"
- depends on NETDEVICES
- select MDIO_DEVICE
- help
- Ethernet controllers are usually attached to PHY
- devices. This option provides infrastructure for
- managing PHY devices.
-
config PHYLINK
tristate
depends on NETDEVICES
@@ -179,6 +170,15 @@
configuration links, PHYs, and Serdes links with MAC level
autonegotiation modes.
+menuconfig PHYLIB
+ tristate "PHY Device support and infrastructure"
+ depends on NETDEVICES
+ select MDIO_DEVICE
+ help
+ Ethernet controllers are usually attached to PHY
+ devices. This option provides infrastructure for
+ managing PHY devices.
+
if PHYLIB
config SWPHY
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index e842d2c..2b1e67b 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -373,7 +373,8 @@
cmd->base.port = PORT_BNC;
else
cmd->base.port = PORT_MII;
-
+ cmd->base.transceiver = phy_is_internal(phydev) ?
+ XCVR_INTERNAL : XCVR_EXTERNAL;
cmd->base.phy_address = phydev->mdio.addr;
cmd->base.autoneg = phydev->autoneg;
cmd->base.eth_tp_mdix_ctrl = phydev->mdix_ctrl;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 8cf0c59..67f25ac 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -879,7 +879,7 @@
{
const char *drv_name = phydev->drv ? phydev->drv->name : "unbound";
char *irq_str;
- char irq_num[4];
+ char irq_num[8];
switch(phydev->irq) {
case PHY_POLL:
diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index d15dd39..2e5150b 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -44,7 +44,7 @@
priv->phy_drv->read_status(phydev);
val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG);
- val &= XILINX_GMII2RGMII_SPEED_MASK;
+ val &= ~XILINX_GMII2RGMII_SPEED_MASK;
if (phydev->speed == SPEED_1000)
val |= BMCR_SPEED1000;
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index b99a7fb..0161f77 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1265,30 +1265,45 @@
struct ethtool_eeprom *ee, u8 *data)
{
struct lan78xx_net *dev = netdev_priv(netdev);
+ int ret;
+
+ ret = usb_autopm_get_interface(dev->intf);
+ if (ret)
+ return ret;
ee->magic = LAN78XX_EEPROM_MAGIC;
- return lan78xx_read_raw_eeprom(dev, ee->offset, ee->len, data);
+ ret = lan78xx_read_raw_eeprom(dev, ee->offset, ee->len, data);
+
+ usb_autopm_put_interface(dev->intf);
+
+ return ret;
}
static int lan78xx_ethtool_set_eeprom(struct net_device *netdev,
struct ethtool_eeprom *ee, u8 *data)
{
struct lan78xx_net *dev = netdev_priv(netdev);
+ int ret;
- /* Allow entire eeprom update only */
- if ((ee->magic == LAN78XX_EEPROM_MAGIC) &&
- (ee->offset == 0) &&
- (ee->len == 512) &&
- (data[0] == EEPROM_INDICATOR))
- return lan78xx_write_raw_eeprom(dev, ee->offset, ee->len, data);
+ ret = usb_autopm_get_interface(dev->intf);
+ if (ret)
+ return ret;
+
+ /* Invalid EEPROM_INDICATOR at offset zero will result in a failure
+ * to load data from EEPROM
+ */
+ if (ee->magic == LAN78XX_EEPROM_MAGIC)
+ ret = lan78xx_write_raw_eeprom(dev, ee->offset, ee->len, data);
else if ((ee->magic == LAN78XX_OTP_MAGIC) &&
(ee->offset == 0) &&
(ee->len == 512) &&
(data[0] == OTP_INDICATOR_1))
- return lan78xx_write_raw_otp(dev, ee->offset, ee->len, data);
+ ret = lan78xx_write_raw_otp(dev, ee->offset, ee->len, data);
- return -EINVAL;
+ usb_autopm_put_interface(dev->intf);
+
+ return ret;
}
static void lan78xx_get_strings(struct net_device *netdev, u32 stringset,
@@ -2434,7 +2449,6 @@
/* LAN7801 only has RGMII mode */
if (dev->chipid == ID_REV_CHIP_ID_7801_)
buf &= ~MAC_CR_GMII_EN_;
- buf |= MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_;
ret = lan78xx_write_reg(dev, MAC_CR, buf);
ret = lan78xx_read_reg(dev, MAC_TX, &buf);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index acc816b..bb2aad0 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -134,8 +134,6 @@
return false;
if (nvme_req(req)->status & NVME_SC_DNR)
return false;
- if (jiffies - req->start_time >= req->timeout)
- return false;
if (nvme_req(req)->retries >= nvme_max_retries)
return false;
return true;
@@ -2590,7 +2588,7 @@
container_of(work, struct nvme_ctrl, async_event_work);
spin_lock_irq(&ctrl->lock);
- while (ctrl->event_limit > 0) {
+ while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) {
int aer_idx = --ctrl->event_limit;
spin_unlock_irq(&ctrl->lock);
@@ -2677,7 +2675,8 @@
/*FALLTHRU*/
case NVME_SC_ABORT_REQ:
++ctrl->event_limit;
- queue_work(nvme_wq, &ctrl->async_event_work);
+ if (ctrl->state == NVME_CTRL_LIVE)
+ queue_work(nvme_wq, &ctrl->async_event_work);
break;
default:
break;
@@ -2692,7 +2691,7 @@
nvme_queue_scan(ctrl);
break;
case NVME_AER_NOTICE_FW_ACT_STARTING:
- schedule_work(&ctrl->fw_act_work);
+ queue_work(nvme_wq, &ctrl->fw_act_work);
break;
default:
dev_warn(ctrl->device, "async event result %08x\n", result);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 4730775..555c976 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -565,6 +565,7 @@
opts->queue_size = NVMF_DEF_QUEUE_SIZE;
opts->nr_io_queues = num_online_cpus();
opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
+ opts->kato = NVME_DEFAULT_KATO;
options = o = kstrdup(buf, GFP_KERNEL);
if (!options)
@@ -655,21 +656,22 @@
goto out;
}
- if (opts->discovery_nqn) {
- pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n");
- ret = -EINVAL;
- goto out;
- }
-
if (token < 0) {
pr_err("Invalid keep_alive_tmo %d\n", token);
ret = -EINVAL;
goto out;
- } else if (token == 0) {
+ } else if (token == 0 && !opts->discovery_nqn) {
/* Allowed for debug */
pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n");
}
opts->kato = token;
+
+ if (opts->discovery_nqn && opts->kato) {
+ pr_err("Discovery controllers cannot accept KATO != 0\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
break;
case NVMF_OPT_CTRL_LOSS_TMO:
if (match_int(args, &token)) {
@@ -762,8 +764,6 @@
uuid_copy(&opts->host->id, &hostid);
out:
- if (!opts->discovery_nqn && !opts->kato)
- opts->kato = NVME_DEFAULT_KATO;
kfree(options);
return ret;
}
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index d2e882c..af075e9 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1376,7 +1376,7 @@
if (atomic_read(&op->state) == FCPOP_STATE_ABORTED)
status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
else if (freq->status)
- status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+ status = cpu_to_le16(NVME_SC_INTERNAL << 1);
/*
* For the linux implementation, if we have an unsuccesful
@@ -1404,7 +1404,7 @@
*/
if (freq->transferred_length !=
be32_to_cpu(op->cmd_iu.data_len)) {
- status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+ status = cpu_to_le16(NVME_SC_INTERNAL << 1);
goto done;
}
result.u64 = 0;
@@ -1421,7 +1421,7 @@
freq->transferred_length ||
op->rsp_iu.status_code ||
sqe->common.command_id != cqe->command_id)) {
- status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+ status = cpu_to_le16(NVME_SC_INTERNAL << 1);
goto done;
}
result = cqe->result;
@@ -1429,7 +1429,7 @@
break;
default:
- status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+ status = cpu_to_le16(NVME_SC_INTERNAL << 1);
goto done;
}
@@ -1989,16 +1989,17 @@
* as well as those by FC-NVME spec.
*/
WARN_ON_ONCE(sqe->common.metadata);
- WARN_ON_ONCE(sqe->common.dptr.prp1);
- WARN_ON_ONCE(sqe->common.dptr.prp2);
sqe->common.flags |= NVME_CMD_SGL_METABUF;
/*
- * format SQE DPTR field per FC-NVME rules
- * type=data block descr; subtype=offset;
- * offset is currently 0.
+ * format SQE DPTR field per FC-NVME rules:
+ * type=0x5 Transport SGL Data Block Descriptor
+ * subtype=0xA Transport-specific value
+ * address=0
+ * length=length of the data series
*/
- sqe->rw.dptr.sgl.type = NVME_SGL_FMT_OFFSET;
+ sqe->rw.dptr.sgl.type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) |
+ NVME_SGL_FMT_TRANSPORT_A;
sqe->rw.dptr.sgl.length = cpu_to_le32(data_len);
sqe->rw.dptr.sgl.addr = 0;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4a21213..cb73bc8 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -24,6 +24,7 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
+#include <linux/once.h>
#include <linux/pci.h>
#include <linux/poison.h>
#include <linux/t10-pi.h>
@@ -540,6 +541,20 @@
}
#endif
+static void nvme_print_sgl(struct scatterlist *sgl, int nents)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, nents, i) {
+ dma_addr_t phys = sg_phys(sg);
+ pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
+ "dma_address:%pad dma_length:%d\n",
+ i, &phys, sg->offset, sg->length, &sg_dma_address(sg),
+ sg_dma_len(sg));
+ }
+}
+
static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -622,19 +637,10 @@
return BLK_STS_OK;
bad_sgl:
- if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n",
- blk_rq_payload_bytes(req), iod->nents)) {
- for_each_sg(iod->sg, sg, iod->nents, i) {
- dma_addr_t phys = sg_phys(sg);
- pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
- "dma_address:%pad dma_length:%d\n", i, &phys,
- sg->offset, sg->length,
- &sg_dma_address(sg),
- sg_dma_len(sg));
- }
- }
+ WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
+ "Invalid SGL for payload:%d nents:%d\n",
+ blk_rq_payload_bytes(req), iod->nents);
return BLK_STS_IOERR;
-
}
static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
@@ -1313,11 +1319,11 @@
if (result < 0)
goto release_cq;
+ nvme_init_queue(nvmeq, qid);
result = queue_request_irq(nvmeq);
if (result < 0)
goto release_sq;
- nvme_init_queue(nvmeq, qid);
return result;
release_sq:
@@ -1464,6 +1470,7 @@
return result;
nvmeq->cq_vector = 0;
+ nvme_init_queue(nvmeq, 0);
result = queue_request_irq(nvmeq);
if (result) {
nvmeq->cq_vector = -1;
@@ -2156,7 +2163,6 @@
if (result)
goto out;
- nvme_init_queue(dev->queues[0], 0);
result = nvme_alloc_admin_tags(dev);
if (result)
goto out;
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 5898300..92a03ff 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -942,7 +942,12 @@
}
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
- WARN_ON_ONCE(!changed);
+ if (!changed) {
+ /* state change failure is ok if we're in DELETING state */
+ WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
+ return;
+ }
+
ctrl->ctrl.nr_reconnects = 0;
nvme_start_ctrl(&ctrl->ctrl);
@@ -962,7 +967,7 @@
struct nvme_rdma_ctrl *ctrl = container_of(work,
struct nvme_rdma_ctrl, err_work);
- nvme_stop_ctrl(&ctrl->ctrl);
+ nvme_stop_keep_alive(&ctrl->ctrl);
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 7c23eaf..1b208be 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -390,10 +390,10 @@
if (status)
nvmet_set_status(req, status);
- /* XXX: need to fill in something useful for sq_head */
- req->rsp->sq_head = 0;
- if (likely(req->sq)) /* may happen during early failure */
- req->rsp->sq_id = cpu_to_le16(req->sq->qid);
+ if (req->sq->size)
+ req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size;
+ req->rsp->sq_head = cpu_to_le16(req->sq->sqhd);
+ req->rsp->sq_id = cpu_to_le16(req->sq->qid);
req->rsp->command_id = req->cmd->common.command_id;
if (req->ns)
@@ -420,6 +420,7 @@
void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
u16 qid, u16 size)
{
+ sq->sqhd = 0;
sq->qid = qid;
sq->size = size;
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 859a667..db3bf6b 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -109,9 +109,14 @@
pr_warn("queue already connected!\n");
return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
}
+ if (!sqsize) {
+ pr_warn("queue size zero!\n");
+ return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+ }
- nvmet_cq_setup(ctrl, req->cq, qid, sqsize);
- nvmet_sq_setup(ctrl, req->sq, qid, sqsize);
+ /* note: convert queue size from 0's-based value to 1's-based value */
+ nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1);
+ nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1);
return 0;
}
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 421e43b..58e010b 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -148,7 +148,7 @@
u32 a_id;
struct nvmet_fc_tgtport *tgtport;
struct list_head a_list;
- struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES];
+ struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1];
struct kref ref;
};
@@ -608,7 +608,7 @@
unsigned long flags;
int ret;
- if (qid >= NVMET_NR_QUEUES)
+ if (qid > NVMET_NR_QUEUES)
return NULL;
queue = kzalloc((sizeof(*queue) +
@@ -783,6 +783,9 @@
u16 qid = nvmet_fc_getqueueid(connection_id);
unsigned long flags;
+ if (qid > NVMET_NR_QUEUES)
+ return NULL;
+
spin_lock_irqsave(&tgtport->lock, flags);
list_for_each_entry(assoc, &tgtport->assoc_list, a_list) {
if (association_id == assoc->association_id) {
@@ -888,7 +891,7 @@
int i;
spin_lock_irqsave(&tgtport->lock, flags);
- for (i = NVMET_NR_QUEUES - 1; i >= 0; i--) {
+ for (i = NVMET_NR_QUEUES; i >= 0; i--) {
queue = assoc->queues[i];
if (queue) {
if (!nvmet_fc_tgt_q_get(queue))
@@ -1910,8 +1913,7 @@
spin_lock_irqsave(&fod->flock, flags);
fod->writedataactive = false;
spin_unlock_irqrestore(&fod->flock, flags);
- nvmet_req_complete(&fod->req,
- NVME_SC_FC_TRANSPORT_ERROR);
+ nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
} else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
fcpreq->fcp_error = ret;
fcpreq->transferred_length = 0;
@@ -1929,8 +1931,7 @@
/* if in the middle of an io and we need to tear down */
if (abort) {
if (fcpreq->op == NVMET_FCOP_WRITEDATA) {
- nvmet_req_complete(&fod->req,
- NVME_SC_FC_TRANSPORT_ERROR);
+ nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
return true;
}
@@ -1968,8 +1969,7 @@
fod->abort = true;
spin_unlock(&fod->flock);
- nvmet_req_complete(&fod->req,
- NVME_SC_FC_TRANSPORT_ERROR);
+ nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
return;
}
@@ -2533,13 +2533,17 @@
{
struct nvmet_fc_tgtport *tgtport = port->priv;
unsigned long flags;
+ bool matched = false;
spin_lock_irqsave(&nvmet_fc_tgtlock, flags);
if (tgtport->port == port) {
- nvmet_fc_tgtport_put(tgtport);
+ matched = true;
tgtport->port = NULL;
}
spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags);
+
+ if (matched)
+ nvmet_fc_tgtport_put(tgtport);
}
static struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = {
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 1cb9847..7b75d9d 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -224,8 +224,6 @@
struct fcloop_lport *lport;
struct list_head nport_list;
struct kref ref;
- struct completion rport_unreg_done;
- struct completion tport_unreg_done;
u64 node_name;
u64 port_name;
u32 port_role;
@@ -576,7 +574,7 @@
tfcp_req->aborted = true;
spin_unlock(&tfcp_req->reqlock);
- tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
+ tfcp_req->status = NVME_SC_INTERNAL;
/*
* nothing more to do. If io wasn't active, the transport should
@@ -631,6 +629,32 @@
}
static void
+fcloop_nport_free(struct kref *ref)
+{
+ struct fcloop_nport *nport =
+ container_of(ref, struct fcloop_nport, ref);
+ unsigned long flags;
+
+ spin_lock_irqsave(&fcloop_lock, flags);
+ list_del(&nport->nport_list);
+ spin_unlock_irqrestore(&fcloop_lock, flags);
+
+ kfree(nport);
+}
+
+static void
+fcloop_nport_put(struct fcloop_nport *nport)
+{
+ kref_put(&nport->ref, fcloop_nport_free);
+}
+
+static int
+fcloop_nport_get(struct fcloop_nport *nport)
+{
+ return kref_get_unless_zero(&nport->ref);
+}
+
+static void
fcloop_localport_delete(struct nvme_fc_local_port *localport)
{
struct fcloop_lport *lport = localport->private;
@@ -644,8 +668,7 @@
{
struct fcloop_rport *rport = remoteport->private;
- /* release any threads waiting for the unreg to complete */
- complete(&rport->nport->rport_unreg_done);
+ fcloop_nport_put(rport->nport);
}
static void
@@ -653,8 +676,7 @@
{
struct fcloop_tport *tport = targetport->private;
- /* release any threads waiting for the unreg to complete */
- complete(&tport->nport->tport_unreg_done);
+ fcloop_nport_put(tport->nport);
}
#define FCLOOP_HW_QUEUES 4
@@ -722,6 +744,7 @@
goto out_free_opts;
}
+ memset(&pinfo, 0, sizeof(pinfo));
pinfo.node_name = opts->wwnn;
pinfo.port_name = opts->wwpn;
pinfo.port_role = opts->roles;
@@ -804,32 +827,6 @@
return ret ? ret : count;
}
-static void
-fcloop_nport_free(struct kref *ref)
-{
- struct fcloop_nport *nport =
- container_of(ref, struct fcloop_nport, ref);
- unsigned long flags;
-
- spin_lock_irqsave(&fcloop_lock, flags);
- list_del(&nport->nport_list);
- spin_unlock_irqrestore(&fcloop_lock, flags);
-
- kfree(nport);
-}
-
-static void
-fcloop_nport_put(struct fcloop_nport *nport)
-{
- kref_put(&nport->ref, fcloop_nport_free);
-}
-
-static int
-fcloop_nport_get(struct fcloop_nport *nport)
-{
- return kref_get_unless_zero(&nport->ref);
-}
-
static struct fcloop_nport *
fcloop_alloc_nport(const char *buf, size_t count, bool remoteport)
{
@@ -938,6 +935,7 @@
if (!nport)
return -EIO;
+ memset(&pinfo, 0, sizeof(pinfo));
pinfo.node_name = nport->node_name;
pinfo.port_name = nport->port_name;
pinfo.port_role = nport->port_role;
@@ -979,24 +977,12 @@
}
static int
-__wait_remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport)
+__remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport)
{
- int ret;
-
if (!rport)
return -EALREADY;
- init_completion(&nport->rport_unreg_done);
-
- ret = nvme_fc_unregister_remoteport(rport->remoteport);
- if (ret)
- return ret;
-
- wait_for_completion(&nport->rport_unreg_done);
-
- fcloop_nport_put(nport);
-
- return ret;
+ return nvme_fc_unregister_remoteport(rport->remoteport);
}
static ssize_t
@@ -1029,7 +1015,7 @@
if (!nport)
return -ENOENT;
- ret = __wait_remoteport_unreg(nport, rport);
+ ret = __remoteport_unreg(nport, rport);
return ret ? ret : count;
}
@@ -1086,24 +1072,12 @@
}
static int
-__wait_targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport)
+__targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport)
{
- int ret;
-
if (!tport)
return -EALREADY;
- init_completion(&nport->tport_unreg_done);
-
- ret = nvmet_fc_unregister_targetport(tport->targetport);
- if (ret)
- return ret;
-
- wait_for_completion(&nport->tport_unreg_done);
-
- fcloop_nport_put(nport);
-
- return ret;
+ return nvmet_fc_unregister_targetport(tport->targetport);
}
static ssize_t
@@ -1136,7 +1110,7 @@
if (!nport)
return -ENOENT;
- ret = __wait_targetport_unreg(nport, tport);
+ ret = __targetport_unreg(nport, tport);
return ret ? ret : count;
}
@@ -1223,11 +1197,11 @@
spin_unlock_irqrestore(&fcloop_lock, flags);
- ret = __wait_targetport_unreg(nport, tport);
+ ret = __targetport_unreg(nport, tport);
if (ret)
pr_warn("%s: Failed deleting target port\n", __func__);
- ret = __wait_remoteport_unreg(nport, rport);
+ ret = __remoteport_unreg(nport, rport);
if (ret)
pr_warn("%s: Failed deleting remote port\n", __func__);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 7d261ab..7b8e20a 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -74,6 +74,7 @@
struct percpu_ref ref;
u16 qid;
u16 size;
+ u16 sqhd;
struct completion free_done;
struct completion confirm_done;
};
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 79ba3ce..23bdb1c 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -884,7 +884,7 @@
wcqe->total_data_placed);
nCmd->transferred_length = 0;
nCmd->rcv_rsplen = 0;
- nCmd->status = NVME_SC_FC_TRANSPORT_ERROR;
+ nCmd->status = NVME_SC_INTERNAL;
}
}
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 1f59e7a..6b33a1f 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -180,7 +180,7 @@
goto rel;
if (unlikely(res == QLA_FUNCTION_FAILED))
- fd->status = NVME_SC_FC_TRANSPORT_ERROR;
+ fd->status = NVME_SC_INTERNAL;
else
fd->status = 0;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 5fa2211..62cf812 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -229,6 +229,7 @@
{
loff_t offset = dio->iocb->ki_pos;
ssize_t transferred = 0;
+ int err;
/*
* AIO submission can race with bio completion to get here while
@@ -258,8 +259,22 @@
if (ret == 0)
ret = transferred;
+ /*
+ * Try again to invalidate clean pages which might have been cached by
+ * non-direct readahead, or faulted in by get_user_pages() if the source
+ * of the write was an mmap'ed region of the file we're writing. Either
+ * one is a pretty crazy thing to do, so we don't support it 100%. If
+ * this invalidation fails, tough, the write still worked...
