5.15.91-rc1 review
Subsystems (6)
Greg Kroah-Hartman
maintainerPATCH 128/204 exit: Add and use make_task_dead.
In reply to Greg Kroah-HartmanFrom: Eric W. Biederman <[email protected]>
commit 0e25498f8cd43c1b5aa327f373dd094e9a006da7 upstream.
There are two big uses of do_exit. The first is it's design use to be the guts of the exit(2) system call. The second use is to terminate a task after something catastrophic has happened like a NULL pointer in kernel code.
Add a function make_task_dead that is initialy exactly the same as do_exit to cover the cases where do_exit is called to handle catastrophic failure. In time this can probably be reduced to just a light wrapper around do_task_dead. For now keep it exactly the same so that there will be no behavioral differences introducing this new concept.
Replace all of the uses of do_exit that use it for catastraphic task cleanup with make_task_dead to make it clear what the code is doing.
As part of this rename rewind_stack_do_exitrewind_stack_and_make_dead.
--- arch/alpha/kernel/traps.c | 6 +++--- arch/alpha/mm/fault.c | 2 +- arch/arm/kernel/traps.c | 2 +- arch/arm/mm/fault.c | 2 +- arch/arm64/kernel/traps.c | 2 +- arch/arm64/mm/fault.c | 2 +- arch/csky/abiv1/alignment.c | 2 +- arch/csky/kernel/traps.c | 2 +- arch/csky/mm/fault.c | 2 +- arch/h8300/kernel/traps.c | 2 +- arch/h8300/mm/fault.c | 2 +- arch/hexagon/kernel/traps.c | 2 +- arch/ia64/kernel/mca_drv.c | 2 +- arch/ia64/kernel/traps.c | 2 +- arch/ia64/mm/fault.c | 2 +- arch/m68k/kernel/traps.c | 2 +- arch/m68k/mm/fault.c | 2 +- arch/microblaze/kernel/exceptions.c | 4 ++-- arch/mips/kernel/traps.c | 2 +- arch/nds32/kernel/fpu.c | 2 +- arch/nds32/kernel/traps.c | 8 ++++---- arch/nios2/kernel/traps.c | 4 ++-- arch/openrisc/kernel/traps.c | 2 +- arch/parisc/kernel/traps.c | 2 +- arch/powerpc/kernel/traps.c | 8 ++++---- arch/riscv/kernel/traps.c | 2 +- arch/riscv/mm/fault.c | 2 +- arch/s390/kernel/dumpstack.c | 2 +- arch/s390/kernel/nmi.c | 2 +- arch/sh/kernel/traps.c | 2 +- arch/sparc/kernel/traps_32.c | 4 +--- arch/sparc/kernel/traps_64.c | 4 +--- arch/x86/entry/entry_32.S | 6 +++--- arch/x86/entry/entry_64.S | 6 +++--- arch/x86/kernel/dumpstack.c | 4 ++-- arch/xtensa/kernel/traps.c | 2 +- include/linux/sched/task.h | 1 + kernel/exit.c | 9 +++++++++ tools/objtool/check.c | 3 ++- 39 files changed, 63 insertions(+), 56 deletions(-)
arch/alpha/kernel/traps.c +3 -3
@@ -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 ); }/*
arch/alpha/mm/fault.c +1 -1
@@ -204,7 +204,7 @@ 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. */
arch/arm/kernel/traps.c +1 -1
@@ -334,7 +334,7 @@ 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); }/*
arch/arm/mm/fault.c +1 -1
@@ -125,7 +125,7 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,show_pte (KERN_ALERT , mm, addr);die ("Oops" , regs, fsr);bust_spinlocks (0 ); -do_exit (SIGKILL ); +make_task_dead (SIGKILL ); }/*
arch/arm64/kernel/traps.c +1 -1
@@ -235,7 +235,7 @@ 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 void arm64_show_signal (int signo,const char *str)
arch/arm64/mm/fault.c +1 -1
@@ -302,7 +302,7 @@ 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 ); }#ifdef CONFIG_KASAN_HW_TAGS
arch/csky/abiv1/alignment.c +1 -1
@@ -294,7 +294,7 @@ void csky_alignment(struct pt_regs *regs) __func__, opcode, rz, rx, imm, addr);show_regs (regs);bust_spinlocks (0 ); -do_exit (SIGKILL ); +make_dead_task (SIGKILL ); }force_sig_fault (SIGBUS ,BUS_ADRALN , (void __user *)addr);
arch/csky/kernel/traps.c +1 -1
@@ -109,7 +109,7 @@ void die(struct pt_regs *regs, const char *str)if (panic_on_oops)panic ("Fatal exception" );if (ret !=NOTIFY_STOP ) -do_exit (SIGSEGV ); +make_dead_task (SIGSEGV ); }void do_trap (struct pt_regs *regs,int signo,int code,unsigned long addr)
arch/csky/mm/fault.c +1 -1
@@ -67,7 +67,7 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr)pr_alert ("Unable to handle kernel paging request at virtual " "addr 0x%08lx, pc: 0x%08lx\n" , addr, regs->pc);die (regs,"Oops" ); -do_exit (SIGKILL ); +make_task_dead (SIGKILL ); }static inline void mm_fault_error (struct pt_regs *regs,unsigned long addr,vm_fault_t fault)
arch/h8300/kernel/traps.c +1 -1
@@ -106,7 +106,7 @@ void die(const char *str, struct pt_regs *fp, unsigned long err)dump (fp);spin_unlock_irq (&die_lock); -do_exit (SIGSEGV ); +make_dead_task (SIGSEGV ); }static int kstack_depth_to_print =24 ;
arch/h8300/mm/fault.c +1 -1
@@ -51,7 +51,7 @@ 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_dead_task (SIGKILL );return 1 ; }
arch/hexagon/kernel/traps.c +1 -1
@@ -214,7 +214,7 @@ int die(const char *str, struct pt_regs *regs, long err)panic ("Fatal exception" );oops_exit (); -do_exit (err); +make_dead_task (err);return 0 ; }
arch/ia64/kernel/mca_drv.c +1 -1
@@ -176,7 +176,7 @@ 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 ); }/**
arch/ia64/kernel/traps.c +1 -1
@@ -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 ; }
arch/ia64/mm/fault.c +1 -1
@@ -259,7 +259,7 @@ 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:
arch/m68k/kernel/traps.c +1 -1
@@ -1131,7 +1131,7 @@ 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)
arch/m68k/mm/fault.c +1 -1
@@ -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 ;
arch/microblaze/kernel/exceptions.c +2 -2
@@ -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 */
arch/mips/kernel/traps.c +1 -1
@@ -416,7 +416,7 @@ 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[];
arch/nds32/kernel/fpu.c +1 -1
@@ -223,7 +223,7 @@ inline void handle_fpu_exception(struct pt_regs *regs) } }else if (fpcsr & FPCSR_mskRIT) {if (!user_mode (regs)) -do_exit (SIGILL ); +make_task_dead (SIGILL ); si_signo =SIGILL ; }
arch/nds32/kernel/traps.c +4 -4
@@ -141,7 +141,7 @@ 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);
@@ -240,7 +240,7 @@ 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 ); }
@@ -251,7 +251,7 @@ 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 ); }
@@ -278,7 +278,7 @@ 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 ); }
arch/nios2/kernel/traps.c +2 -2
@@ -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)
arch/openrisc/kernel/traps.c +1 -1
@@ -212,7 +212,7 @@ 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 */
arch/parisc/kernel/traps.c +1 -1
@@ -268,7 +268,7 @@ 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 */
arch/powerpc/kernel/traps.c +4 -4
@@ -245,7 +245,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs,if (panic_on_oops)panic ("Fatal exception" ); -do_exit (signr); +make_task_dead (signr); }NOKPROBE_SYMBOL (oops_end);
@@ -792,9 +792,9 @@ int machine_check_generic(struct pt_regs *regs)void die_mce (const char *str,struct pt_regs *regs,long err) {/* -* The machine check wants to kill the interrupted context, but -* do_exit() checks for in_interrupt() and panics in that case, so -* exit the irq/nmi before calling die. +* The machine check wants to kill the interrupted context, +* but make_task_dead() checks for in_interrupt() and panics +* in that case, so exit the irq/nmi before calling die. */ if (in_nmi ())nmi_exit ();
arch/riscv/kernel/traps.c +1 -1
@@ -59,7 +59,7 @@ 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,unsigned long addr)
arch/riscv/mm/fault.c +1 -1
@@ -31,7 +31,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr,bust_spinlocks (0 );die (regs,"Oops" ); -do_exit (SIGKILL ); +make_task_dead (SIGKILL ); }static inline void no_context (struct pt_regs *regs,unsigned long addr)
arch/s390/kernel/dumpstack.c +1 -1
@@ -224,5 +224,5 @@ 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 ); }
arch/s390/kernel/nmi.c +1 -1
@@ -175,7 +175,7 @@ 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 ); } }
arch/sh/kernel/traps.c +1 -1
@@ -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)
arch/sparc/kernel/traps_32.c +1 -3
@@ -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)
arch/sparc/kernel/traps_64.c +1 -3
@@ -2559,9 +2559,7 @@ 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);
arch/x86/entry/entry_32.S +3 -3
@@ -1239,14 +1239,14 @@ SYM_CODE_START(asm_exc_nmi) SYM_CODE_END(asm_exc_nmi) .pushsection .text, "ax" -SYM_CODE_START(rewind_stack_do_exit) +SYM_CODE_START(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 -SYM_CODE_END(rewind_stack_do_exit) +SYM_CODE_END(rewind_stack_and_make_dead) .popsection
arch/x86/entry/entry_64.S +3 -3
@@ -1487,7 +1487,7 @@ SYM_CODE_END(ignore_sysret) #endif .pushsection .text, "ax" -SYM_CODE_START(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_and_make_dead) UNWIND_HINT_FUNC /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp
@@ -1496,6 +1496,6 @@ SYM_CODE_START(rewind_stack_do_exit) leaq -PTREGS_SIZE(%rax), %rsp UNWIND_HINT_REGS - call do_exit -SYM_CODE_END(rewind_stack_do_exit) + call make_task_dead +SYM_CODE_END(rewind_stack_and_make_dead) .popsection
arch/x86/kernel/dumpstack.c +2 -2
@@ -351,7 +351,7 @@ 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) {
@@ -386,7 +386,7 @@ 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);
arch/xtensa/kernel/traps.c +1 -1
@@ -552,5 +552,5 @@ 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); }
include/linux/sched/task.h +1 -0
@@ -59,6 +59,7 @@ extern void sched_post_fork(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 );
kernel/exit.c +9 -0
@@ -877,6 +877,15 @@ 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. +*/ +do_exit (signr); +} +void complete_and_exit (struct completion *comp,long code) {if (comp)
tools/objtool/check.c +2 -1
@@ -169,6 +169,7 @@ static bool __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" , "__reiserfs_panic",
@@ -176,7 +177,7 @@ static bool __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" "kunit_try_catch_throw" ,"xen_start_kernel" , "cpu_bringup_and_idle",
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 129/204 objtool: Add a missing comma to avoid string concatenation
In reply to Greg Kroah-HartmanFrom: Eric W. Biederman <[email protected]>
commit 1fb466dff904e4a72282af336f2c355f011eec61 upstream.
Recently the kbuild robot reported two new errors:
Quoted 2 lines
Quoted 2 lines
lib/kunit/kunit-example-test.o: warning: objtool: .text.unlikely: unexpected end of sectionarch/x86/kernel/dumpstack.o: warning: objtool:oops_end()falls through to next functionshow_opcodes()
I don't know why they did not occur in my test setup but after digging it I realized I had accidentally dropped a comma in tools/objtool/check.c when I renamed rewind_stack_do_exit to rewind_stack_and_make_dead.
Add that comma back to fix objtool errors.
--- tools/objtool/check.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/objtool/check.c +1 -1
@@ -177,7 +177,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,"fortify_panic" ,"usercopy_abort" ,"machine_real_restart" , -"rewind_stack_and_make_dead" +"rewind_stack_and_make_dead" ,"kunit_try_catch_throw" ,"xen_start_kernel" , "cpu_bringup_and_idle",
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 130/204 hexagon: Fix function name in die()
In reply to Greg Kroah-HartmanFrom: Nathan Chancellor <[email protected]>
commit 4f0712ccec09c071e221242a2db9a6779a55a949 upstream.
When building ARCH=hexagon defconfig:
arch/hexagon/kernel/traps.c:217:2: error: implicit declaration of function 'make_dead_task' [-Werror,-Wimplicit-function-declaration]
make_dead_task(err);
^The function's name is make_task_dead(), change it so there is no more build error.
--- arch/hexagon/kernel/traps.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/hexagon/kernel/traps.c +1 -1
@@ -214,7 +214,7 @@ int die(const char *str, struct pt_regs *regs, long err)panic ("Fatal exception" );oops_exit (); -make_dead_task (err); +make_task_dead (err);return 0 ; }
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 131/204 h8300: Fix build errors from do_exit() to make_task_dead() transition
In reply to Greg Kroah-HartmanFrom: Nathan Chancellor <[email protected]>
commit ab4ababdf77ccc56c7301c751dff49c79709c51c upstream.
When building ARCH=h8300 defconfig:
arch/h8300/kernel/traps.c: In function 'die':arch/h8300/kernel/traps.c:109:2: error: implicit declaration of function 'make_dead_task' [-Werror=implicit-function-declaration]
109 | make_dead_task(SIGSEGV);
| ^~~~~~~~~~~~~~arch/h8300/mm/fault.c: In function 'do_page_fault':arch/h8300/mm/fault.c:54:2: error: implicit declaration of function 'make_dead_task' [-Werror=implicit-function-declaration]
54 | make_dead_task(SIGKILL);
| ^~~~~~~~~~~~~~The function's name is make_task_dead(), change it so there is no more build error.
Additionally, include linux/sched/task.h in arch/h8300/kernel/traps.c to avoid the same error because do_exit()'s declaration is in kernel.h but make_task_dead()'s is in task.h, which is not included in traps.c.
--- arch/h8300/kernel/traps.c | 3 ++- arch/h8300/mm/fault.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-)
arch/h8300/kernel/traps.c +2 -1
@@ -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>
@@ -106,7 +107,7 @@ void die(const char *str, struct pt_regs *fp, unsigned long err)dump (fp);spin_unlock_irq (&die_lock); -make_dead_task (SIGSEGV ); +make_task_dead (SIGSEGV ); }static int kstack_depth_to_print =24 ;
arch/h8300/mm/fault.c +1 -1
@@ -51,7 +51,7 @@ 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); -make_dead_task (SIGKILL ); +make_task_dead (SIGKILL );return 1 ; }
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 132/204 csky: Fix function name in csky_alignment() and die()
In reply to Greg Kroah-HartmanFrom: Nathan Chancellor <[email protected]>
commit 751971af2e3615dc5bd12674080bc795505fefeb upstream.
When building ARCH=csky defconfig:
arch/csky/kernel/traps.c: In function 'die':arch/csky/kernel/traps.c:112:17: error: implicit declaration of function 'make_dead_task' [-Werror=implicit-function-declaration]
112 | make_dead_task(SIGSEGV);
| ^~~~~~~~~~~~~~The function's name is make_task_dead(), change it so there is no more build error.
--- arch/csky/abiv1/alignment.c | 2 +- arch/csky/kernel/traps.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
arch/csky/abiv1/alignment.c +1 -1
@@ -294,7 +294,7 @@ void csky_alignment(struct pt_regs *regs) __func__, opcode, rz, rx, imm, addr);show_regs (regs);bust_spinlocks (0 ); -make_dead_task (SIGKILL ); +make_task_dead (SIGKILL ); }force_sig_fault (SIGBUS ,BUS_ADRALN , (void __user *)addr);
arch/csky/kernel/traps.c +1 -1
@@ -109,7 +109,7 @@ void die(struct pt_regs *regs, const char *str)if (panic_on_oops)panic ("Fatal exception" );if (ret !=NOTIFY_STOP ) -make_dead_task (SIGSEGV ); +make_task_dead (SIGSEGV ); }void do_trap (struct pt_regs *regs,int signo,int code,unsigned long addr)
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 133/204 ia64: make IA64_MCA_RECOVERY bool instead of tristate
In reply to Greg Kroah-HartmanFrom: Randy Dunlap <[email protected]>
commit dbecf9b8b8ce580f4e11afed9d61e8aa294cddd2 upstream.
In linux-next, IA64_MCA_RECOVERY uses the (new) function make_task_dead(), which is not exported for use by modules. Instead of exporting it for one user, convert IA64_MCA_RECOVERY to be a bool Kconfig symbol.
In a config file from "kernel test robot <[email protected]>" for a different problem, this linker error was exposed when CONFIG_IA64_MCA_RECOVERY=m.
Fixes this build error:
ERROR: modpost: "make_task_dead" [arch/ia64/kernel/mca_recovery.ko] undefined!
--- arch/ia64/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/ia64/Kconfig +1 -1
@@ -323,7 +323,7 @@ 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 IA64_PALINFO tristate "/proc/pal support"
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 134/204 panic: Separate sysctl logic from CONFIG_SMP
In reply to Greg Kroah-HartmanFrom: Kees Cook <[email protected]>
commit 9360d035a579d95d1e76c471061b9065b18a0eb1 upstream.
In preparation for adding more sysctls directly in kernel/panic.c, split CONFIG_SMP from the logic that adds sysctls.
--- kernel/panic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
kernel/panic.c +3 -1
@@ -73,8 +73,9 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list);EXPORT_SYMBOL (panic_notifier_list); -#if defined(CONFIG_SMP) && defined(CONFIG_SYSCTL) +#ifdef CONFIG_SYSCTL static struct ctl_table kern_panic_table[] = { +#ifdef CONFIG_SMP { .procname = "oops_all_cpu_backtrace", .data = &sysctl_oops_all_cpu_backtrace,
@@ -84,6 +85,7 @@ static struct ctl_table kern_panic_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, +#endif { } };
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 135/204 exit: Put an upper limit on how often we can oops
In reply to Greg Kroah-HartmanFrom: Jann Horn <[email protected]>
commit d4ccd54d28d3c8598e2354acc13e28c060961dbb upstream.
Many Linux systems are configured to not panic on oops; but allowing an attacker to oops the system **really** often can make even bugs that look completely unexploitable exploitable (like NULL dereferences and such) if each crash elevates a refcount by one or a lock is taken in read mode, and this causes a counter to eventually overflow.
The most interesting counters for this are 32 bits wide (like open-coded refcounts that don't use refcount_t). (The ldsem reader count on 32-bit platforms is just 16 bits, but probably nobody cares about 32-bit platforms that much nowadays.)
So let's panic the system if the kernel is constantly oopsing.
The speed of oopsing 2^32 times probably depends on several factors, like how long the stack trace is and which unwinder you're using; an empirically important one is whether your console is showing a graphical environment or a text console that oopses will be printed to.
In a quick single-threaded benchmark, it looks like oopsing in a vfork() child with a very short stack trace only takes ~510 microseconds per run when a graphical console is active; but switching to a text console that oopses are printed to slows it down around 87x, to ~45 milliseconds per run.
(Adding more threads makes this faster, but the actual oops printing happens under &die_lock on x86, so you can maybe speed this up by a factor of around 2 and then any further improvement gets eaten up by lock contention.)
It looks like it would take around 8-12 days to overflow a 32-bit counter with repeated oopsing on a multi-core X86 system running a graphical environment; both me (in an X86 VM) and Seth (with a distro kernel on normal hardware in a standard configuration) got numbers in that ballpark.
12 days aren't *that* short on a desktop system, and you'd likely need much longer on a typical server system (assuming that people don't run graphical desktop environments on their servers), and this is a *very* noisy and violent approach to exploiting the kernel; and it also seems to take orders of magnitude longer on some machines, probably because stuff like EFI pstore will slow it down a ton if that's active.
--- Documentation/admin-guide/sysctl/kernel.rst | 8 ++++ kernel/exit.c | 43 +++++++++++++++++++++ 2 files changed, 51 insertions(+)
Documentation/admin-guide/sysctl/kernel.rst +8 -0
@@ -671,6 +671,14 @@ This is the default behavior. an oops event is detected. +oops_limit +========== + +Number of kernel oopses after which the kernel should panic when +``panic_on_oops`` is not set. Setting this to 0 or 1 has the same effect +as setting ``panic_on_oops=1``. + + osrelease, ostype & version ===========================
kernel/exit.c +43 -0
59 lines not on this page · raw message
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 136/204 exit: Expose "oops_count" to sysfs
In reply to Greg Kroah-HartmanFrom: Kees Cook <[email protected]>
commit 9db89b41117024f80b38b15954017fb293133364 upstream.
Since Oops count is now tracked and is a fairly interesting signal, add the entry /sys/kernel/oops_count to expose it to userspace.
--- .../ABI/testing/sysfs-kernel-oops_count | 6 +++++ kernel/exit.c | 22 +++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-oops_count
Documentation/ABI/testing/sysfs-kernel-oops_count new file +6 -0
@@ -0,0 +1,6 @@ +What: /sys/kernel/oops_count +Date: November 2022 +KernelVersion: 6.2.0 +Contact: Linux Kernel Hardening List <[email protected]> +Description: + Shows how many times the system has Oopsed since last boot.
kernel/exit.c +20 -2
@@ -64,6 +64,7 @@#include <linux/rcuwait.h> #include <linux/compat.h> #include <linux/io_uring.h> +#include <linux/sysfs.h> #include <linux/uaccess.h> #include <asm/unistd.h>
@@ -96,6 +97,25 @@ static __init int kernel_exit_sysctls_init(void)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--;
@@ -906,8 +926,6 @@ EXPORT_SYMBOL_GPL(do_exit);void __noreturn make_task_dead (int signr) { -static atomic_t oops_count =ATOMIC_INIT (0 ); -/* * Take the task off the cpu after something catastrophic has * happened.
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 137/204 exit: Allow oops_limit to be disabled
In reply to Greg Kroah-HartmanFrom: Kees Cook <[email protected]>
commit de92f65719cd672f4b48397540b9f9eff67eca40 upstream.
In preparation for keeping oops_limit logic in sync with warn_limit, have oops_limit == 0 disable checking the Oops counter.
--- Documentation/admin-guide/sysctl/kernel.rst | 5 +++-- kernel/exit.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-)
Documentation/admin-guide/sysctl/kernel.rst +3 -2
@@ -675,8 +675,9 @@ oops_limit ========== Number of kernel oopses after which the kernel should panic when -``panic_on_oops`` is not set. Setting this to 0 or 1 has the same effect -as setting ``panic_on_oops=1``. +``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
kernel/exit.c +1 -1
@@ -941,7 +941,7 @@ void __noreturn make_task_dead(int signr)* To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ -if (atomic_inc_return (&oops_count) >=READ_ONCE (oops_limit)) +if (atomic_inc_return (&oops_count) >=READ_ONCE (oops_limit) && oops_limit)panic ("Oopsed too often (kernel.oops_limit is %d)" , oops_limit);do_exit (signr);
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 138/204 panic: Consolidate open-coded panic_on_warn checks
In reply to Greg Kroah-HartmanFrom: Kees Cook <[email protected]>
commit 79cc1ba7badf9e7a12af99695a557e9ce27ee967 upstream.
Several run-time checkers (KASAN, UBSAN, KFENCE, KCSAN, sched) roll their own warnings, and each check "panic_on_warn". Consolidate this into a single function so that future instrumentation can be added in a single location.
