diff --git a/Documentation/ABI/testing/sysfs-kernel-oops_count b/Documentation/ABI/testing/sysfs-kernel-oops_count new file mode 100644 index 000000000000..156cca9dbc96 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-oops_count @@ -0,0 +1,6 @@ +What: /sys/kernel/oops_count +Date: November 2022 +KernelVersion: 6.2.0 +Contact: Linux Kernel Hardening List linux-hardening@vger.kernel.org +Description: + Shows how many times the system has Oopsed since last boot. diff --git a/Documentation/ABI/testing/sysfs-kernel-warn_count b/Documentation/ABI/testing/sysfs-kernel-warn_count new file mode 100644 index 000000000000..90a029813717 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-warn_count @@ -0,0 +1,6 @@ +What: /sys/kernel/warn_count +Date: November 2022 +KernelVersion: 6.2.0 +Contact: Linux Kernel Hardening List linux-hardening@vger.kernel.org +Description: + Shows how many times the system has Warned since last boot. diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index db1676525ca3..c8d3dbda3c1e 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -51,6 +51,7 @@ show up in /proc/sys/kernel: - msgmnb - msgmni - nmi_watchdog +- oops_limit - osrelease - ostype - overflowgid @@ -96,6 +97,7 @@ show up in /proc/sys/kernel: - threads-max - unprivileged_bpf_disabled - unknown_nmi_panic +- warn_limit - watchdog - watchdog_thresh - version @@ -555,6 +557,15 @@ scanned for a given scan.

==============================================================

+oops_limit: + +Number of kernel oopses after which the kernel should panic when +``panic_on_oops`` is not set. Setting this to 0 disables checking +the count. Setting this to 1 has the same effect as setting +``panic_on_oops=1``. The default value is 10000. + +============================================================== + osrelease, ostype & version:

# cat osrelease @@ -1104,6 +1115,15 @@ example. If a system hangs up, try pressing the NMI switch.

==============================================================

+warn_limit: + +Number of kernel warnings after which the kernel should panic when +``panic_on_warn`` is not set. Setting this to 0 disables checking +the warning count. Setting this to 1 has the same effect as setting +``panic_on_warn=1``. The default value is 0. + +============================================================== + watchdog:

This parameter can be used to disable or enable the soft lockup detector diff --git a/Makefile b/Makefile index 560507d1f7a1..e3822e492543 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 19 -SUBLEVEL = 271 +SUBLEVEL = 272 EXTRAVERSION = NAME = "People's Front"

diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index bc9627698796..22f5c27b96b7 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -192,7 +192,7 @@ die_if_kernel(char * str, struct pt_regs *regs, long err, unsigned long *r9_15) local_irq_enable(); while (1); } - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

#ifndef CONFIG_MATHEMU @@ -577,7 +577,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,

printk("Bad unaligned kernel access at %016lx: %p %lx %lu\n", pc, va, opcode, reg); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV);

got_exception: /* Ok, we caught the exception, but we don't want it. Is there @@ -632,7 +632,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg, local_irq_enable(); while (1); } - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

/* diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 188fc9256baf..6ce67b05412e 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -206,7 +206,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr, printk(KERN_ALERT "Unable to handle kernel paging request at " "virtual address %016lx\n", address); die_if_kernel("Oops", regs, cause, (unsigned long*)regs - 16); - do_exit(SIGKILL); + make_task_dead(SIGKILL);

/* We ran out of memory, or some other thing happened to us that made us unable to handle the page fault gracefully. */ diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts index f346673d34ea..0cb5f01f02d1 100644 --- a/arch/arm/boot/dts/imx53-ppd.dts +++ b/arch/arm/boot/dts/imx53-ppd.dts @@ -462,7 +462,7 @@ scl-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; status = "okay";

- i2c-switch@70 { + i2c-mux@70 { compatible = "nxp,pca9547"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi index b5986efe1090..143d249b821e 100644 --- a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi @@ -463,7 +463,6 @@ &uart1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart1>; - uart-has-rtscts; rts-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>; status = "okay"; }; diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index d49fafd2b865..02a4aea52fb0 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -344,7 +344,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, int signr) if (panic_on_oops) panic("Fatal exception"); if (signr) - do_exit(signr); + make_task_dead(signr); }

/* diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a9ee0d9dc740..8457384139cb 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -149,7 +149,7 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, show_pte(mm, addr); die("Oops", regs, fsr); bust_spinlocks(0); - do_exit(SIGKILL); + make_task_dead(SIGKILL); }

/* diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index e803fd16248b..46d2142ebd14 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -160,7 +160,7 @@ void __init paging_init(const struct machine_desc *mdesc) mpu_setup();

/* allocate the zero page. */ - zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!zero_page) panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, PAGE_SIZE, PAGE_SIZE); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 965595fe6804..20f896b27a44 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -224,7 +224,7 @@ void die(const char *str, struct pt_regs *regs, int err) raw_spin_unlock_irqrestore(&die_lock, flags);

if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

static bool show_unhandled_signals_ratelimited(void) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index b046006a387f..0d2be8eb87ec 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -268,7 +268,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, show_pte(addr); die("Oops", regs, esr); bust_spinlocks(0); - do_exit(SIGKILL); + make_task_dead(SIGKILL); }

static void __do_kernel_fault(unsigned long addr, unsigned int esr, diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c index e47a9e0dc278..090adaee4b84 100644 --- a/arch/h8300/kernel/traps.c +++ b/arch/h8300/kernel/traps.c @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/task.h> #include <linux/mm_types.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -110,7 +111,7 @@ void die(const char *str, struct pt_regs *fp, unsigned long err) dump(fp);

spin_unlock_irq(&die_lock); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

static int kstack_depth_to_print = 24; diff --git a/arch/h8300/mm/fault.c b/arch/h8300/mm/fault.c index fabffb83930a..573825c3cb70 100644 --- a/arch/h8300/mm/fault.c +++ b/arch/h8300/mm/fault.c @@ -52,7 +52,7 @@ asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address, printk(" at virtual address %08lx\n", address); if (!user_mode(regs)) die("Oops", regs, error_code); - do_exit(SIGKILL); + make_task_dead(SIGKILL);

return 1; } diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c index 91ee04842c22..34a74f73f169 100644 --- a/arch/hexagon/kernel/traps.c +++ b/arch/hexagon/kernel/traps.c @@ -234,7 +234,7 @@ int die(const char *str, struct pt_regs *regs, long err) panic("Fatal exception");

oops_exit(); - do_exit(err); + make_task_dead(err); return 0; }

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 8b4a0c1748c0..0d56b19b7511 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -445,7 +445,7 @@ config ARCH_PROC_KCORE_TEXT depends on PROC_KCORE

config IA64_MCA_RECOVERY - tristate "MCA recovery from errors other than TLB." + bool "MCA recovery from errors other than TLB."

config PERFMON bool "Performance monitor support" diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index 06419a95af30..07353029b003 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -11,6 +11,7 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/sched.h> +#include <linux/sched/task.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kallsyms.h> @@ -176,7 +177,7 @@ mca_handler_bh(unsigned long paddr, void *iip, unsigned long ipsr) spin_unlock(&mca_bh_lock);

/* This process is about to be killed itself */ - do_exit(SIGKILL); + make_task_dead(SIGKILL); }

/** diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index c6f4932073a1..32c2877b3c0a 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -85,7 +85,7 @@ die (const char *str, struct pt_regs *regs, long err) if (panic_on_oops) panic("Fatal exception");

- do_exit(SIGSEGV); + make_task_dead(SIGSEGV); return 0; }

diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index a9d55ad8d67b..0b072af7e20d 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -302,7 +302,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re regs = NULL; bust_spinlocks(0); if (regs) - do_exit(SIGKILL); + make_task_dead(SIGKILL); return;

out_of_memory: diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index b2fd000b9285..9b70a7f5e705 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -1139,7 +1139,7 @@ void die_if_kernel (char *str, struct pt_regs *fp, int nr) pr_crit("%s: %08x\n", str, nr); show_registers(fp); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

asmlinkage void set_esp0(unsigned long ssp) diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 9b6163c05a75..fc3aea6dcaa7 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -48,7 +48,7 @@ int send_fault_sig(struct pt_regs *regs) pr_alert("Unable to handle kernel access"); pr_cont(" at virtual address %p\n", addr); die_if_kernel("Oops", regs, 0 /*error_code*/); - do_exit(SIGKILL); + make_task_dead(SIGKILL); }

return 1; diff --git a/arch/microblaze/kernel/exceptions.c b/arch/microblaze/kernel/exceptions.c index eafff21fcb0e..182402db6b04 100644 --- a/arch/microblaze/kernel/exceptions.c +++ b/arch/microblaze/kernel/exceptions.c @@ -44,10 +44,10 @@ void die(const char *str, struct pt_regs *fp, long err) pr_warn("Oops: %s, sig: %ld\n", str, err); show_regs(fp); spin_unlock_irq(&die_lock); - /* do_exit() should take care of panic'ing from an interrupt + /* make_task_dead() should take care of panic'ing from an interrupt * context so we don't handle it here */ - do_exit(err); + make_task_dead(err); }

/* for user application debugging */ diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 0ca4185cc5e3..01c85d37c47a 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -412,7 +412,7 @@ void __noreturn die(const char *str, struct pt_regs *regs) if (regs && kexec_should_crash(current)) crash_kexec(regs);

- do_exit(sig); + make_task_dead(sig); }

extern struct exception_table_entry __start___dbe_table[]; diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c index 1496aab48998..a811f286bc85 100644 --- a/arch/nds32/kernel/traps.c +++ b/arch/nds32/kernel/traps.c @@ -183,7 +183,7 @@ void die(const char *str, struct pt_regs *regs, int err)

bust_spinlocks(0); spin_unlock_irq(&die_lock); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