+ */
+ if (ret > 0 && dio->op == REQ_OP_WRITE &&
+ dio->inode->i_mapping->nrpages) {
+ err = invalidate_inode_pages2_range(dio->inode->i_mapping,
+ offset >> PAGE_SHIFT,
+ (offset + ret - 1) >> PAGE_SHIFT);
+ WARN_ON_ONCE(err);
+ }
+
if (dio->end_io) {
- int err;
// XXX: ki_pos??
err = dio->end_io(dio->iocb, offset, ret, dio->private);
@@ -304,6 +319,7 @@
struct dio *dio = bio->bi_private;
unsigned long remaining;
unsigned long flags;
+ bool defer_completion = false;
/* cleanup the bio */
dio_bio_complete(dio, bio);
@@ -315,7 +331,19 @@
spin_unlock_irqrestore(&dio->bio_lock, flags);
if (remaining == 0) {
- if (dio->result && dio->defer_completion) {
+ /*
+ * Defer completion when defer_completion is set or
+ * when the inode has pages mapped and this is AIO write.
+ * We need to invalidate those pages because there is a
+ * chance they contain stale data in the case buffered IO
+ * went in between AIO submission and completion into the
+ * same region.
+ */
+ if (dio->result)
+ defer_completion = dio->defer_completion ||
+ (dio->op == REQ_OP_WRITE &&
+ dio->inode->i_mapping->nrpages);
+ if (defer_completion) {
INIT_WORK(&dio->complete_work, dio_aio_complete_work);
queue_work(dio->inode->i_sb->s_dio_done_wq,
&dio->complete_work);
@@ -1210,10 +1238,19 @@
* For AIO O_(D)SYNC writes we need to defer completions to a workqueue
* so that we can call ->fsync.
*/
- if (dio->is_async && iov_iter_rw(iter) == WRITE &&
- ((iocb->ki_filp->f_flags & O_DSYNC) ||
- IS_SYNC(iocb->ki_filp->f_mapping->host))) {
- retval = dio_set_defer_completion(dio);
+ if (dio->is_async && iov_iter_rw(iter) == WRITE) {
+ retval = 0;
+ if ((iocb->ki_filp->f_flags & O_DSYNC) ||
+ IS_SYNC(iocb->ki_filp->f_mapping->host))
+ retval = dio_set_defer_completion(dio);
+ else if (!dio->inode->i_sb->s_dio_done_wq) {
+ /*
+ * In case of AIO write racing with buffered read we
+ * need to defer completion. We can't decide this now,
+ * however the workqueue needs to be initialized here.
+ */
+ retval = sb_init_dio_done_wq(dio->inode->i_sb);
+ }
if (retval) {
/*
* We grab i_mutex only for reads so we don't have
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 98e845b..11066d8 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1945,13 +1945,9 @@
{
struct gfs2_glock_iter *gi = seq->private;
loff_t n = *pos;
- int ret;
- if (gi->last_pos <= *pos)
- n = (*pos - gi->last_pos);
-
- ret = rhashtable_walk_start(&gi->hti);
- if (ret)
+ rhashtable_walk_enter(&gl_hash_table, &gi->hti);
+ if (rhashtable_walk_start(&gi->hti) != 0)
return NULL;
do {
@@ -1959,6 +1955,7 @@
} while (gi->gl && n--);
gi->last_pos = *pos;
+
return gi->gl;
}
@@ -1970,6 +1967,7 @@
(*pos)++;
gi->last_pos = *pos;
gfs2_glock_iter_next(gi);
+
return gi->gl;
}
@@ -1980,6 +1978,7 @@
gi->gl = NULL;
rhashtable_walk_stop(&gi->hti);
+ rhashtable_walk_exit(&gi->hti);
}
static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
@@ -2042,12 +2041,10 @@
struct gfs2_glock_iter *gi = seq->private;
gi->sdp = inode->i_private;
- gi->last_pos = 0;
seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
if (seq->buf)
seq->size = GFS2_SEQ_GOODSIZE;
gi->gl = NULL;
- rhashtable_walk_enter(&gl_hash_table, &gi->hti);
}
return ret;
}
@@ -2063,7 +2060,6 @@
struct gfs2_glock_iter *gi = seq->private;
gi->gl = NULL;
- rhashtable_walk_exit(&gi->hti);
return seq_release_private(inode, file);
}
diff --git a/fs/iomap.c b/fs/iomap.c
index 269b24a0..8194d30 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -713,8 +713,24 @@
static ssize_t iomap_dio_complete(struct iomap_dio *dio)
{
struct kiocb *iocb = dio->iocb;
+ struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
+ /*
+ * Try again to invalidate clean pages which might have been cached by
+ * non-direct readahead, or faulted in by get_user_pages() if the source
+ * of the write was an mmap'ed region of the file we're writing. Either
+ * one is a pretty crazy thing to do, so we don't support it 100%. If
+ * this invalidation fails, tough, the write still worked...
+ */
+ if (!dio->error &&
+ (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
+ ret = invalidate_inode_pages2_range(inode->i_mapping,
+ iocb->ki_pos >> PAGE_SHIFT,
+ (iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT);
+ WARN_ON_ONCE(ret);
+ }
+
if (dio->end_io) {
ret = dio->end_io(iocb,
dio->error ? dio->error : dio->size,
@@ -1042,19 +1058,6 @@
ret = iomap_dio_complete(dio);
- /*
- * Try again to invalidate clean pages which might have been cached by
- * non-direct readahead, or faulted in by get_user_pages() if the source
- * of the write was an mmap'ed region of the file we're writing. Either
- * one is a pretty crazy thing to do, so we don't support it 100%. If
- * this invalidation fails, tough, the write still worked...
- */
- if (iov_iter_rw(iter) == WRITE) {
- int err = invalidate_inode_pages2_range(mapping,
- start >> PAGE_SHIFT, end >> PAGE_SHIFT);
- WARN_ON_ONCE(err);
- }
-
return ret;
out_free_dio:
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 460294b..02fa42d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -551,6 +551,7 @@
int node;
#ifdef CONFIG_BLK_DEV_IO_TRACE
struct blk_trace *blk_trace;
+ struct mutex blk_trace_mutex;
#endif
/*
* for flush operations
diff --git a/include/linux/irq.h b/include/linux/irq.h
index b99a784..d4728bf 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -783,10 +783,7 @@
static inline
struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d)
{
- if (!cpumask_empty(d->common->effective_affinity))
- return d->common->effective_affinity;
-
- return d->common->affinity;
+ return d->common->effective_affinity;
}
static inline void irq_data_update_effective_affinity(struct irq_data *d,
const struct cpumask *m)
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 9c5cb44..a726f96 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -346,11 +346,6 @@
* indicating an FC transport Aborted status.
* Entrypoint is Mandatory.
*
- * @defer_rcv: Called by the transport to signal the LLLD that it has
- * begun processing of a previously received NVME CMD IU. The LLDD
- * is now free to re-use the rcv buffer associated with the
- * nvmefc_tgt_fcp_req.
- *
* @max_hw_queues: indicates the maximum number of hw queues the LLDD
* supports for cpu affinitization.
* Value is Mandatory. Must be at least 1.
@@ -806,11 +801,19 @@
* outstanding operation (if there was one) to complete, then will
* call the fcp_req_release() callback to return the command's
* exchange context back to the LLDD.
+ * Entrypoint is Mandatory.
*
* @fcp_req_release: Called by the transport to return a nvmefc_tgt_fcp_req
* to the LLDD after all operations on the fcp operation are complete.
* This may be due to the command completing or upon completion of
* abort cleanup.
+ * Entrypoint is Mandatory.
+ *
+ * @defer_rcv: Called by the transport to signal the LLLD that it has
+ * begun processing of a previously received NVME CMD IU. The LLDD
+ * is now free to re-use the rcv buffer associated with the
+ * nvmefc_tgt_fcp_req.
+ * Entrypoint is Optional.
*
* @max_hw_queues: indicates the maximum number of hw queues the LLDD
* supports for cpu affinitization.
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 87723c8..9310ce77 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -471,12 +471,14 @@
*
* @NVME_SGL_FMT_ADDRESS: absolute address of the data block
* @NVME_SGL_FMT_OFFSET: relative offset of the in-capsule data block
+ * @NVME_SGL_FMT_TRANSPORT_A: transport defined format, value 0xA
* @NVME_SGL_FMT_INVALIDATE: RDMA transport specific remote invalidation
* request subtype
*/
enum {
NVME_SGL_FMT_ADDRESS = 0x00,
NVME_SGL_FMT_OFFSET = 0x01,
+ NVME_SGL_FMT_TRANSPORT_A = 0x0A,
NVME_SGL_FMT_INVALIDATE = 0x0f,
};
@@ -490,12 +492,16 @@
*
* For struct nvme_keyed_sgl_desc:
* @NVME_KEY_SGL_FMT_DATA_DESC: keyed data block descriptor
+ *
+ * Transport-specific SGL types:
+ * @NVME_TRANSPORT_SGL_DATA_DESC: Transport SGL data dlock descriptor
*/
enum {
NVME_SGL_FMT_DATA_DESC = 0x00,
NVME_SGL_FMT_SEG_DESC = 0x02,
NVME_SGL_FMT_LAST_SEG_DESC = 0x03,
NVME_KEY_SGL_FMT_DATA_DESC = 0x04,
+ NVME_TRANSPORT_SGL_DATA_DESC = 0x05,
};
struct nvme_sgl_desc {
@@ -1127,19 +1133,6 @@
NVME_SC_UNWRITTEN_BLOCK = 0x287,
NVME_SC_DNR = 0x4000,
-
-
- /*
- * FC Transport-specific error status values for NVME commands
- *
- * Transport-specific status code values must be in the range 0xB0..0xBF
- */
-
- /* Generic FC failure - catchall */
- NVME_SC_FC_TRANSPORT_ERROR = 0x00B0,
-
- /* I/O failure due to FC ABTS'd */
- NVME_SC_FC_TRANSPORT_ABORTED = 0x00B1,
};
struct nvme_completion {
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index e0d1946..fb908e5 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -57,7 +57,14 @@
extern struct platform_device *of_device_alloc(struct device_node *np,
const char *bus_id,
struct device *parent);
+#ifdef CONFIG_OF
extern struct platform_device *of_find_device_by_node(struct device_node *np);
+#else
+static inline struct platform_device *of_find_device_by_node(struct device_node *np)
+{
+ return NULL;
+}
+#endif
/* Platform devices and busses creation */
extern struct platform_device *of_platform_device_create(struct device_node *np,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 95606a2..a78186d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -221,22 +221,26 @@
} \
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
-#ifdef TIF_FSCHECK
/*
* Called before coming back to user-mode. Returning to user-mode with an
* address limit different than USER_DS can allow to overwrite kernel memory.
*/
static inline void addr_limit_user_check(void)
{
-
+#ifdef TIF_FSCHECK
if (!test_thread_flag(TIF_FSCHECK))
return;
-
- BUG_ON(!segment_eq(get_fs(), USER_DS));
- clear_thread_flag(TIF_FSCHECK);
-}
#endif
+ if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS),
+ "Invalid address limit on user-mode return"))
+ force_sig(SIGKILL, current);
+
+#ifdef TIF_FSCHECK
+ clear_thread_flag(TIF_FSCHECK);
+#endif
+}
+
asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special,
qid_t id, void __user *addr);
asmlinkage long sys_time(time_t __user *tloc);
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 7f11050..2e0f222 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -272,6 +272,7 @@
int perf_refcount;
struct hlist_head __percpu *perf_events;
struct bpf_prog *prog;
+ struct perf_event *bpf_prog_owner;
int (*perf_perm)(struct trace_event_call *,
struct perf_event *);
diff --git a/include/net/dst.h b/include/net/dst.h
index 93568bd..06a6765 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -271,7 +271,7 @@
static inline struct dst_entry *dst_clone(struct dst_entry *dst)
{
if (dst)
- atomic_inc(&dst->__refcnt);
+ dst_hold(dst);
return dst;
}
@@ -312,21 +312,6 @@
}
/**
- * skb_dst_force - makes sure skb dst is refcounted
- * @skb: buffer
- *
- * If dst is not yet refcounted, let's do it
- */
-static inline void skb_dst_force(struct sk_buff *skb)
-{
- if (skb_dst_is_noref(skb)) {
- WARN_ON(!rcu_read_lock_held());
- skb->_skb_refdst &= ~SKB_DST_NOREF;
- dst_clone(skb_dst(skb));
- }
-}
-
-/**
* dst_hold_safe - Take a reference on a dst if possible
* @dst: pointer to dst entry
*
@@ -339,16 +324,17 @@
}
/**
- * skb_dst_force_safe - makes sure skb dst is refcounted
+ * skb_dst_force - makes sure skb dst is refcounted
* @skb: buffer
*
* If dst is not yet refcounted and not destroyed, grab a ref on it.
*/
-static inline void skb_dst_force_safe(struct sk_buff *skb)
+static inline void skb_dst_force(struct sk_buff *skb)
{
if (skb_dst_is_noref(skb)) {
struct dst_entry *dst = skb_dst(skb);
+ WARN_ON(!rcu_read_lock_held());
if (!dst_hold_safe(dst))
dst = NULL;
diff --git a/include/net/route.h b/include/net/route.h
index 1b09a93..57dfc68 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -190,7 +190,7 @@
rcu_read_lock();
err = ip_route_input_noref(skb, dst, src, tos, devin);
if (!err) {
- skb_dst_force_safe(skb);
+ skb_dst_force(skb);
if (!skb_dst(skb))
err = -EINVAL;
}
diff --git a/include/net/sock.h b/include/net/sock.h
index 03a3625..a6b9a8d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -856,7 +856,7 @@
static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
/* dont let skb dst not refcounted, we are going to leave rcu lock */
- skb_dst_force_safe(skb);
+ skb_dst_force(skb);
if (!sk->sk_backlog.tail)
sk->sk_backlog.head = skb;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b510f28..3bc910a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -544,7 +544,6 @@
int min_tso_segs);
void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
int nonagle);
-bool tcp_may_send_now(struct sock *sk);
int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
void tcp_retransmit_timer(struct sock *sk);
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 9c041da..5bd1b1d 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1753,6 +1753,8 @@
* %ethtool_link_mode_bit_indices for the link modes, and other
* link features that the link partner advertised through
* autonegotiation; 0 if unknown or not applicable. Read-only.
+ * @transceiver: Used to distinguish different possible PHY types,
+ * reported consistently by PHYLIB. Read-only.
*
* If autonegotiation is disabled, the speed and @duplex represent the
* fixed link mode and are writable if the driver supports multiple
@@ -1804,7 +1806,9 @@
__u8 eth_tp_mdix;
__u8 eth_tp_mdix_ctrl;
__s8 link_mode_masks_nwords;
- __u32 reserved[8];
+ __u8 transceiver;
+ __u8 reserved1[3];
+ __u32 reserved[7];
__u32 link_mode_masks[0];
/* layout of link_mode_masks fields:
* __u32 map_supported[link_mode_masks_nwords];
diff --git a/ipc/shm.c b/ipc/shm.c
index 1e2b169..badac46 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1154,7 +1154,7 @@
info.shm_swp = ip->shm_swp;
info.swap_attempts = ip->swap_attempts;
info.swap_successes = ip->swap_successes;
- return copy_to_user(up, &info, sizeof(info));
+ return copy_to_user(uip, &info, sizeof(info));
}
static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in,
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 959c9a0..e093d9a 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -75,8 +75,8 @@
static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
{
struct bpf_dtab *dtab;
+ int err = -EINVAL;
u64 cost;
- int err;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
@@ -108,6 +108,8 @@
if (err)
goto free_dtab;
+ err = -ENOMEM;
+
/* A per cpu bitfield with a bit per possible net device */
dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr),
__alignof__(unsigned long));
@@ -128,7 +130,7 @@
free_dtab:
free_percpu(dtab->flush_needed);
kfree(dtab);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(err);
}
static void dev_map_free(struct bpf_map *map)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cb17e1c..25d0749 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -186,15 +186,17 @@
static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
{
+ unsigned long flags;
+
if (do_idr_lock)
- spin_lock_bh(&map_idr_lock);
+ spin_lock_irqsave(&map_idr_lock, flags);
else
__acquire(&map_idr_lock);
idr_remove(&map_idr, map->id);
if (do_idr_lock)
- spin_unlock_bh(&map_idr_lock);
+ spin_unlock_irqrestore(&map_idr_lock, flags);
else
__release(&map_idr_lock);
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 799b245..b914fbe 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4205,7 +4205,12 @@
}
if (insn->imm == BPF_FUNC_redirect_map) {
- u64 addr = (unsigned long)prog;
+ /* Note, we cannot use prog directly as imm as subsequent
+ * rewrites would still change the prog pointer. The only
+ * stable address we can use is aux, which also works with
+ * prog clones during blinding.
+ */
+ u64 addr = (unsigned long)prog->aux;
struct bpf_insn r4_ld[] = {
BPF_LD_IMM64(BPF_REG_4, addr),
*insn,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3e691b7..6bc21e2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8171,6 +8171,7 @@
}
}
event->tp_event->prog = prog;
+ event->tp_event->bpf_prog_owner = event;
return 0;
}
@@ -8185,7 +8186,7 @@
return;
prog = event->tp_event->prog;
- if (prog) {
+ if (prog && event->tp_event->bpf_prog_owner == event) {
event->tp_event->prog = NULL;
bpf_prog_put(prog);
}
diff --git a/kernel/extable.c b/kernel/extable.c
index 38c2412..9aa1cc4 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -102,15 +102,7 @@
int __kernel_text_address(unsigned long addr)
{
- if (core_kernel_text(addr))
- return 1;
- if (is_module_text_address(addr))
- return 1;
- if (is_ftrace_trampoline(addr))
- return 1;
- if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
- return 1;
- if (is_bpf_text_address(addr))
+ if (kernel_text_address(addr))
return 1;
/*
* There might be init symbols in saved stacktraces.
@@ -127,17 +119,42 @@
int kernel_text_address(unsigned long addr)
{
+ bool no_rcu;
+ int ret = 1;
+
if (core_kernel_text(addr))
return 1;
+
+ /*
+ * If a stack dump happens while RCU is not watching, then
+ * RCU needs to be notified that it requires to start
+ * watching again. This can happen either by tracing that
+ * triggers a stack trace, or a WARN() that happens during
+ * coming back from idle, or cpu on or offlining.
+ *
+ * is_module_text_address() as well as the kprobe slots
+ * and is_bpf_text_address() require RCU to be watching.
+ */
+ no_rcu = !rcu_is_watching();
+
+ /* Treat this like an NMI as it can happen anywhere */
+ if (no_rcu)
+ rcu_nmi_enter();
+
if (is_module_text_address(addr))
- return 1;
+ goto out;
if (is_ftrace_trampoline(addr))
- return 1;
+ goto out;
if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
- return 1;
+ goto out;
if (is_bpf_text_address(addr))
- return 1;
- return 0;
+ goto out;
+ ret = 0;
+out:
+ if (no_rcu)
+ rcu_nmi_exit();
+
+ return ret;
}
/*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1250e4b..0c44c7b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -882,6 +882,11 @@
RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
rdtp = this_cpu_ptr(&rcu_dynticks);
+
+ /* Page faults can happen in NMI handlers, so check... */
+ if (READ_ONCE(rdtp->dynticks_nmi_nesting))
+ return;
+
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
rdtp->dynticks_nesting < 1);
if (rdtp->dynticks_nesting <= 1) {
@@ -1015,6 +1020,11 @@
RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!");
rdtp = this_cpu_ptr(&rcu_dynticks);
+
+ /* Page faults can happen in NMI handlers, so check... */
+ if (READ_ONCE(rdtp->dynticks_nmi_nesting))
+ return;
+
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting++;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 2a685b4..45a3928 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -648,6 +648,12 @@
}
EXPORT_SYMBOL_GPL(blk_trace_startstop);
+/*
+ * When reading or writing the blktrace sysfs files, the references to the
+ * opened sysfs or device files should prevent the underlying block device
+ * from being removed. So no further delete protection is really needed.