--- include/linux/panic.h | 1 + kernel/kcsan/report.c | 3 +-- kernel/panic.c | 9 +++++++-- kernel/sched/core.c | 3 +-- lib/ubsan.c | 3 +-- mm/kasan/report.c | 4 ++-- mm/kfence/report.c | 3 +-- 7 files changed, 14 insertions(+), 12 deletions(-)
include/linux/panic.h +1 -0
@@ -11,6 +11,7 @@ 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 );extern bool oops_may_print (void );
kernel/kcsan/report.c +1 -2
@@ -432,8 +432,7 @@ static void print_report(enum kcsan_value_change value_change,dump_stack_print_info (KERN_DEFAULT );pr_err ("==================================================================\n" ); -if (panic_on_warn) -panic ("panic_on_warn set ...\n" ); +check_panic_on_warn ("KCSAN" ); }static void release_report (unsigned long *flags,struct other_info *other_info)
kernel/panic.c +7 -2
@@ -193,6 +193,12 @@ static void panic_print_sys_info(void)ftrace_dump (DUMP_ALL ); } +void check_panic_on_warn (const char *origin) +{ +if (panic_on_warn) +panic ("%s: panic_on_warn set ...\n" , origin); +} +/** * panic - halt the system * @fmt: The text string to print
@@ -628,8 +634,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,if (regs)show_regs (regs); -if (panic_on_warn) -panic ("panic_on_warn set ...\n" ); +check_panic_on_warn ("kernel" );if (!regs)dump_stack ();
kernel/sched/core.c +1 -2
@@ -5560,8 +5560,7 @@ static noinline void __schedule_bug(struct task_struct *prev)pr_err ("Preemption disabled at:" );print_ip_sym (KERN_ERR , preempt_disable_ip); } -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 );
lib/ubsan.c +1 -2
@@ -154,8 +154,7 @@ static void ubsan_epilogue(void) current->in_ubsan--; -if (panic_on_warn) -panic ("panic_on_warn set ...\n" ); +check_panic_on_warn ("UBSAN" ); }void __ubsan_handle_divrem_overflow (void *_data,void *lhs,void *rhs)
mm/kasan/report.c +2 -2
@@ -117,8 +117,8 @@ static void end_report(unsigned long *flags, unsigned long addr)pr_err ("==================================================================\n" );add_taint (TAINT_BAD_PAGE ,LOCKDEP_NOW_UNRELIABLE );spin_unlock_irqrestore (&report_lock, *flags); -if (panic_on_warn && !test_bit (KASAN_BIT_MULTI_SHOT , &kasan_flags)) -panic ("panic_on_warn set ...\n" ); +if (!test_bit (KASAN_BIT_MULTI_SHOT , &kasan_flags)) +check_panic_on_warn ("KASAN" );if (kasan_arg_fault ==KASAN_ARG_FAULT_PANIC )panic ("kasan.fault=panic set ...\n" );kasan_enable_current ();
mm/kfence/report.c +1 -2
@@ -267,8 +267,7 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *rlockdep_on (); -if (panic_on_warn) -panic ("panic_on_warn set ...\n" ); +check_panic_on_warn ("KFENCE" );/* We encountered a memory safety error, taint the kernel! */ add_taint (TAINT_BAD_PAGE ,LOCKDEP_STILL_OK );
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 139/204 panic: Introduce warn_limit
In reply to Greg Kroah-HartmanFrom: Kees Cook <[email protected]>
commit 9fc9e278a5c0b708eeffaf47d6eb0c82aa74ed78 upstream.
Like oops_limit, add warn_limit for limiting the number of warnings when panic_on_warn is not set.
--- Documentation/admin-guide/sysctl/kernel.rst | 10 ++++++++++ kernel/panic.c | 14 ++++++++++++++ 2 files changed, 24 insertions(+)
Documentation/admin-guide/sysctl/kernel.rst +10 -0
@@ -1494,6 +1494,16 @@ entry will default to 2 instead of 0. 2 Unprivileged calls to ``bpf()`` are disabled = ============================================================= + +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 ========
kernel/panic.c +14 -0
@@ -57,6 +57,7 @@ bool crash_kexec_post_notifiers;int panic_on_warn__read_mostly ;unsigned long panic_on_taint;bool panic_on_taint_nousertaint = false; +static unsigned int warn_limit__read_mostly ;int panic_timeout =CONFIG_PANIC_TIMEOUT ;EXPORT_SYMBOL_GPL (panic_timeout);
@@ -86,6 +87,13 @@ static struct ctl_table kern_panic_table[] = { .extra2 = SYSCTL_ONE, },#endif + { + .procname = "warn_limit", + .data = &warn_limit, + .maxlen = sizeof(warn_limit), + .mode = 0644, + .proc_handler = proc_douintvec, + }, { } };
@@ -195,8 +203,14 @@ static void panic_print_sys_info(void)void check_panic_on_warn (const char *origin) { +static atomic_t warn_count =ATOMIC_INIT (0 ); +if (panic_on_warn)panic ("%s: panic_on_warn set ...\n" , origin); + +if (atomic_inc_return (&warn_count) >=READ_ONCE (warn_limit) && warn_limit) +panic ("%s: system warned too often (kernel.warn_limit is %d)" , + origin, warn_limit); }/**
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 140/204 panic: Expose "warn_count" to sysfs
In reply to Greg Kroah-HartmanFrom: Kees Cook <[email protected]>
commit 8b05aa26336113c4cea25f1c333ee8cd4fc212a6 upstream.
Since Warn count is now tracked and is a fairly interesting signal, add the entry /sys/kernel/warn_count to expose it to userspace.
--- .../ABI/testing/sysfs-kernel-warn_count | 6 +++++ kernel/panic.c | 22 +++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-warn_count
Documentation/ABI/testing/sysfs-kernel-warn_count new file +6 -0
@@ -0,0 +1,6 @@ +What: /sys/kernel/oops_count +Date: November 2022 +KernelVersion: 6.2.0 +Contact: Linux Kernel Hardening List <[email protected]> +Description: + Shows how many times the system has Warned since last boot.
kernel/panic.c +20 -2
@@ -32,6 +32,7 @@#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
@@ -105,6 +106,25 @@ static __init int kernel_panic_sysctls_init(void)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 ;
@@ -203,8 +223,6 @@ static void panic_print_sys_info(void)void check_panic_on_warn (const char *origin) { -static atomic_t warn_count =ATOMIC_INIT (0 ); -if (panic_on_warn)panic ("%s: panic_on_warn set ...\n" , origin);
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 141/204 docs: Fix path paste-o for /sys/kernel/warn_count
In reply to Greg Kroah-HartmanFrom: Kees Cook <[email protected]>
commit 00dd027f721e0458418f7750d8a5a664ed3e5994 upstream.
Running "make htmldocs" shows that "/sys/kernel/oops_count" was duplicated. This should have been "warn_count":
Warning: /sys/kernel/oops_count is defined 2 times:
./Documentation/ABI/testing/sysfs-kernel-warn_count:0 ./Documentation/ABI/testing/sysfs-kernel-oops_count:0
Fix the typo.
--- Documentation/ABI/testing/sysfs-kernel-warn_count | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
Documentation/ABI/testing/sysfs-kernel-warn_count +1 -1
@@ -1,4 +1,4 @@ -What: /sys/kernel/oops_count +What: /sys/kernel/warn_count Date: November 2022 KernelVersion: 6.2.0 Contact: Linux Kernel Hardening List <[email protected]>
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 142/204 exit: Use READ_ONCE() for all oops/warn limit reads
In reply to Greg Kroah-HartmanFrom: Kees Cook <[email protected]>
commit 7535b832c6399b5ebfc5b53af5c51dd915ee2538 upstream.
Use a temporary variable to take full advantage of READ_ONCE() behavior. Without this, the report (and even the test) might be out of sync with the initial test.
--- kernel/exit.c | 6 ++++-- kernel/panic.c | 7 +++++-- 2 files changed, 9 insertions(+), 4 deletions(-)
kernel/exit.c +4 -2
@@ -930,6 +930,7 @@ 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
@@ -941,8 +942,9 @@ void __noreturn make_task_dead(int signr)* To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ -if (atomic_inc_return (&oops_count) >=READ_ONCE (oops_limit) && oops_limit) -panic ("Oopsed too often (kernel.oops_limit is %d)" , oops_limit); + 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); }
kernel/panic.c +5 -2
@@ -223,12 +223,15 @@ static void panic_print_sys_info(void)void check_panic_on_warn (const char *origin) { +unsigned int limit; +if (panic_on_warn)panic ("%s: panic_on_warn set ...\n" , origin); -if (atomic_inc_return (&warn_count) >=READ_ONCE (warn_limit) && warn_limit) + 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, warn_limit); + origin, limit); }/**
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 143/204 Bluetooth: hci_sync: cancel cmd_timer if hci_open failed
In reply to Greg Kroah-HartmanFrom: Archie Pusaka <[email protected]>
commit 97dfaf073f5881c624856ef293be307b6166115c upstream.
If a command is already sent, we take care of freeing it, but we also need to cancel the timeout as well.
--- net/bluetooth/hci_core.c | 1 + 1 file changed, 1 insertion(+)
net/bluetooth/hci_core.c +1 -0
@@ -1632,6 +1632,7 @@ 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 ; }
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 144/204 drm/amdgpu: complete gfxoff allow signal during suspend without delay
In reply to Greg Kroah-HartmanFrom: Harsh Jain <[email protected]>
commit 4b31b92b143f7d209f3d494c56d4c4673e9fc53d upstream.
change guarantees that gfxoff is allowed before moving further in s2idle sequence to add more reliablity about gfxoff in amdgpu IP's suspend flow
--- drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +7 -3
@@ -580,10 +580,14 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_dif (adev->gfx.gfx_off_req_count ==0 && !adev->gfx.gfx_off_state) {/* If going to s2idle, no need to wait */ -if (adev->in_s0ix) - delay =GFX_OFF_NO_DELAY ; -schedule_delayed_work (&adev->gfx.gfx_off_delay_work, +if (adev->in_s0ix) { +if (!amdgpu_dpm_set_powergating_by_smu (adev, +AMD_IP_BLOCK_TYPE_GFX , true)) + adev->gfx.gfx_off_state = true; + }else { +schedule_delayed_work (&adev->gfx.gfx_off_delay_work, delay); + } } }else {if (adev->gfx.gfx_off_req_count ==0 ) {
Greg Kroah-Hartman
maintainerPATCH 145/204 scsi: hpsa: Fix allocation size for scsi_host_alloc()
In reply to Greg Kroah-HartmanFrom: Alexey V. Vissarionov <[email protected]>
[ Upstream commit bbbd25499100c810ceaf5193c3cfcab9f7402a33 ]
The 'h' is a pointer to struct ctlr_info, so it's just 4 or 8 bytes, while the structure itself is much bigger.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
--- drivers/scsi/hpsa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/scsi/hpsa.c +1 -1
@@ -5848,7 +5848,7 @@ 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 ;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 146/204 KVM: SVM: fix tsc scaling cache logic
In reply to Greg Kroah-HartmanFrom: Maxim Levitsky <[email protected]>
[ Upstream commit 11d39e8cc43e1c6737af19ca9372e590061b5ad2 ]
SVM uses a per-cpu variable to cache the current value of the tsc scaling multiplier msr on each cpu.
Commit 1ab9287add5e2
("KVM: X86: Add vendor callbacks for writing the TSC multiplier") broke this caching logic.
Refactor the code so that all TSC scaling multiplier writes go through a single function which checks and updates the cache.
This fixes the following scenario:
1. A CPU runs a guest with some tsc scaling ratio.
2. New guest with different tsc scaling ratio starts on this CPU and terminates almost immediately.
This ensures that the short running guest had set the tsc scaling ratio just once when it was set via KVM_SET_TSC_KHZ. Due to the bug,
the per-cpu cache is not updated.
3. The original guest continues to run, it doesn't restore the msr value back to its own value, because the cache matches, and thus continues to run with a wrong tsc scaling ratio.
Message-Id: <[email protected]>
--- arch/x86/kvm/svm/svm.c | 34 +++++++++++++++++++++++----------- arch/x86/kvm/svm/svm.h | 1 + 2 files changed, 24 insertions(+), 11 deletions(-)
arch/x86/kvm/svm/svm.c +23 -11
@@ -465,11 +465,24 @@ static int has_svm(void)return 1 ; } +void __svm_write_tsc_multiplier (u64 multiplier) +{ +preempt_disable (); + +if (multiplier ==__this_cpu_read (current_tsc_ratio)) + goto out; + +wrmsrl (MSR_AMD64_TSC_RATIO , multiplier); +__this_cpu_write (current_tsc_ratio, multiplier); +out: +preempt_enable (); +} +static void svm_hardware_disable (void ) {/* Make sure we clean up behind us */ if (static_cpu_has (X86_FEATURE_TSCRATEMSR )) -wrmsrl (MSR_AMD64_TSC_RATIO ,TSC_RATIO_DEFAULT ); +__svm_write_tsc_multiplier (TSC_RATIO_DEFAULT );cpu_svm_disable ();
@@ -511,8 +524,11 @@ static int svm_hardware_enable(void)wrmsrl (MSR_VM_HSAVE_PA ,__sme_page_pa (sd->save_area));if (static_cpu_has (X86_FEATURE_TSCRATEMSR )) { -wrmsrl (MSR_AMD64_TSC_RATIO ,TSC_RATIO_DEFAULT ); -__this_cpu_write (current_tsc_ratio,TSC_RATIO_DEFAULT ); +/* +* Set the default value, even if we don't use TSC scaling +* to avoid having stale value in the msr +*/ +__svm_write_tsc_multiplier (TSC_RATIO_DEFAULT ); }
@@ -1125,9 +1141,10 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)static void svm_write_tsc_multiplier (struct kvm_vcpu *vcpu,u64 multiplier) { -wrmsrl (MSR_AMD64_TSC_RATIO , multiplier); +__svm_write_tsc_multiplier (multiplier); } +/* Evaluate instruction intercepts that depend on guest CPUID features. */ static void svm_recalc_instruction_intercepts (struct kvm_vcpu *vcpu,struct vcpu_svm *svm)
@@ -1451,13 +1468,8 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)vmsave (__sme_page_pa (sd->save_area)); } -if (static_cpu_has (X86_FEATURE_TSCRATEMSR )) { -u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio; -if (tsc_ratio !=__this_cpu_read (current_tsc_ratio)) { -__this_cpu_write (current_tsc_ratio, tsc_ratio); -wrmsrl (MSR_AMD64_TSC_RATIO , tsc_ratio); - } - } +if (static_cpu_has (X86_FEATURE_TSCRATEMSR )) +__svm_write_tsc_multiplier (vcpu->arch.tsc_scaling_ratio);if (likely (tsc_aux_uret_slot >=0 ))kvm_set_user_return_msr (tsc_aux_uret_slot, svm->tsc_aux,-1ull );
arch/x86/kvm/svm/svm.h +1 -0
@@ -487,6 +487,7 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,int nested_svm_exit_special (struct vcpu_svm *svm);void nested_load_control_from_vmcb12 (struct vcpu_svm *svm,struct vmcb_control_area *control); +void __svm_write_tsc_multiplier (u64 multiplier);void nested_sync_control_from_vmcb02 (struct vcpu_svm *svm);void nested_vmcb02_compute_g_pat (struct vcpu_svm *svm);void svm_switch_vmcb (struct vcpu_svm *svm,struct kvm_vmcb_info *target_vmcb);
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 147/204 module: Dont wait for GOING modules
In reply to Greg Kroah-HartmanFrom: Petr Pavlu <[email protected]>
commit 0254127ab977e70798707a7a2b757c9f3c971210 upstream.
During a system boot, it can happen that the kernel receives a burst of requests to insert the same module but loading it eventually fails during its init call. For instance, udev can make a request to insert a frequency module for each individual CPU when another frequency module is already loaded which causes the init function of the new module to return an error.
Since commit 6e6de3dee51a ("kernel/module.c: Only return -EEXIST for modules that have finished loading"), the kernel waits for modules in MODULE_STATE_GOING state to finish unloading before making another attempt to load the same module.
This creates unnecessary work in the described scenario and delays the boot. In the worst case, it can prevent udev from loading drivers for other devices and might cause timeouts of services waiting on them and subsequently a failed boot.
This patch attempts a different solution for the problem 6e6de3dee51a was trying to solve. Rather than waiting for the unloading to complete, it returns a different error code (-EBUSY) for modules in the GOING state. This should avoid the error situation that was described in 6e6de3dee51a (user space attempting to load a dependent module because the -EEXIST error code would suggest to user space that the first module had been loaded successfully), while avoiding the delay situation too.
This has been tested on linux-next since December 2022 and passes all kmod selftests except test 0009 with module compression enabled but it has been confirmed that this issue has existed and has gone unnoticed since prior to this commit and can also be reproduced without module compression with a simple usleep(5000000) on tools/modprobe.c [0]. These failures are caused by hitting the kernel mod_concurrent_max and can happen either due to a self inflicted kernel module auto-loead DoS somehow or on a system with large CPU count and each CPU count incorrectly triggering many module auto-loads. Both of those issues need to be fixed in-kernel.
[0] https://lore.kernel.org/all/Y9A4fiobL6IHp%2F%[email protected]/
--- kernel/module.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-)
kernel/module.c +21 -5
@@ -3665,7 +3665,8 @@ static bool finished_loading(const charsched_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;
@@ -3835,20 +3836,35 @@ static int add_unformed_module(struct mo 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);
Greg Kroah-Hartman
maintainerPATCH 148/204 tracing: Make sure trace_printk() can output as soon as it can be used
In reply to Greg Kroah-HartmanFrom: Steven Rostedt (Google) <[email protected]>
commit 3bb06eb6e9acf7c4a3e1b5bc87aed398ff8e2253 upstream.
Currently trace_printk() can be used as soon as early_trace_init() is called from start_kernel(). But if a crash happens, and "ftrace_dump_on_oops" is set on the kernel command line, all you get will be:
[ 0.456075] <idle>-0 0dN.2. 347519us : Unknown type 6 [ 0.456075] <idle>-0 0dN.2. 353141us : Unknown type 6 [ 0.456075] <idle>-0 0dN.2. 358684us : Unknown type 6
This is because the trace_printk() event (type 6) hasn't been registered yet. That gets done via an early_initcall(), which may be early, but not early enough.
Instead of registering the trace_printk() event (and other ftrace events, which are not trace events) via an early_initcall(), have them registered at the same time that trace_printk() can be used. This way, if there is a crash before early_initcall(), then the trace_printk()s will actually be useful.
--- kernel/trace/trace.c | 2 ++ kernel/trace/trace.h | 1 + kernel/trace/trace_output.c | 3 +-- 3 files changed, 4 insertions(+), 2 deletions(-)
kernel/trace/trace.c +2 -0
@@ -10217,6 +10217,8 @@ void __init early_trace_init(void)static_key_enable (&tracepoint_printk_key.key); }tracer_alloc_buffers (); + +init_events (); }void __init trace_init (void )
kernel/trace/trace.h +1 -0
@@ -1500,6 +1500,7 @@ extern void trace_event_enable_cmd_recorextern 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);extern void __trace_early_add_events (struct trace_array *tr);
kernel/trace/trace_output.c +1 -2
@@ -1569,7 +1569,7 @@ static struct trace_event *events[] __in NULL }; -__init static int init_events (void ) +__init int init_events (void ) {struct trace_event *event;int i, ret;
@@ -1587,4 +1587,3 @@ __init static int init_events(void)return 0 ; } -early_initcall (init_events);
Greg Kroah-Hartman
maintainerPATCH 149/204 trace_events_hist: add check for return value of create_hist_field
In reply to Greg Kroah-HartmanFrom: Natalia Petrova <[email protected]>
commit 8b152e9150d07a885f95e1fd401fc81af202d9a4 upstream.
Function 'create_hist_field' is called recursively at trace_events_hist.c:1954 and can return NULL-value that's why we have to check it to avoid null pointer dereference.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
--- kernel/trace/trace_events_hist.c | 2 ++ 1 file changed, 2 insertions(+)
kernel/trace/trace_events_hist.c +2 -0
@@ -1699,6 +1699,8 @@ static struct hist_field *create_hist_fi hist_field->fn = flags &HIST_FIELD_FL_LOG2 ? hist_field_log2 : hist_field_bucket; 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_const (hist_field->operands[0 ]->type,GFP_KERNEL );if (!hist_field->type)
Greg Kroah-Hartman
maintainerPATCH 150/204 ftrace/scripts: Update the instructions for ftrace-bisect.sh
In reply to Greg Kroah-HartmanFrom: Steven Rostedt (Google) <[email protected]>
commit 7ae4ba7195b1bac04a4210a499da9d8c63b0ba9c upstream.
The instructions for the ftrace-bisect.sh script, which is used to find what function is being traced that is causing a kernel crash, and possibly a triple fault reboot, uses the old method. In 5.1, a new feature was added that let the user write in the index into available_filter_functions that maps to the function a user wants to set in set_ftrace_filter (or set_ftrace_notrace). This takes O(1) to set, as suppose to writing a function name, which takes O(n) (where n is the number of functions in available_filter_functions).
The ftrace-bisect.sh requires setting half of the functions in available_filter_functions, which is O(n^2) using the name method to enable and can take several minutes to complete. The number method is O(n) which takes less than a second to complete. Using the number method for any kernel 5.1 and after is the proper way to do the bisect.
Update the usage to reflect the new change, as well as using the /sys/kernel/tracing path instead of the obsolete debugfs path.
--- scripts/tracing/ftrace-bisect.sh | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-)
scripts/tracing/ftrace-bisect.sh +26 -8
@@ -12,7 +12,7 @@ # (note, if this is a problem with function_graph tracing, then simply # replace "function" with "function_graph" in the following steps). # -# # cd /sys/kernel/debug/tracing +# # cd /sys/kernel/tracing # # echo schedule > set_ftrace_filter # # echo function > current_tracer #
@@ -20,22 +20,40 @@ # # # echo nop > current_tracer # -# # cat available_filter_functions > ~/full-file +# Starting with v5.1 this can be done with numbers, making it much faster: +# +# The old (slow) way, for kernels before v5.1. +# +# [old-way] # cat available_filter_functions > ~/full-file +# +# [old-way] *** Note *** this process will take several minutes to update the +# [old-way] filters. Setting multiple functions is an O(n^2) operation, and we +# [old-way] are dealing with thousands of functions. So go have coffee, talk +# [old-way] with your coworkers, read facebook. And eventually, this operation +# [old-way] will end. +# +# The new way (using numbers) is an O(n) operation, and usually takes less than a second. +# +# seq `wc -l available_filter_functions | cut -d' ' -f1` > ~/full-file +# +# This will create a sequence of numbers that match the functions in +# available_filter_functions, and when echoing in a number into the +# set_ftrace_filter file, it will enable the corresponding function in +# O(1) time. Making enabling all functions O(n) where n is the number of +# functions to enable. +# +# For either the new or old way, the rest of the operations remain the same. +# # # ftrace-bisect ~/full-file ~/test-file ~/non-test-file # # cat ~/test-file > set_ftrace_filter # -# *** Note *** this will take several minutes. Setting multiple functions is -# an O(n^2) operation, and we are dealing with thousands of functions. So go -# have coffee, talk with your coworkers, read facebook. And eventually, this -# operation will end. -# # # echo function > current_tracer # # If it crashes, we know that ~/test-file has a bad function. # # Reboot back to test kernel. # -# # cd /sys/kernel/debug/tracing +# # cd /sys/kernel/tracing # # mv ~/test-file ~/full-file # # If it didn't crash.
Greg Kroah-Hartman
maintainerPATCH 151/204 cifs: Fix oops due to uncleared server->smbd_conn in reconnect
In reply to Greg Kroah-HartmanFrom: David Howells <[email protected]>
commit b7ab9161cf5ddc42a288edf9d1a61f3bdffe17c7 upstream.
In smbd_destroy(), clear the server->smbd_conn pointer after freeing the smbd_connection struct that it points to so that reconnection doesn't get confused.
--- fs/cifs/smbdirect.c | 1 + 1 file changed, 1 insertion(+)
fs/cifs/smbdirect.c +1 -0
@@ -1405,6 +1405,7 @@ void smbd_destroy(struct TCP_Server_Infodestroy_workqueue (info->workqueue);log_rdma_event (INFO ,"rdma session destroyed\n" );kfree (info); + server->smbd_conn =NULL ; }/*
Greg Kroah-Hartman
maintainerPATCH 152/204 i2c: mv64xxx: Remove shutdown method from driver
In reply to Greg Kroah-HartmanFrom: Chris Morgan <[email protected]>
commit 09b343038e3470e4d0da45f0ee09fb42107e5314 upstream.