EXPORT_SYMBOL(die); @@ -286,7 +286,7 @@ void unhandled_interruption(struct pt_regs *regs) pr_emerg("unhandled_interruption\n"); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGKILL); + make_task_dead(SIGKILL); force_sig(SIGKILL, current); }

@@ -297,7 +297,7 @@ void unhandled_exceptions(unsigned long entry, unsigned long addr, addr, type); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGKILL); + make_task_dead(SIGKILL); force_sig(SIGKILL, current); }

@@ -324,7 +324,7 @@ void do_revinsn(struct pt_regs *regs) pr_emerg("Reserved Instruction\n"); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGILL); + make_task_dead(SIGILL); force_sig(SIGILL, current); }

diff --git a/arch/nios2/kernel/traps.c b/arch/nios2/kernel/traps.c index 3bc3cd22b750..dc6c270a355b 100644 --- a/arch/nios2/kernel/traps.c +++ b/arch/nios2/kernel/traps.c @@ -37,10 +37,10 @@ void die(const char *str, struct pt_regs *regs, long err) show_regs(regs); spin_unlock_irq(&die_lock); /* - * do_exit() should take care of panic'ing from an interrupt + * make_task_dead() should take care of panic'ing from an interrupt * context so we don't handle it here */ - do_exit(err); + make_task_dead(err); }

void _exception(int signo, struct pt_regs *regs, int code, unsigned long addr) diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index d8981cbb852a..dfa3db1bccef 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -224,7 +224,7 @@ void die(const char *str, struct pt_regs *regs, long err) __asm__ __volatile__("l.nop 1"); do {} while (1); #endif - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

/* This is normally the 'Oops' routine */ diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index d7a66d852509..5d9cf726e4ec 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -265,7 +265,7 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) panic("Fatal exception");

oops_exit(); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

/* gdb uses break 4,8 */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 2379c4bf3979..63c751ce130a 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -251,7 +251,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, panic("Fatal exception in interrupt"); if (panic_on_oops) panic("Fatal exception"); - do_exit(signr); + make_task_dead(signr); } NOKPROBE_SYMBOL(oops_end);

diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 7c65750508f2..9b736e616131 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -64,7 +64,7 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception"); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

void do_trap(struct pt_regs *regs, int signo, int code, diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 523dbfbac03d..7b5f110f8191 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -200,7 +200,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs) (addr < PAGE_SIZE) ? "NULL pointer dereference" : "paging request", addr); die(regs, "Oops"); - do_exit(SIGKILL); + make_task_dead(SIGKILL);

/* * We ran out of memory, call the OOM killer, and return the userspace diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 5b23c4f6e50c..7b21019096f4 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -187,5 +187,5 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception: panic_on_oops"); oops_exit(); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 8c867b43c8eb..471a965ae75a 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -179,7 +179,7 @@ void s390_handle_mcck(void) "malfunction (code 0x%016lx).\n", mcck.mcck_code); printk(KERN_EMERG "mcck: task: %s, pid: %d.\n", current->comm, current->pid); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } } EXPORT_SYMBOL_GPL(s390_handle_mcck); diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index 8b49cced663d..5fafbef7849b 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -57,7 +57,7 @@ void die(const char *str, struct pt_regs *regs, long err) if (panic_on_oops) panic("Fatal exception");

- do_exit(SIGSEGV); + make_task_dead(SIGSEGV); }

void die_if_kernel(const char *str, struct pt_regs *regs, long err) diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c index bcdfc6168dd5..ec7fcfbad06c 100644 --- a/arch/sparc/kernel/traps_32.c +++ b/arch/sparc/kernel/traps_32.c @@ -86,9 +86,7 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs) } printk("Instruction DUMP:"); instruction_dump ((unsigned long *) regs->pc); - if(regs->psr & PSR_PS) - do_exit(SIGKILL); - do_exit(SIGSEGV); + make_task_dead((regs->psr & PSR_PS) ? SIGKILL : SIGSEGV); }

void do_hw_interrupt(struct pt_regs *regs, unsigned long type) diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 86879c28910b..1a338784a37c 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2565,9 +2565,7 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs) } if (panic_on_oops) panic("Fatal exception"); - if (regs->tstate & TSTATE_PRIV) - do_exit(SIGKILL); - do_exit(SIGSEGV); + make_task_dead((regs->tstate & TSTATE_PRIV)? SIGKILL : SIGSEGV); } EXPORT_SYMBOL(die_if_kernel);

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 78b308f2f2ea..e6c258bf9511 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1500,13 +1500,13 @@ ENTRY(async_page_fault) END(async_page_fault) #endif

-ENTRY(rewind_stack_do_exit) +ENTRY(rewind_stack_and_make_dead) /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp

movl PER_CPU_VAR(cpu_current_top_of_stack), %esi leal -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp

- call do_exit + call make_task_dead 1: jmp 1b -END(rewind_stack_do_exit) +END(rewind_stack_and_make_dead) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 3f418aedef8d..ef693d3689aa 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1759,10 +1759,10 @@ END(nmi) ENTRY(ignore_sysret) UNWIND_HINT_EMPTY mov $-ENOSYS, %eax - sysret + sysretl END(ignore_sysret)

-ENTRY(rewind_stack_do_exit) +ENTRY(rewind_stack_and_make_dead) UNWIND_HINT_FUNC /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp @@ -1771,5 +1771,5 @@ ENTRY(rewind_stack_do_exit) leaq -PTREGS_SIZE(%rax), %rsp UNWIND_HINT_REGS

- call do_exit -END(rewind_stack_do_exit) + call make_task_dead +END(rewind_stack_and_make_dead) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 2b5886401e5f..2b17a5cec099 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -326,7 +326,7 @@ unsigned long oops_begin(void) } NOKPROBE_SYMBOL(oops_begin);

-void __noreturn rewind_stack_do_exit(int signr); +void __noreturn rewind_stack_and_make_dead(int signr);

void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { @@ -361,7 +361,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) * reuse the task stack and that existing poisons are invalid. */ kasan_unpoison_task_stack(current); - rewind_stack_do_exit(signr); + rewind_stack_and_make_dead(signr); } NOKPROBE_SYMBOL(oops_end);

diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index fe522691ac71..8821d0ab0a08 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned int irq) disable_irq_nosync(irq); io_apic_irqs &= ~(1<<irq); irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); + irq_set_status_flags(irq, IRQ_LEVEL); enable_irq(irq); lapic_assign_legacy_vector(irq, true); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index a0693b71cfc1..f2c215e1f64c 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -72,8 +72,10 @@ void __init init_ISA_irqs(void)

legacy_pic->init(0);

- for (i = 0; i < nr_legacy_irqs(); i++) + for (i = 0; i < nr_legacy_irqs(); i++) { irq_set_chip_and_handler(i, chip, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); + } }

void __init init_IRQ(void) diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S index 33147fef3452..f1024b51cfee 100644 --- a/arch/x86/lib/iomap_copy_64.S +++ b/arch/x86/lib/iomap_copy_64.S @@ -22,6 +22,6 @@ */ ENTRY(__iowrite32_copy) movl %edx,%ecx - rep movsd + rep movsl ret ENDPROC(__iowrite32_copy) diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 86507fa7c2d7..2ae5c505894b 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -542,5 +542,5 @@ void die(const char * str, struct pt_regs * regs, long err) if (panic_on_oops) panic("Fatal exception");

- do_exit(err); + make_task_dead(err); } diff --git a/block/blk-core.c b/block/blk-core.c index 80f3e729fdd4..4fbf915d9cb0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2179,10 +2179,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)

if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; - - WARN_ONCE(1, - "generic_make_request: Trying to write " - "to read-only block-device %s (partno %d)\n", + pr_warn("Trying to write to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); /* Older lvm-tools actually trigger this */ return false; diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 8a52a5efee4f..e1cf7c250c33 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -223,7 +223,8 @@ static int dma_chan_get(struct dma_chan *chan) /* The channel is already in use, update client count */ if (chan->client_count) { __module_get(owner); - goto out; + chan->client_count++; + return 0; }

if (!try_module_get(owner)) @@ -236,11 +237,11 @@ static int dma_chan_get(struct dma_chan *chan) goto err_out; }

+ chan->client_count++; + if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask)) balance_ref_count(chan);

-out: - chan->client_count++; return 0;

err_out: diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 709ead443fc5..5794d3120bb8 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1347,10 +1347,12 @@ static struct sdma_desc *sdma_transfer_init(struct sdma_channel *sdmac, sdma_config_ownership(sdmac, false, true, false);

if (sdma_load_context(sdmac)) - goto err_desc_out; + goto err_bd_out;

return desc;

+err_bd_out: + sdma_free_bd(desc); err_desc_out: kfree(desc); err_out: diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 0ba70be4ea85..5f9945651e95 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -164,7 +164,9 @@ #define XILINX_DMA_REG_BTT 0x28

/* AXI DMA Specific Masks/Bit fields */ -#define XILINX_DMA_MAX_TRANS_LEN GENMASK(22, 0) +#define XILINX_DMA_MAX_TRANS_LEN_MIN 8 +#define XILINX_DMA_MAX_TRANS_LEN_MAX 23 +#define XILINX_DMA_V2_MAX_TRANS_LEN_MAX 26 #define XILINX_DMA_CR_COALESCE_MAX GENMASK(23, 16) #define XILINX_DMA_CR_CYCLIC_BD_EN_MASK BIT(4) #define XILINX_DMA_CR_COALESCE_SHIFT 16 @@ -428,6 +430,7 @@ struct xilinx_dma_config { * @rxs_clk: DMA s2mm stream clock * @nr_channels: Number of channels DMA device supports * @chan_id: DMA channel identifier + * @max_buffer_len: Max buffer length */ struct xilinx_dma_device { void __iomem *regs; @@ -447,6 +450,7 @@ struct xilinx_dma_device { struct clk *rxs_clk; u32 nr_channels; u32 chan_id; + u32 max_buffer_len; };