+ */
+
/**
* blk_trace_ioctl: - handle the ioctls associated with tracing
* @bdev: the block device
@@ -665,7 +671,7 @@
if (!q)
return -ENXIO;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&q->blk_trace_mutex);
switch (cmd) {
case BLKTRACESETUP:
@@ -691,7 +697,7 @@
break;
}
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&q->blk_trace_mutex);
return ret;
}
@@ -1727,7 +1733,7 @@
if (q == NULL)
goto out_bdput;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&q->blk_trace_mutex);
if (attr == &dev_attr_enable) {
ret = sprintf(buf, "%u\n", !!q->blk_trace);
@@ -1746,7 +1752,7 @@
ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
out_unlock_bdev:
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&q->blk_trace_mutex);
out_bdput:
bdput(bdev);
out:
@@ -1788,7 +1794,7 @@
if (q == NULL)
goto out_bdput;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&q->blk_trace_mutex);
if (attr == &dev_attr_enable) {
if (value)
@@ -1814,7 +1820,7 @@
}
out_unlock_bdev:
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&q->blk_trace_mutex);
out_bdput:
bdput(bdev);
out:
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index a4df67c..49cb414 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -96,23 +96,9 @@
if (in_nmi())
return;
- /*
- * There's a slight chance that we are tracing inside the
- * RCU infrastructure, and rcu_irq_enter() will not work
- * as expected.
- */
- if (unlikely(rcu_irq_enter_disabled()))
- return;
-
local_irq_save(flags);
arch_spin_lock(&stack_trace_max_lock);
- /*
- * RCU may not be watching, make it see us.
- * The stack trace code uses rcu_sched.
- */
- rcu_irq_enter();
-
/* In case another CPU set the tracer_frame on us */
if (unlikely(!frame_size))
this_size -= tracer_frame;
@@ -205,7 +191,6 @@
}
out:
- rcu_irq_exit();
arch_spin_unlock(&stack_trace_max_lock);
local_irq_restore(flags);
}
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b19c491..2689b7c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -219,7 +219,8 @@
range 0 8192
default 0 if KASAN
default 2048 if GCC_PLUGIN_LATENT_ENTROPY
- default 1024 if !64BIT
+ default 1280 if (!64BIT && PARISC)
+ default 1024 if (!64BIT && !PARISC)
default 2048 if 64BIT
help
Tell gcc to warn at build time for stack frames larger than this.
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 707ca5d..ddd7dde 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -735,9 +735,9 @@
* rhashtable_walk_start - Start a hash table walk
* @iter: Hash table iterator
*
- * Start a hash table walk. Note that we take the RCU lock in all
- * cases including when we return an error. So you must always call
- * rhashtable_walk_stop to clean up.
+ * Start a hash table walk at the current iterator position. Note that we take
+ * the RCU lock in all cases including when we return an error. So you must
+ * always call rhashtable_walk_stop to clean up.
*
* Returns zero if successful.
*
@@ -846,7 +846,8 @@
* rhashtable_walk_stop - Finish a hash table walk
* @iter: Hash table iterator
*
- * Finish a hash table walk.
+ * Finish a hash table walk. Does not reset the iterator to the start of the
+ * hash table.
*/
void rhashtable_walk_stop(struct rhashtable_iter *iter)
__releases(RCU)
diff --git a/mm/filemap.c b/mm/filemap.c
index 870971e..db250d0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2926,9 +2926,15 @@
* we're writing. Either one is a pretty crazy thing to do,
* so we don't support it 100%. If this invalidation
* fails, tough, the write still worked...
+ *
+ * Most of the time we do not need this since dio_complete() will do
+ * the invalidation for us. However there are some file systems that
+ * do not end up with dio_complete() being called, so let's not break
+ * them by removing it completely
*/
- invalidate_inode_pages2_range(mapping,
- pos >> PAGE_SHIFT, end);
+ if (mapping->nrpages)
+ invalidate_inode_pages2_range(mapping,
+ pos >> PAGE_SHIFT, end);
if (written > 0) {
pos += written;
diff --git a/net/compat.c b/net/compat.c
index 6ded6c8..2238171 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -185,6 +185,13 @@
ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen);
}
+ /*
+ * check the length of messages copied in is the same as the
+ * what we get from the first loop
+ */
+ if ((char *)kcmsg - (char *)kcmsg_base != kcmlen)
+ goto Einval;
+
/* Ok, looks like we made it. Hook it up and return success. */
kmsg->msg_control = kcmsg_base;
kmsg->msg_controllen = kcmlen;
diff --git a/net/core/dev.c b/net/core/dev.c
index fb766d9..588b473 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1948,8 +1948,12 @@
goto again;
}
out_unlock:
- if (pt_prev)
- pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
+ if (pt_prev) {
+ if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC))
+ pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
+ else
+ kfree_skb(skb2);
+ }
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(dev_queue_xmit_nit);
@@ -3892,6 +3896,7 @@
__skb_pull(skb, off);
else if (off < 0)
__skb_push(skb, -off);
+ skb->mac_header += off;
switch (act) {
case XDP_REDIRECT:
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 6a582ae..3228411 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -525,6 +525,8 @@
= link_ksettings->base.eth_tp_mdix;
legacy_settings->eth_tp_mdix_ctrl
= link_ksettings->base.eth_tp_mdix_ctrl;
+ legacy_settings->transceiver
+ = link_ksettings->base.transceiver;
return retval;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 24dd33d..82edad5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1794,7 +1794,7 @@
u32 flags;
struct bpf_map *map;
struct bpf_map *map_to_flush;
- const struct bpf_prog *map_owner;
+ unsigned long map_owner;
};
static DEFINE_PER_CPU(struct redirect_info, redirect_info);
@@ -2500,11 +2500,17 @@
}
EXPORT_SYMBOL_GPL(xdp_do_flush_map);
+static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
+ unsigned long aux)
+{
+ return (unsigned long)xdp_prog->aux != aux;
+}
+
static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
- const struct bpf_prog *map_owner = ri->map_owner;
+ unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
struct net_device *fwd = NULL;
u32 index = ri->ifindex;
@@ -2512,9 +2518,9 @@
ri->ifindex = 0;
ri->map = NULL;
- ri->map_owner = NULL;
+ ri->map_owner = 0;
- if (unlikely(map_owner != xdp_prog)) {
+ if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
err = -EFAULT;
map = NULL;
goto err;
@@ -2574,7 +2580,7 @@
struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
- const struct bpf_prog *map_owner = ri->map_owner;
+ unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
struct net_device *fwd = NULL;
u32 index = ri->ifindex;
@@ -2583,10 +2589,10 @@
ri->ifindex = 0;
ri->map = NULL;
- ri->map_owner = NULL;
+ ri->map_owner = 0;
if (map) {
- if (unlikely(map_owner != xdp_prog)) {
+ if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
err = -EFAULT;
map = NULL;
goto err;
@@ -2632,7 +2638,7 @@
ri->ifindex = ifindex;
ri->flags = flags;
ri->map = NULL;
- ri->map_owner = NULL;
+ ri->map_owner = 0;
return XDP_REDIRECT;
}
@@ -2646,7 +2652,7 @@
};
BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags,
- const struct bpf_prog *, map_owner)
+ unsigned long, map_owner)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b9c64b4..c039c93 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -266,7 +266,7 @@
#if IS_ENABLED(CONFIG_IPV6)
if (tb->fast_sk_family == AF_INET6)
return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr,
- &sk->sk_v6_rcv_saddr,
+ inet6_rcv_saddr(sk),
tb->fast_rcv_saddr,
sk->sk_rcv_saddr,
tb->fast_ipv6_only,
@@ -321,13 +321,14 @@
goto fail_unlock;
}
success:
- if (!hlist_empty(&tb->owners)) {
+ if (hlist_empty(&tb->owners)) {
tb->fastreuse = reuse;
if (sk->sk_reuseport) {
tb->fastreuseport = FASTREUSEPORT_ANY;
tb->fastuid = uid;
tb->fast_rcv_saddr = sk->sk_rcv_saddr;
tb->fast_ipv6_only = ipv6_only_sock(sk);
+ tb->fast_sk_family = sk->sk_family;
#if IS_ENABLED(CONFIG_IPV6)
tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
@@ -354,6 +355,7 @@
tb->fastuid = uid;
tb->fast_rcv_saddr = sk->sk_rcv_saddr;
tb->fast_ipv6_only = ipv6_only_sock(sk);
+ tb->fast_sk_family = sk->sk_family;
#if IS_ENABLED(CONFIG_IPV6)
tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1c839c9..0bc9e46 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1806,40 +1806,6 @@
return !after(end_seq, tcp_wnd_end(tp));
}
-/* This checks if the data bearing packet SKB (usually tcp_send_head(sk))
- * should be put on the wire right now. If so, it returns the number of
- * packets allowed by the congestion window.
- */
-static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb,
- unsigned int cur_mss, int nonagle)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- unsigned int cwnd_quota;
-
- tcp_init_tso_segs(skb, cur_mss);
-
- if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
- return 0;
-
- cwnd_quota = tcp_cwnd_test(tp, skb);
- if (cwnd_quota && !tcp_snd_wnd_test(tp, skb, cur_mss))
- cwnd_quota = 0;
-
- return cwnd_quota;
-}
-
-/* Test if sending is allowed right now. */
-bool tcp_may_send_now(struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb = tcp_send_head(sk);
-
- return skb &&
- tcp_snd_test(sk, skb, tcp_current_mss(sk),
- (tcp_skb_is_last(sk, skb) ?
- tp->nonagle : TCP_NAGLE_PUSH));
-}
-
/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
* which is put after SKB on the list. It is very much like
* tcp_fragment() except that it may make several kinds of assumptions
@@ -3423,6 +3389,10 @@
goto done;
}
+ /* data was not sent, this is our new send_head */
+ sk->sk_send_head = syn_data;
+ tp->packets_out -= tcp_skb_pcount(syn_data);
+
fallback:
/* Send a regular SYN with Fast Open cookie request option */
if (fo->cookie.len > 0)
@@ -3475,6 +3445,11 @@
*/
tp->snd_nxt = tp->write_seq;
tp->pushed_seq = tp->write_seq;
+ buff = tcp_send_head(sk);
+ if (unlikely(buff)) {
+ tp->snd_nxt = TCP_SKB_CB(buff)->seq;
+ tp->pushed_seq = TCP_SKB_CB(buff)->seq;
+ }
TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
/* Timer for repeating the SYN until an answer. */
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c2e2a78..96861c7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1399,10 +1399,18 @@
return 0;
}
-static inline bool ipv6_use_optimistic_addr(struct inet6_dev *idev)
+static bool ipv6_use_optimistic_addr(struct net *net,
+ struct inet6_dev *idev)
{
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
- return idev && idev->cnf.optimistic_dad && idev->cnf.use_optimistic;
+ if (!idev)
+ return false;
+ if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad)
+ return false;
+ if (!net->ipv6.devconf_all->use_optimistic && !idev->cnf.use_optimistic)
+ return false;
+
+ return true;
#else
return false;
#endif
@@ -1472,7 +1480,7 @@
/* Rule 3: Avoid deprecated and optimistic addresses */
u8 avoid = IFA_F_DEPRECATED;
- if (!ipv6_use_optimistic_addr(score->ifa->idev))
+ if (!ipv6_use_optimistic_addr(net, score->ifa->idev))
avoid |= IFA_F_OPTIMISTIC;
ret = ipv6_saddr_preferred(score->addr_type) ||
!(score->ifa->flags & avoid);
@@ -2460,7 +2468,8 @@
int max_addresses = in6_dev->cnf.max_addresses;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
- if (in6_dev->cnf.optimistic_dad &&
+ if ((net->ipv6.devconf_all->optimistic_dad ||
+ in6_dev->cnf.optimistic_dad) &&
!net->ipv6.devconf_all->forwarding && sllao)
addr_flags |= IFA_F_OPTIMISTIC;
#endif
@@ -3051,7 +3060,8 @@
u32 addr_flags = flags | IFA_F_PERMANENT;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
- if (idev->cnf.optimistic_dad &&
+ if ((dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad ||
+ idev->cnf.optimistic_dad) &&
!dev_net(idev->dev)->ipv6.devconf_all->forwarding)
addr_flags |= IFA_F_OPTIMISTIC;
#endif
@@ -3810,6 +3820,7 @@
goto out;
if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) ||
+ dev_net(dev)->ipv6.devconf_all->accept_dad < 1 ||
idev->cnf.accept_dad < 1 ||
!(ifp->flags&IFA_F_TENTATIVE) ||
ifp->flags & IFA_F_NODAD) {
@@ -3841,7 +3852,7 @@
*/
if (ifp->flags & IFA_F_OPTIMISTIC) {
ip6_ins_rt(ifp->rt);
- if (ipv6_use_optimistic_addr(idev)) {
+ if (ipv6_use_optimistic_addr(dev_net(dev), idev)) {
/* Because optimistic nodes can use this address,
* notify listeners. If DAD fails, RTM_DELADDR is sent.
*/
@@ -3897,7 +3908,9 @@
action = DAD_ABORT;
ifp->state = INET6_IFADDR_STATE_POSTDAD;
- if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 &&
+ if ((dev_net(idev->dev)->ipv6.devconf_all->accept_dad > 1 ||
+ idev->cnf.accept_dad > 1) &&
+ !idev->cnf.disable_ipv6 &&
!(ifp->flags & IFA_F_STABLE_PRIVACY)) {
struct in6_addr addr;
@@ -4940,9 +4953,10 @@
/* Don't send DELADDR notification for TENTATIVE address,
* since NEWADDR notification is sent only after removing
- * TENTATIVE flag.
+ * TENTATIVE flag, if DAD has not failed.
*/
- if (ifa->flags & IFA_F_TENTATIVE && event == RTM_DELADDR)
+ if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_DADFAILED) &&
+ event == RTM_DELADDR)
return;
skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b7a72d4..20f66f4 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -940,24 +940,25 @@
}
static int ip6gre_header(struct sk_buff *skb, struct net_device *dev,
- unsigned short type,
- const void *daddr, const void *saddr, unsigned int len)
+ unsigned short type, const void *daddr,
+ const void *saddr, unsigned int len)
{
struct ip6_tnl *t = netdev_priv(dev);
- struct ipv6hdr *ipv6h = skb_push(skb, t->hlen);
- __be16 *p = (__be16 *)(ipv6h+1);
+ struct ipv6hdr *ipv6h;
+ __be16 *p;
- ip6_flow_hdr(ipv6h, 0,
- ip6_make_flowlabel(dev_net(dev), skb,
- t->fl.u.ip6.flowlabel, true,
- &t->fl.u.ip6));
+ ipv6h = skb_push(skb, t->hlen + sizeof(*ipv6h));
+ ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb,
+ t->fl.u.ip6.flowlabel,
+ true, &t->fl.u.ip6));
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = NEXTHDR_GRE;
ipv6h->saddr = t->parms.laddr;
ipv6h->daddr = t->parms.raddr;
- p[0] = t->parms.o_flags;
- p[1] = htons(type);
+ p = (__be16 *)(ipv6h + 1);
+ p[0] = t->parms.o_flags;
+ p[1] = htons(type);
/*
* Set the source hardware address.
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index ae73164..f2f21c2 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2259,6 +2259,9 @@
{
int err;
+ if (!ipv6_mod_enabled())
+ return -EOPNOTSUPP;
+
err = register_pernet_device(&ip6_tnl_net_ops);
if (err < 0)
goto out_pernet;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e2ecfb1..40d7234 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1015,6 +1015,7 @@
*/
offset = skb_transport_offset(skb);
skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+ csum = skb->csum;
skb->ip_summed = CHECKSUM_NONE;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index f236c0b..51063d9 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -1041,12 +1041,24 @@
static int
mtype_head(struct ip_set *set, struct sk_buff *skb)
{
- const struct htype *h = set->data;
+ struct htype *h = set->data;
const struct htable *t;
struct nlattr *nested;
size_t memsize;
u8 htable_bits;
+ /* If any members have expired, set->elements will be wrong
+ * mytype_expire function will update it with the right count.
+ * we do not hold set->lock here, so grab it first.
+ * set->elements can still be incorrect in the case of a huge set,
+ * because elements might time out during the listing.
+ */
+ if (SET_WITH_TIMEOUT(set)) {
+ spin_lock_bh(&set->lock);
+ mtype_expire(set, h);
+ spin_unlock_bh(&set->lock);
+ }
+
rcu_read_lock_bh();
t = rcu_dereference_bh_nfnl(h->table);
memsize = mtype_ahash_memsize(h, t) + set->ext_size;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index f393a70..af8345f 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -429,7 +429,7 @@
srchash = hash_by_src(net,
&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- lock = &nf_nat_locks[srchash % ARRAY_SIZE(nf_nat_locks)];
+ lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS];
spin_lock_bh(lock);
hlist_add_head_rcu(&ct->nat_bysource,
&nf_nat_bysource[srchash]);
@@ -532,9 +532,9 @@
unsigned int h;
h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- spin_lock_bh(&nf_nat_locks[h % ARRAY_SIZE(nf_nat_locks)]);
+ spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
hlist_del_rcu(&ct->nat_bysource);
- spin_unlock_bh(&nf_nat_locks[h % ARRAY_SIZE(nf_nat_locks)]);
+ spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
}
static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
@@ -807,8 +807,8 @@
/* Leave them the same for the moment. */
nf_nat_htable_size = nf_conntrack_htable_size;
- if (nf_nat_htable_size < ARRAY_SIZE(nf_nat_locks))
- nf_nat_htable_size = ARRAY_SIZE(nf_nat_locks);
+ if (nf_nat_htable_size < CONNTRACK_LOCKS)
+ nf_nat_htable_size = CONNTRACK_LOCKS;
nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0);
if (!nf_nat_bysource)
@@ -821,7 +821,7 @@
return ret;
}
- for (i = 0; i < ARRAY_SIZE(nf_nat_locks); i++)
+ for (i = 0; i < CONNTRACK_LOCKS; i++)
spin_lock_init(&nf_nat_locks[i]);
nf_ct_helper_expectfn_register(&follow_master_nat);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c261729..d288f52 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1684,10 +1684,6 @@
mutex_lock(&fanout_mutex);
- err = -EINVAL;
- if (!po->running)
- goto out;
-
err = -EALREADY;
if (po->fanout)
goto out;
@@ -1749,7 +1745,10 @@
list_add(&match->list, &fanout_list);
}
err = -EINVAL;
- if (match->type == type &&
+
+ spin_lock(&po->bind_lock);
+ if (po->running &&
+ match->type == type &&
match->prot_hook.type == po->prot_hook.type &&
match->prot_hook.dev == po->prot_hook.dev) {
err = -ENOSPC;
@@ -1761,6 +1760,13 @@
err = 0;
}
}
+ spin_unlock(&po->bind_lock);
+
+ if (err && !refcount_read(&match->sk_ref)) {
+ list_del(&match->list);
+ kfree(match);
+ }
+
out:
if (err && rollover) {
kfree(rollover);
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 1a267e7..d230cb4 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -922,28 +922,28 @@
if (!tc_flags_valid(fnew->flags)) {
err = -EINVAL;
- goto errout;
+ goto errout_idr;
}
}
err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
if (err)
- goto errout;
+ goto errout_idr;
err = fl_check_assign_mask(head, &mask);
if (err)
- goto errout;
+ goto errout_idr;
if (!tc_skip_sw(fnew->flags)) {
if (!fold && fl_lookup(head, &fnew->mkey)) {
err = -EEXIST;
- goto errout;
+ goto errout_idr;
}
err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
head->ht_params);
if (err)
- goto errout;
+ goto errout_idr;
}
if (!tc_skip_hw(fnew->flags)) {
@@ -952,7 +952,7 @@
&mask.key,
fnew);
if (err)
- goto errout;
+ goto errout_idr;
}
if (!tc_in_hw(fnew->flags))
@@ -981,6 +981,9 @@
kfree(tb);
return 0;
+errout_idr:
+ if (fnew->handle)
+ idr_remove_ext(&head->handle_idr, fnew->handle);
errout:
tcf_exts_destroy(&fnew->exts);
kfree(fnew);
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 21cc45ca..eeac606 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -32,6 +32,7 @@
if (tc_skip_sw(head->flags))
return -1;
+ *res = head->res;
return tcf_exts_exec(skb, &head->exts, res);
}
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 92237e7..bf8c81e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -685,6 +685,7 @@
qdisc->gso_skb = NULL;
}
qdisc->q.qlen = 0;
+ qdisc->qstats.backlog = 0;
}
EXPORT_SYMBOL(qdisc_reset);
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index daaf214..3f88b75 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -958,6 +958,8 @@
}
if (cl != NULL) {
+ int old_flags;
+
if (parentid) {
if (cl->cl_parent &&
cl->cl_parent->cl_common.classid != parentid)
@@ -978,6 +980,8 @@
}
sch_tree_lock(sch);
+ old_flags = cl->cl_flags;
+
if (rsc != NULL)
hfsc_change_rsc(cl, rsc, cur_time);
if (fsc != NULL)
@@ -986,10 +990,21 @@
hfsc_change_usc(cl, usc, cur_time);
if (cl->qdisc->q.qlen != 0) {
- if (cl->cl_flags & HFSC_RSC)
- update_ed(cl, qdisc_peek_len(cl->qdisc));
- if (cl->cl_flags & HFSC_FSC)
- update_vf(cl, 0, cur_time);
+ int len = qdisc_peek_len(cl->qdisc);
+
+ if (cl->cl_flags & HFSC_RSC) {
+ if (old_flags & HFSC_RSC)
+ update_ed(cl, len);
+ else
+ init_ed(cl, len);
+ }
+
+ if (cl->cl_flags & HFSC_FSC) {
+ if (old_flags & HFSC_FSC)
+ update_vf(cl, 0, cur_time);
+ else
+ init_vf(cl, len);
+ }
}
sch_tree_unlock(sch);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 8c6d24b..745f145 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -282,6 +282,7 @@
__be32 *subnet, u8 *prefix_len)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
+ struct in_device *in_dev;
struct sockaddr_in addr;
int rc = -ENOENT;
int len;
@@ -298,14 +299,17 @@
/* get address to which the internal TCP socket is bound */
kernel_getsockname(clcsock, (struct sockaddr *)&addr, &len);
/* analyze IPv4 specific data of net_device belonging to TCP socket */
- for_ifa(dst->dev->ip_ptr) {
- if (ifa->ifa_address != addr.sin_addr.s_addr)
+ rcu_read_lock();
+ in_dev = __in_dev_get_rcu(dst->dev);
+ for_ifa(in_dev) {
+ if (!inet_ifa_match(addr.sin_addr.s_addr, ifa))
continue;
*prefix_len = inet_mask_len(ifa->ifa_mask);
*subnet = ifa->ifa_address & ifa->ifa_mask;
rc = 0;
break;
- } endfor_ifa(dst->dev->ip_ptr);
+ } endfor_ifa(in_dev);
+ rcu_read_unlock();
out_rel:
dst_release(dst);
@@ -509,7 +513,7 @@
/* RDMA setup failed, switch back to TCP */
smc->use_fallback = true;
if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
- rc = smc_clc_send_decline(smc, reason_code, 0);
+ rc = smc_clc_send_decline(smc, reason_code);
if (rc < sizeof(struct smc_clc_msg_decline))
goto out_err;
}
@@ -804,8 +808,6 @@
rc = local_contact;
if (rc == -ENOMEM)
reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
- else if (rc == -ENOLINK)
- reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
goto decline_rdma;
}
link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
@@ -899,7 +901,7 @@
smc_conn_free(&new_smc->conn);
new_smc->use_fallback = true;
if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
- rc = smc_clc_send_decline(new_smc, reason_code, 0);
+ rc = smc_clc_send_decline(new_smc, reason_code);
if (rc < sizeof(struct smc_clc_msg_decline))
goto out_err;
}
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 6e44313e..0ccd6fa 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -149,7 +149,7 @@
atomic_t sndbuf_space; /* remaining space in sndbuf */
u16 tx_cdc_seq; /* sequence # for CDC send */
spinlock_t send_lock; /* protect wr_sends */
- struct work_struct tx_work; /* retry of smc_cdc_msg_send */
+ struct delayed_work tx_work; /* retry of smc_cdc_msg_send */
struct smc_host_cdc_msg local_rx_ctrl; /* filled during event_handl.