When I attempt to shut down (or reboot) my R8 based NTC CHIP with this i2c driver I get the following error: "i2c i2c-0: mv64xxx: I2C bus locked, block: 1, time_left: 0". Reboots are successful but shutdowns freeze. If I comment out the shutdown routine the device both reboots and shuts down successfully without receiving this error (however it does receive a warning of missing atomic_xfer).
It appears that very few i2c drivers have a shutdown method, I assume because these devices are often used to communicate with PMICs (such as in my case with the R8 based NTC CHIP). I'm proposing we simply remove this method so long as it doesn't cause trouble for others downstream. I'll work on an atomic_xfer method and submit that in a different patch.
--- drivers/i2c/busses/i2c-mv64xxx.c | 9 --------- 1 file changed, 9 deletions(-)
drivers/i2c/busses/i2c-mv64xxx.c +0 -9
@@ -1047,14 +1047,6 @@ mv64xxx_i2c_remove(struct platform_devicreturn 0 ; } -static void -mv64xxx_i2c_shutdown (struct platform_device *pd) -{ -pm_runtime_disable (&pd->dev); -if (!pm_runtime_status_suspended (&pd->dev)) -mv64xxx_i2c_runtime_suspend (&pd->dev); -} -static const struct dev_pm_ops mv64xxx_i2c_pm_ops = {SET_RUNTIME_PM_OPS (mv64xxx_i2c_runtime_suspend, mv64xxx_i2c_runtime_resume,NULL )
@@ -1065,7 +1057,6 @@ static const struct dev_pm_ops mv64xxx_istatic struct platform_driver mv64xxx_i2c_driver = { .probe = mv64xxx_i2c_probe, .remove = mv64xxx_i2c_remove, - .shutdown = mv64xxx_i2c_shutdown, .driver = { .name =MV64XXX_I2C_CTLR_NAME , .pm = &mv64xxx_i2c_pm_ops,
Greg Kroah-Hartman
maintainerPATCH 153/204 i2c: mv64xxx: Add atomic_xfer method to driver
In reply to Greg Kroah-HartmanFrom: Chris Morgan <[email protected]>
commit 544a8d75f3d6e60e160cd92dc56321484598a993 upstream.
Add an atomic_xfer method to the driver so that it behaves correctly when controlling a PMIC that is responsible for device shutdown.
The atomic_xfer method added is similar to the one from the i2c-rk3x driver. When running an atomic_xfer a bool flag in the driver data is set, the interrupt is not unmasked on transfer start, and the IRQ handler is manually invoked while waiting for pending transfers to complete.
--- drivers/i2c/busses/i2c-mv64xxx.c | 52 ++++++++++++++++++++++++++++++++++----- 1 file changed, 46 insertions(+), 6 deletions(-)
drivers/i2c/busses/i2c-mv64xxx.c +46 -6
@@ -150,6 +150,7 @@ struct mv64xxx_i2c_data {/* Clk div is 2 to the power n, not 2 to the power n + 1 */ bool clk_n_base_0;struct i2c_bus_recovery_info rinfo; +bool atomic; };static struct mv64xxx_i2c_regs mv64xxx_i2c_regs_mv64xxx = {
@@ -179,7 +180,10 @@ mv64xxx_i2c_prepare_for_io(struct mv64xxu32 dir =0 ; drv_data->cntl_bits =MV64XXX_I2C_REG_CONTROL_ACK | -MV64XXX_I2C_REG_CONTROL_INTEN |MV64XXX_I2C_REG_CONTROL_TWSIEN ; +MV64XXX_I2C_REG_CONTROL_TWSIEN ; + +if (!drv_data->atomic) + drv_data->cntl_bits |=MV64XXX_I2C_REG_CONTROL_INTEN ;if (msg->flags &I2C_M_RD ) dir =1 ;
@@ -409,7 +413,8 @@ mv64xxx_i2c_do_action(struct mv64xxx_i2ccase MV64XXX_I2C_ACTION_RCV_DATA_STOP : drv_data->msg->buf[drv_data->byte_posn++] =readl (drv_data->reg_base + drv_data->reg_offsets.data); - drv_data->cntl_bits &= ~MV64XXX_I2C_REG_CONTROL_INTEN ; +if (!drv_data->atomic) + drv_data->cntl_bits &= ~MV64XXX_I2C_REG_CONTROL_INTEN ;writel (drv_data->cntl_bits |MV64XXX_I2C_REG_CONTROL_STOP , drv_data->reg_base + drv_data->reg_offsets.control); drv_data->block =0 ;
@@ -427,7 +432,8 @@ mv64xxx_i2c_do_action(struct mv64xxx_i2c drv_data->rc = -EIO ; fallthrough;case MV64XXX_I2C_ACTION_SEND_STOP : - drv_data->cntl_bits &= ~MV64XXX_I2C_REG_CONTROL_INTEN ; +if (!drv_data->atomic) + drv_data->cntl_bits &= ~MV64XXX_I2C_REG_CONTROL_INTEN ;writel (drv_data->cntl_bits |MV64XXX_I2C_REG_CONTROL_STOP , drv_data->reg_base + drv_data->reg_offsets.control); drv_data->block =0 ;
@@ -575,6 +581,17 @@ mv64xxx_i2c_wait_for_completion(struct mspin_unlock_irqrestore (&drv_data->lock, flags); } +static void mv64xxx_i2c_wait_polling (struct mv64xxx_i2c_data *drv_data) +{ +ktime_t timeout =ktime_add_ms (ktime_get (), drv_data->adapter.timeout); + +while (READ_ONCE (drv_data->block) && +ktime_compare (ktime_get (), timeout) <0 ) { +udelay (5 ); +mv64xxx_i2c_intr (0 , drv_data); + } +} +static int mv64xxx_i2c_execute_msg (struct mv64xxx_i2c_data *drv_data,struct i2c_msg *msg,int is_last)
@@ -590,7 +607,11 @@ mv64xxx_i2c_execute_msg(struct mv64xxx_imv64xxx_i2c_send_start (drv_data);spin_unlock_irqrestore (&drv_data->lock, flags); -mv64xxx_i2c_wait_for_completion (drv_data); +if (!drv_data->atomic) +mv64xxx_i2c_wait_for_completion (drv_data); +else +mv64xxx_i2c_wait_polling (drv_data); +return drv_data->rc; }
@@ -717,7 +738,7 @@ mv64xxx_i2c_functionality(struct i2c_ada }static int -mv64xxx_i2c_xfer (struct i2c_adapter *adap,struct i2c_msg msgs[],int num) +mv64xxx_i2c_xfer_core (struct i2c_adapter *adap,struct i2c_msg msgs[],int num) {struct mv64xxx_i2c_data *drv_data =i2c_get_adapdata (adap);int rc, ret = num;
@@ -730,7 +751,7 @@ mv64xxx_i2c_xfer(struct i2c_adapter *ada drv_data->msgs = msgs; drv_data->num_msgs = num; -if (mv64xxx_i2c_can_offload (drv_data)) +if (mv64xxx_i2c_can_offload (drv_data) && !drv_data->atomic) rc =mv64xxx_i2c_offload_xfer (drv_data);else rc =mv64xxx_i2c_execute_msg (drv_data, &msgs[0 ], num ==1 );
@@ -747,8 +768,27 @@ mv64xxx_i2c_xfer(struct i2c_adapter *adareturn ret; } +static int +mv64xxx_i2c_xfer (struct i2c_adapter *adap,struct i2c_msg msgs[],int num) +{ +struct mv64xxx_i2c_data *drv_data =i2c_get_adapdata (adap); + + drv_data->atomic =0 ; +return mv64xxx_i2c_xfer_core (adap, msgs, num); +} + +static int mv64xxx_i2c_xfer_atomic (struct i2c_adapter *adap, +struct i2c_msg msgs[],int num) +{ +struct mv64xxx_i2c_data *drv_data =i2c_get_adapdata (adap); + + drv_data->atomic =1 ; +return mv64xxx_i2c_xfer_core (adap, msgs, num); +} +static const struct i2c_algorithm mv64xxx_i2c_algo = { .master_xfer = mv64xxx_i2c_xfer, + .master_xfer_atomic = mv64xxx_i2c_xfer_atomic, .functionality = mv64xxx_i2c_functionality, };
Greg Kroah-Hartman
maintainerPATCH 154/204 ksmbd: add smbd max io size parameter
In reply to Greg Kroah-HartmanFrom: Namjae Jeon <[email protected]>
commit 65bb45b97b578c8eed1ffa80caec84708df49729 upstream.
Add 'smbd max io size' parameter to adjust smbd-direct max read/write size.
--- fs/ksmbd/ksmbd_netlink.h | 3 ++- fs/ksmbd/transport_ipc.c | 3 +++ fs/ksmbd/transport_rdma.c | 8 +++++++- fs/ksmbd/transport_rdma.h | 6 ++++++ 4 files changed, 18 insertions(+), 2 deletions(-)
fs/ksmbd/ksmbd_netlink.h +2 -1
@@ -104,7 +104,8 @@ struct ksmbd_startup_request {*/ __u32 sub_auth[3 ];/* Subauth value for Security ID */ __u32 smb2_max_credits;/* MAX credits */ -__u32 reserved[128 ];/* Reserved room */ +__u32 smbd_max_io_size;/* smbd read write size */ +__u32 reserved[127 ];/* Reserved room */ __u32 ifc_list_sz;/* interfaces list size */ __s8 ____payload[]; };
fs/ksmbd/transport_ipc.c +3 -0
@@ -26,6 +26,7 @@#include "mgmt/ksmbd_ida.h" #include "connection.h" #include "transport_tcp.h" +#include "transport_rdma.h" #define IPC_WAIT_TIMEOUT (2 * HZ)
@@ -303,6 +304,8 @@ static int ipc_server_config_on_startup(init_smb2_max_trans_size (req->smb2_max_trans);if (req->smb2_max_credits)init_smb2_max_credits (req->smb2_max_credits); +if (req->smbd_max_io_size) +init_smbd_max_io_size (req->smbd_max_io_size); ret =ksmbd_set_netbios_name (req->netbios_name); ret |=ksmbd_set_server_string (req->server_string);
fs/ksmbd/transport_rdma.c +7 -1
@@ -75,7 +75,7 @@ static int smb_direct_max_fragmented_rec/* The maximum single-message size which can be received */ static int smb_direct_max_receive_size =8192 ; -static int smb_direct_max_read_write_size =1024 *1024 ; +static int smb_direct_max_read_write_size =SMBD_DEFAULT_IOSIZE ;static int smb_direct_max_outstanding_rw_ops =8 ;
@@ -201,6 +201,12 @@ struct smb_direct_rdma_rw_msg {struct scatterlist sg_list[0 ]; }; +void init_smbd_max_io_size (unsigned int sz) +{ + sz =clamp_val (sz,SMBD_MIN_IOSIZE ,SMBD_MAX_IOSIZE ); + smb_direct_max_read_write_size = sz; +} +static inline int get_buf_page_count (void *buf,int size) { return DIV_ROUND_UP((uintptr_t)buf + size, PAGE_SIZE) -
fs/ksmbd/transport_rdma.h +6 -0
@@ -9,6 +9,10 @@#define SMB_DIRECT_PORT 5445 +#define SMBD_DEFAULT_IOSIZE (8 * 1024 * 1024) +#define SMBD_MIN_IOSIZE (512 * 1024) +#define SMBD_MAX_IOSIZE (16 * 1024 * 1024) +/* SMB DIRECT negotiation request packet [MS-SMBD] 2.2.1 */ struct smb_direct_negotiate_req {__le16 min_version;
@@ -54,10 +58,12 @@ struct smb_direct_data_transfer {int ksmbd_rdma_init (void );int ksmbd_rdma_destroy (void );bool ksmbd_rdma_capable_netdev (struct net_device *netdev); +void init_smbd_max_io_size (unsigned int sz);#else static inline int ksmbd_rdma_init (void ) {return 0 ; }static inline int ksmbd_rdma_destroy (void ) {return 0 ; }static inline bool ksmbd_rdma_capable_netdev (struct net_device *netdev) {return false; } +static inline void init_smbd_max_io_size (unsigned int sz) { }#endif #endif /* __KSMBD_TRANSPORT_RDMA_H__ */
Greg Kroah-Hartman
maintainerPATCH 155/204 ksmbd: add max connections parameter
In reply to Greg Kroah-HartmanFrom: Namjae Jeon <[email protected]>
commit 0d0d4680db22eda1eea785c47bbf66a9b33a8b16 upstream.
Add max connections parameter to limit number of maximum simultaneous connections.
--- fs/ksmbd/ksmbd_netlink.h | 3 ++- fs/ksmbd/server.h | 1 + fs/ksmbd/transport_ipc.c | 3 +++ fs/ksmbd/transport_tcp.c | 17 ++++++++++++++++- 4 files changed, 22 insertions(+), 2 deletions(-)
fs/ksmbd/ksmbd_netlink.h +2 -1
@@ -105,7 +105,8 @@ struct ksmbd_startup_request {__u32 sub_auth[3 ];/* Subauth value for Security ID */ __u32 smb2_max_credits;/* MAX credits */ __u32 smbd_max_io_size;/* smbd read write size */ -__u32 reserved[127 ];/* Reserved room */ +__u32 max_connections;/* Number of maximum simultaneous connections */ +__u32 reserved[126 ];/* Reserved room */ __u32 ifc_list_sz;/* interfaces list size */ __s8 ____payload[]; };
fs/ksmbd/server.h +1 -0
@@ -41,6 +41,7 @@ struct ksmbd_server_config {unsigned int share_fake_fscaps;struct smb_sid domain_sid;unsigned int auth_mechs; +unsigned int max_connections;char *conf[SERVER_CONF_WORK_GROUP +1 ]; };
fs/ksmbd/transport_ipc.c +3 -0
@@ -307,6 +307,9 @@ static int ipc_server_config_on_startup(if (req->smbd_max_io_size)init_smbd_max_io_size (req->smbd_max_io_size); +if (req->max_connections) + server_conf.max_connections = req->max_connections; + ret =ksmbd_set_netbios_name (req->netbios_name); ret |=ksmbd_set_server_string (req->server_string); ret |=ksmbd_set_work_group (req->work_group);
fs/ksmbd/transport_tcp.c +16 -1
@@ -15,6 +15,8 @@#define IFACE_STATE_DOWN BIT(0)#define IFACE_STATE_CONFIGURED BIT(1) +static atomic_t active_num_conn; +struct interface {struct task_struct *ksmbd_kthread;struct socket *ksmbd_socket;
@@ -185,8 +187,10 @@ static int ksmbd_tcp_new_connection(strustruct tcp_transport *t; t =alloc_transport (client_sk); -if (!t) +if (!t) { +sock_release (client_sk);return -ENOMEM ; + } csin =KSMBD_TCP_PEER_SOCKADDR (KSMBD_TRANS (t)->conn);if (kernel_getpeername (client_sk, csin) <0 ) {
@@ -239,6 +243,15 @@ static int ksmbd_kthread_fn(void *p)continue ; } +if (server_conf.max_connections && +atomic_inc_return (&active_num_conn) >= server_conf.max_connections) { +pr_info_ratelimited ("Limit the maximum number of connections(%u)\n" , +atomic_read (&active_num_conn)); +atomic_dec (&active_num_conn); +sock_release (client_sk); +continue ; + } +ksmbd_debug (CONN ,"connect success: accepted new connection\n" ); client_sk->sk->sk_rcvtimeo =KSMBD_TCP_RECV_TIMEOUT ; client_sk->sk->sk_sndtimeo =KSMBD_TCP_SEND_TIMEOUT ;
@@ -368,6 +381,8 @@ static int ksmbd_tcp_writev(struct ksmbdstatic void ksmbd_tcp_disconnect (struct ksmbd_transport *t) {free_transport (TCP_TRANS (t)); +if (server_conf.max_connections) +atomic_dec (&active_num_conn); }static void tcp_destroy_socket (struct socket *ksmbd_socket)
Greg Kroah-Hartman
maintainerPATCH 156/204 ksmbd: do not sign response to session request for guest login
In reply to Greg Kroah-HartmanFrom: Marios Makassikis <[email protected]>
commit 5fde3c21cf33830eda7bfd006dc7f4bf07ec9fe6 upstream.
If ksmbd.mountd is configured to assign unknown users to the guest account ("map to guest = bad user" in the config), ksmbd signs the response.
This is wrong according to MS-SMB2 3.3.5.5.3:
12. If the SMB2_SESSION_FLAG_IS_GUEST bit is not set in the SessionFlags field, and Session.IsAnonymous is FALSE, the server MUST sign the final session setup response before sending it to the client, as follows:
[...]
This fixes libsmb2 based applications failing to establish a session ("Wrong signature in received").
--- fs/ksmbd/smb2pdu.c | 2 ++ 1 file changed, 2 insertions(+)
fs/ksmbd/smb2pdu.c +2 -0
@@ -8613,6 +8613,7 @@ int smb3_decrypt_req(struct ksmbd_work *bool smb3_11_final_sess_setup_resp (struct ksmbd_work *work) {struct ksmbd_conn *conn = work->conn; +struct ksmbd_session *sess = work->sess;struct smb2_hdr *rsp = work->response_buf;if (conn->dialect <SMB30_PROT_ID )
@@ -8622,6 +8623,7 @@ bool smb3_11_final_sess_setup_resp(struc rsp =ksmbd_resp_buf_next (work);if (le16_to_cpu (rsp->Command) ==SMB2_SESSION_SETUP_HE && + sess->user && !user_guest (sess->user) && rsp->Status ==STATUS_SUCCESS )return true;return false;
Greg Kroah-Hartman
maintainerPATCH 157/204 ksmbd: downgrade ndr version error message to debug
In reply to Greg Kroah-HartmanFrom: Namjae Jeon <[email protected]>
commit a34dc4a9b9e2fb3a45c179a60bb0b26539c96189 upstream.
When user switch samba to ksmbd, The following message flood is coming when accessing files. Samba seems to changs dos attribute version to v5. This patch downgrade ndr version error message to debug.
$ dmesg ... [68971.766914] ksmbd: v5 version is not supported [68971.779808] ksmbd: v5 version is not supported [68971.871544] ksmbd: v5 version is not supported [68971.910135] ksmbd: v5 version is not supported ...
--- fs/ksmbd/ndr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
fs/ksmbd/ndr.c +4 -4
@@ -242,7 +242,7 @@ int ndr_decode_dos_attr(struct ndr *n, sreturn ret;if (da->version !=3 && da->version !=4 ) { -pr_err ("v%d version is not supported\n" , da->version); +ksmbd_debug (VFS ,"v%d version is not supported\n" , da->version);return -EINVAL ; }
@@ -251,7 +251,7 @@ int ndr_decode_dos_attr(struct ndr *n, sreturn ret;if (da->version != version2) { -pr_err ("ndr version mismatched(version: %d, version2: %d)\n" , +ksmbd_debug (VFS ,"ndr version mismatched(version: %d, version2: %d)\n" , da->version, version2);return -EINVAL ; }
@@ -453,7 +453,7 @@ int ndr_decode_v4_ntacl(struct ndr *n, sif (ret)return ret;if (acl->version !=4 ) { -pr_err ("v%d version is not supported\n" , acl->version); +ksmbd_debug (VFS ,"v%d version is not supported\n" , acl->version);return -EINVAL ; }
@@ -461,7 +461,7 @@ int ndr_decode_v4_ntacl(struct ndr *n, sif (ret)return ret;if (acl->version != version2) { -pr_err ("ndr version mismatched(version: %d, version2: %d)\n" , +ksmbd_debug (VFS ,"ndr version mismatched(version: %d, version2: %d)\n" , acl->version, version2);return -EINVAL ; }
Greg Kroah-Hartman
maintainerPATCH 158/204 ksmbd: limit pdu length size according to connection status
In reply to Greg Kroah-HartmanFrom: Namjae Jeon <[email protected]>
commit 62c487b53a7ff31e322cf2874d3796b8202c54a5 upstream.
Stream protocol length will never be larger than 16KB until session setup. After session setup, the size of requests will not be larger than 16KB + SMB2 MAX WRITE size. This patch limits these invalidly oversized requests and closes the connection immediately.
--- fs/ksmbd/connection.c | 17 +++++++++++++++-- fs/ksmbd/smb2pdu.h | 5 +++-- 2 files changed, 18 insertions(+), 4 deletions(-)
fs/ksmbd/connection.c +15 -2
@@ -274,7 +274,7 @@ int ksmbd_conn_handler_loop(void *p) {struct ksmbd_conn *conn = (struct ksmbd_conn *)p;struct ksmbd_transport *t = conn->transport; -unsigned int pdu_size; +unsigned int pdu_size, max_allowed_pdu_size;char hdr_buf[4 ] = {0 ,};int size;
@@ -299,13 +299,26 @@ int ksmbd_conn_handler_loop(void *p) pdu_size =get_rfc1002_len (hdr_buf);ksmbd_debug (CONN ,"RFC1002 header %u bytes\n" , pdu_size); +if (conn->status ==KSMBD_SESS_GOOD ) + max_allowed_pdu_size = +SMB3_MAX_MSGSIZE + conn->vals->max_write_size; +else + max_allowed_pdu_size =SMB3_MAX_MSGSIZE ; + +if (pdu_size > max_allowed_pdu_size) { +pr_err_ratelimited ("PDU length(%u) excceed maximum allowed pdu size(%u) on connection(%d)\n" , + pdu_size, max_allowed_pdu_size, + conn->status); +break ; + } +/* * Check if pdu size is valid (min : smb header size, * max : 0x00FFFFFF). */ if (pdu_size < __SMB2_HEADER_STRUCTURE_SIZE || pdu_size >MAX_STREAM_PROT_LEN ) { -continue ; +break ; }/* 4 for rfc1002 length field */
fs/ksmbd/smb2pdu.h +3 -2
@@ -113,8 +113,9 @@#define SMB21_DEFAULT_IOSIZE (1024 * 1024)#define SMB3_DEFAULT_IOSIZE (4 * 1024 * 1024)#define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024) -#define SMB3_MIN_IOSIZE (64 * 1024) -#define SMB3_MAX_IOSIZE (8 * 1024 * 1024) +#define SMB3_MIN_IOSIZE (64 * 1024) +#define SMB3_MAX_IOSIZE (8 * 1024 * 1024) +#define SMB3_MAX_MSGSIZE (4 * 4096)/* * SMB2 Header Definition
Greg Kroah-Hartman
maintainerPATCH 159/204 ovl: fail on invalid uid/gid mapping at copy up
In reply to Greg Kroah-HartmanFrom: Miklos Szeredi <[email protected]>
commit 4f11ada10d0ad3fd53e2bd67806351de63a4f9c3 upstream.
If st_uid/st_gid doesn't have a mapping in the mounter's user_ns, then copy-up should fail, just like it would fail if the mounter task was doing the copy using "cp -a".
There's a corner case where the "cp -a" would succeed but copy up fail: if there's a mapping of the invalid uid/gid (65534 by default) in the user namespace. This is because stat(2) will return this value if the mapping doesn't exist in the current user_ns and "cp -a" will in turn be able to create a file with this uid/gid.
This behavior would be inconsistent with POSIX ACL's, which return -1 for invalid uid/gid which result in a failed copy.
For consistency and simplicity fail the copy of the st_uid/st_gid are invalid.
--- fs/overlayfs/copy_up.c | 4 ++++ 1 file changed, 4 insertions(+)
fs/overlayfs/copy_up.c +4 -0
@@ -960,6 +960,10 @@ static int ovl_copy_up_one(struct dentryif (err)return err; +if (!kuid_has_mapping (current_user_ns (), ctx.stat.uid) || + !kgid_has_mapping (current_user_ns (), ctx.stat.gid)) +return -EOVERFLOW ; + ctx.metacopy =ovl_need_meta_copy_up (dentry, ctx.stat.mode, flags);if (parent) {
Greg Kroah-Hartman
maintainerPATCH 160/204 KVM: x86/vmx: Do not skip segment attributes if unusable bit is set
In reply to Greg Kroah-HartmanFrom: Hendrik Borghorst <[email protected]>
commit a44b331614e6f7e63902ed7dff7adc8c85edd8bc upstream.