/* Macros */ @@ -969,6 +973,25 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan) return 0; }

+/** + * xilinx_dma_calc_copysize - Calculate the amount of data to copy + * @chan: Driver specific DMA channel + * @size: Total data that needs to be copied + * @done: Amount of data that has been already copied + * + * Return: Amount of data that has to be copied + */ +static int xilinx_dma_calc_copysize(struct xilinx_dma_chan *chan, + int size, int done) +{ + size_t copy; + + copy = min_t(size_t, size - done, + chan->xdev->max_buffer_len); + + return copy; +} + /** * xilinx_dma_tx_status - Get DMA transaction status * @dchan: DMA channel @@ -1002,7 +1025,7 @@ static enum dma_status xilinx_dma_tx_status(struct dma_chan *dchan, list_for_each_entry(segment, &desc->segments, node) { hw = &segment->hw; residue += (hw->control - hw->status) & - XILINX_DMA_MAX_TRANS_LEN; + chan->xdev->max_buffer_len; } } spin_unlock_irqrestore(&chan->lock, flags); @@ -1262,7 +1285,7 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)

/* Start the transfer */ dma_ctrl_write(chan, XILINX_DMA_REG_BTT, - hw->control & XILINX_DMA_MAX_TRANS_LEN); + hw->control & chan->xdev->max_buffer_len); }

list_splice_tail_init(&chan->pending_list, &chan->active_list); @@ -1365,7 +1388,7 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)

/* Start the transfer */ dma_ctrl_write(chan, XILINX_DMA_REG_BTT, - hw->control & XILINX_DMA_MAX_TRANS_LEN); + hw->control & chan->xdev->max_buffer_len); }

list_splice_tail_init(&chan->pending_list, &chan->active_list); @@ -1729,7 +1752,7 @@ xilinx_cdma_prep_memcpy(struct dma_chan *dchan, dma_addr_t dma_dst, struct xilinx_cdma_tx_segment *segment; struct xilinx_cdma_desc_hw *hw;

- if (!len || len > XILINX_DMA_MAX_TRANS_LEN) + if (!len || len > chan->xdev->max_buffer_len) return NULL;

desc = xilinx_dma_alloc_tx_descriptor(chan); @@ -1819,8 +1842,8 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_slave_sg( * Calculate the maximum number of bytes to transfer, * making sure it is less than the hw limit */ - copy = min_t(size_t, sg_dma_len(sg) - sg_used, - XILINX_DMA_MAX_TRANS_LEN); + copy = xilinx_dma_calc_copysize(chan, sg_dma_len(sg), + sg_used); hw = &segment->hw;

/* Fill in the descriptor */ @@ -1924,8 +1947,8 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_dma_cyclic( * Calculate the maximum number of bytes to transfer, * making sure it is less than the hw limit */ - copy = min_t(size_t, period_len - sg_used, - XILINX_DMA_MAX_TRANS_LEN); + copy = xilinx_dma_calc_copysize(chan, period_len, + sg_used); hw = &segment->hw; xilinx_axidma_buf(chan, hw, buf_addr, sg_used, period_len * i); @@ -2613,7 +2636,7 @@ static int xilinx_dma_probe(struct platform_device *pdev) struct xilinx_dma_device *xdev; struct device_node *child, *np = pdev->dev.of_node; struct resource *io; - u32 num_frames, addr_width; + u32 num_frames, addr_width, len_width; int i, err;

/* Allocate and initialize the DMA engine structure */ @@ -2640,13 +2663,30 @@ static int xilinx_dma_probe(struct platform_device *pdev) /* Request and map I/O memory */ io = platform_get_resource(pdev, IORESOURCE_MEM, 0); xdev->regs = devm_ioremap_resource(&pdev->dev, io); - if (IS_ERR(xdev->regs)) - return PTR_ERR(xdev->regs); - + if (IS_ERR(xdev->regs)) { + err = PTR_ERR(xdev->regs); + goto disable_clks; + } /* Retrieve the DMA engine properties from the device tree */ xdev->has_sg = of_property_read_bool(node, "xlnx,include-sg"); - if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) + xdev->max_buffer_len = GENMASK(XILINX_DMA_MAX_TRANS_LEN_MAX - 1, 0); + + if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) { xdev->mcdma = of_property_read_bool(node, "xlnx,mcdma"); + if (!of_property_read_u32(node, "xlnx,sg-length-width", + &len_width)) { + if (len_width < XILINX_DMA_MAX_TRANS_LEN_MIN || + len_width > XILINX_DMA_V2_MAX_TRANS_LEN_MAX) { + dev_warn(xdev->dev, + "invalid xlnx,sg-length-width property value. Using default width\n"); + } else { + if (len_width > XILINX_DMA_MAX_TRANS_LEN_MAX) + dev_warn(xdev->dev, "Please ensure that IP supports buffer length > 23 bits\n"); + xdev->max_buffer_len = + GENMASK(len_width - 1, 0); + } + } + }

if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) { err = of_property_read_u32(node, "xlnx,num-fstores", @@ -2719,8 +2759,10 @@ static int xilinx_dma_probe(struct platform_device *pdev) /* Initialize the channels */ for_each_child_of_node(node, child) { err = xilinx_dma_child_probe(xdev, child); - if (err < 0) - goto disable_clks; + if (err < 0) { + of_node_put(child); + goto error; + } }

if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) { @@ -2753,12 +2795,12 @@ static int xilinx_dma_probe(struct platform_device *pdev)

return 0;

-disable_clks: - xdma_disable_allclks(xdev); error: for (i = 0; i < xdev->nr_channels; i++) if (xdev->chan[i]) xilinx_dma_chan_remove(xdev->chan[i]); +disable_clks: + xdma_disable_allclks(xdev);

return err; } diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 93d6e6319b3c..0ac6c49ecdbf 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -34,6 +34,9 @@ static DEFINE_MUTEX(device_ctls_mutex); static LIST_HEAD(edac_device_list);

+/* Default workqueue processing interval on this instance, in msecs */ +#define DEFAULT_POLL_INTERVAL 1000 + #ifdef CONFIG_EDAC_DEBUG static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev) { @@ -366,7 +369,7 @@ static void edac_device_workq_function(struct work_struct *work_req) * whole one second to save timers firing all over the period * between integral seconds */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_queue_work(&edac_dev->work, edac_dev->delay); @@ -396,7 +399,7 @@ static void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev, * timers firing on sub-second basis, while they are happy * to fire together on the 1 second exactly */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_queue_work(&edac_dev->work, edac_dev->delay); @@ -430,7 +433,7 @@ void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, edac_dev->delay = msecs_to_jiffies(msec);

/* See comment in edac_device_workq_setup() above */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_mod_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_mod_work(&edac_dev->work, edac_dev->delay); @@ -472,11 +475,7 @@ int edac_device_add_device(struct edac_device_ctl_info *edac_dev) /* This instance is NOW RUNNING */ edac_dev->op_state = OP_RUNNING_POLL;

- /* - * enable workq processing on this instance, - * default = 1000 msec - */ - edac_device_workq_setup(edac_dev, 1000); + edac_device_workq_setup(edac_dev, edac_dev->poll_msec ?: DEFAULT_POLL_INTERVAL); } else { edac_dev->op_state = OP_RUNNING_INTERRUPT; } diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c index 6092e61be605..bcf41601a977 100644 --- a/drivers/edac/highbank_mc_edac.c +++ b/drivers/edac/highbank_mc_edac.c @@ -185,8 +185,10 @@ static int highbank_mc_probe(struct platform_device *pdev) drvdata = mci->pvt_info; platform_set_drvdata(pdev, mci);

- if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) - return -ENOMEM; + if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) { + res = -ENOMEM; + goto free; + }

r = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!r) { @@ -254,6 +256,7 @@ static int highbank_mc_probe(struct platform_device *pdev) edac_mc_del_mc(&pdev->dev); err: devres_release_group(&pdev->dev, NULL); +free: edac_mc_free(mci); return res; } diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 77a2f7fc2b37..dfa6e6c2f808 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4116,7 +4116,18 @@ intel_dp_check_mst_status(struct intel_dp *intel_dp) bool bret;

if (intel_dp->is_mst) { - u8 esi[DP_DPRX_ESI_LEN] = { 0 }; + /* + * The +2 is because DP_DPRX_ESI_LEN is 14, but we then + * pass in "esi+10" to drm_dp_channel_eq_ok(), which + * takes a 6-byte array. So we actually need 16 bytes + * here. + * + * Somebody who knows what the limits actually are + * should check this, but for now this is at least + * harmless and avoids a valid compiler warning about + * using more of the array than we have allocated. + */ + u8 esi[DP_DPRX_ESI_LEN+2] = { 0 }; int ret = 0; int retry; bool handled; diff --git a/drivers/hid/hid-betopff.c b/drivers/hid/hid-betopff.c index 9b60efe6ec44..ba386e5aa055 100644 --- a/drivers/hid/hid-betopff.c +++ b/drivers/hid/hid-betopff.c @@ -63,7 +63,6 @@ static int betopff_init(struct hid_device *hid) struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; struct input_dev *dev; - int field_count = 0; int error; int i, j;

@@ -89,19 +88,21 @@ static int betopff_init(struct hid_device *hid) * ----------------------------------------- * Do init them with default value. */ + if (report->maxfield < 4) { + hid_err(hid, "not enough fields in the report: %d\n", + report->maxfield); + return -ENODEV; + } for (i = 0; i < report->maxfield; i++) { + if (report->field[i]->report_count < 1) { + hid_err(hid, "no values in the field\n"); + return -ENODEV; + } for (j = 0; j < report->field[i]->report_count; j++) { report->field[i]->value[j] = 0x00; - field_count++; } }