* .prod cf. TCP rcv_nxt
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 3934913..b7dd274 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -95,9 +95,10 @@
}
if (clcm->type == SMC_CLC_DECLINE) {
reason_code = SMC_CLC_DECL_REPLY;
- if (ntohl(((struct smc_clc_msg_decline *)buf)->peer_diagnosis)
- == SMC_CLC_DECL_SYNCERR)
+ if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
smc->conn.lgr->sync_err = true;
+ smc_lgr_terminate(smc->conn.lgr);
+ }
}
out:
@@ -105,8 +106,7 @@
}
/* send CLC DECLINE message across internal TCP socket */
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
- u8 out_of_sync)
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
{
struct smc_clc_msg_decline dclc;
struct msghdr msg;
@@ -118,7 +118,7 @@
dclc.hdr.type = SMC_CLC_DECLINE;
dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
dclc.hdr.version = SMC_CLC_V1;
- dclc.hdr.flag = out_of_sync ? 1 : 0;
+ dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid));
dclc.peer_diagnosis = htonl(peer_diag_info);
memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 13db8ce..1c55414 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -106,8 +106,7 @@
int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
u8 expected_type);
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
- u8 out_of_sync);
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev,
u8 ibport);
int smc_clc_send_confirm(struct smc_sock *smc);
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 3c2e166..f0d16fb 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -174,15 +174,15 @@
{
struct smc_cdc_conn_state_flags *txflags =
&smc->conn.local_tx_ctrl.conn_state_flags;
- long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
struct smc_connection *conn = &smc->conn;
struct sock *sk = &smc->sk;
int old_state;
+ long timeout;
int rc = 0;
- if (sock_flag(sk, SOCK_LINGER) &&
- !(current->flags & PF_EXITING))
- timeout = sk->sk_lingertime;
+ timeout = current->flags & PF_EXITING ?
+ 0 : sock_flag(sk, SOCK_LINGER) ?
+ sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
again:
old_state = sk->sk_state;
@@ -208,7 +208,7 @@
case SMC_ACTIVE:
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
if (sk->sk_state == SMC_ACTIVE) {
/* send close request */
@@ -234,7 +234,7 @@
if (!smc_cdc_rxed_any_close(conn))
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
if (sk->sk_err != ECONNABORTED) {
/* confirm close from peer */
@@ -263,7 +263,9 @@
/* peer sending PeerConnectionClosed will cause transition */
break;
case SMC_PROCESSABORT:
- cancel_work_sync(&conn->tx_work);
+ release_sock(sk);
+ cancel_delayed_work_sync(&conn->tx_work);
+ lock_sock(sk);
smc_close_abort(conn);
sk->sk_state = SMC_CLOSED;
smc_close_wait_tx_pends(smc);
@@ -411,13 +413,14 @@
int smc_close_shutdown_write(struct smc_sock *smc)
{
struct smc_connection *conn = &smc->conn;
- long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
struct sock *sk = &smc->sk;
int old_state;
+ long timeout;
int rc = 0;
- if (sock_flag(sk, SOCK_LINGER))
- timeout = sk->sk_lingertime;
+ timeout = current->flags & PF_EXITING ?
+ 0 : sock_flag(sk, SOCK_LINGER) ?
+ sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
again:
old_state = sk->sk_state;
@@ -425,7 +428,7 @@
case SMC_ACTIVE:
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
/* send close wr request */
rc = smc_close_wr(conn);
@@ -439,7 +442,7 @@
if (!smc_cdc_rxed_any_close(conn))
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
/* confirm close from peer */
rc = smc_close_wr(conn);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 1a16d51..20b66e7 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -25,8 +25,9 @@
#include "smc_cdc.h"
#include "smc_close.h"
-#define SMC_LGR_NUM_INCR 256
-#define SMC_LGR_FREE_DELAY (600 * HZ)
+#define SMC_LGR_NUM_INCR 256
+#define SMC_LGR_FREE_DELAY_SERV (600 * HZ)
+#define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10)
static u32 smc_lgr_num; /* unique link group number */
@@ -107,8 +108,15 @@
__smc_lgr_unregister_conn(conn);
}
write_unlock_bh(&lgr->conns_lock);
- if (reduced && !lgr->conns_num)
- schedule_delayed_work(&lgr->free_work, SMC_LGR_FREE_DELAY);
+ if (!reduced || lgr->conns_num)
+ return;
+ /* client link group creation always follows the server link group
+ * creation. For client use a somewhat higher removal delay time,
+ * otherwise there is a risk of out-of-sync link groups.
+ */
+ mod_delayed_work(system_wq, &lgr->free_work,
+ lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT :
+ SMC_LGR_FREE_DELAY_SERV);
}
static void smc_lgr_free_work(struct work_struct *work)
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 547e0e1..0b58522 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -380,6 +380,7 @@
ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport);
if (ndev) {
memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN);
+ dev_put(ndev);
} else if (!rc) {
memcpy(&smcibdev->mac[ibport - 1][0],
&smcibdev->gid[ibport - 1].raw[8], 3);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 78f7af2..31f8453 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -181,8 +181,10 @@
sizeof(new_pnetelem->ndev->name)) ||
smc_pnet_same_ibname(pnetelem,
new_pnetelem->smcibdev->ibdev->name,
- new_pnetelem->ib_port))
+ new_pnetelem->ib_port)) {
+ dev_put(pnetelem->ndev);
goto found;
+ }
}
list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist);
rc = 0;
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index b17a333..3e631ae 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -148,6 +148,8 @@
read_done = sock_intr_errno(timeo);
break;
}
+ if (!timeo)
+ return -EAGAIN;
}
if (!atomic_read(&conn->bytes_to_rcv)) {
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 3c656be..38665732 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -24,6 +24,8 @@
#include "smc_cdc.h"
#include "smc_tx.h"
+#define SMC_TX_WORK_DELAY HZ
+
/***************************** sndbuf producer *******************************/
/* callback implementation for sk.sk_write_space()
@@ -406,7 +408,8 @@
goto out_unlock;
}
rc = 0;
- schedule_work(&conn->tx_work);
+ schedule_delayed_work(&conn->tx_work,
+ SMC_TX_WORK_DELAY);
}
goto out_unlock;
}
@@ -430,7 +433,7 @@
*/
static void smc_tx_work(struct work_struct *work)
{
- struct smc_connection *conn = container_of(work,
+ struct smc_connection *conn = container_of(to_delayed_work(work),
struct smc_connection,
tx_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
@@ -468,7 +471,8 @@
if (!rc)
rc = smc_cdc_msg_send(conn, wr_buf, pend);
if (rc < 0) {
- schedule_work(&conn->tx_work);
+ schedule_delayed_work(&conn->tx_work,
+ SMC_TX_WORK_DELAY);
return;
}
smc_curs_write(&conn->rx_curs_confirmed,
@@ -487,6 +491,6 @@
void smc_tx_init(struct smc_sock *smc)
{
smc->sk.sk_write_space = smc_tx_write_space;
- INIT_WORK(&smc->conn.tx_work, smc_tx_work);
+ INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
spin_lock_init(&smc->conn.send_lock);
}
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index ab56bda..525d91e 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -244,7 +244,7 @@
int rc;
ib_req_notify_cq(link->smcibdev->roce_cq_send,
- IB_CQ_SOLICITED_MASK | IB_CQ_REPORT_MISSED_EVENTS);
+ IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
pend = container_of(priv, struct smc_wr_tx_pend, priv);
rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx],
&failed_wr);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0df8023..6908742 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -9987,6 +9987,9 @@
if (err)
return err;
+ if (!setup.chandef.chan)
+ return -EINVAL;
+
err = validate_beacon_tx_rate(rdev, setup.chandef.chan->band,
&setup.beacon_rate);
if (err)
@@ -10903,6 +10906,9 @@
if (err)
return err;
+ if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] ||
+ !tb[NL80211_REKEY_DATA_KCK])
+ return -EINVAL;
if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN)
return -ERANGE;
if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN)
diff --git a/scripts/dtc/dtx_diff b/scripts/dtc/dtx_diff
index f9a3d8d..8c4fbad 100755
--- a/scripts/dtc/dtx_diff
+++ b/scripts/dtc/dtx_diff
@@ -86,6 +86,7 @@
compile_to_dts() {
dtx="$1"
+ dtc_include="$2"
if [ -d "${dtx}" ] ; then
@@ -113,7 +114,7 @@
# ----- input is DTS (source)
if ( cpp ${cpp_flags} -x assembler-with-cpp ${dtx} \
- | ${DTC} -I dts ) ; then
+ | ${DTC} ${dtc_include} -I dts ) ; then
return
fi
@@ -320,18 +321,13 @@
cpp_flags="\
-nostdinc \
- -I${srctree}/arch/${ARCH}/boot/dts \
-I${srctree}/scripts/dtc/include-prefixes \
- -I${srctree}/drivers/of/testcase-data \
-undef -D__DTS__"
-dtc_flags="\
- -i ${srctree}/arch/${ARCH}/boot/dts/ \
- -i ${srctree}/kernel/dts \
- ${dtx_path_1_dtc_include} \
- ${dtx_path_2_dtc_include}"
-
-DTC="${DTC} ${dtc_flags} -O dts -qq -f ${dtc_sort} -o -"
+DTC="\
+ ${DTC} \
+ -i ${srctree}/scripts/dtc/include-prefixes \
+ -O dts -qq -f ${dtc_sort} -o -"
# ----- do the diff or decompile
@@ -339,11 +335,11 @@
if (( ${cmd_diff} )) ; then
diff ${diff_flags} --label "${dtx_file_1}" --label "${dtx_file_2}" \
- <(compile_to_dts "${dtx_file_1}") \
- <(compile_to_dts "${dtx_file_2}")
+ <(compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}") \
+ <(compile_to_dts "${dtx_file_2}" "${dtx_path_2_dtc_include}")
else
- compile_to_dts "${dtx_file_1}"
+ compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}"
fi
diff --git a/security/apparmor/.gitignore b/security/apparmor/.gitignore
index 9cdec70..d5b291e 100644
--- a/security/apparmor/.gitignore
+++ b/security/apparmor/.gitignore
@@ -1,5 +1,6 @@
#
# Generated include files
#
+net_names.h
capability_names.h
rlim_names.h
diff --git a/security/apparmor/Makefile b/security/apparmor/Makefile
index a16b195..dafdd38 100644
--- a/security/apparmor/Makefile
+++ b/security/apparmor/Makefile
@@ -4,11 +4,44 @@
apparmor-y := apparmorfs.o audit.o capability.o context.o ipc.o lib.o match.o \
path.o domain.o policy.o policy_unpack.o procattr.o lsm.o \
- resource.o secid.o file.o policy_ns.o label.o
+ resource.o secid.o file.o policy_ns.o label.o mount.o net.o
apparmor-$(CONFIG_SECURITY_APPARMOR_HASH) += crypto.o
-clean-files := capability_names.h rlim_names.h
+clean-files := capability_names.h rlim_names.h net_names.h
+# Build a lower case string table of address family names
+# Transform lines from
+# #define AF_LOCAL 1 /* POSIX name for AF_UNIX */
+# #define AF_INET 2 /* Internet IP Protocol */
+# to
+# [1] = "local",
+# [2] = "inet",
+#
+# and build the securityfs entries for the mapping.
+# Transforms lines from
+# #define AF_INET 2 /* Internet IP Protocol */
+# to
+# #define AA_SFS_AF_MASK "local inet"
+quiet_cmd_make-af = GEN $@
+cmd_make-af = echo "static const char *address_family_names[] = {" > $@ ;\
+ sed $< >>$@ -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \
+ 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\
+ echo "};" >> $@ ;\
+ printf '%s' '\#define AA_SFS_AF_MASK "' >> $@ ;\
+ sed -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \
+ 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/\L\1/p'\
+ $< | tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@
+
+# Build a lower case string table of sock type names
+# Transform lines from
+# SOCK_STREAM = 1,
+# to
+# [1] = "stream",
+quiet_cmd_make-sock = GEN $@
+cmd_make-sock = echo "static const char *sock_type_names[] = {" >> $@ ;\
+ sed $^ >>$@ -r -n \
+ -e 's/^\tSOCK_([A-Z0-9_]+)[\t]+=[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\
+ echo "};" >> $@
# Build a lower case string table of capability names
# Transforms lines from
@@ -61,6 +94,7 @@
tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@
$(obj)/capability.o : $(obj)/capability_names.h
+$(obj)/net.o : $(obj)/net_names.h
$(obj)/resource.o : $(obj)/rlim_names.h
$(obj)/capability_names.h : $(srctree)/include/uapi/linux/capability.h \
$(src)/Makefile
@@ -68,3 +102,8 @@
$(obj)/rlim_names.h : $(srctree)/include/uapi/asm-generic/resource.h \
$(src)/Makefile
$(call cmd,make-rlim)
+$(obj)/net_names.h : $(srctree)/include/linux/socket.h \
+ $(srctree)/include/linux/net.h \
+ $(src)/Makefile
+ $(call cmd,make-af)
+ $(call cmd,make-sock)
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 853c2ec..518d592 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -32,6 +32,7 @@
#include "include/audit.h"
#include "include/context.h"
#include "include/crypto.h"
+#include "include/ipc.h"
#include "include/policy_ns.h"
#include "include/label.h"
#include "include/policy.h"
@@ -248,8 +249,10 @@
inode_lock(dir);
dentry = lookup_one_len(name, parent, strlen(name));
- if (IS_ERR(dentry))
+ if (IS_ERR(dentry)) {
+ error = PTR_ERR(dentry);
goto fail_lock;
+ }
if (d_really_is_positive(dentry)) {
error = -EEXIST;
@@ -1443,6 +1446,10 @@
{
int i;
+ AA_BUG(!old);
+ AA_BUG(!new);
+ AA_BUG(!mutex_is_locked(&profiles_ns(old)->lock));
+
for (i = 0; i < AAFS_PROF_SIZEOF; i++) {
new->dents[i] = old->dents[i];
if (new->dents[i])
@@ -1506,6 +1513,9 @@
struct dentry *dent = NULL, *dir;
int error;
+ AA_BUG(!profile);
+ AA_BUG(!mutex_is_locked(&profiles_ns(profile)->lock));
+
if (!parent) {
struct aa_profile *p;
p = aa_deref_parent(profile);
@@ -1731,6 +1741,7 @@
if (!ns)
return;
+ AA_BUG(!mutex_is_locked(&ns->lock));
list_for_each_entry(child, &ns->base.profiles, base.list)
__aafs_profile_rmdir(child);
@@ -1903,6 +1914,10 @@
{
struct aa_ns *parent, *next;
+ AA_BUG(!root);
+ AA_BUG(!ns);
+ AA_BUG(ns != root && !mutex_is_locked(&ns->parent->lock));
+
/* is next namespace a child */
if (!list_empty(&ns->sub_ns)) {
next = list_first_entry(&ns->sub_ns, typeof(*ns), base.list);
@@ -1937,6 +1952,9 @@
static struct aa_profile *__first_profile(struct aa_ns *root,
struct aa_ns *ns)
{
+ AA_BUG(!root);
+ AA_BUG(ns && !mutex_is_locked(&ns->lock));
+
for (; ns; ns = __next_ns(root, ns)) {
if (!list_empty(&ns->base.profiles))
return list_first_entry(&ns->base.profiles,
@@ -1959,6 +1977,8 @@
struct aa_profile *parent;
struct aa_ns *ns = p->ns;
+ AA_BUG(!mutex_is_locked(&profiles_ns(p)->lock));
+
/* is next profile a child */
if (!list_empty(&p->base.profiles))
return list_first_entry(&p->base.profiles, typeof(*p),
@@ -2127,6 +2147,11 @@
{ }
};
+static struct aa_sfs_entry aa_sfs_entry_signal[] = {
+ AA_SFS_FILE_STRING("mask", AA_SFS_SIG_MASK),
+ { }
+};
+
static struct aa_sfs_entry aa_sfs_entry_domain[] = {
AA_SFS_FILE_BOOLEAN("change_hat", 1),
AA_SFS_FILE_BOOLEAN("change_hatv", 1),
@@ -2151,9 +2176,14 @@
{ }
};
+static struct aa_sfs_entry aa_sfs_entry_mount[] = {
+ AA_SFS_FILE_STRING("mask", "mount umount pivot_root"),
+ { }
+};
+
static struct aa_sfs_entry aa_sfs_entry_ns[] = {
AA_SFS_FILE_BOOLEAN("profile", 1),
- AA_SFS_FILE_BOOLEAN("pivot_root", 1),
+ AA_SFS_FILE_BOOLEAN("pivot_root", 0),
{ }
};
@@ -2172,22 +2202,25 @@
AA_SFS_DIR("policy", aa_sfs_entry_policy),
AA_SFS_DIR("domain", aa_sfs_entry_domain),
AA_SFS_DIR("file", aa_sfs_entry_file),
+ AA_SFS_DIR("network", aa_sfs_entry_network),
+ AA_SFS_DIR("mount", aa_sfs_entry_mount),
AA_SFS_DIR("namespaces", aa_sfs_entry_ns),
AA_SFS_FILE_U64("capability", VFS_CAP_FLAGS_MASK),
AA_SFS_DIR("rlimit", aa_sfs_entry_rlimit),
AA_SFS_DIR("caps", aa_sfs_entry_caps),
AA_SFS_DIR("ptrace", aa_sfs_entry_ptrace),
+ AA_SFS_DIR("signal", aa_sfs_entry_signal),
AA_SFS_DIR("query", aa_sfs_entry_query),
{ }
};
static struct aa_sfs_entry aa_sfs_entry_apparmor[] = {
- AA_SFS_FILE_FOPS(".access", 0640, &aa_sfs_access),
+ AA_SFS_FILE_FOPS(".access", 0666, &aa_sfs_access),
AA_SFS_FILE_FOPS(".stacked", 0444, &seq_ns_stacked_fops),
AA_SFS_FILE_FOPS(".ns_stacked", 0444, &seq_ns_nsstacked_fops),
- AA_SFS_FILE_FOPS(".ns_level", 0666, &seq_ns_level_fops),
- AA_SFS_FILE_FOPS(".ns_name", 0640, &seq_ns_name_fops),
- AA_SFS_FILE_FOPS("profiles", 0440, &aa_sfs_profiles_fops),
+ AA_SFS_FILE_FOPS(".ns_level", 0444, &seq_ns_level_fops),
+ AA_SFS_FILE_FOPS(".ns_name", 0444, &seq_ns_name_fops),
+ AA_SFS_FILE_FOPS("profiles", 0444, &aa_sfs_profiles_fops),
AA_SFS_DIR("features", aa_sfs_entry_features),
{ }
};
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 17a601c..dd754b7 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -374,8 +374,8 @@
*
* Returns: refcounted label, or NULL on failure (MAYBE NULL)
*/
-static struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
- const char **name)
+struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
+ const char **name)
{
struct aa_label *label = NULL;
u32 xtype = xindex & AA_X_TYPE_MASK;
diff --git a/security/apparmor/file.c b/security/apparmor/file.c
index 3382518..db80221 100644
--- a/security/apparmor/file.c
+++ b/security/apparmor/file.c
@@ -21,6 +21,7 @@
#include "include/context.h"
#include "include/file.h"
#include "include/match.h"
+#include "include/net.h"
#include "include/path.h"
#include "include/policy.h"
#include "include/label.h"
@@ -566,6 +567,32 @@
return error;
}
+static int __file_sock_perm(const char *op, struct aa_label *label,
+ struct aa_label *flabel, struct file *file,
+ u32 request, u32 denied)
+{
+ struct socket *sock = (struct socket *) file->private_data;
+ int error;
+
+ AA_BUG(!sock);
+
+ /* revalidation due to label out of date. No revocation at this time */
+ if (!denied && aa_label_is_subset(flabel, label))
+ return 0;
+
+ /* TODO: improve to skip profiles cached in flabel */
+ error = aa_sock_file_perm(label, op, request, sock);
+ if (denied) {
+ /* TODO: improve to skip profiles checked above */
+ /* check every profile in file label to is cached */
+ last_error(error, aa_sock_file_perm(flabel, op, request, sock));
+ }
+ if (!error)
+ update_file_ctx(file_ctx(file), label, request);
+
+ return error;
+}
+
/**
* aa_file_perm - do permission revalidation check & audit for @file
* @op: operation being checked
@@ -610,6 +637,9 @@
error = __file_path_perm(op, label, flabel, file, request,
denied);
+ else if (S_ISSOCK(file_inode(file)->i_mode))
+ error = __file_sock_perm(op, label, flabel, file, request,
+ denied);
done:
rcu_read_unlock();
diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h
index aaf893f..829082c 100644
--- a/security/apparmor/include/apparmor.h
+++ b/security/apparmor/include/apparmor.h
@@ -27,7 +27,9 @@
#define AA_CLASS_NET 4
#define AA_CLASS_RLIMITS 5
#define AA_CLASS_DOMAIN 6
+#define AA_CLASS_MOUNT 7
#define AA_CLASS_PTRACE 9
+#define AA_CLASS_SIGNAL 10
#define AA_CLASS_LABEL 16
#define AA_CLASS_LAST AA_CLASS_LABEL
diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h
index c68839a..ff4316e 100644
--- a/security/apparmor/include/audit.h
+++ b/security/apparmor/include/audit.h
@@ -71,6 +71,10 @@
#define OP_FMPROT "file_mprotect"
#define OP_INHERIT "file_inherit"
+#define OP_PIVOTROOT "pivotroot"