When serializing and deserializing kvm_sregs, attributes of the segment descriptors are stored by user space. For unusable segments, vmx_segment_access_rights skips all attributes and sets them to 0.
This means we zero out the DPL (Descriptor Privilege Level) for unusable entries.
Unusable segments are - contrary to their name - usable in 64bit mode and are used by guests to for example create a linear map through the NULL selector.
VMENTER checks if SS.DPL is correct depending on the CS segment type. For types 9 (Execute Only) and 11 (Execute Read), CS.DPL must be equal to SS.DPL [1].
We have seen real world guests setting CS to a usable segment with DPL=3 and SS to an unusable segment with DPL=3. Once we go through an sregs get/set cycle, SS.DPL turns to 0. This causes the virtual machine to crash reproducibly.
This commit changes the attribute logic to always preserve attributes for unusable segments. According to [2] SS.DPL is always saved on VM exits, regardless of the unusable bit so user space applications should have saved the information on serialization correctly.
[3] specifies that besides SS.DPL the rest of the attributes of the descriptors are undefined after VM entry if unusable bit is set. So, there should be no harm in setting them all to the previous state.
[1] Intel SDM Vol 3C 26.3.1.2 Checks on Guest Segment Registers
[2] Intel SDM Vol 3C 27.3.2 Saving Segment Registers and Descriptor-Table Registers
[3] Intel SDM Vol 3C 26.3.2.2 Loading Guest Segment Registers and Descriptor-Table Registers
Message-Id: <[email protected]>
--- arch/x86/kvm/vmx/vmx.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-)
arch/x86/kvm/vmx/vmx.c +9 -12
@@ -3361,18 +3361,15 @@ static u32 vmx_segment_access_rights(str {u32 ar; -if (var->unusable || !var->present) - ar =1 <<16 ; -else { - ar = var->type &15 ; - ar |= (var->s &1 ) <<4 ; - ar |= (var->dpl &3 ) <<5 ; - ar |= (var->present &1 ) <<7 ; - ar |= (var->avl &1 ) <<12 ; - ar |= (var->l &1 ) <<13 ; - ar |= (var->db &1 ) <<14 ; - ar |= (var->g &1 ) <<15 ; - } + ar = var->type &15 ; + ar |= (var->s &1 ) <<4 ; + ar |= (var->dpl &3 ) <<5 ; + ar |= (var->present &1 ) <<7 ; + ar |= (var->avl &1 ) <<12 ; + ar |= (var->l &1 ) <<13 ; + ar |= (var->db &1 ) <<14 ; + ar |= (var->g &1 ) <<15 ; + ar |= (var->unusable || !var->present) <<16 ;return ar; }
Greg Kroah-Hartman
maintainerPATCH 161/204 KVM: arm64: GICv4.1: Fix race with doorbell on VPE activation/deactivation
In reply to Greg Kroah-HartmanFrom: Marc Zyngier <[email protected]>
commit ef3691683d7bfd0a2acf48812e4ffe894f10bfa8 upstream.
To save the vgic LPI pending state with GICv4.1, the VPEs must all be unmapped from the ITSs so that the sGIC caches can be flushed. The opposite is done once the state is saved.
This is all done by using the activate/deactivate irqdomain callbacks directly from the vgic code. Crutially, this is done without holding the irqdesc lock for the interrupts that represent the VPE. And these callbacks are changing the state of the irqdesc. What could possibly go wrong?
If a doorbell fires while we are messing with the irqdesc state, it will acquire the lock and change the interrupt state concurrently. Since we don't hole the lock, curruption occurs in on the interrupt state. Oh well.
While acquiring the lock would fix this (and this was Shanker's initial approach), this is still a layering violation we could do without. A better approach is actually to free the VPE interrupt, do what we have to do, and re-request it.
It is more work, but this usually happens only once in the lifetime of the VM and we don't really care about this sort of overhead.
--- arch/arm64/kvm/vgic/vgic-v3.c | 25 +++++++++++-------------- arch/arm64/kvm/vgic/vgic-v4.c | 8 ++++++-- arch/arm64/kvm/vgic/vgic.h | 1 + 3 files changed, 18 insertions(+), 16 deletions(-)
arch/arm64/kvm/vgic/vgic-v3.c +11 -14
@@ -347,26 +347,23 @@ retry:* The deactivation of the doorbell interrupt will trigger the * unmapping of the associated vPE. */ -static void unmap_all_vpes (struct vgic_dist *dist) +static void unmap_all_vpes (struct kvm *kvm) { -struct irq_desc *desc; +struct vgic_dist *dist = &kvm->arch.vgic;int i; -for (i =0 ; i < dist->its_vm.nr_vpes; i++) { - desc =irq_to_desc (dist->its_vm.vpes[i]->irq); -irq_domain_deactivate_irq (irq_desc_get_irq_data (desc)); - } +for (i =0 ; i < dist->its_vm.nr_vpes; i++) +free_irq (dist->its_vm.vpes[i]->irq,kvm_get_vcpu (kvm, i)); } -static void map_all_vpes (struct vgic_dist *dist) +static void map_all_vpes (struct kvm *kvm) { -struct irq_desc *desc; +struct vgic_dist *dist = &kvm->arch.vgic;int i; -for (i =0 ; i < dist->its_vm.nr_vpes; i++) { - desc =irq_to_desc (dist->its_vm.vpes[i]->irq); -irq_domain_activate_irq (irq_desc_get_irq_data (desc), false); - } +for (i =0 ; i < dist->its_vm.nr_vpes; i++) +WARN_ON (vgic_v4_request_vpe_irq (kvm_get_vcpu (kvm, i), + dist->its_vm.vpes[i]->irq)); }/**
@@ -391,7 +388,7 @@ int vgic_v3_save_pending_tables(struct k* and enabling of the doorbells have already been done. */ if (kvm_vgic_global_state.has_gicv4_1) { -unmap_all_vpes (dist); +unmap_all_vpes (kvm); vlpi_avail = true; }
@@ -441,7 +438,7 @@ int vgic_v3_save_pending_tables(struct k out:if (vlpi_avail) -map_all_vpes (dist); +map_all_vpes (kvm);return ret; }
arch/arm64/kvm/vgic/vgic-v4.c +6 -2
@@ -222,6 +222,11 @@ void vgic_v4_get_vlpi_state(struct vgic_ *val = !!(*ptr & mask); } +int vgic_v4_request_vpe_irq (struct kvm_vcpu *vcpu,int irq) +{ +return request_irq (irq, vgic_v4_doorbell_handler,0 ,"vcpu" , vcpu); +} +/** * vgic_v4_init - Initialize the GICv4 data structures * @kvm: Pointer to the VM being initialized
@@ -282,8 +287,7 @@ int vgic_v4_init(struct kvm *kvm) irq_flags &= ~IRQ_NOAUTOEN ;irq_set_status_flags (irq, irq_flags); - ret =request_irq (irq, vgic_v4_doorbell_handler, -0 ,"vcpu" , vcpu); + ret =vgic_v4_request_vpe_irq (vcpu, irq);if (ret) {kvm_err ("failed to allocate vcpu IRQ%d\n" , irq);/*
arch/arm64/kvm/vgic/vgic.h +1 -0
@@ -321,5 +321,6 @@ int vgic_v4_init(struct kvm *kvm);void vgic_v4_teardown (struct kvm *kvm);void vgic_v4_configure_vsgis (struct kvm *kvm);void vgic_v4_get_vlpi_state (struct vgic_irq *irq,bool *val); +int vgic_v4_request_vpe_irq (struct kvm_vcpu *vcpu,int irq);#endif
Greg Kroah-Hartman
maintainerPATCH 162/204 thermal: intel: int340x: Protect trip temperature from concurrent updates
In reply to Greg Kroah-HartmanFrom: Srinivas Pandruvada <[email protected]>
commit 6757a7abe47bcb12cb2d45661067e182424b0ee3 upstream.
Trip temperatures are read using ACPI methods and stored in the memory during zone initializtion and when the firmware sends a notification for change. This trip temperature is returned when the thermal core calls via callback get_trip_temp().
But it is possible that while updating the memory copy of the trips when the firmware sends a notification for change, thermal core is reading the trip temperature via the callback get_trip_temp(). This may return invalid trip temperature.
To address this add a mutex to protect the invalid temperature reads in the callback get_trip_temp() and int340x_thermal_read_trips().
--- drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c | 18 +++++++++-- drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h | 1 2 files changed, 16 insertions(+), 3 deletions(-)
drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +15 -3
@@ -44,11 +44,13 @@ static int int340x_thermal_get_trip_temp int trip, int *temp) { struct int34x_thermal_zone *d = zone->devdata; -int i; +int i, ret =0 ;if (d->override_ops && d->override_ops->get_trip_temp)return d->override_ops->get_trip_temp (zone, trip, temp); +mutex_lock (&d->trip_mutex); +if (trip < d->aux_trip_nr) *temp = d->aux_trips[trip];else if (trip == d->crt_trip_id)
@@ -66,10 +68,12 @@ static int int340x_thermal_get_trip_temp } }if (i ==INT340X_THERMAL_MAX_ACT_TRIP_COUNT ) -return -EINVAL ; + ret = -EINVAL ; } -return 0 ; +mutex_unlock (&d->trip_mutex); + +return ret; } static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone,
@@ -180,6 +184,8 @@ int int340x_thermal_read_trips(struct inint trip_cnt = int34x_zone->aux_trip_nr;int i; +mutex_lock (&int34x_zone->trip_mutex); + int34x_zone->crt_trip_id =-1 ;if (!int340x_thermal_get_trip_config (int34x_zone->adev->handle,"_CRT" , &int34x_zone->crt_temp))
@@ -207,6 +213,8 @@ int int340x_thermal_read_trips(struct in int34x_zone->act_trips[i].valid = true; } +mutex_unlock (&int34x_zone->trip_mutex); +return trip_cnt; }EXPORT_SYMBOL_GPL (int340x_thermal_read_trips);
@@ -230,6 +238,8 @@ struct int34x_thermal_zone *int340x_therif (!int34x_thermal_zone)return ERR_PTR (-ENOMEM ); +mutex_init (&int34x_thermal_zone->trip_mutex); + int34x_thermal_zone->adev = adev; int34x_thermal_zone->override_ops = override_ops;
@@ -281,6 +291,7 @@ err_thermal_zone:acpi_lpat_free_conversion_table (int34x_thermal_zone->lpat_table);kfree (int34x_thermal_zone->aux_trips); err_trip_alloc: +mutex_destroy (&int34x_thermal_zone->trip_mutex);kfree (int34x_thermal_zone);return ERR_PTR (ret); }
@@ -292,6 +303,7 @@ void int340x_thermal_zone_remove(structthermal_zone_device_unregister (int34x_thermal_zone->zone);acpi_lpat_free_conversion_table (int34x_thermal_zone->lpat_table);kfree (int34x_thermal_zone->aux_trips); +mutex_destroy (&int34x_thermal_zone->trip_mutex);kfree (int34x_thermal_zone); }EXPORT_SYMBOL_GPL (int340x_thermal_zone_remove);
drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h +1 -0
@@ -32,6 +32,7 @@ struct int34x_thermal_zone {struct thermal_zone_device_ops *override_ops;void *priv_data;struct acpi_lpat_conversion_table *lpat_table; +struct mutex trip_mutex; }; struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *,
Greg Kroah-Hartman
maintainerPATCH 163/204 ipv6: fix reachability confirmation with proxy_ndp
In reply to Greg Kroah-HartmanFrom: Gergely Risko <[email protected]>
commit 9f535c870e493841ac7be390610ff2edec755762 upstream.
When proxying IPv6 NDP requests, the adverts to the initial multicast solicits are correct and working. On the other hand, when later a reachability confirmation is requested (on unicast), no reply is sent.
This causes the neighbor entry expiring on the sending node, which is mostly a non-issue, as a new multicast request is sent. There are routers, where the multicast requests are intentionally delayed, and in these environments the current implementation causes periodic packet loss for the proxied endpoints.
The root cause is the erroneous decrease of the hop limit, as this is checked in ndisc.c and no answer is generated when it's 254 instead of the correct 255.
--- net/ipv6/ip6_output.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)
net/ipv6/ip6_output.c +14 -1
@@ -527,7 +527,20 @@ int ip6_forward(struct sk_buff *skb) pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {int proxied =ip6_forward_proxy_check (skb);if (proxied >0 ) { - hdr->hop_limit--; +/* It's tempting to decrease the hop limit +* here by 1, as we do at the end of the +* function too. +* +* But that would be incorrect, as proxying is +* not forwarding. The ip6_input function +* will handle this packet locally, and it +* depends on the hop limit being unchanged. +* +* One example is the NDP hop limit, that +* always has to stay 255, but other would be +* similar checks around RA packets, where the +* user can even change the desired limit. +*/ return ip6_input (skb); }else if (proxied <0 ) {__IP6_INC_STATS (net, idev,IPSTATS_MIB_INDISCARDS );
Greg Kroah-Hartman
maintainerPATCH 164/204 ARM: 9280/1: mm: fix warning on phys_addr_t to void pointer assignment
In reply to Greg Kroah-HartmanFrom: Giulio Benetti <[email protected]>
commit a4e03921c1bb118e6718e0a3b0322a2c13ed172b upstream.
zero_page is a void* pointer but memblock_alloc() returns phys_addr_t type so this generates a warning while using clang and with -Wint-error enabled that becomes and error. So let's cast the return of memblock_alloc() to (void *).
--- arch/arm/mm/nommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm/mm/nommu.c +1 -1
@@ -161,7 +161,7 @@ void __init paging_init(const struct macmpu_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 );
Greg Kroah-Hartman
maintainerPATCH 165/204 EDAC/device: Respect any driver-supplied workqueue polling value
In reply to Greg Kroah-HartmanFrom: Manivannan Sadhasivam <[email protected]>
commit cec669ff716cc83505c77b242aecf6f7baad869d upstream.
The EDAC drivers may optionally pass the poll_msec value. Use that value if available, else fall back to 1000ms.
[ bp: Touchups. ]
--- drivers/edac/edac_device.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-)
drivers/edac/edac_device.c +7 -8
@@ -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(s* 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(stru* 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(stru 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_d/* 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 ; }
Greg Kroah-Hartman
maintainerPATCH 166/204 EDAC/qcom: Do not pass llcc_driv_data as edac_device_ctl_infos pvt_info
In reply to Greg Kroah-HartmanFrom: Manivannan Sadhasivam <[email protected]>
commit 977c6ba624f24ae20cf0faee871257a39348d4a9 upstream.
The memory for llcc_driv_data is allocated by the LLCC driver. But when it is passed as the private driver info to the EDAC core, it will get freed during the qcom_edac driver release. So when the qcom_edac driver gets probed again, it will try to use the freed data leading to the use-after-free bug.
Hence, do not pass llcc_driv_data as pvt_info but rather reference it using the platform_data pointer in the qcom_edac driver.
--- drivers/edac/qcom_edac.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/edac/qcom_edac.c +2 -3
@@ -252,7 +252,7 @@ clear:static int dump_syn_reg (struct edac_device_ctl_info *edev_ctl,int err_type,u32 bank) { -struct llcc_drv_data *drv = edev_ctl->pvt_info; +struct llcc_drv_data *drv = edev_ctl->dev->platform_data;int ret; ret =dump_syn_reg_values (drv, bank, err_type);
@@ -289,7 +289,7 @@ static irqreturn_t llcc_ecc_irq_handler(int irq, void *edev_ctl) { struct edac_device_ctl_info *edac_dev_ctl = edev_ctl; -struct llcc_drv_data *drv = edac_dev_ctl->pvt_info; +struct llcc_drv_data *drv = edac_dev_ctl->dev->platform_data;irqreturn_t irq_rc =IRQ_NONE ;u32 drp_error, trp_error, i;int ret;
@@ -358,7 +358,6 @@ static int qcom_llcc_edac_probe(struct p edev_ctl->dev_name =dev_name (dev); edev_ctl->ctl_name ="llcc" ; edev_ctl->panic_on_ue =LLCC_ERP_PANIC_ON_UE ; - edev_ctl->pvt_info = llcc_driv_data; rc =edac_device_add_device (edev_ctl);if (rc)
Greg Kroah-Hartman
maintainerPATCH 167/204 net: mana: Fix IRQ name - add PCI and queue number
In reply to Greg Kroah-HartmanFrom: Haiyang Zhang <[email protected]>
[ Upstream commit 20e3028c39a5bf882e91e717da96d14f1acec40e ]
The PCI and queue number info is missing in IRQ names.
Add PCI and queue number to IRQ names, to allow CPU affinity tuning scripts to work.
--- drivers/net/ethernet/microsoft/mana/gdma.h | 3 +++ drivers/net/ethernet/microsoft/mana/gdma_main.c | 9 ++++++++- 2 files changed, 11 insertions(+), 1 deletion(-)
drivers/net/ethernet/microsoft/mana/gdma.h +3 -0
@@ -324,9 +324,12 @@ struct gdma_queue_spec { }; }; +#define MANA_IRQ_NAME_SZ 32 +struct gdma_irq_context {void (*handler)(void *arg);void *arg; +char name[MANA_IRQ_NAME_SZ ]; };struct gdma_context {
drivers/net/ethernet/microsoft/mana/gdma_main.c +8 -1
@@ -1195,13 +1195,20 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) gic->handler =NULL ; gic->arg =NULL ; +if (!i) +snprintf (gic->name,MANA_IRQ_NAME_SZ ,"mana_hwc@pci:%s" , +pci_name (pdev)); +else +snprintf (gic->name,MANA_IRQ_NAME_SZ ,"mana_q%d@pci:%s" , + i -1 ,pci_name (pdev)); + irq =pci_irq_vector (pdev, i);if (irq <0 ) { err = irq; goto free_irq; } - err =request_irq (irq, mana_gd_intr,0 ,"mana_intr" , gic); + err =request_irq (irq, mana_gd_intr,0 , gic->name, gic);if (err) goto free_irq; }
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 168/204 scsi: ufs: core: Fix devfreq deadlocks
In reply to Greg Kroah-HartmanFrom: Johan Hovold <[email protected]>
[ Upstream commit ba81043753fffbc2ad6e0c5ff2659f12ac2f46b4 ]
There is a lock inversion and rwsem read-lock recursion in the devfreq target callback which can lead to deadlocks.
Specifically, ufshcd_devfreq_scale() already holds a clk_scaling_lock read lock when toggling the write booster, which involves taking the dev_cmd mutex before taking another clk_scaling_lock read lock.
This can lead to a deadlock if another thread:
1) tries to acquire the dev_cmd and clk_scaling locks in the correct order, or
2) takes a clk_scaling write lock before the attempt to take the clk_scaling read lock a second time.
Fix this by dropping the clk_scaling_lock before toggling the write booster as was done before commit 0e9d4ca43ba8 ("scsi: ufs: Protect some contexts from unexpected clock scaling").
While the devfreq callbacks are already serialised, add a second serialising mutex to handle the unlikely case where a callback triggered through the devfreq sysfs interface is racing with a request to disable clock scaling through the UFS controller 'clkscale_enable' sysfs attribute. This could otherwise lead to the write booster being left disabled after having disabled clock scaling.
Also take the new mutex in ufshcd_clk_scaling_allow() to make sure that any pending write booster update has completed on return.
Note that this currently only affects Qualcomm platforms since commit 87bd05016a64 ("scsi: ufs: core: Allow host driver to disable wb toggling during clock scaling").
The lock inversion (i.e. 1 above) was reported by lockdep as:
======================================================
WARNING: possible circular locking dependency detected 6.1.0-next-20221216 #211 Not tainted
------------------------------------------------------
kworker/u16:2/71 is trying to acquire lock:
ffff076280ba98a0 (&hba->dev_cmd.lock){+.+.}-{3:3}, at: ufshcd_query_flag+0x50/0x1c0
but task is already holding lock:
ffff076280ba9cf0 (&hba->clk_scaling_lock){++++}-{3:3}, at: ufshcd_devfreq_scale+0x2b8/0x380
which lock already depends on the new lock.
[ +0.011606]
the existing dependency chain (in reverse order) is:
-> #1 (&hba->clk_scaling_lock){++++}-{3:3}:
lock_acquire+0x68/0x90
down_read+0x58/0x80
ufshcd_exec_dev_cmd+0x70/0x2c0
ufshcd_verify_dev_init+0x68/0x170
ufshcd_probe_hba+0x398/0x1180
ufshcd_async_scan+0x30/0x320
async_run_entry_fn+0x34/0x150
process_one_work+0x288/0x6c0
worker_thread+0x74/0x450
kthread+0x118/0x120
ret_from_fork+0x10/0x20-> #0 (&hba->dev_cmd.lock){+.+.}-{3:3}:
__lock_acquire+0x12a0/0x2240
lock_acquire.part.0+0xcc/0x220
lock_acquire+0x68/0x90
__mutex_lock+0x98/0x430
mutex_lock_nested+0x2c/0x40
ufshcd_query_flag+0x50/0x1c0
ufshcd_query_flag_retry+0x64/0x100
ufshcd_wb_toggle+0x5c/0x120
ufshcd_devfreq_scale+0x2c4/0x380
ufshcd_devfreq_target+0xf4/0x230
devfreq_set_target+0x84/0x2f0
devfreq_update_target+0xc4/0xf0
devfreq_monitor+0x38/0x1f0
process_one_work+0x288/0x6c0
worker_thread+0x74/0x450
kthread+0x118/0x120
ret_from_fork+0x10/0x20other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&hba->clk_scaling_lock);
lock(&hba->dev_cmd.lock);
lock(&hba->clk_scaling_lock);
lock(&hba->dev_cmd.lock);*** DEADLOCK ***
--- drivers/scsi/ufs/ufshcd.c | 26 ++++++++++++++------------ drivers/scsi/ufs/ufshcd.h | 2 ++ 2 files changed, 16 insertions(+), 12 deletions(-)
drivers/scsi/ufs/ufshcd.c +14 -12
@@ -1185,12 +1185,14 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba)* clock scaling is in progress */ ufshcd_scsi_block_requests (hba); +mutex_lock (&hba->wb_mutex);down_write (&hba->clk_scaling_lock);if (!hba->clk_scaling.is_allowed ||ufshcd_wait_for_doorbell_clr (hba,DOORBELL_CLR_TOUT_US )) { ret = -EBUSY ;up_write (&hba->clk_scaling_lock); +mutex_unlock (&hba->wb_mutex);ufshcd_scsi_unblock_requests (hba); goto out; }
@@ -1202,12 +1204,15 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba)return ret; } -static void ufshcd_clock_scaling_unprepare (struct ufs_hba *hba,bool writelock) +static void ufshcd_clock_scaling_unprepare (struct ufs_hba *hba,int err,bool scale_up) { -if (writelock) -up_write (&hba->clk_scaling_lock); -else -up_read (&hba->clk_scaling_lock); +up_write (&hba->clk_scaling_lock); + +/* Enable Write Booster if we have scaled up else disable it */ +ufshcd_wb_toggle (hba, scale_up); + +mutex_unlock (&hba->wb_mutex); +ufshcd_scsi_unblock_requests (hba);ufshcd_release (hba); }
@@ -1224,7 +1229,6 @@ static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, bool writelock)static int ufshcd_devfreq_scale (struct ufs_hba *hba,bool scale_up) {int ret =0 ; -bool is_writelock = true; ret =ufshcd_clock_scaling_prepare (hba);if (ret)
@@ -1253,13 +1257,8 @@ static int ufshcd_devfreq_scale(struct ufs_hba *hba, bool scale_up) } } -/* Enable Write Booster if we have scaled up else disable it */ -downgrade_write (&hba->clk_scaling_lock); - is_writelock = false; -ufshcd_wb_toggle (hba, scale_up); - out_unprepare: -ufshcd_clock_scaling_unprepare (hba, is_writelock); +ufshcd_clock_scaling_unprepare (hba, ret, scale_up);return ret; }
@@ -5919,9 +5918,11 @@ static void ufshcd_force_error_recovery(struct ufs_hba *hba)static void ufshcd_clk_scaling_allow (struct ufs_hba *hba,bool allow) { +mutex_lock (&hba->wb_mutex);down_write (&hba->clk_scaling_lock); hba->clk_scaling.is_allowed = allow;up_write (&hba->clk_scaling_lock); +mutex_unlock (&hba->wb_mutex); }static void ufshcd_clk_scaling_suspend (struct ufs_hba *hba,bool suspend)
@@ -9480,6 +9481,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)/* Initialize mutex for exception event control */ mutex_init (&hba->ee_ctrl_mutex); +mutex_init (&hba->wb_mutex);init_rwsem (&hba->clk_scaling_lock);ufshcd_init_clk_gating (hba);
drivers/scsi/ufs/ufshcd.h +2 -0
@@ -763,6 +763,7 @@ struct ufs_hba_monitor {* @urgent_bkops_lvl: keeps track of urgent bkops level for device * @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for * device is known or not. +* @wb_mutex: used to serialize devfreq and sysfs write booster toggling * @scsi_block_reqs_cnt: reference counting for scsi block requests * @crypto_capabilities: Content of crypto capabilities register (0x100) * @crypto_cap_array: Array of crypto capabilities
@@ -892,6 +893,7 @@ struct ufs_hba {enum bkops_status urgent_bkops_lvl;bool is_urgent_bkops_lvl_checked; +struct mutex wb_mutex;struct rw_semaphore clk_scaling_lock;unsigned char desc_size[QUERY_DESC_IDN_MAX ];atomic_t scsi_block_reqs_cnt;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 169/204 i2c: designware: use casting of u64 in clock multiplication to avoid overflow
In reply to Greg Kroah-HartmanFrom: Lareine Khawaly <[email protected]>
[ Upstream commit c8c37bc514514999e62a17e95160ed9ebf75ca8d ]
In functions i2c_dw_scl_lcnt() and i2c_dw_scl_hcnt() may have overflow by depending on the values of the given parameters including the ic_clk. For example in our use case where ic_clk is larger than one million, multiplication of ic_clk * 4700 will result in 32 bit overflow.