- if (field_count < 4) { - hid_err(hid, "not enough fields in the report: %d\n", - field_count); - return -ENODEV; - } - betopff = kzalloc(sizeof(*betopff), GFP_KERNEL); if (!betopff) return -ENOMEM; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 62656636d30c..8cc79d0d11fb 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -980,8 +980,8 @@ struct hid_report *hid_validate_values(struct hid_device *hid, * Validating on id 0 means we should examine the first * report in the list. */ - report = list_entry( - hid->report_enum[type].report_list.next, + report = list_first_entry_or_null( + &hid->report_enum[type].report_list, struct hid_report, list); } else { report = hid->report_enum[type].report_id_hash[id]; diff --git a/drivers/hid/intel-ish-hid/ishtp/dma-if.c b/drivers/hid/intel-ish-hid/ishtp/dma-if.c index 2783f3666114..ff4419c8ed4f 100644 --- a/drivers/hid/intel-ish-hid/ishtp/dma-if.c +++ b/drivers/hid/intel-ish-hid/ishtp/dma-if.c @@ -113,6 +113,11 @@ void *ishtp_cl_get_dma_send_buf(struct ishtp_device *dev, int required_slots = (size / DMA_SLOT_SIZE) + 1 * (size % DMA_SLOT_SIZE != 0);

+ if (!dev->ishtp_dma_tx_map) { + dev_err(dev->devc, "Fail to allocate Tx map\n"); + return NULL; + } + spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags); for (i = 0; i <= (dev->ishtp_dma_num_slots - required_slots); i++) { free = 1; @@ -159,6 +164,11 @@ void ishtp_cl_release_dma_acked_mem(struct ishtp_device *dev, return; }

+ if (!dev->ishtp_dma_tx_map) { + dev_err(dev->devc, "Fail to allocate Tx map\n"); + return; + } + i = (msg_addr - dev->ishtp_host_dma_tx_buf) / DMA_SLOT_SIZE; spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags); for (j = 0; j < acked_slots; j++) { diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index 4e417ed08b09..dab823aac95e 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -325,6 +325,8 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,

if (!PAGE_ALIGNED(tinfo->vaddr)) return -EINVAL; + if (tinfo->length == 0) + return -EINVAL;

tidbuf = kzalloc(sizeof(*tidbuf), GFP_KERNEL); if (!tidbuf) @@ -335,40 +337,38 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets), GFP_KERNEL); if (!tidbuf->psets) { - kfree(tidbuf); - return -ENOMEM; + ret = -ENOMEM; + goto fail_release_mem; }

pinned = pin_rcv_pages(fd, tidbuf); if (pinned <= 0) { - kfree(tidbuf->psets); - kfree(tidbuf); - return pinned; + ret = (pinned < 0) ? pinned : -ENOSPC; + goto fail_unpin; }

/* Find sets of physically contiguous pages */ tidbuf->n_psets = find_phys_blocks(tidbuf, pinned);

- /* - * We don't need to access this under a lock since tid_used is per - * process and the same process cannot be in hfi1_user_exp_rcv_clear() - * and hfi1_user_exp_rcv_setup() at the same time. - */ + /* Reserve the number of expected tids to be used. */ spin_lock(&fd->tid_lock); if (fd->tid_used + tidbuf->n_psets > fd->tid_limit) pageset_count = fd->tid_limit - fd->tid_used; else pageset_count = tidbuf->n_psets; + fd->tid_used += pageset_count; spin_unlock(&fd->tid_lock);

- if (!pageset_count) - goto bail; + if (!pageset_count) { + ret = -ENOSPC; + goto fail_unreserve; + }

ngroups = pageset_count / dd->rcv_entries.group_size; tidlist = kcalloc(pageset_count, sizeof(*tidlist), GFP_KERNEL); if (!tidlist) { ret = -ENOMEM; - goto nomem; + goto fail_unreserve; }

tididx = 0; @@ -464,43 +464,60 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, } unlock: mutex_unlock(&uctxt->exp_mutex); -nomem: hfi1_cdbg(TID, "total mapped: tidpairs:%u pages:%u (%d)", tididx, mapped_pages, ret); - if (tididx) { - spin_lock(&fd->tid_lock); - fd->tid_used += tididx; - spin_unlock(&fd->tid_lock); - tinfo->tidcnt = tididx; - tinfo->length = mapped_pages * PAGE_SIZE; - - if (copy_to_user(u64_to_user_ptr(tinfo->tidlist), - tidlist, sizeof(tidlist[0]) * tididx)) { - /* - * On failure to copy to the user level, we need to undo - * everything done so far so we don't leak resources. - */ - tinfo->tidlist = (unsigned long)&tidlist; - hfi1_user_exp_rcv_clear(fd, tinfo); - tinfo->tidlist = 0; - ret = -EFAULT; - goto bail; - } + + /* fail if nothing was programmed, set error if none provided */ + if (tididx == 0) { + if (ret >= 0) + ret = -ENOSPC; + goto fail_unreserve; }

- /* - * If not everything was mapped (due to insufficient RcvArray entries, - * for example), unpin all unmapped pages so we can pin them nex time. - */ - if (mapped_pages != pinned) - unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, - (pinned - mapped_pages), false); -bail: + /* adjust reserved tid_used to actual count */ + spin_lock(&fd->tid_lock); + fd->tid_used -= pageset_count - tididx; + spin_unlock(&fd->tid_lock); + + /* unpin all pages not covered by a TID */ + unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, pinned - mapped_pages, + false); + + tinfo->tidcnt = tididx; + tinfo->length = mapped_pages * PAGE_SIZE; + + if (copy_to_user(u64_to_user_ptr(tinfo->tidlist), + tidlist, sizeof(tidlist[0]) * tididx)) { + ret = -EFAULT; + goto fail_unprogram; + } + + kfree(tidbuf->pages); kfree(tidbuf->psets); + kfree(tidbuf); kfree(tidlist); + return 0; + +fail_unprogram: + /* unprogram, unmap, and unpin all allocated TIDs */ + tinfo->tidlist = (unsigned long)tidlist; + hfi1_user_exp_rcv_clear(fd, tinfo); + tinfo->tidlist = 0; + pinned = 0; /* nothing left to unpin */ + pageset_count = 0; /* nothing left reserved */ +fail_unreserve: + spin_lock(&fd->tid_lock); + fd->tid_used -= pageset_count; + spin_unlock(&fd->tid_lock); +fail_unpin: + if (pinned > 0) + unpin_rcv_pages(fd, tidbuf, NULL, 0, pinned, false); +fail_release_mem: kfree(tidbuf->pages); + kfree(tidbuf->psets); kfree(tidbuf); - return ret > 0 ? 0 : ret; + kfree(tidlist); + return ret; }

int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd, diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 7dc8ca5fd75f..c6d393114502 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -192,7 +192,6 @@ static const char * const smbus_pnp_ids[] = { "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ - "SYN3286", /* HP Laptop 15-da3001TU */ NULL };

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 4666084eda16..9d6fe5a892d9 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -524,19 +524,28 @@ static void xgbe_disable_vxlan(struct xgbe_prv_data *pdata) netif_dbg(pdata, drv, pdata->netdev, "VXLAN acceleration disabled\n"); }

+static unsigned int xgbe_get_fc_queue_count(struct xgbe_prv_data *pdata) +{ + unsigned int max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; + + /* From MAC ver 30H the TFCR is per priority, instead of per queue */ + if (XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER) >= 0x30) + return max_q_count; + else + return min_t(unsigned int, pdata->tx_q_count, max_q_count); +} + static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata) { - unsigned int max_q_count, q_count; unsigned int reg, reg_val; - unsigned int i; + unsigned int i, q_count;

/* Clear MTL flow control */ for (i = 0; i < pdata->rx_q_count; i++) XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, EHFC, 0);

/* Clear MAC flow control */ - max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + q_count = xgbe_get_fc_queue_count(pdata); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg); @@ -553,9 +562,8 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata) { struct ieee_pfc *pfc = pdata->pfc; struct ieee_ets *ets = pdata->ets; - unsigned int max_q_count, q_count; unsigned int reg, reg_val; - unsigned int i; + unsigned int i, q_count;

/* Set MTL flow control */ for (i = 0; i < pdata->rx_q_count; i++) { @@ -579,8 +587,7 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata) }

/* Set MAC flow control */ - max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + q_count = xgbe_get_fc_queue_count(pdata); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 97167fc9bebe..7840eb4cdb8d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -496,6 +496,7 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata, reg |= XGBE_KR_TRAINING_ENABLE; reg |= XGBE_KR_TRAINING_START; XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg); + pdata->kr_start_time = jiffies;

netif_dbg(pdata, link, pdata->netdev, "KR training initiated\n"); @@ -632,6 +633,8 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata)

xgbe_switch_mode(pdata);

+ pdata->an_result = XGBE_AN_READY; + xgbe_an_restart(pdata);

return XGBE_AN_INCOMPAT_LINK; @@ -1275,9 +1278,30 @@ static bool xgbe_phy_aneg_done(struct xgbe_prv_data *pdata) static void xgbe_check_link_timeout(struct xgbe_prv_data *pdata) { unsigned long link_timeout; + unsigned long kr_time; + int wait;

link_timeout = pdata->link_check + (XGBE_LINK_TIMEOUT * HZ); if (time_after(jiffies, link_timeout)) { + if ((xgbe_cur_mode(pdata) == XGBE_MODE_KR) && + pdata->phy.autoneg == AUTONEG_ENABLE) { + /* AN restart should not happen while KR training is in progress. + * The while loop ensures no AN restart during KR training, + * waits up to 500ms and AN restart is triggered only if KR + * training is failed. + */ + wait = XGBE_KR_TRAINING_WAIT_ITER; + while (wait--) { + kr_time = pdata->kr_start_time + + msecs_to_jiffies(XGBE_AN_MS_TIMEOUT); + if (time_after(jiffies, kr_time)) + break; + /* AN restart is not required, if AN result is COMPLETE */ + if (pdata->an_result == XGBE_AN_COMPLETE) + return; + usleep_range(10000, 11000); + } + } netif_dbg(pdata, link, pdata->netdev, "AN link timeout\n"); xgbe_phy_config_aneg(pdata); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 0c93a552b921..729307a96c50 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -290,6 +290,7 @@ /* Auto-negotiation */ #define XGBE_AN_MS_TIMEOUT 500 #define XGBE_LINK_TIMEOUT 5 +#define XGBE_KR_TRAINING_WAIT_ITER 50