+#define OP_MOUNT "mount"
+#define OP_UMOUNT "umount"
+
#define OP_CREATE "create"
#define OP_POST_CREATE "post_create"
#define OP_BIND "bind"
@@ -86,6 +90,7 @@
#define OP_SHUTDOWN "socket_shutdown"
#define OP_PTRACE "ptrace"
+#define OP_SIGNAL "signal"
#define OP_EXEC "exec"
@@ -116,20 +121,36 @@
/* these entries require a custom callback fn */
struct {
struct aa_label *peer;
- struct {
- const char *target;
- kuid_t ouid;
- } fs;
+ union {
+ struct {
+ kuid_t ouid;
+ const char *target;
+ } fs;
+ struct {
+ int type, protocol;
+ struct sock *peer_sk;
+ void *addr;
+ int addrlen;
+ } net;
+ int signal;
+ struct {
+ int rlim;
+ unsigned long max;
+ } rlim;
+ };
};
struct {
- const char *name;
- long pos;
+ struct aa_profile *profile;
const char *ns;
+ long pos;
} iface;
struct {
- int rlim;
- unsigned long max;
- } rlim;
+ const char *src_name;
+ const char *type;
+ const char *trans;
+ const char *data;
+ unsigned long flags;
+ } mnt;
};
};
diff --git a/security/apparmor/include/domain.h b/security/apparmor/include/domain.h
index 24c5976..ac9862f 100644
--- a/security/apparmor/include/domain.h
+++ b/security/apparmor/include/domain.h
@@ -15,6 +15,8 @@
#include <linux/binfmts.h>
#include <linux/types.h>
+#include "label.h"
+
#ifndef __AA_DOMAIN_H
#define __AA_DOMAIN_H
@@ -29,6 +31,9 @@
#define AA_CHANGE_ONEXEC 4
#define AA_CHANGE_STACK 8
+struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
+ const char **name);
+
int apparmor_bprm_set_creds(struct linux_binprm *bprm);
void aa_free_domain_entries(struct aa_domain *domain);
diff --git a/security/apparmor/include/ipc.h b/security/apparmor/include/ipc.h
index 656fdb8..5ffc218 100644
--- a/security/apparmor/include/ipc.h
+++ b/security/apparmor/include/ipc.h
@@ -27,8 +27,14 @@
#define AA_PTRACE_PERM_MASK (AA_PTRACE_READ | AA_PTRACE_TRACE | \
AA_MAY_BE_READ | AA_MAY_BE_TRACED)
+#define AA_SIGNAL_PERM_MASK (MAY_READ | MAY_WRITE)
+
+#define AA_SFS_SIG_MASK "hup int quit ill trap abrt bus fpe kill usr1 " \
+ "segv usr2 pipe alrm term stkflt chld cont stop stp ttin ttou urg " \
+ "xcpu xfsz vtalrm prof winch io pwr sys emt lost"
int aa_may_ptrace(struct aa_label *tracer, struct aa_label *tracee,
u32 request);
+int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig);
#endif /* __AA_IPC_H */
diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h
index 9a283b7..af22dcb 100644
--- a/security/apparmor/include/label.h
+++ b/security/apparmor/include/label.h
@@ -310,6 +310,7 @@
#define FLAG_SHOW_MODE 1
#define FLAG_VIEW_SUBNS 2
#define FLAG_HIDDEN_UNCONFINED 4
+#define FLAG_ABS_ROOT 8
int aa_label_snxprint(char *str, size_t size, struct aa_ns *view,
struct aa_label *label, int flags);
int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label,
diff --git a/security/apparmor/include/mount.h b/security/apparmor/include/mount.h
new file mode 100644
index 0000000..25d6067
--- /dev/null
+++ b/security/apparmor/include/mount.h
@@ -0,0 +1,54 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor file mediation function definitions.
+ *
+ * Copyright 2017 Canonical Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_MOUNT_H
+#define __AA_MOUNT_H
+
+#include <linux/fs.h>
+#include <linux/path.h>
+
+#include "domain.h"
+#include "policy.h"
+
+/* mount perms */
+#define AA_MAY_PIVOTROOT 0x01
+#define AA_MAY_MOUNT 0x02
+#define AA_MAY_UMOUNT 0x04
+#define AA_AUDIT_DATA 0x40
+#define AA_MNT_CONT_MATCH 0x40
+
+#define AA_MS_IGNORE_MASK (MS_KERNMOUNT | MS_NOSEC | MS_ACTIVE | MS_BORN)
+
+int aa_remount(struct aa_label *label, const struct path *path,
+ unsigned long flags, void *data);
+
+int aa_bind_mount(struct aa_label *label, const struct path *path,
+ const char *old_name, unsigned long flags);
+
+
+int aa_mount_change_type(struct aa_label *label, const struct path *path,
+ unsigned long flags);
+
+int aa_move_mount(struct aa_label *label, const struct path *path,
+ const char *old_name);
+
+int aa_new_mount(struct aa_label *label, const char *dev_name,
+ const struct path *path, const char *type, unsigned long flags,
+ void *data);
+
+int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags);
+
+int aa_pivotroot(struct aa_label *label, const struct path *old_path,
+ const struct path *new_path);
+
+#endif /* __AA_MOUNT_H */
diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h
new file mode 100644
index 0000000..140c8efc
--- /dev/null
+++ b/security/apparmor/include/net.h
@@ -0,0 +1,114 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor network mediation definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_NET_H
+#define __AA_NET_H
+
+#include <net/sock.h>
+#include <linux/path.h>
+
+#include "apparmorfs.h"
+#include "label.h"
+#include "perms.h"
+#include "policy.h"
+
+#define AA_MAY_SEND AA_MAY_WRITE
+#define AA_MAY_RECEIVE AA_MAY_READ
+
+#define AA_MAY_SHUTDOWN AA_MAY_DELETE
+
+#define AA_MAY_CONNECT AA_MAY_OPEN
+#define AA_MAY_ACCEPT 0x00100000
+
+#define AA_MAY_BIND 0x00200000
+#define AA_MAY_LISTEN 0x00400000
+
+#define AA_MAY_SETOPT 0x01000000
+#define AA_MAY_GETOPT 0x02000000
+
+#define NET_PERMS_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE | \
+ AA_MAY_SHUTDOWN | AA_MAY_BIND | AA_MAY_LISTEN | \
+ AA_MAY_CONNECT | AA_MAY_ACCEPT | AA_MAY_SETATTR | \
+ AA_MAY_GETATTR | AA_MAY_SETOPT | AA_MAY_GETOPT)
+
+#define NET_FS_PERMS (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE | \
+ AA_MAY_SHUTDOWN | AA_MAY_CONNECT | AA_MAY_RENAME |\
+ AA_MAY_SETATTR | AA_MAY_GETATTR | AA_MAY_CHMOD | \
+ AA_MAY_CHOWN | AA_MAY_CHGRP | AA_MAY_LOCK | \
+ AA_MAY_MPROT)
+
+#define NET_PEER_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CONNECT | \
+ AA_MAY_ACCEPT)
+struct aa_sk_ctx {
+ struct aa_label *label;
+ struct aa_label *peer;
+ struct path path;
+};
+
+#define SK_CTX(X) ((X)->sk_security)
+#define SOCK_ctx(X) SOCK_INODE(X)->i_security
+#define DEFINE_AUDIT_NET(NAME, OP, SK, F, T, P) \
+ struct lsm_network_audit NAME ## _net = { .sk = (SK), \
+ .family = (F)}; \
+ DEFINE_AUDIT_DATA(NAME, \
+ ((SK) && (F) != AF_UNIX) ? LSM_AUDIT_DATA_NET : \
+ LSM_AUDIT_DATA_NONE, \
+ OP); \
+ NAME.u.net = &(NAME ## _net); \
+ aad(&NAME)->net.type = (T); \
+ aad(&NAME)->net.protocol = (P)
+
+#define DEFINE_AUDIT_SK(NAME, OP, SK) \
+ DEFINE_AUDIT_NET(NAME, OP, SK, (SK)->sk_family, (SK)->sk_type, \
+ (SK)->sk_protocol)
+
+/* struct aa_net - network confinement data
+ * @allow: basic network families permissions
+ * @audit: which network permissions to force audit
+ * @quiet: which network permissions to quiet rejects
+ */
+struct aa_net {
+ u16 allow[AF_MAX];
+ u16 audit[AF_MAX];
+ u16 quiet[AF_MAX];
+};
+
+
+extern struct aa_sfs_entry aa_sfs_entry_network[];
+
+void audit_net_cb(struct audit_buffer *ab, void *va);
+int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa,
+ u32 request, u16 family, int type);
+int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family,
+ int type, int protocol);
+static inline int aa_profile_af_sk_perm(struct aa_profile *profile,
+ struct common_audit_data *sa,
+ u32 request,
+ struct sock *sk)
+{
+ return aa_profile_af_perm(profile, sa, request, sk->sk_family,
+ sk->sk_type);
+}
+int aa_sk_perm(const char *op, u32 request, struct sock *sk);
+
+int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request,
+ struct socket *sock);
+
+
+static inline void aa_free_net_rules(struct aa_net *new)
+{
+ /* NOP */
+}
+
+#endif /* __AA_NET_H */
diff --git a/security/apparmor/include/perms.h b/security/apparmor/include/perms.h
index 2b27bb7..af04d5a 100644
--- a/security/apparmor/include/perms.h
+++ b/security/apparmor/include/perms.h
@@ -135,9 +135,10 @@
void aa_perm_mask_to_str(char *str, const char *chrs, u32 mask);
-void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask);
+void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names,
+ u32 mask);
void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs,
- u32 chrsmask, const char **names, u32 namesmask);
+ u32 chrsmask, const char * const *names, u32 namesmask);
void aa_apply_modes_to_perms(struct aa_profile *profile,
struct aa_perms *perms);
void aa_compute_perms(struct aa_dfa *dfa, unsigned int state,
diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h
index 17fe41a..4364088 100644
--- a/security/apparmor/include/policy.h
+++ b/security/apparmor/include/policy.h
@@ -30,6 +30,7 @@
#include "file.h"
#include "lib.h"
#include "label.h"
+#include "net.h"
#include "perms.h"
#include "resource.h"
@@ -111,6 +112,7 @@
* @policy: general match rules governing policy
* @file: The set of rules governing basic file access and domain transitions
* @caps: capabilities for the profile
+ * @net: network controls for the profile
* @rlimits: rlimits for the profile
*
* @dents: dentries for the profiles file entries in apparmorfs
@@ -148,6 +150,7 @@
struct aa_policydb policy;
struct aa_file_rules file;
struct aa_caps caps;
+ struct aa_net net;
struct aa_rlimit rlimits;
struct aa_loaddata *rawdata;
@@ -220,6 +223,16 @@
return 0;
}
+static inline unsigned int PROFILE_MEDIATES_AF(struct aa_profile *profile,
+ u16 AF) {
+ unsigned int state = PROFILE_MEDIATES(profile, AA_CLASS_NET);
+ u16 be_af = cpu_to_be16(AF);
+
+ if (!state)
+ return 0;
+ return aa_dfa_match_len(profile->policy.dfa, state, (char *) &be_af, 2);
+}
+
/**
* aa_get_profile - increment refcount on profile @p
* @p: profile (MAYBE NULL)
diff --git a/security/apparmor/include/sig_names.h b/security/apparmor/include/sig_names.h
new file mode 100644
index 0000000..92e62fe
--- /dev/null
+++ b/security/apparmor/include/sig_names.h
@@ -0,0 +1,98 @@
+#include <linux/signal.h>
+
+#define SIGUNKNOWN 0
+#define MAXMAPPED_SIG 35
+/* provide a mapping of arch signal to internal signal # for mediation
+ * those that are always an alias SIGCLD for SIGCLHD and SIGPOLL for SIGIO
+ * map to the same entry those that may/or may not get a separate entry
+ */
+static const int sig_map[MAXMAPPED_SIG] = {
+ [0] = MAXMAPPED_SIG, /* existence test */
+ [SIGHUP] = 1,
+ [SIGINT] = 2,
+ [SIGQUIT] = 3,
+ [SIGILL] = 4,
+ [SIGTRAP] = 5, /* -, 5, - */
+ [SIGABRT] = 6, /* SIGIOT: -, 6, - */
+ [SIGBUS] = 7, /* 10, 7, 10 */
+ [SIGFPE] = 8,
+ [SIGKILL] = 9,
+ [SIGUSR1] = 10, /* 30, 10, 16 */
+ [SIGSEGV] = 11,
+ [SIGUSR2] = 12, /* 31, 12, 17 */
+ [SIGPIPE] = 13,
+ [SIGALRM] = 14,
+ [SIGTERM] = 15,
+#ifdef SIGSTKFLT
+ [SIGSTKFLT] = 16, /* -, 16, - */
+#endif
+ [SIGCHLD] = 17, /* 20, 17, 18. SIGCHLD -, -, 18 */
+ [SIGCONT] = 18, /* 19, 18, 25 */
+ [SIGSTOP] = 19, /* 17, 19, 23 */
+ [SIGTSTP] = 20, /* 18, 20, 24 */
+ [SIGTTIN] = 21, /* 21, 21, 26 */
+ [SIGTTOU] = 22, /* 22, 22, 27 */
+ [SIGURG] = 23, /* 16, 23, 21 */
+ [SIGXCPU] = 24, /* 24, 24, 30 */
+ [SIGXFSZ] = 25, /* 25, 25, 31 */
+ [SIGVTALRM] = 26, /* 26, 26, 28 */
+ [SIGPROF] = 27, /* 27, 27, 29 */
+ [SIGWINCH] = 28, /* 28, 28, 20 */
+ [SIGIO] = 29, /* SIGPOLL: 23, 29, 22 */
+ [SIGPWR] = 30, /* 29, 30, 19. SIGINFO 29, -, - */
+#ifdef SIGSYS
+ [SIGSYS] = 31, /* 12, 31, 12. often SIG LOST/UNUSED */
+#endif
+#ifdef SIGEMT
+ [SIGEMT] = 32, /* 7, - , 7 */
+#endif
+#if defined(SIGLOST) && SIGPWR != SIGLOST /* sparc */
+ [SIGLOST] = 33, /* unused on Linux */
+#endif
+#if defined(SIGUNUSED) && \
+ defined(SIGLOST) && defined(SIGSYS) && SIGLOST != SIGSYS
+ [SIGUNUSED] = 34, /* -, 31, - */
+#endif
+};
+
+/* this table is ordered post sig_map[sig] mapping */
+static const char *const sig_names[MAXMAPPED_SIG + 1] = {
+ "unknown",
+ "hup",
+ "int",
+ "quit",
+ "ill",
+ "trap",
+ "abrt",
+ "bus",
+ "fpe",
+ "kill",
+ "usr1",
+ "segv",
+ "usr2",
+ "pipe",
+ "alrm",
+ "term",
+ "stkflt",
+ "chld",
+ "cont",
+ "stop",
+ "stp",
+ "ttin",
+ "ttou",
+ "urg",
+ "xcpu",
+ "xfsz",
+ "vtalrm",
+ "prof",
+ "winch",
+ "io",
+ "pwr",
+ "sys",
+ "emt",
+ "lost",
+ "unused",
+
+ "exists", /* always last existence test mapped to MAXMAPPED_SIG */
+};
+
diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c
index 11e66b5..66fb9ed 100644
--- a/security/apparmor/ipc.c
+++ b/security/apparmor/ipc.c
@@ -20,6 +20,7 @@
#include "include/context.h"
#include "include/policy.h"
#include "include/ipc.h"
+#include "include/sig_names.h"
/**
* audit_ptrace_mask - convert mask to permission string
@@ -121,3 +122,101 @@
}
+static inline int map_signal_num(int sig)
+{
+ if (sig > SIGRTMAX)
+ return SIGUNKNOWN;
+ else if (sig >= SIGRTMIN)
+ return sig - SIGRTMIN + 128; /* rt sigs mapped to 128 */
+ else if (sig <= MAXMAPPED_SIG)
+ return sig_map[sig];
+ return SIGUNKNOWN;
+}
+
+/**
+ * audit_file_mask - convert mask to permission string
+ * @buffer: buffer to write string to (NOT NULL)
+ * @mask: permission mask to convert
+ */
+static void audit_signal_mask(struct audit_buffer *ab, u32 mask)
+{
+ if (mask & MAY_READ)
+ audit_log_string(ab, "receive");
+ if (mask & MAY_WRITE)
+ audit_log_string(ab, "send");
+}
+
+/**
+ * audit_cb - call back for signal specific audit fields
+ * @ab: audit_buffer (NOT NULL)
+ * @va: audit struct to audit values of (NOT NULL)
+ */
+static void audit_signal_cb(struct audit_buffer *ab, void *va)
+{
+ struct common_audit_data *sa = va;
+
+ if (aad(sa)->request & AA_SIGNAL_PERM_MASK) {
+ audit_log_format(ab, " requested_mask=");
+ audit_signal_mask(ab, aad(sa)->request);
+ if (aad(sa)->denied & AA_SIGNAL_PERM_MASK) {
+ audit_log_format(ab, " denied_mask=");
+ audit_signal_mask(ab, aad(sa)->denied);
+ }
+ }
+ if (aad(sa)->signal <= MAXMAPPED_SIG)
+ audit_log_format(ab, " signal=%s", sig_names[aad(sa)->signal]);
+ else
+ audit_log_format(ab, " signal=rtmin+%d",
+ aad(sa)->signal - 128);
+ audit_log_format(ab, " peer=");
+ aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer,
+ FLAGS_NONE, GFP_ATOMIC);
+}
+
+/* TODO: update to handle compound name&name2, conditionals */
+static void profile_match_signal(struct aa_profile *profile, const char *label,
+ int signal, struct aa_perms *perms)
+{
+ unsigned int state;
+
+ /* TODO: secondary cache check <profile, profile, perm> */
+ state = aa_dfa_next(profile->policy.dfa,
+ profile->policy.start[AA_CLASS_SIGNAL],
+ signal);
+ state = aa_dfa_match(profile->policy.dfa, state, label);
+ aa_compute_perms(profile->policy.dfa, state, perms);
+}
+
+static int profile_signal_perm(struct aa_profile *profile,
+ struct aa_profile *peer, u32 request,
+ struct common_audit_data *sa)
+{
+ struct aa_perms perms;
+
+ if (profile_unconfined(profile) ||
+ !PROFILE_MEDIATES(profile, AA_CLASS_SIGNAL))
+ return 0;
+
+ aad(sa)->peer = &peer->label;
+ profile_match_signal(profile, peer->base.hname, aad(sa)->signal,
+ &perms);
+ aa_apply_modes_to_perms(profile, &perms);
+ return aa_check_perms(profile, &perms, request, sa, audit_signal_cb);
+}
+
+static int aa_signal_cross_perm(struct aa_profile *sender,
+ struct aa_profile *target,
+ struct common_audit_data *sa)
+{
+ return xcheck(profile_signal_perm(sender, target, MAY_WRITE, sa),
+ profile_signal_perm(target, sender, MAY_READ, sa));
+}
+
+int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig)
+{
+ DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, OP_SIGNAL);
+
+ aad(&sa)->signal = map_signal_num(sig);
+ return xcheck_labels_profiles(sender, target, aa_signal_cross_perm,
+ &sa);
+}
diff --git a/security/apparmor/label.c b/security/apparmor/label.c
index e052eab..c5b99b9 100644
--- a/security/apparmor/label.c
+++ b/security/apparmor/label.c
@@ -49,7 +49,7 @@
/* p->label will not updated any more as p is dead */
aa_put_label(rcu_dereference_protected(proxy->label, true));
memset(proxy, 0, sizeof(*proxy));
- proxy->label = (struct aa_label *) PROXY_POISON;
+ RCU_INIT_POINTER(proxy->label, (struct aa_label *)PROXY_POISON);
kfree(proxy);
}
}
@@ -1450,9 +1450,11 @@
* cached label name is present and visible
* @label->hname only exists if label is namespace hierachical
*/
-static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label)
+static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label,
+ int flags)
{
- if (label->hname && labels_ns(label) == ns)
+ if (label->hname && (!ns || labels_ns(label) == ns) &&
+ !(flags & ~FLAG_SHOW_MODE))
return true;
return false;
@@ -1495,7 +1497,7 @@
view = profiles_ns(profile);
if (view != profile->ns &&
- (!prev_ns || (prev_ns && *prev_ns != profile->ns))) {
+ (!prev_ns || (*prev_ns != profile->ns))) {
if (prev_ns)
*prev_ns = profile->ns;
ns_name = aa_ns_name(view, profile->ns,
@@ -1605,8 +1607,13 @@
AA_BUG(!str && size != 0);
AA_BUG(!label);
- if (!ns)
+ if (flags & FLAG_ABS_ROOT) {
+ ns = root_ns;
+ len = snprintf(str, size, "=");
+ update_for_len(total, len, size, str);
+ } else if (!ns) {
ns = labels_ns(label);
+ }
label_for_each(i, label, profile) {
if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) {
@@ -1710,10 +1717,8 @@
AA_BUG(!ab);
AA_BUG(!label);
- if (!ns)
- ns = labels_ns(label);
-
- if (!use_label_hname(ns, label) || display_mode(ns, label, flags)) {
+ if (!use_label_hname(ns, label, flags) ||
+ display_mode(ns, label, flags)) {
len = aa_label_asxprint(&name, ns, label, flags, gfp);
if (len == -1) {
AA_DEBUG("label print error");
@@ -1738,10 +1743,7 @@
AA_BUG(!f);
AA_BUG(!label);
- if (!ns)
- ns = labels_ns(label);
-
- if (!use_label_hname(ns, label)) {
+ if (!use_label_hname(ns, label, flags)) {
char *str;
int len;
@@ -1764,10 +1766,7 @@
{
AA_BUG(!label);
- if (!ns)
- ns = labels_ns(label);
-
- if (!use_label_hname(ns, label)) {
+ if (!use_label_hname(ns, label, flags)) {
char *str;
int len;
@@ -1874,6 +1873,9 @@
if (*str == '&')
str++;
}
+ if (*str == '=')
+ base = &root_ns->unconfined->label;
+
error = vec_setup(profile, vec, len, gfp);
if (error)
return ERR_PTR(error);
diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c
index 08ca26b..8818621 100644
--- a/security/apparmor/lib.c
+++ b/security/apparmor/lib.c
@@ -211,7 +211,8 @@
*str = '\0';
}
-void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask)
+void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names,
+ u32 mask)
{
const char *fmt = "%s";
unsigned int i, perm = 1;
@@ -229,7 +230,7 @@
}
void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs,
- u32 chrsmask, const char **names, u32 namesmask)
+ u32 chrsmask, const char * const *names, u32 namesmask)
{
char str[33];
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 7a82c0f..72b915df 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -33,11 +33,13 @@
#include "include/context.h"
#include "include/file.h"
#include "include/ipc.h"
+#include "include/net.h"
#include "include/path.h"
#include "include/label.h"
#include "include/policy.h"
#include "include/policy_ns.h"
#include "include/procattr.h"
+#include "include/mount.h"
/* Flag indicating whether initialization completed */