Add cast of u64 to the calculation to avoid multiplication overflow, and use the corresponding define for divide.
--- drivers/i2c/busses/i2c-designware-common.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/i2c/busses/i2c-designware-common.c +6 -3
@@ -351,7 +351,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset)* * If your hardware is free from tHD;STA issue, try this one. */ -return DIV_ROUND_CLOSEST (ic_clk * tSYMBOL,MICRO ) -8 + offset; +return DIV_ROUND_CLOSEST_ULL ((u64 )ic_clk * tSYMBOL,MICRO ) - +8 + offset; else/* * Conditional expression:
@@ -367,7 +368,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset)* The reason why we need to take into account "tf" here, * is the same as described in i2c_dw_scl_lcnt(). */ -return DIV_ROUND_CLOSEST (ic_clk * (tSYMBOL + tf),MICRO ) -3 + offset; +return DIV_ROUND_CLOSEST_ULL ((u64 )ic_clk * (tSYMBOL + tf),MICRO ) - +3 + offset; }u32 i2c_dw_scl_lcnt (u32 ic_clk,u32 tLOW,u32 tf,int offset)
@@ -383,7 +385,8 @@ u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset)* account the fall time of SCL signal (tf). Default tf value * should be 0.3 us, for safety. */ -return DIV_ROUND_CLOSEST (ic_clk * (tLOW + tf),MICRO ) -1 + offset; +return DIV_ROUND_CLOSEST_ULL ((u64 )ic_clk * (tLOW + tf),MICRO ) - +1 + offset; }int i2c_dw_set_sda_hold (struct dw_i2c_dev *dev)
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 170/204 netlink: prevent potential spectre v1 gadgets
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit f0950402e8c76e7dcb08563f1b4e8000fbc62455 ]
Most netlink attributes are parsed and validated from __nla_validate_parse() or validate_nla()
u16 type = nla_type(nla);
if (type == 0 || type > maxtype) {
/* error or continue */
}@type is then used as an array index and can be used as a Spectre v1 gadget.
array_index_nospec() can be used to prevent leaking content of kernel memory to malicious users.
This should take care of vast majority of netlink uses, but an audit is needed to take care of others where validation is not yet centralized in core netlink functions.
--- lib/nlattr.c | 3 +++ 1 file changed, 3 insertions(+)
lib/nlattr.c +3 -0
@@ -10,6 +10,7 @@#include <linux/kernel.h> #include <linux/errno.h> #include <linux/jiffies.h> +#include <linux/nospec.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h>
@@ -369,6 +370,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype,if (type <=0 || type > maxtype)return 0 ; + type =array_index_nospec (type, maxtype +1 ); pt = &policy[type];BUG_ON (pt->type >NLA_TYPE_MAX );
@@ -584,6 +586,7 @@ static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, }continue ; } + type =array_index_nospec (type, maxtype +1 );if (policy) {int err =validate_nla (nla, maxtype, policy, validate, extack, depth);
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 171/204 net: fix UaF in netns ops registration error path
In reply to Greg Kroah-HartmanFrom: Paolo Abeni <[email protected]>
[ Upstream commit 71ab9c3e2253619136c31c89dbb2c69305cc89b1 ]
If net_assign_generic() fails, the current error path in ops_init() tries to clear the gen pointer slot. Anyway, in such error path, the gen pointer itself has not been modified yet, and the existing and accessed one is smaller than the accessed index, causing an out-of-bounds error:
BUG: KASAN: slab-out-of-bounds in ops_init+0x2de/0x320
Write of size 8 at addr ffff888109124978 by task modprobe/1018
CPU: 2 PID: 1018 Comm: modprobe Not tainted 6.2.0-rc2.mptcp_ae5ac65fbed5+ #1641
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.1-2.fc37 04/01/2014
Call Trace:
<TASK>
dump_stack_lvl+0x6a/0x9f
print_address_description.constprop.0+0x86/0x2b5
print_report+0x11b/0x1fb
kasan_report+0x87/0xc0
ops_init+0x2de/0x320
register_pernet_operations+0x2e4/0x750
register_pernet_subsys+0x24/0x40
tcf_register_action+0x9f/0x560
do_one_initcall+0xf9/0x570
do_init_module+0x190/0x650
load_module+0x1fa5/0x23c0
__do_sys_finit_module+0x10d/0x1b0
do_syscall_64+0x58/0x80
entry_SYSCALL_64_after_hwframe+0x72/0xdc
RIP: 0033:0x7f42518f778d
Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48
89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff
ff 73 01 c3 48 8b 0d cb 56 2c 00 f7 d8 64 89 01 48
RSP: 002b:00007fff96869688 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
RAX: ffffffffffffffda RBX: 00005568ef7f7c90 RCX: 00007f42518f778d
RDX: 0000000000000000 RSI: 00005568ef41d796 RDI: 0000000000000003
RBP: 00005568ef41d796 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000000
R13: 00005568ef7f7d30 R14: 0000000000040000 R15: 0000000000000000
</TASK>This change addresses the issue by skipping the gen pointer de-reference in the mentioned error-path.
Found by code inspection and verified with explicit error injection on a kasan-enabled kernel.
--- net/core/net_namespace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/core/net_namespace.c +1 -1
@@ -137,12 +137,12 @@ 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:
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 172/204 drm/i915/selftest: fix intel_selftest_modify_policy argument types
In reply to Greg Kroah-HartmanFrom: Arnd Bergmann <[email protected]>
[ Upstream commit 2255bbcdc39d5b0311968f86614ae4f25fdd465d ]
The definition of intel_selftest_modify_policy() does not match the declaration, as gcc-13 points out:
drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c:29:5: error: conflicting types for 'intel_selftest_modify_policy' due to enum/integer mismatch; have 'int(struct intel_engine_cs *, struct intel_selftest_saved_policy *, u32)' {aka 'int(struct intel_engine_cs *, struct intel_selftest_saved_policy *, unsigned int)'} [-Werror=enum-int-mismatch]
29 | int intel_selftest_modify_policy(struct intel_engine_cs *engine,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c:11:
drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h:28:5: note: previous declaration of 'intel_selftest_modify_policy' with type 'int(struct intel_engine_cs *, struct intel_selftest_saved_policy *, enum selftest_scheduler_modify)'
28 | int intel_selftest_modify_policy(struct intel_engine_cs *engine,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~Change the type in the definition to match.
--- drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c +1 -2
@@ -16,8 +16,7 @@int intel_selftest_modify_policy (struct intel_engine_cs *engine,struct intel_selftest_saved_policy *saved, -u32 modify_type) - +enum selftest_scheduler_modify modify_type) {int err;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 173/204 netfilter: nft_set_rbtree: Switch to node list walk for overlap detection
In reply to Greg Kroah-HartmanFrom: Pablo Neira Ayuso <[email protected]>
[ Upstream commit c9e6978e2725a7d4b6cd23b2facd3f11422c0643 ]
...instead of a tree descent, which became overly complicated in an attempt to cover cases where expired or inactive elements would affect comparisons with the new element being inserted.
Further, it turned out that it's probably impossible to cover all those cases, as inactive nodes might entirely hide subtrees consisting of a complete interval plus a node that makes the current insertion not overlap.
To speed up the overlap check, descent the tree to find a greater element that is closer to the key value to insert. Then walk down the node list for overlap detection. Starting the overlap check from rb_first() unconditionally is slow, it takes 10 times longer due to the full linear traversal of the list.
Moreover, perform garbage collection of expired elements when walking down the node list to avoid bogus overlap reports.
For the insertion operation itself, this essentially reverts back to the implementation before commit 7c84d41416d8 ("netfilter: nft_set_rbtree:
Detect partial overlaps on insertion"), except that cases of complete overlap are already handled in the overlap detection phase itself, which slightly simplifies the loop to find the insertion point.
Based on initial patch from Stefano Brivio, including text from the original patch description too.
--- net/netfilter/nft_set_rbtree.c | 316 ++++++++++++++++++++------------- 1 file changed, 189 insertions(+), 127 deletions(-)
net/netfilter/nft_set_rbtree.c +189 -127
@@ -38,10 +38,12 @@ static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe)return !nft_rbtree_interval_end (rbe); } -static bool nft_rbtree_equal (const struct nft_set *set,const void *this, -const struct nft_rbtree_elem *interval) +static int nft_rbtree_cmp (const struct nft_set *set, +const struct nft_rbtree_elem *e1, +const struct nft_rbtree_elem *e2) { -return memcmp (this,nft_set_ext_key (&interval->ext), set->klen) ==0 ; +return memcmp (nft_set_ext_key (&e1->ext),nft_set_ext_key (&e2->ext), + set->klen); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
@@ -52,7 +54,6 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *setconst struct nft_rbtree_elem *rbe, *interval =NULL ;u8 genmask =nft_genmask_cur (net);const struct rb_node *parent; -const void *this;int d; parent =rcu_dereference_raw (priv->root.rb_node);
@@ -62,12 +63,11 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set rbe = rb_entry(parent, struct nft_rbtree_elem, node); - this =nft_set_ext_key (&rbe->ext); - d =memcmp (this, key, set->klen); + d =memcmp (nft_set_ext_key (&rbe->ext), key, set->klen);if (d <0 ) { parent =rcu_dereference_raw (parent->rb_left);if (interval && -nft_rbtree_equal (set, this, interval) && + !nft_rbtree_cmp (set, rbe, interval) &&nft_rbtree_interval_end (rbe) &&nft_rbtree_interval_start (interval))continue ;
@@ -215,154 +215,216 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set,return rbe; } +static int nft_rbtree_gc_elem (const struct nft_set *__set, +struct nft_rbtree *priv, +struct nft_rbtree_elem *rbe) +{ +struct nft_set *set = (struct nft_set *)__set; +struct rb_node *prev =rb_prev (&rbe->node); +struct nft_rbtree_elem *rbe_prev; +struct nft_set_gc_batch *gcb; + + gcb =nft_set_gc_batch_check (set,NULL ,GFP_ATOMIC ); +if (!gcb) +return -ENOMEM ; + +/* search for expired end interval coming before this element. */ +do { + rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); +if (nft_rbtree_interval_end (rbe_prev)) +break ; + + prev =rb_prev (prev); + }while (prev !=NULL ); + +rb_erase (&rbe_prev->node, &priv->root); +rb_erase (&rbe->node, &priv->root); +atomic_sub (2 , &set->nelems); + +nft_set_gc_batch_add (gcb, rbe); +nft_set_gc_batch_complete (gcb); + +return 0 ; +} + +static bool nft_rbtree_update_first (const struct nft_set *set, +struct nft_rbtree_elem *rbe, +struct rb_node *first) +{ +struct nft_rbtree_elem *first_elem; + + first_elem = rb_entry(first, struct nft_rbtree_elem, node); +/* this element is closest to where the new element is to be inserted: +* update the first element for the node list path. +*/ +if (nft_rbtree_cmp (set, rbe, first_elem) <0 ) +return true; + +return false; +} +static int __nft_rbtree_insert (const struct net *net,const struct nft_set *set,struct nft_rbtree_elem *new,struct nft_set_ext **ext) { -bool overlap = false, dup_end_left = false, dup_end_right = false; +struct nft_rbtree_elem *rbe, *rbe_le =NULL , *rbe_ge =NULL ; +struct rb_node *node, *parent, **p, *first =NULL ;struct nft_rbtree *priv =nft_set_priv (set);u8 genmask =nft_genmask_next (net); -struct nft_rbtree_elem *rbe; -struct rb_node *parent, **p; -int d; +int d, err; -/* Detect overlaps as we descend the tree. Set the flag in these cases: -* -* a1. _ _ __>| ?_ _ __| (insert end before existing end) -* a2. _ _ ___| ?_ _ _>| (insert end after existing end) -* a3. _ _ ___? >|_ _ __| (insert start before existing end) -* -* and clear it later on, as we eventually reach the points indicated by -* '?' above, in the cases described below. We'll always meet these -* later, locally, due to tree ordering, and overlaps for the intervals -* that are the closest together are always evaluated last. -* -* b1. _ _ __>| !_ _ __| (insert end before existing start) -* b2. _ _ ___| !_ _ _>| (insert end after existing start) -* b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf) -* '--' no nodes falling in this range -* b4. >|_ _ ! (insert start before existing start) -* -* Case a3. resolves to b3.: -* - if the inserted start element is the leftmost, because the '0' -* element in the tree serves as end element -* - otherwise, if an existing end is found immediately to the left. If -* there are existing nodes in between, we need to further descend the -* tree before we can conclude the new start isn't causing an overlap -* -* or to b4., which, preceded by a3., means we already traversed one or -* more existing intervals entirely, from the right. -* -* For a new, rightmost pair of elements, we'll hit cases b3. and b2., -* in that order. -* -* The flag is also cleared in two special cases: -* -* b5. |__ _ _!|<_ _ _ (insert start right before existing end) -* b6. |__ _ >|!__ _ _ (insert end right after existing start) -* -* which always happen as last step and imply that no further -* overlapping is possible. -* -* Another special case comes from the fact that start elements matching -* an already existing start element are allowed: insertion is not -* performed but we return -EEXIST in that case, and the error will be -* cleared by the caller if NLM_F_EXCL is not present in the request. -* This way, request for insertion of an exact overlap isn't reported as -* error to userspace if not desired. -* -* However, if the existing start matches a pre-existing start, but the -* end element doesn't match the corresponding pre-existing end element, -* we need to report a partial overlap. This is a local condition that -* can be noticed without need for a tracking flag, by checking for a -* local duplicated end for a corresponding start, from left and right, -* separately. +/* Descend the tree to search for an existing element greater than the +* key value to insert that is greater than the new element. This is the +* first element to walk the ordered elements to find possible overlap. */ - parent =NULL ; p = &priv->root.rb_node;while (*p !=NULL ) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d =memcmp (nft_set_ext_key (&rbe->ext), -nft_set_ext_key (&new->ext), - set->klen); + d =nft_rbtree_cmp (set, rbe, new); +if (d <0 ) { p = &parent->rb_left; - -if (nft_rbtree_interval_start (new)) { -if (nft_rbtree_interval_end (rbe) && -nft_set_elem_active (&rbe->ext, genmask) && - !nft_set_elem_expired (&rbe->ext) && !*p) - overlap = false; - }else { -if (dup_end_left && !*p) -return -ENOTEMPTY ; - - overlap =nft_rbtree_interval_end (rbe) && -nft_set_elem_active (&rbe->ext, - genmask) && - !nft_set_elem_expired (&rbe->ext); - -if (overlap) { - dup_end_right = true; -continue ; - } - } }else if (d >0 ) { - p = &parent->rb_right; +if (!first || +nft_rbtree_update_first (set, rbe, first)) + first = &rbe->node; -if (nft_rbtree_interval_end (new)) { -if (dup_end_right && !*p) -return -ENOTEMPTY ; - - overlap =nft_rbtree_interval_end (rbe) && -nft_set_elem_active (&rbe->ext, - genmask) && - !nft_set_elem_expired (&rbe->ext); - -if (overlap) { - dup_end_left = true; -continue ; - } - }else if (nft_set_elem_active (&rbe->ext, genmask) && - !nft_set_elem_expired (&rbe->ext)) { - overlap =nft_rbtree_interval_end (rbe); - } + p = &parent->rb_right; }else { -if (nft_rbtree_interval_end (rbe) && -nft_rbtree_interval_start (new)) { +if (nft_rbtree_interval_end (rbe)) p = &parent->rb_left; - -if (nft_set_elem_active (&rbe->ext, genmask) && - !nft_set_elem_expired (&rbe->ext)) - overlap = false; - }else if (nft_rbtree_interval_start (rbe) && -nft_rbtree_interval_end (new)) { +else p = &parent->rb_right; + } + } + +if (!first) + first =rb_first (&priv->root); + +/* Detect overlap by going through the list of valid tree nodes. +* Values stored in the tree are in reversed order, starting from +* highest to lowest value. +*/ +for (node = first; node !=NULL ; node =rb_next (node)) { + rbe = rb_entry(node, struct nft_rbtree_elem, node); + +if (!nft_set_elem_active (&rbe->ext, genmask)) +continue ; -if (nft_set_elem_active (&rbe->ext, genmask) && - !nft_set_elem_expired (&rbe->ext)) - overlap = false; - }else if (nft_set_elem_active (&rbe->ext, genmask) && - !nft_set_elem_expired (&rbe->ext)) { - *ext = &rbe->ext; -return -EEXIST ; - }else { - overlap = false; -if (nft_rbtree_interval_end (rbe)) - p = &parent->rb_left; -else - p = &parent->rb_right; +/* perform garbage collection to avoid bogus overlap reports. */ +if (nft_set_elem_expired (&rbe->ext)) { + err =nft_rbtree_gc_elem (set, priv, rbe); +if (err <0 ) +return err; + +continue ; + } + + d =nft_rbtree_cmp (set, rbe, new); +if (d ==0 ) { +/* Matching end element: no need to look for an +* overlapping greater or equal element. +*/ +if (nft_rbtree_interval_end (rbe)) { + rbe_le = rbe; +break ; + } + +/* first element that is greater or equal to key value. */ +if (!rbe_ge) { + rbe_ge = rbe; +continue ; + } + +/* this is a closer more or equal element, update it. */ +if (nft_rbtree_cmp (set, rbe_ge, new) !=0 ) { + rbe_ge = rbe; +continue ; } + +/* element is equal to key value, make sure flags are +* the same, an existing more or equal start element +* must not be replaced by more or equal end element. +*/ +if ((nft_rbtree_interval_start (new) && +nft_rbtree_interval_start (rbe_ge)) || + (nft_rbtree_interval_end (new) && +nft_rbtree_interval_end (rbe_ge))) { + rbe_ge = rbe; +continue ; + } + }else if (d >0 ) { +/* annotate element greater than the new element. */ + rbe_ge = rbe; +continue ; + }else if (d <0 ) { +/* annotate element less than the new element. */ + rbe_le = rbe; +break ; } + } - dup_end_left = dup_end_right = false; +/* - new start element matching existing start element: full overlap +* reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. +*/ +if (rbe_ge && !nft_rbtree_cmp (set, new, rbe_ge) && +nft_rbtree_interval_start (rbe_ge) ==nft_rbtree_interval_start (new)) { + *ext = &rbe_ge->ext; +return -EEXIST ; + } + +/* - new end element matching existing end element: full overlap +* reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. +*/ +if (rbe_le && !nft_rbtree_cmp (set, new, rbe_le) && +nft_rbtree_interval_end (rbe_le) ==nft_rbtree_interval_end (new)) { + *ext = &rbe_le->ext; +return -EEXIST ; } -if (overlap) +/* - new start element with existing closest, less or equal key value +* being a start element: partial overlap, reported as -ENOTEMPTY. +* Anonymous sets allow for two consecutive start element since they +* are constant, skip them to avoid bogus overlap reports. +*/ +if (!nft_set_is_anonymous (set) && rbe_le && +nft_rbtree_interval_start (rbe_le) &&nft_rbtree_interval_start (new)) +return -ENOTEMPTY ; + +/* - new end element with existing closest, less or equal key value +* being a end element: partial overlap, reported as -ENOTEMPTY. +*/ +if (rbe_le && +nft_rbtree_interval_end (rbe_le) &&nft_rbtree_interval_end (new))return -ENOTEMPTY ; +/* - new end element with existing closest, greater or equal key value +* being an end element: partial overlap, reported as -ENOTEMPTY +*/ +if (rbe_ge && +nft_rbtree_interval_end (rbe_ge) &&nft_rbtree_interval_end (new)) +return -ENOTEMPTY ; + +/* Accepted element: pick insertion point depending on key value */ + parent =NULL ; + p = &priv->root.rb_node; +while (*p !=NULL ) { + parent = *p; + rbe = rb_entry(parent, struct nft_rbtree_elem, node); + d =nft_rbtree_cmp (set, rbe, new); + +if (d <0 ) + p = &parent->rb_left; +else if (d >0 ) + p = &parent->rb_right; +else if (nft_rbtree_interval_end (rbe)) + p = &parent->rb_left; +else + p = &parent->rb_right; + } +rb_link_node_rcu (&new->node, parent, p);rb_insert_color (&new->node, &priv->root);return 0 ;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 174/204 netfilter: nft_set_rbtree: skip elements in transaction from garbage collection
In reply to Greg Kroah-HartmanFrom: Pablo Neira Ayuso <[email protected]>
[ Upstream commit 5d235d6ce75c12a7fdee375eb211e4116f7ab01b ]
Skip interference with an ongoing transaction, do not perform garbage collection on inactive elements. Reset annotated previous end interval if the expired element is marked as busy (control plane removed the element right before expiration).
--- net/netfilter/nft_set_rbtree.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)
net/netfilter/nft_set_rbtree.c +15 -1
@@ -563,23 +563,37 @@ 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);
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 175/204 netlink: annotate data races around nlk->portid
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit c1bb9484e3b05166880da8574504156ccbd0549e ]
syzbot reminds us netlink_getname() runs locklessly [1]
This first patch annotates the race against nlk->portid.
Following patches take care of the remaining races.
[1]
BUG: KCSAN: data-race in netlink_getname / netlink_insert
write to 0xffff88814176d310 of 4 bytes by task 2315 on cpu 1:
netlink_insert+0xf1/0x9a0 net/netlink/af_netlink.c:583 netlink_autobind+0xae/0x180 net/netlink/af_netlink.c:856 netlink_sendmsg+0x444/0x760 net/netlink/af_netlink.c:1895 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x19a/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd
read to 0xffff88814176d310 of 4 bytes by task 2316 on cpu 0:
netlink_getname+0xcd/0x1a0 net/netlink/af_netlink.c:1144 __sys_getsockname+0x11d/0x1b0 net/socket.c:2026 __do_sys_getsockname net/socket.c:2041 [inline] __se_sys_getsockname net/socket.c:2038 [inline] __x64_sys_getsockname+0x3e/0x50 net/socket.c:2038 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd
value changed: 0x00000000 -> 0xc9a49780
Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 2316 Comm: syz-executor.2 Not tainted 6.2.0-rc3-syzkaller-00030-ge8f60cd7db24-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022
--- net/netlink/af_netlink.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
net/netlink/af_netlink.c +5 -2
@@ -578,7 +578,9 @@ static int netlink_insert(struct sock *sk, u32 portid)if (nlk_sk (sk)->bound) goto err; -nlk_sk (sk)->portid = portid; +/* portid can be read locklessly from netlink_getname(). */ +WRITE_ONCE (nlk_sk (sk)->portid, portid); +sock_hold (sk); err =__netlink_insert (table, sk);
@@ -1132,7 +1134,8 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_pid = nlk->dst_portid; nladdr->nl_groups =netlink_group_mask (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 ();
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 176/204 netlink: annotate data races around dst_portid and dst_group
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit 004db64d185a5f23dfb891d7701e23713b2420ee ]
netlink_getname(), netlink_sendmsg() and netlink_getsockbyportid() can read nlk->dst_portid and nlk->dst_group while another thread is changing them.