#define XGBE_SGMII_AN_LINK_STATUS BIT(1) #define XGBE_SGMII_AN_LINK_SPEED (BIT(2) | BIT(3)) @@ -1266,6 +1267,7 @@ struct xgbe_prv_data { unsigned int parallel_detect; unsigned int fec_ability; unsigned long an_start; + unsigned long kr_start_time; enum xgbe_an_mode an_mode;

/* I2C support */ diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index d1ca3d3f51a7..2cf144bbef3e 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -11189,7 +11189,7 @@ static void tg3_reset_task(struct work_struct *work) rtnl_lock(); tg3_full_lock(tp, 0);

- if (!netif_running(tp->dev)) { + if (tp->pcierr_recovery || !netif_running(tp->dev)) { tg3_flag_clear(tp, RESET_TASK_PENDING); tg3_full_unlock(tp); rtnl_unlock(); @@ -18240,6 +18240,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,

netdev_info(netdev, "PCI I/O error detected\n");

+ /* Want to make sure that the reset task doesn't run */ + tg3_reset_task_cancel(tp); + rtnl_lock();

/* Could be second call or maybe we don't have netdev yet */ @@ -18256,9 +18259,6 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,

tg3_timer_stop(tp);

- /* Want to make sure that the reset task doesn't run */ - tg3_reset_task_cancel(tp); - netif_device_detach(netdev);

/* Clean up software state, even if MMIO is blocked */ diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 50331b202f73..324d81516832 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1738,7 +1738,6 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) || skb_is_nonlinear(*skb); int padlen = ETH_ZLEN - (*skb)->len; - int headroom = skb_headroom(*skb); int tailroom = skb_tailroom(*skb); struct sk_buff *nskb; u32 fcs; @@ -1752,9 +1751,6 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) /* FCS could be appeded to tailroom. */ if (tailroom >= ETH_FCS_LEN) goto add_fcs; - /* FCS could be appeded by moving data to headroom. */ - else if (!cloned && headroom + tailroom >= ETH_FCS_LEN) - padlen = 0; /* No room for FCS, need to reallocate skb. */ else padlen = ETH_FCS_LEN; @@ -1763,10 +1759,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) padlen += ETH_FCS_LEN; }

- if (!cloned && headroom + tailroom >= padlen) { - (*skb)->data = memmove((*skb)->head, (*skb)->data, (*skb)->len); - skb_set_tail_pointer(*skb, (*skb)->len); - } else { + if (cloned || tailroom < padlen) { nskb = skb_copy_expand(*skb, 0, padlen, GFP_ATOMIC); if (!nskb) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a2b25afa2472..e09bd059984e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1683,7 +1683,7 @@ static void mlx5_core_verify_params(void) } }

-static int __init init(void) +static int __init mlx5_init(void) { int err;

@@ -1708,7 +1708,7 @@ static int __init init(void) return err; }

-static void __exit cleanup(void) +static void __exit mlx5_cleanup(void) { #ifdef CONFIG_MLX5_CORE_EN mlx5e_cleanup(); @@ -1717,5 +1717,5 @@ static void __exit cleanup(void) mlx5_unregister_debugfs(); }

-module_init(init); -module_exit(cleanup); +module_init(mlx5_init); +module_exit(mlx5_cleanup); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ff374d0d80a7..a1906804c139 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -738,14 +738,14 @@ static void ravb_error_interrupt(struct net_device *ndev) ravb_write(ndev, ~(EIS_QFS | EIS_RESERVED), EIS); if (eis & EIS_QFS) { ris2 = ravb_read(ndev, RIS2); - ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF | RIS2_RESERVED), + ravb_write(ndev, ~(RIS2_QFF0 | RIS2_QFF1 | RIS2_RFFF | RIS2_RESERVED), RIS2);

/* Receive Descriptor Empty int */ if (ris2 & RIS2_QFF0) priv->stats[RAVB_BE].rx_over_errors++;

- /* Receive Descriptor Empty int */ + /* Receive Descriptor Empty int */ if (ris2 & RIS2_QFF1) priv->stats[RAVB_NC].rx_over_errors++;

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 1d1fbd7bd6fc..550806351049 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -103,7 +103,12 @@ EXPORT_SYMBOL(mdiobus_unregister_device);

struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr) { - struct mdio_device *mdiodev = bus->mdio_map[addr]; + struct mdio_device *mdiodev; + + if (addr < 0 || addr >= ARRAY_SIZE(bus->mdio_map)) + return NULL; + + mdiodev = bus->mdio_map[addr];

if (!mdiodev) return NULL; diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 83640628c47d..8bee8286e41a 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -410,7 +410,7 @@ static int sr9700_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* ignore the CRC length */ len = (skb->data[1] | (skb->data[2] << 8)) - 4;

- if (len > ETH_FRAME_LEN || len > skb->len) + if (len > ETH_FRAME_LEN || len > skb->len || len < 0) return 0;

/* the last packet of current skb */ diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 51e4e92d95a0..0bbeb61ec3a3 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -712,8 +712,8 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len) struct rndis_query *get; struct rndis_query_c *get_c; } u; - int ret, buflen; - int resplen, respoffs, copylen; + int ret; + size_t buflen, resplen, respoffs, copylen;

buflen = *len + sizeof(*u.get); if (buflen < CONTROL_BUFFER_SIZE) @@ -748,22 +748,15 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len)

if (respoffs > buflen) { /* Device returned data offset outside buffer, error. */ - netdev_dbg(dev->net, "%s(%s): received invalid " - "data offset: %d > %d\n", __func__, - oid_to_string(oid), respoffs, buflen); + netdev_dbg(dev->net, + "%s(%s): received invalid data offset: %zu > %zu\n", + __func__, oid_to_string(oid), respoffs, buflen);

ret = -EINVAL; goto exit_unlock; }

- if ((resplen + respoffs) > buflen) { - /* Device would have returned more data if buffer would - * have been big enough. Copy just the bits that we got. - */ - copylen = buflen - respoffs; - } else { - copylen = resplen; - } + copylen = min(resplen, buflen - respoffs);

if (copylen > *len) copylen = *len; diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c index 5049dac79bd0..77c1c3ffaed7 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c @@ -477,8 +477,10 @@ static int rockchip_usb2phy_power_on(struct phy *phy) return ret;

ret = property_enable(base, &rport->port_cfg->phy_sus, false); - if (ret) + if (ret) { + clk_disable_unprepare(rphy->clk480m); return ret; + }

/* waiting for the utmi_clk to become stable */ usleep_range(1500, 2000); diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 13931c5c0eff..25d9bdd4bc69 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -5771,7 +5771,7 @@ static int hpsa_scsi_host_alloc(struct ctlr_info *h) { struct Scsi_Host *sh;

- sh = scsi_host_alloc(&hpsa_driver_template, sizeof(h)); + sh = scsi_host_alloc(&hpsa_driver_template, sizeof(struct ctlr_info)); if (sh == NULL) { dev_err(&h->pdev->dev, "scsi_host_alloc failed\n"); return -ENOMEM; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 49eb4e3c760f..48bdb2a3972b 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -271,6 +271,9 @@ static int __ffs_ep0_queue_wait(struct ffs_data *ffs, char *data, size_t len) struct usb_request *req = ffs->ep0req; int ret;

+ if (!req) + return -EINVAL; + req->zero = len < le16_to_cpu(ffs->ev.setup.wLength);

spin_unlock_irq(&ffs->ev.waitq.lock); @@ -1807,10 +1810,14 @@ static void functionfs_unbind(struct ffs_data *ffs) ENTER();

if (!WARN_ON(!ffs->gadget)) { + /* dequeue before freeing ep0req */ + usb_ep_dequeue(ffs->gadget->ep0, ffs->ep0req); + mutex_lock(&ffs->mutex); usb_ep_free_request(ffs->gadget->ep0, ffs->ep0req); ffs->ep0req = NULL; ffs->gadget = NULL; clear_bit(FFS_FL_BOUND, &ffs->flags); + mutex_unlock(&ffs->mutex); ffs_data_put(ffs); } } diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index adc437ca83b8..cb3ba2adae64 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -261,7 +261,7 @@ static int xhci_plat_probe(struct platform_device *pdev) *priv = *priv_match; }

- device_wakeup_enable(hcd->self.controller); + device_set_wakeup_capable(&pdev->dev, true);

xhci->clk = clk; xhci->reg_clk = reg_clk; diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 890c038c25f8..cb3650efc29c 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -1140,6 +1140,8 @@ int w1_process(void *data) /* remainder if it woke up early */ unsigned long jremain = 0;

+ atomic_inc(&dev->refcnt); + for (;;) {

if (!jremain && dev->search_count) { @@ -1167,8 +1169,10 @@ int w1_process(void *data) */ mutex_unlock(&dev->list_mutex);

- if (kthread_should_stop()) + if (kthread_should_stop()) { + __set_current_state(TASK_RUNNING); break; + }

/* Only sleep when the search is active. */ if (dev->search_count) { diff --git a/drivers/w1/w1_int.c b/drivers/w1/w1_int.c index 1c776178f598..eb851eb44300 100644 --- a/drivers/w1/w1_int.c +++ b/drivers/w1/w1_int.c @@ -60,10 +60,9 @@ static struct w1_master *w1_alloc_dev(u32 id, int slave_count, int slave_ttl, dev->search_count = w1_search_count; dev->enable_pullup = w1_enable_pullup;