int apparmor_initialized;
@@ -511,6 +513,65 @@
!(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0);
}
+static int apparmor_sb_mount(const char *dev_name, const struct path *path,
+ const char *type, unsigned long flags, void *data)
+{
+ struct aa_label *label;
+ int error = 0;
+
+ /* Discard magic */
+ if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
+ flags &= ~MS_MGC_MSK;
+
+ flags &= ~AA_MS_IGNORE_MASK;
+
+ label = __begin_current_label_crit_section();
+ if (!unconfined(label)) {
+ if (flags & MS_REMOUNT)
+ error = aa_remount(label, path, flags, data);
+ else if (flags & MS_BIND)
+ error = aa_bind_mount(label, path, dev_name, flags);
+ else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE |
+ MS_UNBINDABLE))
+ error = aa_mount_change_type(label, path, flags);
+ else if (flags & MS_MOVE)
+ error = aa_move_mount(label, path, dev_name);
+ else
+ error = aa_new_mount(label, dev_name, path, type,
+ flags, data);
+ }
+ __end_current_label_crit_section(label);
+
+ return error;
+}
+
+static int apparmor_sb_umount(struct vfsmount *mnt, int flags)
+{
+ struct aa_label *label;
+ int error = 0;
+
+ label = __begin_current_label_crit_section();
+ if (!unconfined(label))
+ error = aa_umount(label, mnt, flags);
+ __end_current_label_crit_section(label);
+
+ return error;
+}
+
+static int apparmor_sb_pivotroot(const struct path *old_path,
+ const struct path *new_path)
+{
+ struct aa_label *label;
+ int error = 0;
+
+ label = aa_get_current_label();
+ if (!unconfined(label))
+ error = aa_pivotroot(label, old_path, new_path);
+ aa_put_label(label);
+
+ return error;
+}
+
static int apparmor_getprocattr(struct task_struct *task, char *name,
char **value)
{
@@ -656,12 +717,398 @@
return error;
}
+static int apparmor_task_kill(struct task_struct *target, struct siginfo *info,
+ int sig, u32 secid)
+{
+ struct aa_label *cl, *tl;
+ int error;
+
+ if (secid)
+ /* TODO: after secid to label mapping is done.
+ * Dealing with USB IO specific behavior
+ */
+ return 0;
+ cl = __begin_current_label_crit_section();
+ tl = aa_get_task_label(target);
+ error = aa_may_signal(cl, tl, sig);
+ aa_put_label(tl);
+ __end_current_label_crit_section(cl);
+
+ return error;
+}
+
+/**
+ * apparmor_sk_alloc_security - allocate and attach the sk_security field
+ */
+static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags)
+{
+ struct aa_sk_ctx *ctx;
+
+ ctx = kzalloc(sizeof(*ctx), flags);
+ if (!ctx)
+ return -ENOMEM;
+
+ SK_CTX(sk) = ctx;
+
+ return 0;
+}
+
+/**
+ * apparmor_sk_free_security - free the sk_security field
+ */
+static void apparmor_sk_free_security(struct sock *sk)
+{
+ struct aa_sk_ctx *ctx = SK_CTX(sk);
+
+ SK_CTX(sk) = NULL;
+ aa_put_label(ctx->label);
+ aa_put_label(ctx->peer);
+ path_put(&ctx->path);
+ kfree(ctx);
+}
+
+/**
+ * apparmor_clone_security - clone the sk_security field
+ */
+static void apparmor_sk_clone_security(const struct sock *sk,
+ struct sock *newsk)
+{
+ struct aa_sk_ctx *ctx = SK_CTX(sk);
+ struct aa_sk_ctx *new = SK_CTX(newsk);
+
+ new->label = aa_get_label(ctx->label);
+ new->peer = aa_get_label(ctx->peer);
+ new->path = ctx->path;
+ path_get(&new->path);
+}
+
+static int aa_sock_create_perm(struct aa_label *label, int family, int type,
+ int protocol)
+{
+ AA_BUG(!label);
+ AA_BUG(in_interrupt());
+
+ return aa_af_perm(label, OP_CREATE, AA_MAY_CREATE, family, type,
+ protocol);
+}
+
+
+/**
+ * apparmor_socket_create - check perms before creating a new socket
+ */
+static int apparmor_socket_create(int family, int type, int protocol, int kern)
+{
+ struct aa_label *label;
+ int error = 0;
+
+ label = begin_current_label_crit_section();
+ if (!(kern || unconfined(label)))
+ error = aa_sock_create_perm(label, family, type, protocol);
+ end_current_label_crit_section(label);
+
+ return error;
+}
+
+/**
+ * apparmor_socket_post_create - setup the per-socket security struct
+ *
+ * Note:
+ * - kernel sockets currently labeled unconfined but we may want to
+ * move to a special kernel label
+ * - socket may not have sk here if created with sock_create_lite or
+ * sock_alloc. These should be accept cases which will be handled in
+ * sock_graft.
+ */
+static int apparmor_socket_post_create(struct socket *sock, int family,
+ int type, int protocol, int kern)
+{
+ struct aa_label *label;
+
+ if (kern) {
+ struct aa_ns *ns = aa_get_current_ns();
+
+ label = aa_get_label(ns_unconfined(ns));
+ aa_put_ns(ns);
+ } else
+ label = aa_get_current_label();
+
+ if (sock->sk) {
+ struct aa_sk_ctx *ctx = SK_CTX(sock->sk);
+
+ aa_put_label(ctx->label);
+ ctx->label = aa_get_label(label);
+ }
+ aa_put_label(label);
+
+ return 0;
+}
+
+/**
+ * apparmor_socket_bind - check perms before bind addr to socket
+ */
+static int apparmor_socket_bind(struct socket *sock,
+ struct sockaddr *address, int addrlen)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(!address);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk);
+}
+
+/**
+ * apparmor_socket_connect - check perms before connecting @sock to @address
+ */
+static int apparmor_socket_connect(struct socket *sock,
+ struct sockaddr *address, int addrlen)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(!address);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk);
+}
+
+/**
+ * apparmor_socket_list - check perms before allowing listen
+ */
+static int apparmor_socket_listen(struct socket *sock, int backlog)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk);
+}
+
+/**
+ * apparmor_socket_accept - check perms before accepting a new connection.
+ *
+ * Note: while @newsock is created and has some information, the accept
+ * has not been done.
+ */
+static int apparmor_socket_accept(struct socket *sock, struct socket *newsock)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(!newsock);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(OP_ACCEPT, AA_MAY_ACCEPT, sock->sk);
+}
+
+static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock,
+ struct msghdr *msg, int size)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(!msg);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(op, request, sock->sk);
+}
+
+/**
+ * apparmor_socket_sendmsg - check perms before sending msg to another socket
+ */
+static int apparmor_socket_sendmsg(struct socket *sock,
+ struct msghdr *msg, int size)
+{
+ return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size);
+}
+
+/**
+ * apparmor_socket_recvmsg - check perms before receiving a message
+ */
+static int apparmor_socket_recvmsg(struct socket *sock,
+ struct msghdr *msg, int size, int flags)
+{
+ return aa_sock_msg_perm(OP_RECVMSG, AA_MAY_RECEIVE, sock, msg, size);
+}
+
+/* revaliation, get/set attr, shutdown */
+static int aa_sock_perm(const char *op, u32 request, struct socket *sock)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(op, request, sock->sk);
+}
+
+/**
+ * apparmor_socket_getsockname - check perms before getting the local address
+ */
+static int apparmor_socket_getsockname(struct socket *sock)
+{
+ return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock);
+}
+
+/**
+ * apparmor_socket_getpeername - check perms before getting remote address
+ */
+static int apparmor_socket_getpeername(struct socket *sock)
+{
+ return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock);
+}
+
+/* revaliation, get/set attr, opt */
+static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock,
+ int level, int optname)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(op, request, sock->sk);
+}
+
+/**
+ * apparmor_getsockopt - check perms before getting socket options
+ */
+static int apparmor_socket_getsockopt(struct socket *sock, int level,
+ int optname)
+{
+ return aa_sock_opt_perm(OP_GETSOCKOPT, AA_MAY_GETOPT, sock,
+ level, optname);
+}
+
+/**
+ * apparmor_setsockopt - check perms before setting socket options
+ */
+static int apparmor_socket_setsockopt(struct socket *sock, int level,
+ int optname)
+{
+ return aa_sock_opt_perm(OP_SETSOCKOPT, AA_MAY_SETOPT, sock,
+ level, optname);
+}
+
+/**
+ * apparmor_socket_shutdown - check perms before shutting down @sock conn
+ */
+static int apparmor_socket_shutdown(struct socket *sock, int how)
+{
+ return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock);
+}
+
+/**
+ * apparmor_socket_sock_recv_skb - check perms before associating skb to sk
+ *
+ * Note: can not sleep may be called with locks held
+ *
+ * dont want protocol specific in __skb_recv_datagram()
+ * to deny an incoming connection socket_sock_rcv_skb()
+ */
+static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ return 0;
+}
+
+
+static struct aa_label *sk_peer_label(struct sock *sk)
+{
+ struct aa_sk_ctx *ctx = SK_CTX(sk);
+
+ if (ctx->peer)
+ return ctx->peer;
+
+ return ERR_PTR(-ENOPROTOOPT);
+}
+
+/**
+ * apparmor_socket_getpeersec_stream - get security context of peer
+ *
+ * Note: for tcp only valid if using ipsec or cipso on lan
+ */
+static int apparmor_socket_getpeersec_stream(struct socket *sock,
+ char __user *optval,
+ int __user *optlen,
+ unsigned int len)
+{
+ char *name;
+ int slen, error = 0;
+ struct aa_label *label;
+ struct aa_label *peer;
+
+ label = begin_current_label_crit_section();
+ peer = sk_peer_label(sock->sk);
+ if (IS_ERR(peer)) {
+ error = PTR_ERR(peer);
+ goto done;
+ }
+ slen = aa_label_asxprint(&name, labels_ns(label), peer,
+ FLAG_SHOW_MODE | FLAG_VIEW_SUBNS |
+ FLAG_HIDDEN_UNCONFINED, GFP_KERNEL);
+ /* don't include terminating \0 in slen, it breaks some apps */
+ if (slen < 0) {
+ error = -ENOMEM;
+ } else {
+ if (slen > len) {
+ error = -ERANGE;
+ } else if (copy_to_user(optval, name, slen)) {
+ error = -EFAULT;
+ goto out;
+ }
+ if (put_user(slen, optlen))
+ error = -EFAULT;
+out:
+ kfree(name);
+
+ }
+
+done:
+ end_current_label_crit_section(label);
+
+ return error;
+}
+
+/**
+ * apparmor_socket_getpeersec_dgram - get security label of packet
+ * @sock: the peer socket
+ * @skb: packet data
+ * @secid: pointer to where to put the secid of the packet
+ *
+ * Sets the netlabel socket state on sk from parent
+ */
+static int apparmor_socket_getpeersec_dgram(struct socket *sock,
+ struct sk_buff *skb, u32 *secid)
+
+{
+ /* TODO: requires secid support */
+ return -ENOPROTOOPT;
+}
+
+/**
+ * apparmor_sock_graft - Initialize newly created socket
+ * @sk: child sock
+ * @parent: parent socket
+ *
+ * Note: could set off of SOCK_CTX(parent) but need to track inode and we can
+ * just set sk security information off of current creating process label
+ * Labeling of sk for accept case - probably should be sock based
+ * instead of task, because of the case where an implicitly labeled
+ * socket is shared by different tasks.
+ */
+static void apparmor_sock_graft(struct sock *sk, struct socket *parent)
+{
+ struct aa_sk_ctx *ctx = SK_CTX(sk);
+
+ if (!ctx->label)
+ ctx->label = aa_get_current_label();
+}
+
static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = {
LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check),
LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme),
LSM_HOOK_INIT(capget, apparmor_capget),
LSM_HOOK_INIT(capable, apparmor_capable),
+ LSM_HOOK_INIT(sb_mount, apparmor_sb_mount),
+ LSM_HOOK_INIT(sb_umount, apparmor_sb_umount),
+ LSM_HOOK_INIT(sb_pivotroot, apparmor_sb_pivotroot),
+
LSM_HOOK_INIT(path_link, apparmor_path_link),
LSM_HOOK_INIT(path_unlink, apparmor_path_unlink),
LSM_HOOK_INIT(path_symlink, apparmor_path_symlink),
@@ -686,6 +1133,30 @@
LSM_HOOK_INIT(getprocattr, apparmor_getprocattr),
LSM_HOOK_INIT(setprocattr, apparmor_setprocattr),
+ LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security),
+ LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security),
+ LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security),
+
+ LSM_HOOK_INIT(socket_create, apparmor_socket_create),
+ LSM_HOOK_INIT(socket_post_create, apparmor_socket_post_create),
+ LSM_HOOK_INIT(socket_bind, apparmor_socket_bind),
+ LSM_HOOK_INIT(socket_connect, apparmor_socket_connect),
+ LSM_HOOK_INIT(socket_listen, apparmor_socket_listen),
+ LSM_HOOK_INIT(socket_accept, apparmor_socket_accept),
+ LSM_HOOK_INIT(socket_sendmsg, apparmor_socket_sendmsg),
+ LSM_HOOK_INIT(socket_recvmsg, apparmor_socket_recvmsg),
+ LSM_HOOK_INIT(socket_getsockname, apparmor_socket_getsockname),
+ LSM_HOOK_INIT(socket_getpeername, apparmor_socket_getpeername),
+ LSM_HOOK_INIT(socket_getsockopt, apparmor_socket_getsockopt),
+ LSM_HOOK_INIT(socket_setsockopt, apparmor_socket_setsockopt),
+ LSM_HOOK_INIT(socket_shutdown, apparmor_socket_shutdown),
+ LSM_HOOK_INIT(socket_sock_rcv_skb, apparmor_socket_sock_rcv_skb),
+ LSM_HOOK_INIT(socket_getpeersec_stream,
+ apparmor_socket_getpeersec_stream),
+ LSM_HOOK_INIT(socket_getpeersec_dgram,
+ apparmor_socket_getpeersec_dgram),
+ LSM_HOOK_INIT(sock_graft, apparmor_sock_graft),
+
LSM_HOOK_INIT(cred_alloc_blank, apparmor_cred_alloc_blank),
LSM_HOOK_INIT(cred_free, apparmor_cred_free),
LSM_HOOK_INIT(cred_prepare, apparmor_cred_prepare),
@@ -696,6 +1167,7 @@
LSM_HOOK_INIT(bprm_committed_creds, apparmor_bprm_committed_creds),
LSM_HOOK_INIT(task_setrlimit, apparmor_task_setrlimit),
+ LSM_HOOK_INIT(task_kill, apparmor_task_kill),
};
/*
diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c
new file mode 100644
index 0000000..82a64b5
--- /dev/null
+++ b/security/apparmor/mount.c
@@ -0,0 +1,696 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor mediation of files
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/context.h"
+#include "include/domain.h"
+#include "include/file.h"
+#include "include/match.h"
+#include "include/mount.h"
+#include "include/path.h"
+#include "include/policy.h"
+
+
+static void audit_mnt_flags(struct audit_buffer *ab, unsigned long flags)
+{
+ if (flags & MS_RDONLY)
+ audit_log_format(ab, "ro");
+ else
+ audit_log_format(ab, "rw");
+ if (flags & MS_NOSUID)
+ audit_log_format(ab, ", nosuid");
+ if (flags & MS_NODEV)
+ audit_log_format(ab, ", nodev");
+ if (flags & MS_NOEXEC)
+ audit_log_format(ab, ", noexec");
+ if (flags & MS_SYNCHRONOUS)
+ audit_log_format(ab, ", sync");
+ if (flags & MS_REMOUNT)
+ audit_log_format(ab, ", remount");
+ if (flags & MS_MANDLOCK)
+ audit_log_format(ab, ", mand");
+ if (flags & MS_DIRSYNC)
+ audit_log_format(ab, ", dirsync");
+ if (flags & MS_NOATIME)
+ audit_log_format(ab, ", noatime");
+ if (flags & MS_NODIRATIME)
+ audit_log_format(ab, ", nodiratime");
+ if (flags & MS_BIND)
+ audit_log_format(ab, flags & MS_REC ? ", rbind" : ", bind");
+ if (flags & MS_MOVE)
+ audit_log_format(ab, ", move");
+ if (flags & MS_SILENT)
+ audit_log_format(ab, ", silent");
+ if (flags & MS_POSIXACL)
+ audit_log_format(ab, ", acl");
+ if (flags & MS_UNBINDABLE)
+ audit_log_format(ab, flags & MS_REC ? ", runbindable" :
+ ", unbindable");
+ if (flags & MS_PRIVATE)
+ audit_log_format(ab, flags & MS_REC ? ", rprivate" :
+ ", private");
+ if (flags & MS_SLAVE)
+ audit_log_format(ab, flags & MS_REC ? ", rslave" :
+ ", slave");
+ if (flags & MS_SHARED)
+ audit_log_format(ab, flags & MS_REC ? ", rshared" :
+ ", shared");
+ if (flags & MS_RELATIME)
+ audit_log_format(ab, ", relatime");
+ if (flags & MS_I_VERSION)
+ audit_log_format(ab, ", iversion");
+ if (flags & MS_STRICTATIME)
+ audit_log_format(ab, ", strictatime");
+ if (flags & MS_NOUSER)
+ audit_log_format(ab, ", nouser");
+}
+
+/**
+ * audit_cb - call back for mount specific audit fields
+ * @ab: audit_buffer (NOT NULL)
+ * @va: audit struct to audit values of (NOT NULL)
+ */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+ struct common_audit_data *sa = va;
+
+ if (aad(sa)->mnt.type) {
+ audit_log_format(ab, " fstype=");
+ audit_log_untrustedstring(ab, aad(sa)->mnt.type);
+ }
+ if (aad(sa)->mnt.src_name) {
+ audit_log_format(ab, " srcname=");
+ audit_log_untrustedstring(ab, aad(sa)->mnt.src_name);
+ }
+ if (aad(sa)->mnt.trans) {
+ audit_log_format(ab, " trans=");
+ audit_log_untrustedstring(ab, aad(sa)->mnt.trans);
+ }
+ if (aad(sa)->mnt.flags) {
+ audit_log_format(ab, " flags=\"");
+ audit_mnt_flags(ab, aad(sa)->mnt.flags);
+ audit_log_format(ab, "\"");
+ }
+ if (aad(sa)->mnt.data) {
+ audit_log_format(ab, " options=");
+ audit_log_untrustedstring(ab, aad(sa)->mnt.data);
+ }
+}
+
+/**
+ * audit_mount - handle the auditing of mount operations
+ * @profile: the profile being enforced (NOT NULL)
+ * @op: operation being mediated (NOT NULL)
+ * @name: name of object being mediated (MAYBE NULL)
+ * @src_name: src_name of object being mediated (MAYBE_NULL)
+ * @type: type of filesystem (MAYBE_NULL)
+ * @trans: name of trans (MAYBE NULL)
+ * @flags: filesystem idependent mount flags
+ * @data: filesystem mount flags
+ * @request: permissions requested
+ * @perms: the permissions computed for the request (NOT NULL)
+ * @info: extra information message (MAYBE NULL)
+ * @error: 0 if operation allowed else failure error code
+ *
+ * Returns: %0 or error on failure
+ */
+static int audit_mount(struct aa_profile *profile, const char *op,
+ const char *name, const char *src_name,
+ const char *type, const char *trans,
+ unsigned long flags, const void *data, u32 request,
+ struct aa_perms *perms, const char *info, int error)
+{
+ int audit_type = AUDIT_APPARMOR_AUTO;
+ DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, op);
+
+ if (likely(!error)) {
+ u32 mask = perms->audit;
+
+ if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL))
+ mask = 0xffff;
+
+ /* mask off perms that are not being force audited */
+ request &= mask;
+
+ if (likely(!request))
+ return 0;
+ audit_type = AUDIT_APPARMOR_AUDIT;
+ } else {
+ /* only report permissions that were denied */
+ request = request & ~perms->allow;
+
+ if (request & perms->kill)
+ audit_type = AUDIT_APPARMOR_KILL;
+
+ /* quiet known rejects, assumes quiet and kill do not overlap */
+ if ((request & perms->quiet) &&
+ AUDIT_MODE(profile) != AUDIT_NOQUIET &&
+ AUDIT_MODE(profile) != AUDIT_ALL)
+ request &= ~perms->quiet;
+
+ if (!request)
+ return error;
+ }
+
+ aad(&sa)->name = name;
+ aad(&sa)->mnt.src_name = src_name;
+ aad(&sa)->mnt.type = type;
+ aad(&sa)->mnt.trans = trans;
+ aad(&sa)->mnt.flags = flags;
+ if (data && (perms->audit & AA_AUDIT_DATA))
+ aad(&sa)->mnt.data = data;
+ aad(&sa)->info = info;
+ aad(&sa)->error = error;
+
+ return aa_audit(audit_type, profile, &sa, audit_cb);
+}
+
+/**
+ * match_mnt_flags - Do an ordered match on mount flags
+ * @dfa: dfa to match against
+ * @state: state to start in
+ * @flags: mount flags to match against
+ *
+ * Mount flags are encoded as an ordered match. This is done instead of
+ * checking against a simple bitmask, to allow for logical operations
+ * on the flags.