--- net/netlink/af_netlink.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-)
net/netlink/af_netlink.c +14 -9
@@ -1090,8 +1090,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,if (addr->sa_family ==AF_UNSPEC ) { sk->sk_state =NETLINK_UNCONNECTED ; - nlk->dst_portid =0 ; - nlk->dst_group =0 ; +/* 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 )
@@ -1113,8 +1114,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,if (err ==0 ) { sk->sk_state =NETLINK_CONNECTED ; - nlk->dst_portid = nladdr->nl_pid; - nlk->dst_group =ffs (nladdr->nl_groups); +/* 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;
@@ -1131,8 +1133,9 @@ 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 {/* Paired with WRITE_ONCE() in netlink_insert() */ nladdr->nl_pid =READ_ONCE (nlk->portid);
@@ -1162,8 +1165,9 @@ 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); +/* dst_portid can be changed in netlink_connect() */ if (sock->sk_state ==NETLINK_CONNECTED && - nlk->dst_portid !=nlk_sk (ssk)->portid) { +READ_ONCE (nlk->dst_portid) !=nlk_sk (ssk)->portid) {sock_put (sock);return ERR_PTR (-ECONNREFUSED ); }
@@ -1899,8 +1903,9 @@ 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() */
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 177/204 netlink: annotate data races around sk_state
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit 9b663b5cbb15b494ef132a3c937641c90646eb73 ]
netlink_getsockbyportid() reads sk_state while a concurrent netlink_connect() can change its value.
--- net/netlink/af_netlink.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
net/netlink/af_netlink.c +6 -4
@@ -1089,7 +1089,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,return -EINVAL ;if (addr->sa_family ==AF_UNSPEC ) { - sk->sk_state =NETLINK_UNCONNECTED ; +/* 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 );
@@ -1113,7 +1114,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, err =netlink_autobind (sock);if (err ==0 ) { - sk->sk_state =NETLINK_CONNECTED ; +/* 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));
@@ -1165,8 +1167,8 @@ 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); -/* dst_portid can be changed in netlink_connect() */ -if (sock->sk_state ==NETLINK_CONNECTED && +/* 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 );
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 178/204 ipv4: prevent potential spectre v1 gadget in ip_metrics_convert()
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit 1d1d63b612801b3f0a39b7d4467cad0abd60e5c8 ]
if (!type)
continue; if (type > RTAX_MAX) return -EINVAL; ... metrics[type - 1] = val;
@type being used as an array index, we need to prevent cpu speculation or risk leaking kernel memory content.
--- net/ipv4/metrics.c | 2 ++ 1 file changed, 2 insertions(+)
net/ipv4/metrics.c +2 -0
@@ -1,5 +1,6 @@// SPDX-License-Identifier: GPL-2.0-only #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/rtnetlink.h> #include <linux/types.h> #include <net/ip.h>
@@ -28,6 +29,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,return -EINVAL ; } + type =array_index_nospec (type,RTAX_MAX +1 );if (type ==RTAX_CC_ALGO ) {char tmp[TCP_CA_NAME_MAX ];
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 179/204 ipv4: prevent potential spectre v1 gadget in fib_metrics_match()
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit 5e9398a26a92fc402d82ce1f97cc67d832527da0 ]
if (!type)
continue;
if (type > RTAX_MAX)
return false;
...
fi_val = fi->fib_metrics->metrics[type - 1];@type being used as an array index, we need to prevent cpu speculation or risk leaking kernel memory content.
--- net/ipv4/fib_semantics.c | 2 ++ 1 file changed, 2 insertions(+)
net/ipv4/fib_semantics.c +2 -0
@@ -30,6 +30,7 @@#include <linux/slab.h> #include <linux/netlink.h> #include <linux/hash.h> +#include <linux/nospec.h> #include <net/arp.h> #include <net/ip.h>
@@ -1020,6 +1021,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)if (type >RTAX_MAX )return false; + type =array_index_nospec (type,RTAX_MAX +1 );if (type ==RTAX_CC_ALGO ) {char tmp[TCP_CA_NAME_MAX ];bool ecn_ca = false;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 180/204 netfilter: conntrack: fix vtag checks for ABORT/SHUTDOWN_COMPLETE
In reply to Greg Kroah-HartmanFrom: Sriram Yagnaraman <[email protected]>
[ Upstream commit a9993591fa94246b16b444eea55d84c54608282a ]
RFC 9260, Sec 8.5.1 states that for ABORT/SHUTDOWN_COMPLETE, the chunk MUST be accepted if the vtag of the packet matches its own tag and the T bit is not set OR if it is set to its peer's vtag and the T bit is set in chunk flags. Otherwise the packet MUST be silently dropped.
Update vtag verification for ABORT/SHUTDOWN_COMPLETE based on the above description.
--- net/netfilter/nf_conntrack_proto_sctp.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-)
net/netfilter/nf_conntrack_proto_sctp.c +16 -9
@@ -412,22 +412,29 @@ int nf_conntrack_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 ) {
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 181/204 netfilter: conntrack: fix bug in for_each_sctp_chunk
In reply to Greg Kroah-HartmanFrom: Sriram Yagnaraman <[email protected]>
[ Upstream commit 98ee0077452527f971567db01386de3c3d97ce13 ]
skb_header_pointer() will return NULL if offset + sizeof(_sch) exceeds skb->len, so this offset < skb->len test is redundant.
if sch->length == 0, this will end up in an infinite loop, add a check for sch->length > 0
--- net/netfilter/nf_conntrack_proto_sctp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/netfilter/nf_conntrack_proto_sctp.c +2 -2
@@ -155,8 +155,8 @@ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)#define for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) \ for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \ - (offset) < (skb)->len && \ - ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))); \ + ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))) && \ + (sch)->length; \ (offset) += (ntohs((sch)->length) + 3) & ~3, (count)++)/* Some validity checks to make sure the chunks are fine */
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 182/204 netrom: Fix use-after-free of a listening socket.
In reply to Greg Kroah-HartmanFrom: Kuniyuki Iwashima <[email protected]>
[ Upstream commit 409db27e3a2eb5e8ef7226ca33be33361b3ed1c9 ]
syzbot reported a use-after-free in do_accept(), precisely nr_accept() as sk_prot_alloc() allocated the memory and sock_put() frees it. [0]
The issue could happen if the heartbeat timer is fired and nr_heartbeat_expiry() calls nr_destroy_socket(), where a socket has SOCK_DESTROY or a listening socket has SOCK_DEAD.
In this case, the first condition cannot be true. SOCK_DESTROY is flagged in nr_release() only when the file descriptor is close()d, but accept() is being called for the listening socket, so the second condition must be true.
Usually, the AF_NETROM listener neither starts timers nor sets SOCK_DEAD. However, the condition is met if connect() fails before listen(). connect() starts the t1 timer and heartbeat timer, and t1timer calls nr_disconnect() when timeout happens. Then, SOCK_DEAD is set, and if we call listen(), the heartbeat timer calls nr_destroy_socket().
nr_connect
nr_establish_data_link(sk)
nr_start_t1timer(sk)
nr_start_heartbeat(sk)
nr_t1timer_expiry
nr_disconnect(sk, ETIMEDOUT)
nr_sk(sk)->state = NR_STATE_0
sk->sk_state = TCP_CLOSE
sock_set_flag(sk, SOCK_DEAD)
nr_listen
if (sk->sk_state != TCP_LISTEN)
sk->sk_state = TCP_LISTEN
nr_heartbeat_expiry
switch (nr->state)
case NR_STATE_0
if (sk->sk_state == TCP_LISTEN &&
sock_flag(sk, SOCK_DEAD))
nr_destroy_socket(sk)This path seems expected, and nr_destroy_socket() is called to clean up resources. Initially, there was sock_hold() before nr_destroy_socket() so that the socket would not be freed, but the commit 517a16b1a88b ("netrom: Decrease sock refcount when sock timers expire") accidentally removed it.
To fix use-after-free, let's add sock_hold().
[0]:
BUG: KASAN: use-after-free in do_accept+0x483/0x510 net/socket.c:1848 Read of size 8 at addr ffff88807978d398 by task syz-executor.3/5315 CPU: 0 PID: 5315 Comm: syz-executor.3 Not tainted 6.2.0-rc3-syzkaller-00165-gd9fc1511728c #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:306 [inline] print_report+0x15e/0x461 mm/kasan/report.c:417 kasan_report+0xbf/0x1f0 mm/kasan/report.c:517 do_accept+0x483/0x510 net/socket.c:1848 __sys_accept4_file net/socket.c:1897 [inline] __sys_accept4+0x9a/0x120 net/socket.c:1927 __do_sys_accept net/socket.c:1944 [inline] __se_sys_accept net/socket.c:1941 [inline] __x64_sys_accept+0x75/0xb0 net/socket.c:1941 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fa436a8c0c9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fa437784168 EFLAGS: 00000246 ORIG_RAX: 000000000000002b RAX: ffffffffffffffda RBX: 00007fa436bac050 RCX: 00007fa436a8c0c9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000005 RBP: 00007fa436ae7ae9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffebc6700df R14: 00007fa437784300 R15: 0000000000022000 </TASK> Allocated by task 5294: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:371 [inline] ____kasan_kmalloc mm/kasan/common.c:330 [inline] __kasan_kmalloc+0xa3/0xb0 mm/kasan/common.c:380 kasan_kmalloc include/linux/kasan.h:211 [inline] __do_kmalloc_node mm/slab_common.c:968 [inline] __kmalloc+0x5a/0xd0 mm/slab_common.c:981 kmalloc include/linux/slab.h:584 [inline] sk_prot_alloc+0x140/0x290 net/core/sock.c:2038 sk_alloc+0x3a/0x7a0 net/core/sock.c:2091 nr_create+0xb6/0x5f0 net/netrom/af_netrom.c:433 __sock_create+0x359/0x790 net/socket.c:1515 sock_create net/socket.c:1566 [inline] __sys_socket_create net/socket.c:1603 [inline] __sys_socket_create net/socket.c:1588 [inline] __sys_socket+0x133/0x250 net/socket.c:1636 __do_sys_socket net/socket.c:1649 [inline] __se_sys_socket net/socket.c:1647 [inline] __x64_sys_socket+0x73/0xb0 net/socket.c:1647 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 14: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2b/0x40 mm/kasan/generic.c:518 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free+0x13b/0x1a0 mm/kasan/common.c:200 kasan_slab_free include/linux/kasan.h:177 [inline] __cache_free mm/slab.c:3394 [inline] __do_kmem_cache_free mm/slab.c:3580 [inline] __kmem_cache_free+0xcd/0x3b0 mm/slab.c:3587 sk_prot_free net/core/sock.c:2074 [inline] __sk_destruct+0x5df/0x750 net/core/sock.c:2166 sk_destruct net/core/sock.c:2181 [inline] __sk_free+0x175/0x460 net/core/sock.c:2192 sk_free+0x7c/0xa0 net/core/sock.c:2203 sock_put include/net/sock.h:1991 [inline] nr_heartbeat_expiry+0x1d7/0x460 net/netrom/nr_timer.c:148 call_timer_fn+0x1da/0x7c0 kernel/time/timer.c:1700 expire_timers+0x2c6/0x5c0 kernel/time/timer.c:1751 __run_timers kernel/time/timer.c:2022 [inline] __run_timers kernel/time/timer.c:1995 [inline] run_timer_softirq+0x326/0x910 kernel/time/timer.c:2035 __do_softirq+0x1fb/0xadc kernel/softirq.c:571
--- net/netrom/nr_timer.c | 1 + 1 file changed, 1 insertion(+)
net/netrom/nr_timer.c +1 -0
@@ -121,6 +121,7 @@ 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;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 183/204 net/sched: sch_taprio: do not schedule in taprio_reset()
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit ea4fdbaa2f7798cb25adbe4fd52ffc6356f097bb ]
As reported by syzbot and hinted by Vinicius, I should not have added a qdisc_synchronize() call in taprio_reset()
taprio_reset() can be called with qdisc spinlock held (and BH disabled) as shown in included syzbot report [1].
Only taprio_destroy() needed this synchronization, as explained in the blamed commit changelog.
[1]
BUG: scheduling while atomic: syz-executor150/5091/0x00000202 2 locks held by syz-executor150/5091: Modules linked in: Preemption disabled at: [<0000000000000000>] 0x0 Kernel panic - not syncing: scheduling while atomic: panic_on_warn set ... CPU: 1 PID: 5091 Comm: syz-executor150 Not tainted 6.2.0-rc3-syzkaller-00219-g010a74f52203 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106 panic+0x2cc/0x626 kernel/panic.c:318 check_panic_on_warn.cold+0x19/0x35 kernel/panic.c:238 __schedule_bug.cold+0xd5/0xfe kernel/sched/core.c:5836 schedule_debug kernel/sched/core.c:5865 [inline] __schedule+0x34e4/0x5450 kernel/sched/core.c:6500 schedule+0xde/0x1b0 kernel/sched/core.c:6682 schedule_timeout+0x14e/0x2a0 kernel/time/timer.c:2167 schedule_timeout_uninterruptible kernel/time/timer.c:2201 [inline] msleep+0xb6/0x100 kernel/time/timer.c:2322 qdisc_synchronize include/net/sch_generic.h:1295 [inline] taprio_reset+0x93/0x270 net/sched/sch_taprio.c:1703 qdisc_reset+0x10c/0x770 net/sched/sch_generic.c:1022 dev_reset_queue+0x92/0x130 net/sched/sch_generic.c:1285 netdev_for_each_tx_queue include/linux/netdevice.h:2464 [inline] dev_deactivate_many+0x36d/0x9f0 net/sched/sch_generic.c:1351 dev_deactivate+0xed/0x1b0 net/sched/sch_generic.c:1374 qdisc_graft+0xe4a/0x1380 net/sched/sch_api.c:1080 tc_modify_qdisc+0xb6b/0x19a0 net/sched/sch_api.c:1689 rtnetlink_rcv_msg+0x43e/0xca0 net/core/rtnetlink.c:6141 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2564 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x91b/0xe10 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xd3/0x120 net/socket.c:734 ____sys_sendmsg+0x712/0x8c0 net/socket.c:2476 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2530 __sys_sendmsg+0xf7/0x1c0 net/socket.c:2559 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
--- net/sched/sch_taprio.c | 1 - 1 file changed, 1 deletion(-)
net/sched/sch_taprio.c +0 -1
@@ -1632,7 +1632,6 @@ static void taprio_reset(struct Qdisc *sch)int i;hrtimer_cancel (&q->advance_timer); -qdisc_synchronize (sch);if (q->qdiscs) {for (i =0 ; i < dev->num_tx_queues; i++)
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 184/204 sctp: fail if no bound addresses can be used for a given scope
In reply to Greg Kroah-HartmanFrom: Marcelo Ricardo Leitner <[email protected]>
[ Upstream commit 458e279f861d3f61796894cd158b780765a1569f ]
Currently, if you bind the socket to something like:
servaddr.sin6_family = AF_INET6;
servaddr.sin6_port = htons(0);
servaddr.sin6_scope_id = 0;
inet_pton(AF_INET6, "::1", &servaddr.sin6_addr);And then request a connect to:
connaddr.sin6_family = AF_INET6;
connaddr.sin6_port = htons(20000);
connaddr.sin6_scope_id = if_nametoindex("lo");
inet_pton(AF_INET6, "fe88::1", &connaddr.sin6_addr);What the stack does is:
- bind the socket
- create a new asoc
- to handle the connect
- copy the addresses that can be used for the given scope
- try to connect
But the copy returns 0 addresses, and the effect is that it ends up trying to connect as if the socket wasn't bound, which is not the desired behavior. This unexpected behavior also allows KASLR leaks through SCTP diag interface.
The fix here then is, if when trying to copy the addresses that can be used for the scope used in connect() it returns 0 addresses, bail out. This is what TCP does with a similar reproducer.
--- net/sctp/bind_addr.c | 6 ++++++ 1 file changed, 6 insertions(+)
net/sctp/bind_addr.c +6 -0
@@ -73,6 +73,12 @@ 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);
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 185/204 riscv/kprobe: Fix instruction simulation of JALR
In reply to Greg Kroah-HartmanFrom: Liao Chang <[email protected]>
[ Upstream commit ca0254998be4d74cf6add70ccfab0d2dbd362a10 ]
Set kprobe at 'jalr 1140(ra)' of vfs_write results in the following crash:
[ 32.092235] Unable to handle kernel access to user memory without uaccess routines at virtual address 00aaaaaad77b1170 [ 32.093115] Oops [#1] [ 32.093251] Modules linked in: [ 32.093626] CPU: 0 PID: 135 Comm: ftracetest Not tainted 6.2.0-rc2-00013-gb0aa5e5df0cb-dirty #16 [ 32.093985] Hardware name: riscv-virtio,qemu (DT) [ 32.094280] epc : ksys_read+0x88/0xd6 [ 32.094855] ra : ksys_read+0xc0/0xd6 [ 32.095016] epc : ffffffff801cda80 ra : ffffffff801cdab8 sp : ff20000000d7bdc0 [ 32.095227] gp : ffffffff80f14000 tp : ff60000080f9cb40 t0 : ffffffff80f13e80 [ 32.095500] t1 : ffffffff8000c29c t2 : ffffffff800dbc54 s0 : ff20000000d7be60 [ 32.095716] s1 : 0000000000000000 a0 : ffffffff805a64ae a1 : ffffffff80a83708 [ 32.095921] a2 : ffffffff80f160a0 a3 : 0000000000000000 a4 : f229b0afdb165300 [ 32.096171] a5 : f229b0afdb165300 a6 : ffffffff80eeebd0 a7 : 00000000000003ff [ 32.096411] s2 : ff6000007ff76800 s3 : fffffffffffffff7 s4 : 00aaaaaad77b1170 [ 32.096638] s5 : ffffffff80f160a0 s6 : ff6000007ff76800 s7 : 0000000000000030 [ 32.096865] s8 : 00ffffffc3d97be0 s9 : 0000000000000007 s10: 00aaaaaad77c9410 [ 32.097092] s11: 0000000000000000 t3 : ffffffff80f13e48 t4 : ffffffff8000c29c [ 32.097317] t5 : ffffffff8000c29c t6 : ffffffff800dbc54 [ 32.097505] status: 0000000200000120 badaddr: 00aaaaaad77b1170 cause: 000000000000000d [ 32.098011] [<ffffffff801cdb72>] ksys_write+0x6c/0xd6 [ 32.098222] [<ffffffff801cdc06>] sys_write+0x2a/0x38 [ 32.098405] [<ffffffff80003c76>] ret_from_syscall+0x0/0x2
Since the rs1 and rd might be the same one, such as 'jalr 1140(ra)', hence it requires obtaining the target address from rs1 followed by updating rd.
--- arch/riscv/kernel/probes/simulate-insn.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/riscv/kernel/probes/simulate-insn.c +2 -2
@@ -71,11 +71,11 @@ bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regu32 rd_index = (opcode >>7 ) &0x1f ;u32 rs1_index = (opcode >>15 ) &0x1f ; - ret =rv_insn_reg_set_val (regs, rd_index, addr +4 ); + ret =rv_insn_reg_get_val (regs, rs1_index, &base_addr);if (!ret)return ret; - ret =rv_insn_reg_get_val (regs, rs1_index, &base_addr); + ret =rv_insn_reg_set_val (regs, rd_index, addr +4 );if (!ret)return ret;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 186/204 nvme: fix passthrough csi check
In reply to Greg Kroah-HartmanFrom: Keith Busch <[email protected]>
[ Upstream commit 85eee6341abb81ac6a35062ffd5c3029eb53be6b ]
The namespace head saves the Command Set Indicator enum, so use that instead of the Command Set Selected. The two values are not the same.
--- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/nvme/host/core.c +1 -1
@@ -1132,7 +1132,7 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)if (ns) {if (ns->head->effects) effects =le32_to_cpu (ns->head->effects->iocs[opcode]); -if (ns->head->ids.csi ==NVME_CAP_CSS_NVM ) +if (ns->head->ids.csi ==NVME_CSI_NVM ) effects |=nvme_known_nvm_effects (opcode);if (effects & ~(NVME_CMD_EFFECTS_CSUPP |NVME_CMD_EFFECTS_LBCC )) dev_warn_once(ctrl->device,
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 187/204 gpio: mxc: Unlock on error path in mxc_flip_edge()
In reply to Greg Kroah-HartmanFrom: Dan Carpenter <[email protected]>
[ Upstream commit 37870358616ca7fdb1e90ad1cdd791655ec54414 ]
We recently added locking to this function but one error path was over looked. Drop the lock before returning.
--- drivers/gpio/gpio-mxc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/gpio/gpio-mxc.c +2 -1
@@ -236,10 +236,11 @@ static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio) }else {pr_err ("mxc: invalid configuration for GPIO %d: %x\n" , gpio, edge); -return ; + goto unlock; }writel (val | (edge << (bit <<1 )), reg); +unlock:raw_spin_unlock_irqrestore (&port->gc.bgpio_lock, flags); }
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 188/204 ravb: Rename "no_ptp_cfg_active" and "ptp_cfg_active" variables
In reply to Greg Kroah-HartmanFrom: Biju Das <[email protected]>
[ Upstream commit 2b061b545cd0d393585da2909044b15db1ac426f ]
Rename the variable "no_ptp_cfg_active" with "gptp" and "ptp_cfg_active" with "ccc_gac" to match the HW features.
There is no functional change.