- /* 1 for w1_process to decrement - * 1 for __w1_remove_master_device to decrement + /* For __w1_remove_master_device to decrement */ - atomic_set(&dev->refcnt, 2); + atomic_set(&dev->refcnt, 1);

INIT_LIST_HEAD(&dev->slist); INIT_LIST_HEAD(&dev->async_list); diff --git a/fs/affs/file.c b/fs/affs/file.c index ba084b0b214b..82bb38370aa9 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -878,7 +878,7 @@ affs_truncate(struct inode *inode) if (inode->i_size > AFFS_I(inode)->mmu_private) { struct address_space *mapping = inode->i_mapping; struct page *page; - void *fsdata; + void *fsdata = NULL; loff_t isize = inode->i_size; int res;

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a7ef847f285d..37e91f27f49b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -429,7 +429,8 @@ cifs_reconnect(struct TCP_Server_Info *server) server->ssocket->state, server->ssocket->flags); sock_release(server->ssocket); server->ssocket = NULL; - } + } else if (cifs_rdma_enabled(server)) + smbd_destroy(server); server->sequence_number = 0; server->session_estab = false; kfree(server->session_key.response); @@ -799,10 +800,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) wake_up_all(&server->request_q); /* give those requests time to exit */ msleep(125); - if (cifs_rdma_enabled(server) && server->smbd_conn) { - smbd_destroy(server->smbd_conn); - server->smbd_conn = NULL; - } + if (cifs_rdma_enabled(server)) + smbd_destroy(server); if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 784628ec4bc4..591cd5c70432 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -320,6 +320,9 @@ static int smbd_conn_upcall(

info->transport_status = SMBD_DISCONNECTED; smbd_process_disconnected(info); + wake_up(&info->disconn_wait); + wake_up_interruptible(&info->wait_reassembly_queue); + wake_up_interruptible_all(&info->wait_send_queue); break;

default: @@ -1478,21 +1481,102 @@ static void idle_connection_timer(struct work_struct *work) info->keep_alive_interval*HZ); }

-/* Destroy this SMBD connection, called from upper layer */ -void smbd_destroy(struct smbd_connection *info) +/* + * Destroy the transport and related RDMA and memory resources + * Need to go through all the pending counters and make sure on one is using + * the transport while it is destroyed + */ +void smbd_destroy(struct TCP_Server_Info *server) { + struct smbd_connection *info = server->smbd_conn; + struct smbd_response *response; + unsigned long flags; + + if (!info) { + log_rdma_event(INFO, "rdma session already destroyed\n"); + return; + } + log_rdma_event(INFO, "destroying rdma session\n"); + if (info->transport_status != SMBD_DISCONNECTED) { + rdma_disconnect(server->smbd_conn->id); + log_rdma_event(INFO, "wait for transport being disconnected\n"); + wait_event( + info->disconn_wait, + info->transport_status == SMBD_DISCONNECTED); + }

- /* Kick off the disconnection process */ - smbd_disconnect_rdma_connection(info); + log_rdma_event(INFO, "destroying qp\n"); + ib_drain_qp(info->id->qp); + rdma_destroy_qp(info->id); + + log_rdma_event(INFO, "cancelling idle timer\n"); + cancel_delayed_work_sync(&info->idle_timer_work); + log_rdma_event(INFO, "cancelling send immediate work\n"); + cancel_delayed_work_sync(&info->send_immediate_work); + + log_rdma_event(INFO, "wait for all send posted to IB to finish\n"); + wait_event(info->wait_send_pending, + atomic_read(&info->send_pending) == 0); + wait_event(info->wait_send_payload_pending, + atomic_read(&info->send_payload_pending) == 0); + + /* It's not posssible for upper layer to get to reassembly */ + log_rdma_event(INFO, "drain the reassembly queue\n"); + do { + spin_lock_irqsave(&info->reassembly_queue_lock, flags); + response = _get_first_reassembly(info); + if (response) { + list_del(&response->list); + spin_unlock_irqrestore( + &info->reassembly_queue_lock, flags); + put_receive_buffer(info, response); + } else + spin_unlock_irqrestore( + &info->reassembly_queue_lock, flags); + } while (response); + info->reassembly_data_length = 0; + + log_rdma_event(INFO, "free receive buffers\n"); + wait_event(info->wait_receive_queues, + info->count_receive_queue + info->count_empty_packet_queue + == info->receive_credit_max); + destroy_receive_buffers(info); + + /* + * For performance reasons, memory registration and deregistration + * are not locked by srv_mutex. It is possible some processes are + * blocked on transport srv_mutex while holding memory registration. + * Release the transport srv_mutex to allow them to hit the failure + * path when sending data, and then release memory registartions. + */ + log_rdma_event(INFO, "freeing mr list\n"); + wake_up_interruptible_all(&info->wait_mr); + while (atomic_read(&info->mr_used_count)) { + mutex_unlock(&server->srv_mutex); + msleep(1000); + mutex_lock(&server->srv_mutex); + } + destroy_mr_list(info); + + ib_free_cq(info->send_cq); + ib_free_cq(info->recv_cq); + ib_dealloc_pd(info->pd); + rdma_destroy_id(info->id);

- log_rdma_event(INFO, "wait for transport being destroyed\n"); - wait_event(info->wait_destroy, - info->transport_status == SMBD_DESTROYED); + /* free mempools */ + mempool_destroy(info->request_mempool); + kmem_cache_destroy(info->request_cache); + + mempool_destroy(info->response_mempool); + kmem_cache_destroy(info->response_cache); + + info->transport_status = SMBD_DESTROYED;

destroy_workqueue(info->workqueue); log_rdma_event(INFO, "rdma session destroyed\n"); kfree(info); + server->smbd_conn = NULL; }

/* @@ -1514,17 +1598,9 @@ int smbd_reconnect(struct TCP_Server_Info *server) */ if (server->smbd_conn->transport_status == SMBD_CONNECTED) { log_rdma_event(INFO, "disconnecting transport\n"); - smbd_disconnect_rdma_connection(server->smbd_conn); + smbd_destroy(server); }

- /* wait until the transport is destroyed */ - if (!wait_event_timeout(server->smbd_conn->wait_destroy, - server->smbd_conn->transport_status == SMBD_DESTROYED, 5*HZ)) - return -EAGAIN; - - destroy_workqueue(server->smbd_conn->workqueue); - kfree(server->smbd_conn); - create_conn: log_rdma_event(INFO, "creating rdma session\n"); server->smbd_conn = smbd_get_connection( @@ -1741,12 +1817,13 @@ static struct smbd_connection *_smbd_get_connection( conn_param.retry_count = SMBD_CM_RETRY; conn_param.rnr_retry_count = SMBD_CM_RNR_RETRY; conn_param.flow_control = 0; - init_waitqueue_head(&info->wait_destroy);

log_rdma_event(INFO, "connecting to IP %pI4 port %d\n", &addr_in->sin_addr, port);

init_waitqueue_head(&info->conn_wait); + init_waitqueue_head(&info->disconn_wait); + init_waitqueue_head(&info->wait_reassembly_queue); rc = rdma_connect(info->id, &conn_param); if (rc) { log_rdma_event(ERR, "rdma_connect() failed with %i\n", rc); @@ -1770,8 +1847,6 @@ static struct smbd_connection *_smbd_get_connection( }

init_waitqueue_head(&info->wait_send_queue); - init_waitqueue_head(&info->wait_reassembly_queue); - INIT_DELAYED_WORK(&info->idle_timer_work, idle_connection_timer); INIT_DELAYED_WORK(&info->send_immediate_work, send_immediate_work); queue_delayed_work(info->workqueue, &info->idle_timer_work, @@ -1812,7 +1887,7 @@ static struct smbd_connection *_smbd_get_connection(

allocate_mr_failed: /* At this point, need to a full transport shutdown */ - smbd_destroy(info); + smbd_destroy(server); return NULL;

negotiation_failed: diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h index b5c240ff2191..b0ca7df41454 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/cifs/smbdirect.h @@ -71,6 +71,7 @@ struct smbd_connection { struct completion ri_done; wait_queue_head_t conn_wait; wait_queue_head_t wait_destroy; + wait_queue_head_t disconn_wait;

struct completion negotiate_completion; bool negotiate_done; @@ -288,7 +289,7 @@ struct smbd_connection *smbd_get_connection( /* Reconnect SMBDirect session */ int smbd_reconnect(struct TCP_Server_Info *server); /* Destroy SMBDirect session */ -void smbd_destroy(struct smbd_connection *info); +void smbd_destroy(struct TCP_Server_Info *server);

/* Interface for carrying upper layer I/O through send/recv */ int smbd_recv(struct smbd_connection *info, struct msghdr *msg); @@ -331,7 +332,7 @@ struct smbd_connection {}; static inline void *smbd_get_connection( struct TCP_Server_Info *server, struct sockaddr *dstaddr) {return NULL;} static inline int smbd_reconnect(struct TCP_Server_Info *server) {return -1; } -static inline void smbd_destroy(struct smbd_connection *info) {} +static inline void smbd_destroy(struct TCP_Server_Info *server) {} static inline int smbd_recv(struct smbd_connection *info, struct msghdr *msg) {return -1; } static inline int smbd_send(struct TCP_Server_Info *server, int num_rqst, struct smb_rqst *rqst) {return -1; } #endif diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index c95f32b83a94..7c62a526506c 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -13,6 +13,7 @@ #include <linux/namei.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/kmemleak.h> #include "internal.h"

static const struct dentry_operations proc_sys_dentry_operations; @@ -1376,6 +1377,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab } EXPORT_SYMBOL(register_sysctl);