+ *
+ * Returns: next state after flags match
+ */
+static unsigned int match_mnt_flags(struct aa_dfa *dfa, unsigned int state,
+ unsigned long flags)
+{
+ unsigned int i;
+
+ for (i = 0; i <= 31 ; ++i) {
+ if ((1 << i) & flags)
+ state = aa_dfa_next(dfa, state, i + 1);
+ }
+
+ return state;
+}
+
+/**
+ * compute_mnt_perms - compute mount permission associated with @state
+ * @dfa: dfa to match against (NOT NULL)
+ * @state: state match finished in
+ *
+ * Returns: mount permissions
+ */
+static struct aa_perms compute_mnt_perms(struct aa_dfa *dfa,
+ unsigned int state)
+{
+ struct aa_perms perms;
+
+ perms.kill = 0;
+ perms.allow = dfa_user_allow(dfa, state);
+ perms.audit = dfa_user_audit(dfa, state);
+ perms.quiet = dfa_user_quiet(dfa, state);
+ perms.xindex = dfa_user_xindex(dfa, state);
+
+ return perms;
+}
+
+static const char * const mnt_info_table[] = {
+ "match succeeded",
+ "failed mntpnt match",
+ "failed srcname match",
+ "failed type match",
+ "failed flags match",
+ "failed data match"
+};
+
+/*
+ * Returns 0 on success else element that match failed in, this is the
+ * index into the mnt_info_table above
+ */
+static int do_match_mnt(struct aa_dfa *dfa, unsigned int start,
+ const char *mntpnt, const char *devname,
+ const char *type, unsigned long flags,
+ void *data, bool binary, struct aa_perms *perms)
+{
+ unsigned int state;
+
+ AA_BUG(!dfa);
+ AA_BUG(!perms);
+
+ state = aa_dfa_match(dfa, start, mntpnt);
+ state = aa_dfa_null_transition(dfa, state);
+ if (!state)
+ return 1;
+
+ if (devname)
+ state = aa_dfa_match(dfa, state, devname);
+ state = aa_dfa_null_transition(dfa, state);
+ if (!state)
+ return 2;
+
+ if (type)
+ state = aa_dfa_match(dfa, state, type);
+ state = aa_dfa_null_transition(dfa, state);
+ if (!state)
+ return 3;
+
+ state = match_mnt_flags(dfa, state, flags);
+ if (!state)
+ return 4;
+ *perms = compute_mnt_perms(dfa, state);
+ if (perms->allow & AA_MAY_MOUNT)
+ return 0;
+
+ /* only match data if not binary and the DFA flags data is expected */
+ if (data && !binary && (perms->allow & AA_MNT_CONT_MATCH)) {
+ state = aa_dfa_null_transition(dfa, state);
+ if (!state)
+ return 4;
+
+ state = aa_dfa_match(dfa, state, data);
+ if (!state)
+ return 5;
+ *perms = compute_mnt_perms(dfa, state);
+ if (perms->allow & AA_MAY_MOUNT)
+ return 0;
+ }
+
+ /* failed at end of flags match */
+ return 4;
+}
+
+
+static int path_flags(struct aa_profile *profile, const struct path *path)
+{
+ AA_BUG(!profile);
+ AA_BUG(!path);
+
+ return profile->path_flags |
+ (S_ISDIR(path->dentry->d_inode->i_mode) ? PATH_IS_DIR : 0);
+}
+
+/**
+ * match_mnt_path_str - handle path matching for mount
+ * @profile: the confining profile
+ * @mntpath: for the mntpnt (NOT NULL)
+ * @buffer: buffer to be used to lookup mntpath
+ * @devnme: string for the devname/src_name (MAY BE NULL OR ERRPTR)
+ * @type: string for the dev type (MAYBE NULL)
+ * @flags: mount flags to match
+ * @data: fs mount data (MAYBE NULL)
+ * @binary: whether @data is binary
+ * @devinfo: error str if (IS_ERR(@devname))
+ *
+ * Returns: 0 on success else error
+ */
+static int match_mnt_path_str(struct aa_profile *profile,
+ const struct path *mntpath, char *buffer,
+ const char *devname, const char *type,
+ unsigned long flags, void *data, bool binary,
+ const char *devinfo)
+{
+ struct aa_perms perms = { };
+ const char *mntpnt = NULL, *info = NULL;
+ int pos, error;
+
+ AA_BUG(!profile);
+ AA_BUG(!mntpath);
+ AA_BUG(!buffer);
+
+ error = aa_path_name(mntpath, path_flags(profile, mntpath), buffer,
+ &mntpnt, &info, profile->disconnected);
+ if (error)
+ goto audit;
+ if (IS_ERR(devname)) {
+ error = PTR_ERR(devname);
+ devname = NULL;
+ info = devinfo;
+ goto audit;
+ }
+
+ error = -EACCES;
+ pos = do_match_mnt(profile->policy.dfa,
+ profile->policy.start[AA_CLASS_MOUNT],
+ mntpnt, devname, type, flags, data, binary, &perms);
+ if (pos) {
+ info = mnt_info_table[pos];
+ goto audit;
+ }
+ error = 0;
+
+audit:
+ return audit_mount(profile, OP_MOUNT, mntpnt, devname, type, NULL,
+ flags, data, AA_MAY_MOUNT, &perms, info, error);
+}
+
+/**
+ * match_mnt - handle path matching for mount
+ * @profile: the confining profile
+ * @mntpath: for the mntpnt (NOT NULL)
+ * @buffer: buffer to be used to lookup mntpath
+ * @devpath: path devname/src_name (MAYBE NULL)
+ * @devbuffer: buffer to be used to lookup devname/src_name
+ * @type: string for the dev type (MAYBE NULL)
+ * @flags: mount flags to match
+ * @data: fs mount data (MAYBE NULL)
+ * @binary: whether @data is binary
+ *
+ * Returns: 0 on success else error
+ */
+static int match_mnt(struct aa_profile *profile, const struct path *path,
+ char *buffer, struct path *devpath, char *devbuffer,
+ const char *type, unsigned long flags, void *data,
+ bool binary)
+{
+ const char *devname = NULL, *info = NULL;
+ int error = -EACCES;
+
+ AA_BUG(!profile);
+ AA_BUG(devpath && !devbuffer);
+
+ if (devpath) {
+ error = aa_path_name(devpath, path_flags(profile, devpath),
+ devbuffer, &devname, &info,
+ profile->disconnected);
+ if (error)
+ devname = ERR_PTR(error);
+ }
+
+ return match_mnt_path_str(profile, path, buffer, devname, type, flags,
+ data, binary, info);
+}
+
+int aa_remount(struct aa_label *label, const struct path *path,
+ unsigned long flags, void *data)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL;
+ bool binary;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ binary = path->dentry->d_sb->s_type->fs_flags & FS_BINARY_MOUNTDATA;
+
+ get_buffers(buffer);
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, NULL, NULL, NULL,
+ flags, data, binary));
+ put_buffers(buffer);
+
+ return error;
+}
+
+int aa_bind_mount(struct aa_label *label, const struct path *path,
+ const char *dev_name, unsigned long flags)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL, *old_buffer = NULL;
+ struct path old_path;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ if (!dev_name || !*dev_name)
+ return -EINVAL;
+
+ flags &= MS_REC | MS_BIND;
+
+ error = kern_path(dev_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
+ if (error)
+ return error;
+
+ get_buffers(buffer, old_buffer);
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, &old_path, old_buffer,
+ NULL, flags, NULL, false));
+ put_buffers(buffer, old_buffer);
+ path_put(&old_path);
+
+ return error;
+}
+
+int aa_mount_change_type(struct aa_label *label, const struct path *path,
+ unsigned long flags)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ /* These are the flags allowed by do_change_type() */
+ flags &= (MS_REC | MS_SILENT | MS_SHARED | MS_PRIVATE | MS_SLAVE |
+ MS_UNBINDABLE);
+
+ get_buffers(buffer);
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, NULL, NULL, NULL,
+ flags, NULL, false));
+ put_buffers(buffer);
+
+ return error;
+}
+
+int aa_move_mount(struct aa_label *label, const struct path *path,
+ const char *orig_name)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL, *old_buffer = NULL;
+ struct path old_path;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ if (!orig_name || !*orig_name)
+ return -EINVAL;
+
+ error = kern_path(orig_name, LOOKUP_FOLLOW, &old_path);
+ if (error)
+ return error;
+
+ get_buffers(buffer, old_buffer);
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, &old_path, old_buffer,
+ NULL, MS_MOVE, NULL, false));
+ put_buffers(buffer, old_buffer);
+ path_put(&old_path);
+
+ return error;
+}
+
+int aa_new_mount(struct aa_label *label, const char *dev_name,
+ const struct path *path, const char *type, unsigned long flags,
+ void *data)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL, *dev_buffer = NULL;
+ bool binary = true;
+ int error;
+ int requires_dev = 0;
+ struct path tmp_path, *dev_path = NULL;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ if (type) {
+ struct file_system_type *fstype;
+
+ fstype = get_fs_type(type);
+ if (!fstype)
+ return -ENODEV;
+ binary = fstype->fs_flags & FS_BINARY_MOUNTDATA;
+ requires_dev = fstype->fs_flags & FS_REQUIRES_DEV;
+ put_filesystem(fstype);
+
+ if (requires_dev) {
+ if (!dev_name || !*dev_name)
+ return -ENOENT;
+
+ error = kern_path(dev_name, LOOKUP_FOLLOW, &tmp_path);
+ if (error)
+ return error;
+ dev_path = &tmp_path;
+ }
+ }
+
+ get_buffers(buffer, dev_buffer);
+ if (dev_path) {
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, dev_path, dev_buffer,
+ type, flags, data, binary));
+ } else {
+ error = fn_for_each_confined(label, profile,
+ match_mnt_path_str(profile, path, buffer, dev_name,
+ type, flags, data, binary, NULL));
+ }
+ put_buffers(buffer, dev_buffer);
+ if (dev_path)
+ path_put(dev_path);
+
+ return error;
+}
+
+static int profile_umount(struct aa_profile *profile, struct path *path,
+ char *buffer)
+{
+ struct aa_perms perms = { };
+ const char *name = NULL, *info = NULL;
+ unsigned int state;
+ int error;
+
+ AA_BUG(!profile);
+ AA_BUG(!path);
+
+ error = aa_path_name(path, path_flags(profile, path), buffer, &name,
+ &info, profile->disconnected);
+ if (error)
+ goto audit;
+
+ state = aa_dfa_match(profile->policy.dfa,
+ profile->policy.start[AA_CLASS_MOUNT],
+ name);
+ perms = compute_mnt_perms(profile->policy.dfa, state);
+ if (AA_MAY_UMOUNT & ~perms.allow)
+ error = -EACCES;
+
+audit:
+ return audit_mount(profile, OP_UMOUNT, name, NULL, NULL, NULL, 0, NULL,
+ AA_MAY_UMOUNT, &perms, info, error);
+}
+
+int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL;
+ int error;
+ struct path path = { .mnt = mnt, .dentry = mnt->mnt_root };
+
+ AA_BUG(!label);
+ AA_BUG(!mnt);
+
+ get_buffers(buffer);
+ error = fn_for_each_confined(label, profile,
+ profile_umount(profile, &path, buffer));
+ put_buffers(buffer);
+
+ return error;
+}
+
+/* helper fn for transition on pivotroot
+ *
+ * Returns: label for transition or ERR_PTR. Does not return NULL
+ */
+static struct aa_label *build_pivotroot(struct aa_profile *profile,
+ const struct path *new_path,
+ char *new_buffer,
+ const struct path *old_path,
+ char *old_buffer)
+{
+ const char *old_name, *new_name = NULL, *info = NULL;
+ const char *trans_name = NULL;
+ struct aa_perms perms = { };
+ unsigned int state;
+ int error;
+
+ AA_BUG(!profile);
+ AA_BUG(!new_path);
+ AA_BUG(!old_path);
+
+ if (profile_unconfined(profile))
+ return aa_get_newest_label(&profile->label);
+
+ error = aa_path_name(old_path, path_flags(profile, old_path),
+ old_buffer, &old_name, &info,
+ profile->disconnected);
+ if (error)
+ goto audit;
+ error = aa_path_name(new_path, path_flags(profile, new_path),
+ new_buffer, &new_name, &info,
+ profile->disconnected);
+ if (error)
+ goto audit;
+
+ error = -EACCES;
+ state = aa_dfa_match(profile->policy.dfa,
+ profile->policy.start[AA_CLASS_MOUNT],
+ new_name);
+ state = aa_dfa_null_transition(profile->policy.dfa, state);
+ state = aa_dfa_match(profile->policy.dfa, state, old_name);
+ perms = compute_mnt_perms(profile->policy.dfa, state);
+
+ if (AA_MAY_PIVOTROOT & perms.allow)
+ error = 0;
+
+audit:
+ error = audit_mount(profile, OP_PIVOTROOT, new_name, old_name,
+ NULL, trans_name, 0, NULL, AA_MAY_PIVOTROOT,
+ &perms, info, error);
+ if (error)
+ return ERR_PTR(error);
+
+ return aa_get_newest_label(&profile->label);
+}
+
+int aa_pivotroot(struct aa_label *label, const struct path *old_path,
+ const struct path *new_path)
+{
+ struct aa_profile *profile;
+ struct aa_label *target = NULL;
+ char *old_buffer = NULL, *new_buffer = NULL, *info = NULL;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!old_path);
+ AA_BUG(!new_path);
+
+ get_buffers(old_buffer, new_buffer);
+ target = fn_label_build(label, profile, GFP_ATOMIC,
+ build_pivotroot(profile, new_path, new_buffer,
+ old_path, old_buffer));
+ if (!target) {
+ info = "label build failed";
+ error = -ENOMEM;
+ goto fail;
+ } else if (!IS_ERR(target)) {
+ error = aa_replace_current_label(target);
+ if (error) {
+ /* TODO: audit target */
+ aa_put_label(target);
+ goto out;
+ }
+ } else
+ /* already audited error */
+ error = PTR_ERR(target);
+out:
+ put_buffers(old_buffer, new_buffer);
+
+ return error;
+
+fail:
+ /* TODO: add back in auditing of new_name and old_name */
+ error = fn_for_each(label, profile,
+ audit_mount(profile, OP_PIVOTROOT, NULL /*new_name */,
+ NULL /* old_name */,
+ NULL, NULL,
+ 0, NULL, AA_MAY_PIVOTROOT, &nullperms, info,
+ error));
+ goto out;
+}
diff --git a/security/apparmor/net.c b/security/apparmor/net.c
new file mode 100644
index 0000000..33d5443
--- /dev/null
+++ b/security/apparmor/net.c
@@ -0,0 +1,184 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor network mediation
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/context.h"
+#include "include/label.h"
+#include "include/net.h"
+#include "include/policy.h"
+
+#include "net_names.h"
+
+
+struct aa_sfs_entry aa_sfs_entry_network[] = {
+ AA_SFS_FILE_STRING("af_mask", AA_SFS_AF_MASK),
+ { }
+};
+
+static const char * const net_mask_names[] = {
+ "unknown",
+ "send",
+ "receive",
+ "unknown",
+
+ "create",
+ "shutdown",
+ "connect",
+ "unknown",
+
+ "setattr",
+ "getattr",
+ "setcred",
+ "getcred",
+
+ "chmod",
+ "chown",
+ "chgrp",
+ "lock",
+
+ "mmap",
+ "mprot",
+ "unknown",
+ "unknown",
+
+ "accept",
+ "bind",
+ "listen",
+ "unknown",
+
+ "setopt",
+ "getopt",
+ "unknown",
+ "unknown",
+
+ "unknown",
+ "unknown",
+ "unknown",
+ "unknown",
+};
+
+
+/* audit callback for net specific fields */
+void audit_net_cb(struct audit_buffer *ab, void *va)
+{
+ struct common_audit_data *sa = va;
+
+ audit_log_format(ab, " family=");
+ if (address_family_names[sa->u.net->family])
+ audit_log_string(ab, address_family_names[sa->u.net->family]);
+ else
+ audit_log_format(ab, "\"unknown(%d)\"", sa->u.net->family);
+ audit_log_format(ab, " sock_type=");
+ if (sock_type_names[aad(sa)->net.type])
+ audit_log_string(ab, sock_type_names[aad(sa)->net.type]);
+ else
+ audit_log_format(ab, "\"unknown(%d)\"", aad(sa)->net.type);
+ audit_log_format(ab, " protocol=%d", aad(sa)->net.protocol);
+
+ if (aad(sa)->request & NET_PERMS_MASK) {
+ audit_log_format(ab, " requested_mask=");
+ aa_audit_perm_mask(ab, aad(sa)->request, NULL, 0,
+ net_mask_names, NET_PERMS_MASK);
+
+ if (aad(sa)->denied & NET_PERMS_MASK) {
+ audit_log_format(ab, " denied_mask=");
+ aa_audit_perm_mask(ab, aad(sa)->denied, NULL, 0,
+ net_mask_names, NET_PERMS_MASK);
+ }
+ }
+ if (aad(sa)->peer) {
+ audit_log_format(ab, " peer=");
+ aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer,
+ FLAGS_NONE, GFP_ATOMIC);
+ }
+}
+
+
+/* Generic af perm */
+int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa,
+ u32 request, u16 family, int type)
+{
+ struct aa_perms perms = { };
+
+ AA_BUG(family >= AF_MAX);
+ AA_BUG(type < 0 || type >= SOCK_MAX);
+
+ if (profile_unconfined(profile))
+ return 0;
+
+ perms.allow = (profile->net.allow[family] & (1 << type)) ?