Stable-dep-of: c2b6cdee1d13 ("net: ravb: Fix lack of register setting after system resumed for Gen3")
--- drivers/net/ethernet/renesas/ravb.h | 4 ++-- drivers/net/ethernet/renesas/ravb_main.c | 26 ++++++++++++------------ 2 files changed, 15 insertions(+), 15 deletions(-)
drivers/net/ethernet/renesas/ravb.h +2 -2
@@ -1000,8 +1000,8 @@ struct ravb_hw_info { unsigned internal_delay:1; /* AVB-DMAC has internal delays */ unsigned tx_counters:1; /* E-MAC has TX counters */ unsigned multi_irqs:1; /* AVB-DMAC and E-MAC has multiple irqs */ - unsigned no_ptp_cfg_active:1; /* AVB-DMAC does not support gPTP active in config mode */ - unsigned ptp_cfg_active:1; /* AVB-DMAC has gPTP support active in config mode */ + unsigned gptp:1; /* AVB-DMAC has gPTP support */ + unsigned ccc_gac:1; /* AVB-DMAC has gPTP support active in config mode */ };struct ravb_private {
drivers/net/ethernet/renesas/ravb_main.c +13 -13
@@ -1275,7 +1275,7 @@ static int ravb_set_ringparam(struct net_device *ndev,if (netif_running (ndev)) {netif_device_detach (ndev);/* Stop PTP Clock driver */ -if (info->no_ptp_cfg_active) +if (info->gptp)ravb_ptp_stop (ndev);/* Wait for DMA stopping */ error =ravb_stop_dma (ndev);
@@ -1307,7 +1307,7 @@ static int ravb_set_ringparam(struct net_device *ndev,ravb_emac_init (ndev);/* Initialise PTP Clock driver */ -if (info->no_ptp_cfg_active) +if (info->gptp)ravb_ptp_init (ndev, priv->pdev);netif_device_attach (ndev);
@@ -1447,7 +1447,7 @@ static int ravb_open(struct net_device *ndev)ravb_emac_init (ndev);/* Initialise PTP Clock driver */ -if (info->no_ptp_cfg_active) +if (info->gptp)ravb_ptp_init (ndev, priv->pdev);netif_tx_start_all_queues (ndev);
@@ -1461,7 +1461,7 @@ static int ravb_open(struct net_device *ndev) out_ptp_stop:/* Stop PTP Clock driver */ -if (info->no_ptp_cfg_active) +if (info->gptp)ravb_ptp_stop (ndev); out_free_irq_nc_tx:if (!info->multi_irqs)
@@ -1509,7 +1509,7 @@ static void ravb_tx_timeout_work(struct work_struct *work)netif_tx_stop_all_queues (ndev);/* Stop PTP Clock driver */ -if (info->no_ptp_cfg_active) +if (info->gptp)ravb_ptp_stop (ndev);/* Wait for DMA stopping */
@@ -1544,7 +1544,7 @@ static void ravb_tx_timeout_work(struct work_struct *work) out:/* Initialise PTP Clock driver */ -if (info->no_ptp_cfg_active) +if (info->gptp)ravb_ptp_init (ndev, priv->pdev);netif_tx_start_all_queues (ndev);
@@ -1753,7 +1753,7 @@ static int ravb_close(struct net_device *ndev)ravb_write (ndev,0 ,TIC );/* Stop PTP Clock driver */ -if (info->no_ptp_cfg_active) +if (info->gptp)ravb_ptp_stop (ndev);/* Set the config mode to stop the AVB-DMAC's processes */
@@ -2019,7 +2019,7 @@ static const struct ravb_hw_info ravb_gen3_hw_info = { .internal_delay = 1, .tx_counters = 1, .multi_irqs = 1, - .ptp_cfg_active = 1, + .ccc_gac = 1, };static const struct ravb_hw_info ravb_gen2_hw_info = {
@@ -2038,7 +2038,7 @@ static const struct ravb_hw_info ravb_gen2_hw_info = { .stats_len = ARRAY_SIZE(ravb_gstrings_stats), .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, .aligned_tx = 1, - .no_ptp_cfg_active = 1, + .gptp = 1, };static const struct of_device_id ravb_match_table[] = {
@@ -2080,7 +2080,7 @@ static void ravb_set_config_mode(struct net_device *ndev)struct ravb_private *priv =netdev_priv (ndev);const struct ravb_hw_info *info = priv->info; -if (info->no_ptp_cfg_active) { +if (info->gptp) {ravb_modify (ndev,CCC ,CCC_OPC ,CCC_OPC_CONFIG );/* Set CSEL value */ ravb_modify (ndev,CCC ,CCC_CSEL ,CCC_CSEL_HPB );
@@ -2301,7 +2301,7 @@ static int ravb_probe(struct platform_device *pdev)INIT_LIST_HEAD (&priv->ts_skb_list);/* Initialise PTP Clock driver */ -if (info->ptp_cfg_active) +if (info->ccc_gac)ravb_ptp_init (ndev, pdev);/* Debug message level */
@@ -2349,7 +2349,7 @@ static int ravb_probe(struct platform_device *pdev) priv->desc_bat_dma);/* Stop PTP Clock driver */ -if (info->ptp_cfg_active) +if (info->ccc_gac)ravb_ptp_stop (ndev); out_disable_refclk:clk_disable_unprepare (priv->refclk);
@@ -2369,7 +2369,7 @@ static int ravb_remove(struct platform_device *pdev)const struct ravb_hw_info *info = priv->info;/* Stop PTP Clock driver */ -if (info->ptp_cfg_active) +if (info->ccc_gac)ravb_ptp_stop (ndev);clk_disable_unprepare (priv->refclk);
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 189/204 net: ravb: Fix lack of register setting after system resumed for Gen3
In reply to Greg Kroah-HartmanFrom: Yoshihiro Shimoda <[email protected]>
[ Upstream commit c2b6cdee1d13ffbb24baca3c9b8a572d6b541e4e ]
After system entered Suspend to RAM, registers setting of this hardware is reset because the SoC will be turned off. On R-Car Gen3 (info->ccc_gac), ravb_ptp_init() is called in ravb_probe() only. So, after system resumed, it lacks of the initial settings for ptp. So, add ravb_ptp_{init,stop}() into ravb_{resume,suspend}().
--- drivers/net/ethernet/renesas/ravb_main.c | 6 ++++++ 1 file changed, 6 insertions(+)
drivers/net/ethernet/renesas/ravb_main.c +6 -0
@@ -2446,6 +2446,9 @@ static int __maybe_unused ravb_suspend(struct device *dev)else ret =ravb_close (ndev); +if (priv->info->ccc_gac) +ravb_ptp_stop (ndev); +return ret; }
@@ -2482,6 +2485,9 @@ static int __maybe_unused ravb_resume(struct device *dev)/* Restore descriptor base address table */ ravb_write (ndev, priv->desc_bat_dma,DBAT ); +if (priv->info->ccc_gac) +ravb_ptp_init (ndev, priv->pdev); +if (netif_running (ndev)) {if (priv->wol_enabled) { ret =ravb_wol_restore (ndev);
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 190/204 net: ravb: Fix possible hang if RIS2_QFF1 happen
In reply to Greg Kroah-HartmanFrom: Yoshihiro Shimoda <[email protected]>
[ Upstream commit f3c07758c9007a6bfff5290d9e19d3c41930c897 ]
Since this driver enables the interrupt by RIC2_QFE1, this driver should clear the interrupt flag if it happens. Otherwise, the interrupt causes to hang the system.
Note that this also fix a minor coding style (a comment indentation) around the fixed code.
--- drivers/net/ethernet/renesas/ravb_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/renesas/ravb_main.c +2 -2
@@ -792,14 +792,14 @@ 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++;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 191/204 net: mctp: mark socks as dead on unhash, prevent re-add
In reply to Greg Kroah-HartmanFrom: Jeremy Kerr <[email protected]>
[ Upstream commit b98e1a04e27fddfdc808bf46fe78eca30db89ab3 ]
Once a socket has been unhashed, we want to prevent it from being re-used in a sk_key entry as part of a routing operation.
This change marks the sk as SOCK_DEAD on unhash, which prevents addition into the net's key list.
We need to do this during the key add path, rather than key lookup, as we release the net keys_lock between those operations.
--- net/mctp/af_mctp.c | 1 + net/mctp/route.c | 6 ++++++ 2 files changed, 7 insertions(+)
net/mctp/af_mctp.c +1 -0
@@ -288,6 +288,7 @@ static void mctp_sk_unhash(struct sock *sk)kfree_rcu (key, rcu); } +sock_set_flag (sk,SOCK_DEAD );spin_unlock_irqrestore (&net->mctp.keys_lock, flags);synchronize_rcu ();
net/mctp/route.c +6 -0
@@ -135,6 +135,11 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk)spin_lock_irqsave (&net->mctp.keys_lock, flags); +if (sock_flag (&msk->sk,SOCK_DEAD )) { + rc = -EINVAL ; + goto out_unlock; + } +hlist_for_each_entry (tmp, &net->mctp.keys, hlist) {if (mctp_key_match (tmp, key->local_addr, key->peer_addr, key->tag)) {
@@ -148,6 +153,7 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk)hlist_add_head (&key->sklist, &msk->keys); } +out_unlock:spin_unlock_irqrestore (&net->mctp.keys_lock, flags);return rc;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 192/204 thermal: intel: int340x: Add locking to int340x_thermal_get_trip_type()
In reply to Greg Kroah-HartmanFrom: Rafael J. Wysocki <[email protected]>
[ Upstream commit acd7e9ee57c880b99671dd99680cb707b7b5b0ee ]
In order to prevent int340x_thermal_get_trip_type() from possibly racing with int340x_thermal_read_trips() invoked by int3403_notify() add locking to it in analogy with int340x_thermal_get_trip_temp().
--- .../intel/int340x_thermal/int340x_thermal_zone.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)
drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +7 -3
@@ -81,11 +81,13 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, enum thermal_trip_type *type) {struct int34x_thermal_zone *d = zone->devdata; -int i; +int i, ret =0 ;if (d->override_ops && d->override_ops->get_trip_type)return d->override_ops->get_trip_type (zone, trip, type); +mutex_lock (&d->trip_mutex); +if (trip < d->aux_trip_nr) *type =THERMAL_TRIP_PASSIVE ;else if (trip == d->crt_trip_id)
@@ -103,10 +105,12 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, } }if (i ==INT340X_THERMAL_MAX_ACT_TRIP_COUNT ) -return -EINVAL ; + ret = -EINVAL ; } -return 0 ; +mutex_unlock (&d->trip_mutex); + +return ret; } static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone,
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 193/204 net/tg3: resolve deadlock in tg3_reset_task() during EEH
In reply to Greg Kroah-HartmanFrom: David Christensen <[email protected]>
[ Upstream commit 6c4ca03bd890566d873e3593b32d034bf2f5a087 ]
During EEH error injection testing, a deadlock was encountered in the tg3 driver when tg3_io_error_detected() was attempting to cancel outstanding reset tasks:
crash> foreach UN bt
...
PID: 159 TASK: c0000000067c6000 CPU: 8 COMMAND: "eehd"
...
#5 [c00000000681f990] __cancel_work_timer at c00000000019fd18 #6 [c00000000681fa30] tg3_io_error_detected at c00800000295f098 [tg3] #7 [c00000000681faf0] eeh_report_error at c00000000004e25c
...
PID: 290 TASK: c000000036e5f800 CPU: 6 COMMAND: "kworker/6:1"
...
#4 [c00000003721fbc0] rtnl_lock at c000000000c940d8 #5 [c00000003721fbe0] tg3_reset_task at c008000002969358 [tg3] #6 [c00000003721fc60] process_one_work at c00000000019e5c4
...
PID: 296 TASK: c000000037a65800 CPU: 21 COMMAND: "kworker/21:1"
...
#4 [c000000037247bc0] rtnl_lock at c000000000c940d8 #5 [c000000037247be0] tg3_reset_task at c008000002969358 [tg3] #6 [c000000037247c60] process_one_work at c00000000019e5c4
...
PID: 655 TASK: c000000036f49000 CPU: 16 COMMAND: "kworker/16:2"
...:1
#4 [c0000000373ebbc0] rtnl_lock at c000000000c940d8 #5 [c0000000373ebbe0] tg3_reset_task at c008000002969358 [tg3] #6 [c0000000373ebc60] process_one_work at c00000000019e5c4
...
Code inspection shows that both tg3_io_error_detected() and tg3_reset_task() attempt to acquire the RTNL lock at the beginning of their code blocks. If tg3_reset_task() should happen to execute between the times when tg3_io_error_deteced() acquires the RTNL lock and tg3_reset_task_cancel() is called, a deadlock will occur.
Moving tg3_reset_task_cancel() call earlier within the code block, prior to acquiring RTNL, prevents this from happening, but also exposes another deadlock issue where tg3_reset_task() may execute AFTER tg3_io_error_detected() has executed:
crash> foreach UN bt
PID: 159 TASK: c0000000067d2000 CPU: 9 COMMAND: "eehd"
...
#4 [c000000006867a60] rtnl_lock at c000000000c940d8
#5 [c000000006867a80] tg3_io_slot_reset at c0080000026c2ea8 [tg3] #6 [c000000006867b00] eeh_report_reset at c00000000004de88
...
PID: 363 TASK: c000000037564000 CPU: 6 COMMAND: "kworker/6:1"
...
#3 [c000000036c1bb70] msleep at c000000000259e6c
#4 [c000000036c1bba0] napi_disable at c000000000c6b848 #5 [c000000036c1bbe0] tg3_reset_task at c0080000026d942c [tg3] #6 [c000000036c1bc60] process_one_work at c00000000019e5c4
...
This issue can be avoided by aborting tg3_reset_task() if EEH error recovery is already in progress.
--- drivers/net/ethernet/broadcom/tg3.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/net/ethernet/broadcom/tg3.c +4 -4
@@ -11176,7 +11176,7 @@ 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 ();
@@ -18111,6 +18111,9 @@ 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 */
@@ -18127,9 +18130,6 @@ 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 */
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 194/204 net: mdio-mux-meson-g12a: force internal PHY off on mux switch
In reply to Greg Kroah-HartmanFrom: Jerome Brunet <[email protected]>
[ Upstream commit 7083df59abbc2b7500db312cac706493be0273ff ]
Force the internal PHY off then on when switching to the internal path. This fixes problems where the PHY ID is not properly set.
--- drivers/net/mdio/mdio-mux-meson-g12a.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-)
drivers/net/mdio/mdio-mux-meson-g12a.c +16 -7
@@ -4,6 +4,7 @@*/ #include <linux/bitfield.h> +#include <linux/delay.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/device.h>
@@ -150,6 +151,7 @@ static const struct clk_ops g12a_ephy_pll_ops = {static int g12a_enable_internal_mdio (struct g12a_mdio_mux *priv) { +u32 value;int ret;/* Enable the phy clock */
@@ -163,18 +165,25 @@ static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv)/* Initialize ephy control */ writel (EPHY_G12A_ID , priv->regs +ETH_PHY_CNTL0 ); -writel (FIELD_PREP (PHY_CNTL1_ST_MODE ,3 ) | -FIELD_PREP (PHY_CNTL1_ST_PHYADD ,EPHY_DFLT_ADD ) | -FIELD_PREP (PHY_CNTL1_MII_MODE ,EPHY_MODE_RMII ) | -PHY_CNTL1_CLK_EN | -PHY_CNTL1_CLKFREQ | -PHY_CNTL1_PHY_ENB , - priv->regs +ETH_PHY_CNTL1 ); + +/* Make sure we get a 0 -> 1 transition on the enable bit */ + value =FIELD_PREP (PHY_CNTL1_ST_MODE ,3 ) | +FIELD_PREP (PHY_CNTL1_ST_PHYADD ,EPHY_DFLT_ADD ) | +FIELD_PREP (PHY_CNTL1_MII_MODE ,EPHY_MODE_RMII ) | +PHY_CNTL1_CLK_EN | +PHY_CNTL1_CLKFREQ ; +writel (value, priv->regs +ETH_PHY_CNTL1 );writel (PHY_CNTL2_USE_INTERNAL |PHY_CNTL2_SMI_SRC_MAC |PHY_CNTL2_RX_CLK_EPHY , priv->regs +ETH_PHY_CNTL2 ); + value |=PHY_CNTL1_PHY_ENB ; +writel (value, priv->regs +ETH_PHY_CNTL1 ); + +/* The phy needs a bit of time to power up */ +mdelay (10 ); +return 0 ; }
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 195/204 treewide: fix up files incorrectly marked executable
In reply to Greg Kroah-HartmanFrom: Linus Torvalds <[email protected]>
[ Upstream commit 262b42e02d1e0b5ad1b33e9b9842e178c16231de ]
I'm not exactly clear on what strange workflow causes people to do it, but clearly occasionally some files end up being committed as executable even though they clearly aren't.
This is a reprise of commit 90fda63fa115 ("treewide: fix up files incorrectly marked executable"), just with a different set of files (but with the same trivial shell scripting).
So apparently we need to re-do this every five years or so, and Joe needs to just keep reminding me to do so ;)
--- drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 0 1 file changed, 0 insertions(+), 0 deletions(-) mode change 100755 => 100644 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h
drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h +0 -0
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 196/204 tools: gpio: fix -c option of gpio-event-mon
In reply to Greg Kroah-HartmanFrom: Ivo Borisov Shopov <[email protected]>
[ Upstream commit 677d85e1a1ee69fa05ccea83847309484be3781c ]
Following line should listen for a rising edge and exit after the first one since '-c 1' is provided.
# gpio-event-mon -n gpiochip1 -o 0 -r -c 1
It works with kernel 4.19 but it doesn't work with 5.10. In 5.10 the above command doesn't exit after the first rising edge it keep listening for an event forever. The '-c 1' is not taken into an account. The problem is in commit 62757c32d5db ("tools: gpio: add multi-line monitoring to gpio-event-mon").
Before this commit the iterator 'i' in monitor_device() is used for counting of the events (loops). In the case of the above command (-c 1) we should start from 0 and increment 'i' only ones and hit the 'break' statement and exit the process. But after the above commit counting doesn't start from 0, it start from 1 when we listen on one line. It is because 'i' is used from one more purpose, counting of lines (num_lines) and it isn't restore to 0 after following code
for (i = 0; i < num_lines; i++)
gpiotools_set_bit(&values.mask, i);Restore the initial value of the iterator to 0 in order to allow counting of loops to work for any cases.
--- tools/gpio/gpio-event-mon.c | 1 + 1 file changed, 1 insertion(+)
tools/gpio/gpio-event-mon.c +1 -0
@@ -86,6 +86,7 @@ int monitor_device(const char *device_name, gpiotools_test_bit(values.bits, i)); } + i =0 ;while (1 ) {struct gpio_v2_line_event event;
Signature · 1 line
2.39.0
Greg Kroah-Hartman
maintainerPATCH 197/204 Revert "Input: synaptics - switch touchpad on HP Laptop 15-da3001TU to RMI mode"
In reply to Greg Kroah-HartmanFrom: Dmitry Torokhov <[email protected]>
commit 3c44e2b6cde674797b76e76d3a903a63ce8a18bb upstream.
This reverts commit ac5408991ea6b06e29129b4d4861097c4c3e0d59 because it causes loss of keyboard on HP 15-da1xxx.
Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1206358
--- drivers/input/mouse/synaptics.c | 1 - 1 file changed, 1 deletion(-)
drivers/input/mouse/synaptics.c +0 -1
@@ -191,7 +191,6 @@ 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 };
Greg Kroah-Hartman
maintainerPATCH 198/204 cpufreq: Move to_gov_attr_set() to cpufreq.h
In reply to Greg Kroah-HartmanFrom: Kevin Hao <[email protected]>
commit ae26508651272695a3ab353f75ab9a8daf3da324 upstream.
So it can be reused by other codes.
--- drivers/cpufreq/cpufreq_governor_attr_set.c | 5 ----- include/linux/cpufreq.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-)
drivers/cpufreq/cpufreq_governor_attr_set.c +0 -5
@@ -8,11 +8,6 @@#include "cpufreq_governor.h" -static inline struct gov_attr_set *to_gov_attr_set (struct kobject *kobj) -{ - return container_of(kobj, struct gov_attr_set, kobj); -} -static inline struct governor_attr *to_gov_attr (struct attribute *attr) { return container_of(attr, struct governor_attr, attr);
include/linux/cpufreq.h +5 -0
@@ -643,6 +643,11 @@ struct gov_attr_set {/* sysfs ops for cpufreq governors */ extern const struct sysfs_ops governor_sysfs_ops; +static inline struct gov_attr_set *to_gov_attr_set (struct kobject *kobj) +{ + return container_of(kobj, struct gov_attr_set, kobj); +} +void gov_attr_set_init (struct gov_attr_set *attr_set,struct list_head *list_node);void gov_attr_set_get (struct gov_attr_set *attr_set,struct list_head *list_node);unsigned int gov_attr_set_put (struct gov_attr_set *attr_set,struct list_head *list_node);
Greg Kroah-Hartman
maintainerPATCH 199/204 cpufreq: governor: Use kobject release() method to free dbs_data
In reply to Greg Kroah-HartmanFrom: Kevin Hao <[email protected]>
commit a85ee6401a47ae3fc64ba506cacb3e7873823c65 upstream.
The struct dbs_data embeds a struct gov_attr_set and
the struct gov_attr_set embeds a kobject. Since every kobject must have a release() method and we can't use kfree() to free it directly, so introduce cpufreq_dbs_data_release() to release the dbs_data via the kobject::release() method. This fixes the calltrace like below:
ODEBUG: free active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x34
WARNING: CPU: 12 PID: 810 at lib/debugobjects.c:505 debug_print_object+0xb8/0x100 Modules linked in: CPU: 12 PID: 810 Comm: sh Not tainted 5.16.0-next-20220120-yocto-standard+ #536 Hardware name: Marvell OcteonTX CN96XX board (DT) pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : debug_print_object+0xb8/0x100 lr : debug_print_object+0xb8/0x100 sp : ffff80001dfcf9a0 x29: ffff80001dfcf9a0 x28: 0000000000000001 x27: ffff0001464f0000 x26: 0000000000000000 x25: ffff8000090e3f00 x24: ffff80000af60210 x23: ffff8000094dfb78 x22: ffff8000090e3f00 x21: ffff0001080b7118 x20: ffff80000aeb2430 x19: ffff800009e8f5e0 x18: 0000000000000000 x17: 0000000000000002 x16: 00004d62e58be040 x15: 013590470523aff8 x14: ffff8000090e1828 x13: 0000000001359047 x12: 00000000f5257d14 x11: 0000000000040591 x10: 0000000066c1ffea x9 : ffff8000080d15e0 x8 : ffff80000a1765a8 x7 : 0000000000000000 x6 : 0000000000000001 x5 : ffff800009e8c000 x4 : ffff800009e8c760 x3 : 0000000000000000 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0001474ed040 Call trace: debug_print_object+0xb8/0x100 __debug_check_no_obj_freed+0x1d0/0x25c debug_check_no_obj_freed+0x24/0xa0 kfree+0x11c/0x440 cpufreq_dbs_governor_exit+0xa8/0xac cpufreq_exit_governor+0x44/0x90 cpufreq_set_policy+0x29c/0x570 store_scaling_governor+0x110/0x154 store+0xb0/0xe0 sysfs_kf_write+0x58/0x84 kernfs_fop_write_iter+0x12c/0x1c0 new_sync_write+0xf0/0x18c vfs_write+0x1cc/0x220 ksys_write+0x74/0x100 __arm64_sys_write+0x28/0x3c invoke_syscall.constprop.0+0x58/0xf0 do_el0_svc+0x70/0x170 el0_svc+0x54/0x190 el0t_64_sync_handler+0xa4/0x130 el0t_64_sync+0x1a0/0x1a4 irq event stamp: 189006 hardirqs last enabled at (189005): [<ffff8000080849d0>] finish_task_switch.isra.0+0xe0/0x2c0 hardirqs last disabled at (189006): [<ffff8000090667a4>] el1_dbg+0x24/0xa0 softirqs last enabled at (188966): [<ffff8000080106d0>] __do_softirq+0x4b0/0x6a0 softirqs last disabled at (188957): [<ffff80000804a618>] __irq_exit_rcu+0x108/0x1a4
[ rjw: Because can be freed by the gov_attr_set_put() in
cpufreq_dbs_governor_exit() now, it is also necessary to put the invocation of the governor ->exit() callback into the new cpufreq_dbs_data_release() function. ]
--- drivers/cpufreq/cpufreq_governor.c | 20 +++++++++++++------- drivers/cpufreq/cpufreq_governor.h | 1 + 2 files changed, 14 insertions(+), 7 deletions(-)
drivers/cpufreq/cpufreq_governor.c +13 -7
@@ -388,6 +388,15 @@ static void free_policy_dbs_info(struct gov->free (policy_dbs); } +static void cpufreq_dbs_data_release (struct kobject *kobj) +{ +struct dbs_data *dbs_data =to_dbs_data (to_gov_attr_set (kobj)); +struct dbs_governor *gov = dbs_data->gov; + + gov->exit (dbs_data); +kfree (dbs_data); +} +int cpufreq_dbs_governor_init (struct cpufreq_policy *policy) {struct dbs_governor *gov =dbs_governor_of (policy);
@@ -425,6 +434,7 @@ int cpufreq_dbs_governor_init(struct cpu goto free_policy_dbs_info; } + dbs_data->gov = gov;gov_attr_set_init (&dbs_data->attr_set, &policy_dbs->list); ret = gov->init (dbs_data);
@@ -447,6 +457,7 @@ int cpufreq_dbs_governor_init(struct cpu policy->governor_data = policy_dbs; gov->kobj_type.sysfs_ops = &governor_sysfs_ops; + gov->kobj_type.release = cpufreq_dbs_data_release; ret =kobject_init_and_add (&dbs_data->attr_set.kobj, &gov->kobj_type,get_governor_parent_kobj (policy),"%s" , gov->gov.name);
@@ -488,13 +499,8 @@ void cpufreq_dbs_governor_exit(struct cp policy->governor_data =NULL ; -if (!count) { -if (!have_governor_per_policy ()) - gov->gdbs_data =NULL ; - - gov->exit (dbs_data); -kfree (dbs_data); - } +if (!count && !have_governor_per_policy ()) + gov->gdbs_data =NULL ;free_policy_dbs_info (policy_dbs, gov);
drivers/cpufreq/cpufreq_governor.h +1 -0
@@ -37,6 +37,7 @@ enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};/* Governor demand based switching data (per-policy or global). */ struct dbs_data {struct gov_attr_set attr_set; +struct dbs_governor *gov;void *tuners;unsigned int ignore_nice_load;unsigned int sampling_rate;
Greg Kroah-Hartman
maintainerPATCH 200/204 kbuild: Allow kernel installation packaging to override pkg-config
In reply to Greg Kroah-HartmanFrom: Chun-Tse Shao <[email protected]>
commit d5ea4fece4508bf8e72b659cd22fa4840d8d61e5 upstream.