+/** + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base + * @table: This is the sysctl table that needs to be registered to the path + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. + * + * Context: Can only be called after your respective sysctl base path has been + * registered. So for instance, most base directories are registered early on + * init before init levels are processed through proc_sys_init() and + * sysctl_init(). + */ +void __init __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name) +{ + struct ctl_table_header *hdr = register_sysctl(path, table); + + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl %s to %s\n", table_name, path); + return; + } + kmemleak_not_leak(hdr); +} + static char *append_path(const char *path, char *pos, const char *name) { int namelen; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 831a542c22c6..e5be1d747c03 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1443,7 +1443,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) unsigned long safe_mask = 0; unsigned int commit_max_age = (unsigned int)-1; struct reiserfs_journal *journal = SB_JOURNAL(s); - char *new_opts; int err; char *qf_names[REISERFS_MAXQUOTAS]; unsigned int qfmt = 0; @@ -1451,10 +1450,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) int i; #endif

- new_opts = kstrdup(arg, GFP_KERNEL); - if (arg && !new_opts) - return -ENOMEM; - sync_filesystem(s); reiserfs_write_lock(s);

@@ -1605,7 +1600,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) out_err_unlock: reiserfs_write_unlock(s); out_err: - kfree(new_opts); return err; }

diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 50733abbe548..a28ec4c2f3f5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -327,6 +327,7 @@ extern long (*panic_blink)(int state); __printf(1, 2) void panic(const char *fmt, ...) __noreturn __cold; void nmi_panic(struct pt_regs *regs, const char *msg); +void check_panic_on_warn(const char *origin); extern void oops_enter(void); extern void oops_exit(void); void print_oops_end_marker(void); diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 91401309b1aa..0ee9aab3e309 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -36,6 +36,7 @@ extern int sched_fork(unsigned long clone_flags, struct task_struct *p); extern void sched_dead(struct task_struct *p);

void __noreturn do_task_dead(void); +void __noreturn make_task_dead(int signr);

extern void proc_caches_init(void);

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index b769ecfcc3bd..0a980aecc8f0 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -198,6 +198,9 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table);

extern int sysctl_init(void); +extern void __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name); +#define register_sysctl_init(path, table) __register_sysctl_init(path, table, #table)

extern struct ctl_table sysctl_mount_point[];

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 694ee0b1fefe..61f3a31abc1a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1012,7 +1012,9 @@ static int check_stack_write(struct bpf_verifier_env *env, bool sanitize = reg && is_spillable_regtype(reg->type);

for (i = 0; i < size; i++) { - if (state->stack[spi].slot_type[i] == STACK_INVALID) { + u8 type = state->stack[spi].slot_type[i]; + + if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; } diff --git a/kernel/exit.c b/kernel/exit.c index 908e7a33e1fc..02360ec3b122 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -62,12 +62,59 @@ #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> +#include <linux/sysfs.h>

#include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/pgtable.h> #include <asm/mmu_context.h>

+/* + * The default value should be high enough to not crash a system that randomly + * crashes its kernel from time to time, but low enough to at least not permit + * overflowing 32-bit refcounts or the ldsem writer count. + */ +static unsigned int oops_limit = 10000; + +#ifdef CONFIG_SYSCTL +static struct ctl_table kern_exit_table[] = { + { + .procname = "oops_limit", + .data = &oops_limit, + .maxlen = sizeof(oops_limit), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + { } +}; + +static __init int kernel_exit_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_exit_table); + return 0; +} +late_initcall(kernel_exit_sysctls_init); +#endif + +static atomic_t oops_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); +} + +static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); + +static __init int kernel_exit_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_exit_sysfs_init); +#endif + static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; @@ -922,6 +969,31 @@ void __noreturn do_exit(long code) } EXPORT_SYMBOL_GPL(do_exit);

+void __noreturn make_task_dead(int signr) +{ + /* + * Take the task off the cpu after something catastrophic has + * happened. + */ + unsigned int limit; + + /* + * Every time the system oopses, if the oops happens while a reference + * to an object was held, the reference leaks. + * If the oops doesn't also leak memory, repeated oopsing can cause + * reference counters to wrap around (if they're not using refcount_t). + * This means that repeated oopsing can make unexploitable-looking bugs + * exploitable through repeated oopsing. + * To make sure this can't happen, place an upper bound on how often the + * kernel may oops without panic(). + */ + limit = READ_ONCE(oops_limit); + if (atomic_inc_return(&oops_count) >= limit && limit) + panic("Oopsed too often (kernel.oops_limit is %d)", limit); + + do_exit(signr); +} + void complete_and_exit(struct completion *comp, long code) { if (comp) diff --git a/kernel/module.c b/kernel/module.c index 42a604401c4d..6ec0b2e0f01f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3478,7 +3478,8 @@ static bool finished_loading(const char *name) sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); - ret = !mod || mod->state == MODULE_STATE_LIVE; + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex);

return ret; @@ -3632,20 +3633,35 @@ static int add_unformed_module(struct module *mod)

mod->state = MODULE_STATE_UNFORMED;

-again: mutex_lock(&module_mutex); old = find_module_all(mod->name, strlen(mod->name), true); if (old != NULL) { - if (old->state != MODULE_STATE_LIVE) { + if (old->state == MODULE_STATE_COMING + || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); err = wait_event_interruptible(module_wq, finished_loading(mod->name)); if (err) goto out_unlocked; - goto again; + + /* The module might have gone in the meantime. */ + mutex_lock(&module_mutex); + old = find_module_all(mod->name, strlen(mod->name), + true); } - err = -EEXIST; + + /* + * We are here only when the same module was being loaded. Do + * not try to load it again right now. It prevents long delays + * caused by serialized module load failures. It might happen + * when more devices of the same type trigger load of + * a particular module. + */ + if (old && old->state == MODULE_STATE_LIVE) + err = -EEXIST; + else + err = -EBUSY; goto out; } mod_update_bounds(mod); diff --git a/kernel/panic.c b/kernel/panic.c index 8138a676fb7d..982ecba286c0 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -29,6 +29,7 @@ #include <linux/bug.h> #include <linux/ratelimit.h> #include <linux/debugfs.h> +#include <linux/sysfs.h> #include <asm/sections.h>

#define PANIC_TIMER_STEP 100 @@ -42,6 +43,7 @@ static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); bool crash_kexec_post_notifiers; int panic_on_warn __read_mostly; +static unsigned int warn_limit __read_mostly;

int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -50,6 +52,45 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list);

EXPORT_SYMBOL(panic_notifier_list);

+#ifdef CONFIG_SYSCTL +static struct ctl_table kern_panic_table[] = { + { + .procname = "warn_limit", + .data = &warn_limit, + .maxlen = sizeof(warn_limit), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + { } +}; + +static __init int kernel_panic_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_panic_table); + return 0; +} +late_initcall(kernel_panic_sysctls_init); +#endif + +static atomic_t warn_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&warn_count)); +} + +static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count); + +static __init int kernel_panic_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_panic_sysfs_init); +#endif + static long no_blink(int state) { return 0; @@ -125,6 +166,19 @@ void nmi_panic(struct pt_regs *regs, const char *msg) } EXPORT_SYMBOL(nmi_panic);

+void check_panic_on_warn(const char *origin) +{ + unsigned int limit; + + if (panic_on_warn) + panic("%s: panic_on_warn set ...\n", origin); + + limit = READ_ONCE(warn_limit); + if (atomic_inc_return(&warn_count) >= limit && limit) + panic("%s: system warned too often (kernel.warn_limit is %d)", + origin, limit); +} + /** * panic - halt the system * @fmt: The text string to print @@ -142,6 +196,16 @@ void panic(const char *fmt, ...) int old_cpu, this_cpu; bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;

+ if (panic_on_warn) { + /* + * This thread may hit another WARN() in the panic path. + * Resetting this prevents additional WARN() from panicking the + * system on this thread. Other threads are blocked by the + * panic_mutex in panic(). + */ + panic_on_warn = 0; + } + /* * Disable local interrupts. This will prevent panic_smp_self_stop * from deadlocking the first cpu that invokes the panic, since @@ -530,16 +594,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, if (args) vprintk(args->fmt, args->args);

- if (panic_on_warn) { - /* - * This thread may hit another WARN() in the panic path. - * Resetting this prevents additional WARN() from panicking the - * system on this thread. Other threads are blocked by the - * panic_mutex in panic(). - */ - panic_on_warn = 0; - panic("panic_on_warn set ...\n"); - } + check_panic_on_warn("kernel");

print_modules();

diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a03464249771..46227cc48124 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3316,8 +3316,7 @@ static noinline void __schedule_bug(struct task_struct *prev) print_ip_sym(preempt_disable_ip); pr_cont("\n"); } - if (panic_on_warn) - panic("scheduling while atomic\n"); + check_panic_on_warn("scheduling while atomic");

dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 59ad83499ba2..98abff046236 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8674,6 +8674,8 @@ void __init early_trace_init(void) static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); + + init_events(); }

void __init trace_init(void) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 74185fb040f3..0923d1b18d1f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1530,6 +1530,7 @@ extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable);

extern int event_trace_init(void); +extern int init_events(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr);

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 17b15bd97857..a56ee4ba2afb 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2314,6 +2314,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, unsigned long fl = flags & ~HIST_FIELD_FL_LOG2; hist_field->fn = hist_field_log2; hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL); + if (!hist_field->operands[0]) + goto free; hist_field->size = hist_field->operands[0]->size; hist_field->type = kstrdup(hist_field->operands[0]->type, GFP_KERNEL); if (!hist_field->type) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 6e6cc64faa38..62015d62dd6f 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1395,7 +1395,7 @@ static struct trace_event *events[] __initdata = { NULL };

-__init static int init_events(void) +__init int init_events(void) { struct trace_event *event; int i, ret; @@ -1413,4 +1413,3 @@ __init static int init_events(void)

return 0; } -early_initcall(init_events); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 5c169aa688fd..3ae996824a04 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -176,8 +176,7 @@ static void kasan_end_report(unsigned long *flags) pr_err("==================================================================\n"); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); spin_unlock_irqrestore(&report_lock, *flags); - if (panic_on_warn) - panic("panic_on_warn set ...\n"); + check_panic_on_warn("KASAN"); kasan_enable_current(); }