+ ALL_PERMS_MASK : 0;
+ perms.audit = (profile->net.audit[family] & (1 << type)) ?
+ ALL_PERMS_MASK : 0;
+ perms.quiet = (profile->net.quiet[family] & (1 << type)) ?
+ ALL_PERMS_MASK : 0;
+ aa_apply_modes_to_perms(profile, &perms);
+
+ return aa_check_perms(profile, &perms, request, sa, audit_net_cb);
+}
+
+int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family,
+ int type, int protocol)
+{
+ struct aa_profile *profile;
+ DEFINE_AUDIT_NET(sa, op, NULL, family, type, protocol);
+
+ return fn_for_each_confined(label, profile,
+ aa_profile_af_perm(profile, &sa, request, family,
+ type));
+}
+
+static int aa_label_sk_perm(struct aa_label *label, const char *op, u32 request,
+ struct sock *sk)
+{
+ struct aa_profile *profile;
+ DEFINE_AUDIT_SK(sa, op, sk);
+
+ AA_BUG(!label);
+ AA_BUG(!sk);
+
+ if (unconfined(label))
+ return 0;
+
+ return fn_for_each_confined(label, profile,
+ aa_profile_af_sk_perm(profile, &sa, request, sk));
+}
+
+int aa_sk_perm(const char *op, u32 request, struct sock *sk)
+{
+ struct aa_label *label;
+ int error;
+
+ AA_BUG(!sk);
+ AA_BUG(in_interrupt());
+
+ /* TODO: switch to begin_current_label ???? */
+ label = begin_current_label_crit_section();
+ error = aa_label_sk_perm(label, op, request, sk);
+ end_current_label_crit_section(label);
+
+ return error;
+}
+
+
+int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request,
+ struct socket *sock)
+{
+ AA_BUG(!label);
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+
+ return aa_label_sk_perm(label, op, request, sock->sk);
+}
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 244ea4a..4243b0c 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -289,85 +289,6 @@
return NULL;
}
-/**
- * aa_new_null_profile - create or find a null-X learning profile
- * @parent: profile that caused this profile to be created (NOT NULL)
- * @hat: true if the null- learning profile is a hat
- * @base: name to base the null profile off of
- * @gfp: type of allocation
- *
- * Find/Create a null- complain mode profile used in learning mode. The
- * name of the profile is unique and follows the format of parent//null-XXX.
- * where XXX is based on the @name or if that fails or is not supplied
- * a unique number
- *
- * null profiles are added to the profile list but the list does not
- * hold a count on them so that they are automatically released when
- * not in use.
- *
- * Returns: new refcounted profile else NULL on failure
- */
-struct aa_profile *aa_new_null_profile(struct aa_profile *parent, bool hat,
- const char *base, gfp_t gfp)
-{
- struct aa_profile *profile;
- char *name;
-
- AA_BUG(!parent);
-
- if (base) {
- name = kmalloc(strlen(parent->base.hname) + 8 + strlen(base),
- gfp);
- if (name) {
- sprintf(name, "%s//null-%s", parent->base.hname, base);
- goto name;
- }
- /* fall through to try shorter uniq */
- }
-
- name = kmalloc(strlen(parent->base.hname) + 2 + 7 + 8, gfp);
- if (!name)
- return NULL;
- sprintf(name, "%s//null-%x", parent->base.hname,
- atomic_inc_return(&parent->ns->uniq_null));
-
-name:
- /* lookup to see if this is a dup creation */
- profile = aa_find_child(parent, basename(name));
- if (profile)
- goto out;
-
- profile = aa_alloc_profile(name, NULL, gfp);
- if (!profile)
- goto fail;
-
- profile->mode = APPARMOR_COMPLAIN;
- profile->label.flags |= FLAG_NULL;
- if (hat)
- profile->label.flags |= FLAG_HAT;
- profile->path_flags = parent->path_flags;
-
- /* released on free_profile */
- rcu_assign_pointer(profile->parent, aa_get_profile(parent));
- profile->ns = aa_get_ns(parent->ns);
- profile->file.dfa = aa_get_dfa(nulldfa);
- profile->policy.dfa = aa_get_dfa(nulldfa);
-
- mutex_lock(&profile->ns->lock);
- __add_profile(&parent->base.profiles, profile);
- mutex_unlock(&profile->ns->lock);
-
- /* refcount released by caller */
-out:
- kfree(name);
-
- return profile;
-
-fail:
- aa_free_profile(profile);
- return NULL;
-}
-
/* TODO: profile accounting - setup in remove */
/**
@@ -559,6 +480,93 @@
}
/**
+ * aa_new_null_profile - create or find a null-X learning profile
+ * @parent: profile that caused this profile to be created (NOT NULL)
+ * @hat: true if the null- learning profile is a hat
+ * @base: name to base the null profile off of
+ * @gfp: type of allocation
+ *
+ * Find/Create a null- complain mode profile used in learning mode. The
+ * name of the profile is unique and follows the format of parent//null-XXX.
+ * where XXX is based on the @name or if that fails or is not supplied
+ * a unique number
+ *
+ * null profiles are added to the profile list but the list does not
+ * hold a count on them so that they are automatically released when
+ * not in use.
+ *
+ * Returns: new refcounted profile else NULL on failure
+ */
+struct aa_profile *aa_new_null_profile(struct aa_profile *parent, bool hat,
+ const char *base, gfp_t gfp)
+{
+ struct aa_profile *p, *profile;
+ const char *bname;
+ char *name;
+
+ AA_BUG(!parent);
+
+ if (base) {
+ name = kmalloc(strlen(parent->base.hname) + 8 + strlen(base),
+ gfp);
+ if (name) {
+ sprintf(name, "%s//null-%s", parent->base.hname, base);
+ goto name;
+ }
+ /* fall through to try shorter uniq */
+ }
+
+ name = kmalloc(strlen(parent->base.hname) + 2 + 7 + 8, gfp);
+ if (!name)
+ return NULL;
+ sprintf(name, "%s//null-%x", parent->base.hname,
+ atomic_inc_return(&parent->ns->uniq_null));
+
+name:
+ /* lookup to see if this is a dup creation */
+ bname = basename(name);
+ profile = aa_find_child(parent, bname);
+ if (profile)
+ goto out;
+
+ profile = aa_alloc_profile(name, NULL, gfp);
+ if (!profile)
+ goto fail;
+
+ profile->mode = APPARMOR_COMPLAIN;
+ profile->label.flags |= FLAG_NULL;
+ if (hat)
+ profile->label.flags |= FLAG_HAT;
+ profile->path_flags = parent->path_flags;
+
+ /* released on free_profile */
+ rcu_assign_pointer(profile->parent, aa_get_profile(parent));
+ profile->ns = aa_get_ns(parent->ns);
+ profile->file.dfa = aa_get_dfa(nulldfa);
+ profile->policy.dfa = aa_get_dfa(nulldfa);
+
+ mutex_lock(&profile->ns->lock);
+ p = __find_child(&parent->base.profiles, bname);
+ if (p) {
+ aa_free_profile(profile);
+ profile = aa_get_profile(p);
+ } else {
+ __add_profile(&parent->base.profiles, profile);
+ }
+ mutex_unlock(&profile->ns->lock);
+
+ /* refcount released by caller */
+out:
+ kfree(name);
+
+ return profile;
+
+fail:
+ aa_free_profile(profile);
+ return NULL;
+}
+
+/**
* replacement_allowed - test to see if replacement is allowed
* @profile: profile to test if it can be replaced (MAYBE NULL)
* @noreplace: true if replacement shouldn't be allowed but addition is okay
diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c
index 351d3ba..62a3589 100644
--- a/security/apparmor/policy_ns.c
+++ b/security/apparmor/policy_ns.c
@@ -112,6 +112,8 @@
ns->unconfined->label.flags |= FLAG_IX_ON_NAME_ERROR |
FLAG_IMMUTIBLE | FLAG_NS_COUNT | FLAG_UNCONFINED;
ns->unconfined->mode = APPARMOR_UNCONFINED;
+ ns->unconfined->file.dfa = aa_get_dfa(nulldfa);
+ ns->unconfined->policy.dfa = aa_get_dfa(nulldfa);
/* ns and ns->unconfined share ns->unconfined refcount */
ns->unconfined->ns = ns;
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index c600f4d..5a2aec3 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -85,9 +85,9 @@
audit_log_format(ab, " ns=");
audit_log_untrustedstring(ab, aad(sa)->iface.ns);
}
- if (aad(sa)->iface.name) {
+ if (aad(sa)->name) {
audit_log_format(ab, " name=");
- audit_log_untrustedstring(ab, aad(sa)->iface.name);
+ audit_log_untrustedstring(ab, aad(sa)->name);
}
if (aad(sa)->iface.pos)
audit_log_format(ab, " offset=%ld", aad(sa)->iface.pos);
@@ -114,9 +114,9 @@
aad(&sa)->iface.pos = e->pos - e->start;
aad(&sa)->iface.ns = ns_name;
if (new)
- aad(&sa)->iface.name = new->base.hname;
+ aad(&sa)->name = new->base.hname;
else
- aad(&sa)->iface.name = name;
+ aad(&sa)->name = name;
aad(&sa)->info = info;
aad(&sa)->error = error;
@@ -275,6 +275,19 @@
return 0;
}
+static bool unpack_u16(struct aa_ext *e, u16 *data, const char *name)
+{
+ if (unpack_nameX(e, AA_U16, name)) {
+ if (!inbounds(e, sizeof(u16)))
+ return 0;
+ if (data)
+ *data = le16_to_cpu(get_unaligned((__le16 *) e->pos));
+ e->pos += sizeof(u16);
+ return 1;
+ }
+ return 0;
+}
+
static bool unpack_u32(struct aa_ext *e, u32 *data, const char *name)
{
if (unpack_nameX(e, AA_U32, name)) {
@@ -448,7 +461,7 @@
*/
static bool unpack_trans_table(struct aa_ext *e, struct aa_profile *profile)
{
- void *pos = e->pos;
+ void *saved_pos = e->pos;
/* exec table is optional */
if (unpack_nameX(e, AA_STRUCT, "xtable")) {
@@ -511,7 +524,7 @@
fail:
aa_free_domain_entries(&profile->file.trans);
- e->pos = pos;
+ e->pos = saved_pos;
return 0;
}
@@ -583,7 +596,8 @@
{
struct aa_profile *profile = NULL;
const char *tmpname, *tmpns = NULL, *name = NULL;
- size_t ns_len;
+ const char *info = "failed to unpack profile";
+ size_t size = 0, ns_len;
struct rhashtable_params params = { 0 };
char *key = NULL;
struct aa_data *data;
@@ -604,8 +618,10 @@
tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len);
if (tmpns) {
*ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL);
- if (!*ns_name)
+ if (!*ns_name) {
+ info = "out of memory";
goto fail;
+ }
name = tmpname;
}
@@ -624,12 +640,15 @@
if (IS_ERR(profile->xmatch)) {
error = PTR_ERR(profile->xmatch);
profile->xmatch = NULL;
+ info = "bad xmatch";
goto fail;
}
/* xmatch_len is not optional if xmatch is set */
if (profile->xmatch) {
- if (!unpack_u32(e, &tmp, NULL))
+ if (!unpack_u32(e, &tmp, NULL)) {
+ info = "missing xmatch len";
goto fail;
+ }
profile->xmatch_len = tmp;
}
@@ -637,8 +656,11 @@
(void) unpack_str(e, &profile->disconnected, "disconnected");
/* per profile debug flags (complain, audit) */
- if (!unpack_nameX(e, AA_STRUCT, "flags"))
+ if (!unpack_nameX(e, AA_STRUCT, "flags")) {
+ info = "profile missing flags";
goto fail;
+ }
+ info = "failed to unpack profile flags";
if (!unpack_u32(e, &tmp, NULL))
goto fail;
if (tmp & PACKED_FLAG_HAT)
@@ -667,6 +689,7 @@
/* set a default value if path_flags field is not present */
profile->path_flags = PATH_MEDIATE_DELETED;
+ info = "failed to unpack profile capabilities";
if (!unpack_u32(e, &(profile->caps.allow.cap[0]), NULL))
goto fail;
if (!unpack_u32(e, &(profile->caps.audit.cap[0]), NULL))
@@ -676,6 +699,7 @@
if (!unpack_u32(e, &tmpcap.cap[0], NULL))
goto fail;
+ info = "failed to unpack upper profile capabilities";
if (unpack_nameX(e, AA_STRUCT, "caps64")) {
/* optional upper half of 64 bit caps */
if (!unpack_u32(e, &(profile->caps.allow.cap[1]), NULL))
@@ -690,6 +714,7 @@
goto fail;
}
+ info = "failed to unpack extended profile capabilities";
if (unpack_nameX(e, AA_STRUCT, "capsx")) {
/* optional extended caps mediation mask */
if (!unpack_u32(e, &(profile->caps.extended.cap[0]), NULL))
@@ -700,11 +725,46 @@
goto fail;
}
- if (!unpack_rlimits(e, profile))
+ if (!unpack_rlimits(e, profile)) {
+ info = "failed to unpack profile rlimits";
goto fail;
+ }
+
+ size = unpack_array(e, "net_allowed_af");
+ if (size) {
+
+ for (i = 0; i < size; i++) {
+ /* discard extraneous rules that this kernel will
+ * never request
+ */
+ if (i >= AF_MAX) {
+ u16 tmp;
+
+ if (!unpack_u16(e, &tmp, NULL) ||
+ !unpack_u16(e, &tmp, NULL) ||
+ !unpack_u16(e, &tmp, NULL))
+ goto fail;
+ continue;
+ }
+ if (!unpack_u16(e, &profile->net.allow[i], NULL))
+ goto fail;
+ if (!unpack_u16(e, &profile->net.audit[i], NULL))
+ goto fail;
+ if (!unpack_u16(e, &profile->net.quiet[i], NULL))
+ goto fail;
+ }
+ if (!unpack_nameX(e, AA_ARRAYEND, NULL))
+ goto fail;
+ }
+ if (VERSION_LT(e->version, v7)) {
+ /* pre v7 policy always allowed these */
+ profile->net.allow[AF_UNIX] = 0xffff;
+ profile->net.allow[AF_NETLINK] = 0xffff;
+ }
if (unpack_nameX(e, AA_STRUCT, "policydb")) {
/* generic policy dfa - optional and may be NULL */
+ info = "failed to unpack policydb";
profile->policy.dfa = unpack_dfa(e);
if (IS_ERR(profile->policy.dfa)) {
error = PTR_ERR(profile->policy.dfa);
@@ -734,6 +794,7 @@
if (IS_ERR(profile->file.dfa)) {
error = PTR_ERR(profile->file.dfa);
profile->file.dfa = NULL;
+ info = "failed to unpack profile file rules";
goto fail;
} else if (profile->file.dfa) {
if (!unpack_u32(e, &profile->file.start, "dfa_start"))
@@ -746,10 +807,13 @@
} else
profile->file.dfa = aa_get_dfa(nulldfa);
- if (!unpack_trans_table(e, profile))
+ if (!unpack_trans_table(e, profile)) {
+ info = "failed to unpack profile transition table";
goto fail;
+ }
if (unpack_nameX(e, AA_STRUCT, "data")) {
+ info = "out of memory";
profile->data = kzalloc(sizeof(*profile->data), GFP_KERNEL);
if (!profile->data)
goto fail;
@@ -761,8 +825,10 @@
params.hashfn = strhash;
params.obj_cmpfn = datacmp;
- if (rhashtable_init(profile->data, ¶ms))
+ if (rhashtable_init(profile->data, ¶ms)) {
+ info = "failed to init key, value hash table";
goto fail;
+ }
while (unpack_strdup(e, &key, NULL)) {
data = kzalloc(sizeof(*data), GFP_KERNEL);
@@ -784,12 +850,16 @@
profile->data->p);
}
- if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+ if (!unpack_nameX(e, AA_STRUCTEND, NULL)) {
+ info = "failed to unpack end of key, value data table";
goto fail;
+ }
}
- if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+ if (!unpack_nameX(e, AA_STRUCTEND, NULL)) {
+ info = "failed to unpack end of profile";
goto fail;
+ }
return profile;
@@ -798,8 +868,7 @@
name = NULL;
else if (!name)
name = "unknown";
- audit_iface(profile, NULL, name, "failed to unpack profile", e,
- error);
+ audit_iface(profile, NULL, name, info, e, error);
aa_free_profile(profile);
return ERR_PTR(error);
@@ -832,7 +901,7 @@
* if not specified use previous version
* Mask off everything that is not kernel abi version
*/
- if (VERSION_LT(e->version, v5) && VERSION_GT(e->version, v7)) {
+ if (VERSION_LT(e->version, v5) || VERSION_GT(e->version, v7)) {
audit_iface(NULL, NULL, NULL, "unsupported interface version",
e, error);
return error;
diff --git a/security/commoncap.c b/security/commoncap.c
index 6bf72b1..c25e0d2 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -294,10 +294,10 @@
*
* Determine if an inode having a change applied that's marked ATTR_KILL_PRIV
* affects the security markings on that inode, and if it is, should
- * inode_killpriv() be invoked or the change rejected?
+ * inode_killpriv() be invoked or the change rejected.
*
- * Returns 0 if granted; +ve if granted, but inode_killpriv() is required; and
- * -ve to deny the change.
+ * Returns 1 if security.capability has a value, meaning inode_killpriv()
+ * is required, 0 otherwise, meaning inode_killpriv() is not required.
*/
int cap_inode_need_killpriv(struct dentry *dentry)
{
diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt
index 6a1af43..3995735 100644
--- a/tools/objtool/Documentation/stack-validation.txt
+++ b/tools/objtool/Documentation/stack-validation.txt
@@ -194,10 +194,10 @@
If it's a GCC-compiled .c file, the error may be because the function
uses an inline asm() statement which has a "call" instruction. An
asm() statement with a call instruction must declare the use of the
- stack pointer in its output operand. For example, on x86_64:
+ stack pointer in its output operand. On x86_64, this means adding
+ the ASM_CALL_CONSTRAINT as an output constraint:
- register void *__sp asm("rsp");
- asm volatile("call func" : "+r" (__sp));
+ asm volatile("call func" : ASM_CALL_CONSTRAINT);
Otherwise the stack frame may not get created before the call.
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 0e8c8ec..0f22768 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -208,14 +208,14 @@
break;
case 0x89:
- if (rex == 0x48 && modrm == 0xe5) {
+ if (rex_w && !rex_r && modrm_mod == 3 && modrm_reg == 4) {
- /* mov %rsp, %rbp */
+ /* mov %rsp, reg */
*type = INSN_STACK;
op->src.type = OP_SRC_REG;
op->src.reg = CFI_SP;
op->dest.type = OP_DEST_REG;
- op->dest.reg = CFI_BP;
+ op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b];
break;
}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f744617..a0c518e 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1203,24 +1203,39 @@
switch (op->src.type) {
case OP_SRC_REG:
- if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP) {
+ if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP &&
+ cfa->base == CFI_SP &&
+ regs[CFI_BP].base == CFI_CFA &&
+ regs[CFI_BP].offset == -cfa->offset) {
- if (cfa->base == CFI_SP &&
- regs[CFI_BP].base == CFI_CFA &&
- regs[CFI_BP].offset == -cfa->offset) {
+ /* mov %rsp, %rbp */
+ cfa->base = op->dest.reg;
+ state->bp_scratch = false;
+ }
- /* mov %rsp, %rbp */
- cfa->base = op->dest.reg;
- state->bp_scratch = false;
- }
+ else if (op->src.reg == CFI_SP &&
+ op->dest.reg == CFI_BP && state->drap) {
- else if (state->drap) {
+ /* drap: mov %rsp, %rbp */
+ regs[CFI_BP].base = CFI_BP;
+ regs[CFI_BP].offset = -state->stack_size;
+ state->bp_scratch = false;
+ }
- /* drap: mov %rsp, %rbp */
- regs[CFI_BP].base = CFI_BP;
- regs[CFI_BP].offset = -state->stack_size;
- state->bp_scratch = false;
- }
+ else if (op->src.reg == CFI_SP && cfa->base == CFI_SP) {
+
+ /*
+ * mov %rsp, %reg
+ *
+ * This is needed for the rare case where GCC
+ * does:
+ *
+ * mov %rsp, %rax
+ * ...
+ * mov %rax, %rsp
+ */
+ state->vals[op->dest.reg].base = CFI_CFA;
+ state->vals[op->dest.reg].offset = -state->stack_size;
}
else if (op->dest.reg == cfa->base) {