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e87777255c47..497c8ac140d1 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1519,6 +1519,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) hdev->flush(hdev);

if (hdev->sent_cmd) { + cancel_delayed_work_sync(&hdev->cmd_timer); kfree_skb(hdev->sent_cmd); hdev->sent_cmd = NULL; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 56c240c98a56..a87774424829 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -132,12 +132,12 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) return 0;

if (ops->id && ops->size) { -cleanup: ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; }

+cleanup: kfree(data);

out: diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3c58019f0718..d64522af9c3a 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -579,8 +579,20 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_nulls_del_node_init_rcu(osk); - } else if (found_dup_sk) { + ret = sk_hashed(osk); + if (ret) { + /* Before deleting the node, we insert a new one to make + * sure that the look-up-sk process would not miss either + * of them and that at least one node would exist in ehash + * table all the time. Otherwise there's a tiny chance + * that lookup process could find nothing in ehash table. + */ + __sk_nulls_add_node_tail_rcu(sk, list); + sk_nulls_del_node_init_rcu(osk); + } + goto unlock; + } + if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -589,6 +601,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list);

+unlock: spin_unlock(lock);

return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 88c5069b5d20..fedd19c22b39 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -80,10 +80,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put);

-static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_head_rcu(&tw->tw_node, list); + hlist_nulls_add_tail_rcu(&tw->tw_node, list); }

static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -119,7 +119,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,

spin_lock(lock);

- inet_twsk_add_node_rcu(tw, &ehead->chain); + inet_twsk_add_node_tail_rcu(tw, &ehead->chain);

/* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 04311f7067e2..9a6b01d85cd0 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -1,4 +1,5 @@ #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/rtnetlink.h> #include <linux/types.h> #include <net/ip.h> @@ -24,6 +25,7 @@ int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, if (type > RTAX_MAX) return -EINVAL;

+ type = array_index_nospec(type, RTAX_MAX + 1); if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX];

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index e617a98f4df6..00601bc4fdfa 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1154,14 +1154,16 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, dev->needed_headroom = dst_len;

if (set_mtu) { - dev->mtu = rt->dst.dev->mtu - t_hlen; + int mtu = rt->dst.dev->mtu - t_hlen; + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8; if (dev->type == ARPHRD_ETHER) - dev->mtu -= ETH_HLEN; + mtu -= ETH_HLEN;

- if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } ip6_rt_put(rt); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b647a4037679..75a1ec2605fc 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1435,6 +1435,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; int t_hlen; + int mtu;

memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); @@ -1477,12 +1478,13 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) dev->hard_header_len = rt->dst.dev->hard_header_len + t_hlen;

- dev->mtu = rt->dst.dev->mtu - t_hlen; + mtu = rt->dst.dev->mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8;

- if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } ip6_rt_put(rt); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 420b9fcc10d7..df734fe64d10 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1082,10 +1082,12 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)

if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int mtu;

- dev->mtu = tdev->mtu - t_hlen; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + mtu = tdev->mtu - t_hlen; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } }

diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 8cb62805fd68..cadeb22a48f2 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -317,22 +317,29 @@ static int sctp_packet(struct nf_conn *ct, for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Special cases of Verification tag check (Sec 8.5.1) */ if (sch->type == SCTP_CID_INIT) { - /* Sec 8.5.1 (A) */ + /* (A) vtag MUST be zero */ if (sh->vtag != 0) goto out_unlock; } else if (sch->type == SCTP_CID_ABORT) { - /* Sec 8.5.1 (B) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir]) + /* (B) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) { - /* Sec 8.5.1 (C) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir] && - sch->flags & SCTP_CHUNK_FLAG_T) + /* (C) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_COOKIE_ECHO) { - /* Sec 8.5.1 (D) */ + /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; } else if (sch->type == SCTP_CID_HEARTBEAT) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 66cda5e2d6b9..955b73a9a05e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1094,6 +1094,16 @@ static int tcp_packet(struct nf_conn *ct, nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } + + if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) { + /* do not renew timeout on SYN retransmit. + * + * Else port reuse by client or NAT middlebox can keep + * entry alive indefinitely (including nat info). + */ + return NF_ACCEPT; + } + /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection * pickup with loose=1. Avoid large ESTABLISHED timeout. */ diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 84d317418d18..78a0f4283787 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -375,23 +375,37 @@ static void nft_rbtree_gc(struct work_struct *work) struct nft_rbtree *priv; struct rb_node *node; struct nft_set *set; + struct net *net; + u8 genmask;

priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + genmask = nft_genmask_cur(net);

write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node);

+ if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* elements are reversed in the rbtree for historical reasons, + * from highest to lowest value, that is why end element is + * always visited before the start element. + */ if (nft_rbtree_interval_end(rbe)) { rbe_end = rbe; continue; } if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) + + if (nft_set_elem_mark_busy(&rbe->ext)) { + rbe_end = NULL; continue; + }

if (rbe_prev) { rb_erase(&rbe_prev->node, &priv->root); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6ffa83319d08..6a49c0aa55bd 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -578,12 +578,9 @@ static int netlink_insert(struct sock *sk, u32 portid) if (nlk_sk(sk)->bound) goto err;

- err = -ENOMEM; - if (BITS_PER_LONG > 32 && - unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX)) - goto err; + /* portid can be read locklessly from netlink_getname(). */ + WRITE_ONCE(nlk_sk(sk)->portid, portid);

- nlk_sk(sk)->portid = portid; sock_hold(sk);

err = __netlink_insert(table, sk); @@ -1093,9 +1090,11 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL;

if (addr->sa_family == AF_UNSPEC) { - sk->sk_state = NETLINK_UNCONNECTED; - nlk->dst_portid = 0; - nlk->dst_group = 0; + /* paired with READ_ONCE() in netlink_getsockbyportid() */ + WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, 0); + WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) @@ -1116,9 +1115,11 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, err = netlink_autobind(sock);

if (err == 0) { - sk->sk_state = NETLINK_CONNECTED; - nlk->dst_portid = nladdr->nl_pid; - nlk->dst_group = ffs(nladdr->nl_groups); + /* paired with READ_ONCE() in netlink_getsockbyportid() */ + WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); + WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); }

return err; @@ -1135,10 +1136,12 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_pad = 0;

if (peer) { - nladdr->nl_pid = nlk->dst_portid; - nladdr->nl_groups = netlink_group_mask(nlk->dst_group); + /* Paired with WRITE_ONCE() in netlink_connect() */ + nladdr->nl_pid = READ_ONCE(nlk->dst_portid); + nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { - nladdr->nl_pid = nlk->portid; + /* Paired with WRITE_ONCE() in netlink_insert() */ + nladdr->nl_pid = READ_ONCE(nlk->portid); netlink_lock_table(); nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); @@ -1165,8 +1168,9 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid)

/* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); - if (sock->sk_state == NETLINK_CONNECTED && - nlk->dst_portid != nlk_sk(ssk)->portid) { + /* dst_portid and sk_state can be changed in netlink_connect() */ + if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && + READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } @@ -1878,8 +1882,9 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { - dst_portid = nlk->dst_portid; - dst_group = nlk->dst_group; + /* Paired with WRITE_ONCE() in netlink_connect() */ + dst_portid = READ_ONCE(nlk->dst_portid); + dst_group = READ_ONCE(nlk->dst_group); }

/* Paired with WRITE_ONCE() in netlink_insert() */ diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 426d49609524..2bf99bd5be58 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -124,6 +124,7 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { + sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); goto out; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 4fa015208aab..3290f2275b85 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -171,6 +171,7 @@ static void local_cleanup(struct nfc_llcp_local *local) cancel_work_sync(&local->rx_work); cancel_work_sync(&local->timeout_work); kfree_skb(local->rx_pending); + local->rx_pending = NULL; del_timer_sync(&local->sdreq_timer); cancel_work_sync(&local->sdreq_timeout_work); nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs); diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index f8a283245672..d723942e5e65 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -88,6 +88,12 @@ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, } }

+ /* If somehow no addresses were found that can be used with this + * scope, it's an error. + */ + if (list_empty(&dest->address_list)) + error = -ENETUNREACH; + out: if (error) sctp_bind_addr_clean(dest); diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile index cca5a3012fee..221eaadffb09 100644 --- a/security/tomoyo/Makefile +++ b/security/tomoyo/Makefile @@ -10,7 +10,7 @@ endef quiet_cmd_policy = POLICY $@ cmd_policy = ($(call do_policy,profile); $(call do_policy,exception_policy); $(call do_policy,domain_policy); $(call do_policy,manager); $(call do_policy,stat)) >$@

-$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE +$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE $(call if_changed,policy)

$(obj)/common.o: $(obj)/builtin-policy.h diff --git a/tools/objtool/check.c b/tools/objtool/check.c index c0ab27368a34..55f3e7fa1c5d 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -159,6 +159,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func, "panic", "do_exit", "do_task_dead", + "make_task_dead", "__module_put_and_exit", "complete_and_exit", "kvm_spurious_fault", @@ -167,7 +168,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func, "fortify_panic", "usercopy_abort", "machine_real_restart", - "rewind_stack_do_exit", + "rewind_stack_and_make_dead", };

if (func->bind == STB_WEAK) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 4c23779e271a..3641a96a2de4 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -163,11 +163,11 @@ static const char *normalize_arch(char *arch)

const char *perf_env__arch(struct perf_env *env) { - struct utsname uts; char *arch_name;

if (!env || !env->arch) { /* Assume local operation */ - if (uname(&uts) < 0) + static struct utsname uts = { .machine[0] = '\0', }; + if (uts.machine[0] == '\0' && uname(&uts) < 0) return NULL; arch_name = uts.machine; } else