Add HOSTPKG_CONFIG to allow tooling that builds the kernel to override what pkg-config and parameters are used.
[[email protected]: Drop certs/Makefile hunk that doesn't apply because pkg-config isn't used there, add dtc/Makefile hunk to fix dtb builds]
--- Makefile | 3 ++- scripts/Makefile | 4 ++-- scripts/dtc/Makefile | 6 +++--- scripts/kconfig/gconf-cfg.sh | 12 ++++++------ scripts/kconfig/mconf-cfg.sh | 16 ++++++++-------- scripts/kconfig/nconf-cfg.sh | 16 ++++++++-------- scripts/kconfig/qconf-cfg.sh | 14 +++++++------- tools/objtool/Makefile | 4 ++-- 8 files changed, 38 insertions(+), 37 deletions(-)
Makefile +2 -1
@@ -430,6 +430,7 @@ else HOSTCC = gcc HOSTCXX = g++ endif +HOSTPKG_CONFIG = pkg-config export KBUILD_USERCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes \ -O2 -fomit-frame-pointer -std=gnu89
@@ -525,7 +526,7 @@ KBUILD_LDFLAGS_MODULE := KBUILD_LDFLAGS := CLANG_FLAGS := -export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC +export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC HOSTPKG_CONFIG export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL export PERL PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD
scripts/Makefile +2 -2
@@ -3,8 +3,8 @@ # scripts contains sources for various helper programs used throughout # the kernel for the build process. -CRYPTO_LIBS = $(shell pkg-config --libs libcrypto 2> /dev/null || echo -lcrypto) -CRYPTO_CFLAGS = $(shell pkg-config --cflags libcrypto 2> /dev/null) +CRYPTO_LIBS = $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto) +CRYPTO_CFLAGS = $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) hostprogs-always-$(CONFIG_BUILD_BIN2C) += bin2c hostprogs-always-$(CONFIG_KALLSYMS) += kallsyms
scripts/dtc/Makefile +3 -3
@@ -18,7 +18,7 @@ fdtoverlay-objs := $(libfdt) fdtoverlay. # Source files need to get at the userspace version of libfdt_env.h to compile HOST_EXTRACFLAGS += -I $(srctree)/$(src)/libfdt -ifeq ($(shell pkg-config --exists yaml-0.1 2>/dev/null && echo yes),) +ifeq ($(shell $(HOSTPKG_CONFIG) --exists yaml-0.1 2>/dev/null && echo yes),) ifneq ($(CHECK_DT_BINDING)$(CHECK_DTBS),) $(error dtc needs libyaml for DT schema validation support. \ Install the necessary libyaml development package.)
@@ -27,9 +27,9 @@ HOST_EXTRACFLAGS += -DNO_YAML else dtc-objs += yamltree.o # To include <yaml.h> installed in a non-default path -HOSTCFLAGS_yamltree.o := $(shell pkg-config --cflags yaml-0.1) +HOSTCFLAGS_yamltree.o := $(shell $(HOSTPKG_CONFIG) --cflags yaml-0.1) # To link libyaml installed in a non-default path -HOSTLDLIBS_dtc := $(shell pkg-config --libs yaml-0.1) +HOSTLDLIBS_dtc := $(shell $(HOSTPKG_CONFIG) --libs yaml-0.1) endif # Generated files need one more search path to include headers in source tree
scripts/kconfig/gconf-cfg.sh +6 -6
@@ -3,14 +3,14 @@ PKG="gtk+-2.0 gmodule-2.0 libglade-2.0" -if [ -z "$(command -v pkg-config)" ]; then +if [ -z "$(command -v ${HOSTPKG_CONFIG})" ]; then echo >&2 "*" - echo >&2 "* 'make gconfig' requires 'pkg-config'. Please install it." + echo >&2 "* 'make gconfig' requires '${HOSTPKG_CONFIG}'. Please install it." echo >&2 "*" exit 1 fi -if ! pkg-config --exists $PKG; then +if ! ${HOSTPKG_CONFIG} --exists $PKG; then echo >&2 "*" echo >&2 "* Unable to find the GTK+ installation. Please make sure that" echo >&2 "* the GTK+ 2.0 development package is correctly installed."
@@ -19,12 +19,12 @@ if ! pkg-config --exists $PKG; then exit 1 fi -if ! pkg-config --atleast-version=2.0.0 gtk+-2.0; then +if ! ${HOSTPKG_CONFIG} --atleast-version=2.0.0 gtk+-2.0; then echo >&2 "*" echo >&2 "* GTK+ is present but version >= 2.0.0 is required." echo >&2 "*" exit 1 fi -echo cflags=\"$(pkg-config --cflags $PKG)\" -echo libs=\"$(pkg-config --libs $PKG)\" +echo cflags=\"$(${HOSTPKG_CONFIG} --cflags $PKG)\" +echo libs=\"$(${HOSTPKG_CONFIG} --libs $PKG)\"
scripts/kconfig/mconf-cfg.sh +8 -8
@@ -4,16 +4,16 @@ PKG="ncursesw" PKG2="ncurses" -if [ -n "$(command -v pkg-config)" ]; then - if pkg-config --exists $PKG; then - echo cflags=\"$(pkg-config --cflags $PKG)\" - echo libs=\"$(pkg-config --libs $PKG)\" +if [ -n "$(command -v ${HOSTPKG_CONFIG})" ]; then + if ${HOSTPKG_CONFIG} --exists $PKG; then + echo cflags=\"$(${HOSTPKG_CONFIG} --cflags $PKG)\" + echo libs=\"$(${HOSTPKG_CONFIG} --libs $PKG)\" exit 0 fi - if pkg-config --exists $PKG2; then - echo cflags=\"$(pkg-config --cflags $PKG2)\" - echo libs=\"$(pkg-config --libs $PKG2)\" + if ${HOSTPKG_CONFIG} --exists $PKG2; then + echo cflags=\"$(${HOSTPKG_CONFIG} --cflags $PKG2)\" + echo libs=\"$(${HOSTPKG_CONFIG} --libs $PKG2)\" exit 0 fi fi
@@ -46,7 +46,7 @@ echo >&2 "* Unable to find the ncurses p echo >&2 "* Install ncurses (ncurses-devel or libncurses-dev" echo >&2 "* depending on your distribution)." echo >&2 "*" -echo >&2 "* You may also need to install pkg-config to find the" +echo >&2 "* You may also need to install ${HOSTPKG_CONFIG} to find the" echo >&2 "* ncurses installed in a non-default location." echo >&2 "*" exit 1
scripts/kconfig/nconf-cfg.sh +8 -8
@@ -4,16 +4,16 @@ PKG="ncursesw menuw panelw" PKG2="ncurses menu panel" -if [ -n "$(command -v pkg-config)" ]; then - if pkg-config --exists $PKG; then - echo cflags=\"$(pkg-config --cflags $PKG)\" - echo libs=\"$(pkg-config --libs $PKG)\" +if [ -n "$(command -v ${HOSTPKG_CONFIG})" ]; then + if ${HOSTPKG_CONFIG} --exists $PKG; then + echo cflags=\"$(${HOSTPKG_CONFIG} --cflags $PKG)\" + echo libs=\"$(${HOSTPKG_CONFIG} --libs $PKG)\" exit 0 fi - if pkg-config --exists $PKG2; then - echo cflags=\"$(pkg-config --cflags $PKG2)\" - echo libs=\"$(pkg-config --libs $PKG2)\" + if ${HOSTPKG_CONFIG} --exists $PKG2; then + echo cflags=\"$(${HOSTPKG_CONFIG} --cflags $PKG2)\" + echo libs=\"$(${HOSTPKG_CONFIG} --libs $PKG2)\" exit 0 fi fi
@@ -44,7 +44,7 @@ echo >&2 "* Unable to find the ncurses p echo >&2 "* Install ncurses (ncurses-devel or libncurses-dev" echo >&2 "* depending on your distribution)." echo >&2 "*" -echo >&2 "* You may also need to install pkg-config to find the" +echo >&2 "* You may also need to install ${HOSTPKG_CONFIG} to find the" echo >&2 "* ncurses installed in a non-default location." echo >&2 "*" exit 1
scripts/kconfig/qconf-cfg.sh +7 -7
@@ -3,22 +3,22 @@ PKG="Qt5Core Qt5Gui Qt5Widgets" -if [ -z "$(command -v pkg-config)" ]; then +if [ -z "$(command -v ${HOSTPKG_CONFIG})" ]; then echo >&2 "*" - echo >&2 "* 'make xconfig' requires 'pkg-config'. Please install it." + echo >&2 "* 'make xconfig' requires '${HOSTPKG_CONFIG}'. Please install it." echo >&2 "*" exit 1 fi -if pkg-config --exists $PKG; then - echo cflags=\"-std=c++11 -fPIC $(pkg-config --cflags $PKG)\" - echo libs=\"$(pkg-config --libs $PKG)\" - echo moc=\"$(pkg-config --variable=host_bins Qt5Core)/moc\" +if ${HOSTPKG_CONFIG} --exists $PKG; then + echo cflags=\"-std=c++11 -fPIC $(${HOSTPKG_CONFIG} --cflags $PKG)\" + echo libs=\"$(${HOSTPKG_CONFIG} --libs $PKG)\" + echo moc=\"$(${HOSTPKG_CONFIG} --variable=host_bins Qt5Core)/moc\" exit 0 fi echo >&2 "*" -echo >&2 "* Could not find Qt5 via pkg-config." +echo >&2 "* Could not find Qt5 via ${HOSTPKG_CONFIG}." echo >&2 "* Please install Qt5 and make sure it's in PKG_CONFIG_PATH" echo >&2 "*" exit 1
tools/objtool/Makefile +2 -2
@@ -19,8 +19,8 @@ LIBSUBCMD = $(LIBSUBCMD_OUTPUT)libsubcm OBJTOOL := $(OUTPUT)objtool OBJTOOL_IN := $(OBJTOOL)-in.o -LIBELF_FLAGS := $(shell pkg-config libelf --cflags 2>/dev/null) -LIBELF_LIBS := $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf) +LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) +LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) all: $(OBJTOOL)
Greg Kroah-Hartman
maintainerPATCH 201/204 block: fix and cleanup bio_check_ro
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
commit 57e95e4670d1126c103305bcf34a9442f49f6d6a upstream.
Don't use a WARN_ON when printing a potentially user triggered condition. Also don't print the partno when the block device name already includes it, and use the %pg specifier to simplify printing the block device name.
--- block/blk-core.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)
block/blk-core.c +2 -6
@@ -698,14 +698,10 @@ static inline bool should_fail_request(sstatic inline bool bio_check_ro (struct bio *bio) {if (op_is_write (bio_op (bio)) &&bdev_read_only (bio->bi_bdev)) { -char b[BDEVNAME_SIZE ]; -if (op_is_flush (bio->bi_opf) && !bio_sectors (bio))return false; - -WARN_ONCE (1 , -"Trying to write to read-only block-device %s (partno %d)\n" , -bio_devname (bio, b), bio->bi_bdev->bd_partno); +pr_warn ("Trying to write to read-only block-device %pg\n" , + bio->bi_bdev);/* Older lvm-tools actually trigger this */ return false; }
Greg Kroah-Hartman
maintainerPATCH 202/204 x86/i8259: Mark legacy PIC interrupts with IRQ_LEVEL
In reply to Greg Kroah-HartmanFrom: Thomas Gleixner <[email protected]>
commit 5fa55950729d0762a787451dc52862c3f850f859 upstream.
Baoquan reported that after triggering a crash the subsequent crash-kernel fails to boot about half of the time. It triggers a NULL pointer dereference in the periodic tick code.
This happens because the legacy timer interrupt (IRQ0) is resent in software which happens in soft interrupt (tasklet) context. In this context get_irq_regs() returns NULL which leads to the NULL pointer dereference.
The reason for the resend is a spurious APIC interrupt on the IRQ0 vector which is captured and leads to a resend when the legacy timer interrupt is enabled. This is wrong because the legacy PIC interrupts are level triggered and therefore should never be resent in software, but nothing ever sets the IRQ_LEVEL flag on those interrupts, so the core code does not know about their trigger type.
Ensure that IRQ_LEVEL is set when the legacy PCI interrupts are set up.
--- arch/x86/kernel/i8259.c | 1 + arch/x86/kernel/irqinit.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-)
arch/x86/kernel/i8259.c +1 -0
@@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned intdisable_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); }
arch/x86/kernel/irqinit.c +3 -1
@@ -65,8 +65,10 @@ 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 )
Greg Kroah-Hartman
maintainerPATCH 203/204 netfilter: conntrack: unify established states for SCTP paths
In reply to Greg Kroah-HartmanFrom: Sriram Yagnaraman <[email protected]>
commit a44b7651489f26271ac784b70895e8a85d0cebf4 upstream.
An SCTP endpoint can start an association through a path and tear it down over another one. That means the initial path will not see the shutdown sequence, and the conntrack entry will remain in ESTABLISHED state for 5 days.
By merging the HEARTBEAT_ACKED and ESTABLISHED states into one ESTABLISHED state, there remains no difference between a primary or secondary path. The timeout for the merged ESTABLISHED state is set to 210 seconds (hb_interval * max_path_retrans + rto_max). So, even if a path doesn't see the shutdown sequence, it will expire in a reasonable amount of time.
With this change in place, there is now more than one state from which we can transition to ESTABLISHED, COOKIE_ECHOED and HEARTBEAT_SENT, so handle the setting of ASSURED bit whenever a state change has happened and the new state is ESTABLISHED. Removed the check for dir==REPLY since the transition to ESTABLISHED can happen only in the reply direction.
--- include/uapi/linux/netfilter/nf_conntrack_sctp.h | 2 include/uapi/linux/netfilter/nfnetlink_cttimeout.h | 2 net/netfilter/nf_conntrack_proto_sctp.c | 93 ++++++++------------- net/netfilter/nf_conntrack_standalone.c | 8 - 4 files changed, 41 insertions(+), 64 deletions(-)
include/uapi/linux/netfilter/nf_conntrack_sctp.h +1 -1
@@ -15,7 +15,7 @@ enum sctp_conntrack {SCTP_CONNTRACK_SHUTDOWN_RECD ,SCTP_CONNTRACK_SHUTDOWN_ACK_SENT ,SCTP_CONNTRACK_HEARTBEAT_SENT , -SCTP_CONNTRACK_HEARTBEAT_ACKED , +SCTP_CONNTRACK_HEARTBEAT_ACKED ,/* no longer used */ SCTP_CONNTRACK_MAX };
include/uapi/linux/netfilter/nfnetlink_cttimeout.h +1 -1
@@ -94,7 +94,7 @@ enum ctattr_timeout_sctp {CTA_TIMEOUT_SCTP_SHUTDOWN_RECD ,CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT ,CTA_TIMEOUT_SCTP_HEARTBEAT_SENT , -CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED , +CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED ,/* no longer used */ __CTA_TIMEOUT_SCTP_MAX };#define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1)
net/netfilter/nf_conntrack_proto_sctp.c +39 -54
144 lines not on this page · raw message
net/netfilter/nf_conntrack_standalone.c +0 -8
@@ -599,7 +599,6 @@ enum nf_ct_sysctl_index {NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD ,NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT ,NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT , -NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED , #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST,
@@ -892,12 +891,6 @@ static struct ctl_table nf_ct_sysctl_tab .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { - .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - },#endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = {
@@ -1041,7 +1034,6 @@ static void nf_conntrack_standalone_initXASSIGN (SHUTDOWN_RECD , sn);XASSIGN (SHUTDOWN_ACK_SENT , sn);XASSIGN (HEARTBEAT_SENT , sn); -XASSIGN (HEARTBEAT_ACKED , sn);#undef XASSIGN#endif }
Greg Kroah-Hartman
maintainerPATCH 204/204 perf/x86/amd: fix potential integer overflow on shift of a int
In reply to Greg Kroah-HartmanFrom: Colin Ian King <[email protected]>
commit 08245672cdc6505550d1a5020603b0a8d4a6dcc7 upstream.
The left shift of int 32 bit integer constant 1 is evaluated using 32 bit arithmetic and then passed as a 64 bit function argument. In the case where i is 32 or more this can lead to an overflow. Avoid this by shifting using the BIT_ULL macro instead.
--- arch/x86/events/amd/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/events/amd/core.c +1 -1
@@ -976,7 +976,7 @@ static int __init amd_core_pmu_init(void* numbered counter following it. */ for (i =0 ; i < x86_pmu.num_counters -1 ; i +=2 ) - even_ctr_mask |=1 << i; + even_ctr_mask |=BIT_ULL (i); pair_constraint = (struct event_constraint ) __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
Quoted 9 lines · Greg Kroah-Hartman
This is the start of the stable review cycle for the 5.15.91 release. There are 204 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 01 Feb 2023 13:42:39 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
Quoted 8 lines
https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.91-rc1.gzor in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.gitlinux-5.15.y
and the diffstat can be found below.thanks,
greg k-h
On ARCH_BRCMSTB using 32-bit and 64-bit, build tested on BMIPS_GENERIC:
Signature · 1 line
Florian
Quoted 9 lines · Greg Kroah-Hartman
This is the start of the stable review cycle for the 5.15.91 release. There are 204 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 01 Feb 2023 13:42:39 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
Quoted 9 lines
https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.91-rc1.gzor in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.gitlinux-5.15.y
and the diffstat can be found below.thanks,
greg k-h
Compiled and booted on my test system. No dmesg regressions.
thanks,
-- Shuah
Quoted 8 lines · Greg Kroah-Hartman
This is the start of the stable review cycle for the 5.15.91 release. There are 204 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 01 Feb 2023 13:42:39 +0000. Anything received after that time might be too late.
Build results:
total: 160 pass: 160 fail: 0 Qemu test results: total: 492 pass: 492 fail: 0
Guenter
Quoted 5 lines · Greg Kroah-Hartman
This is the start of the stable review cycle for the 5.15.91 release. There are 204 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Successfully cross-compiled for arm64 (bcm2711_defconfig, GCC 10.2.0) and powerpc (ps3_defconfig, GCC 12.2.0).
Signature · 1 line
An old man doll... just what I always wanted! - Clara
Quoted 10 lines · Greg Kroah-Hartman
This is the start of the stable review cycle for the 5.15.91 release. There are 204 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 01 Feb 2023 13:42:39 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
Quoted 8 lines
https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.91-rc1.gzor in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.gitlinux-5.15.y
and the diffstat can be found below.thanks,
greg k-h
Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.
## Build
* kernel: 5.15.91-rc1
* git: https://gitlab.com/Linaro/lkft/mirrors/stable/linux-stable-rc
* git branch: linux-5.15.y
* git commit: 5605d15db0225e49efaa8f83e03f78a8bee3bb5d
* git describe: v5.15.90-205-g5605d15db022
* test details:
https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.15.y/build/v5.15.90-205-g5605d15db022
## Test Regressions (compared to v5.15.90)
## Metric Regressions (compared to v5.15.90)
## Test Fixes (compared to v5.15.90)
## Metric Fixes (compared to v5.15.90)
## Test result summary
total: 154391, pass: 127547, fail: 4115, skip: 22498, xfail: 231
## Build Summary
* arc: 5 total, 5 passed, 0 failed
* arm: 151 total, 150 passed, 1 failed
* arm64: 49 total, 47 passed, 2 failed
* i386: 39 total, 35 passed, 4 failed
* mips: 31 total, 29 passed, 2 failed
* parisc: 8 total, 8 passed, 0 failed
* powerpc: 34 total, 32 passed, 2 failed
* riscv: 14 total, 14 passed, 0 failed
* s390: 16 total, 14 passed, 2 failed
* sh: 14 total, 12 passed, 2 failed
* sparc: 8 total, 8 passed, 0 failed
* x86_64: 42 total, 40 passed, 2 failed
## Test suites summary
* boot
* fwts
* kselftest-android
* kselftest-arm64
* kselftest-breakpoints
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-drivers-dma-buf
* kselftest-efivarfs
* kselftest-filesystems
* kselftest-filesystems-binderfs
* kselftest-firmware
* kselftest-fpu
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-kexec
* kselftest-kvm
* kselftest-lib
* kselftest-livepatch
* kselftest-membarrier
* kselftest-memfd
* kselftest-memory-hotplug
* kselftest-mincore
* kselftest-mount
* kselftest-mqueue
* kselftest-net
* kselftest-net-forwarding
* kselftest-net-mptcp
* kselftest-netfilter
* kselftest-nsfs
* kselftest-openat2
* kselftest-pid_namespace
* kselftest-pidfd
* kselftest-proc
* kselftest-pstore
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-splice
* kselftest-static_keys
* kselftest-sync
* kselftest-sysctl
* kselftest-tc-testing
* kselftest-timens
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-vm
* kselftest-x86
* kselftest-zram
* kunit
* kvm-unit-tests
* libgpiod
* libhugetlbfs
* log-parser-boot
* log-parser-test
* ltp-cap_bounds
* ltp-commands
* ltp-containers
* ltp-controllers
* ltp-cpuhotplug
* ltp-crypto
* ltp-cve
* ltp-dio
* ltp-fcntl-locktests
* ltp-filecaps
* ltp-fs
* ltp-fs_bind
* ltp-fs_perms_simple
* ltp-fsx
* ltp-hugetlb
* ltp-io
* ltp-ipc
* ltp-math
* ltp-mm
* ltp-nptl
* ltp-open-posix-tests
* ltp-pty
* ltp-sched
* ltp-securebits
* ltp-smoke
* ltp-syscalls
* ltp-tracing
* network-basic-tests
* perf
* rcutorture
* v4l2-compliance
* vdso
--
Linaro LKFT
https://lkft.linaro.org
Hi Greg,
Quoted 7 lines · Greg Kroah-Hartman
This is the start of the stable review cycle for the 5.15.91 release. There are 204 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 01 Feb 2023 13:42:39 +0000. Anything received after that time might be too late.
Build test (gcc version 12.2.1 20230113):
mips: 62 configs -> no failure
arm: 99 configs -> no failure
arm64: 3 configs -> no failurex86_64: 4 configs -> no failure
alpha allmodconfig -> no failure
csky allmodconfig -> no failure
powerpc allmodconfig -> no failure
riscv allmodconfig -> no failure
s390 allmodconfig -> no failure
xtensa allmodconfig -> no failure
Boot test:x86_64: Booted on my test laptop. No regression.x86_64: Booted on qemu. No regression. [1]
arm64: Booted on rpi4b (4GB model). No regression. [2]
mips: Booted on ci20 board. No regression. [3]
[1]. https://openqa.qa.codethink.co.uk/tests/2768
[2]. https://openqa.qa.codethink.co.uk/tests/2771
[3]. https://openqa.qa.codethink.co.uk/tests/2775
Signature · 2 lines
Regards Sudip
Quoted 9 lines · Greg Kroah-Hartman
This is the start of the stable review cycle for the 5.15.91 release. There are 204 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 01 Feb 2023 13:42:39 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
Quoted 8 lines
https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.91-rc1.gzor in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.gitlinux-5.15.y
and the diffstat can be found below.thanks,
greg k-h
All tests passing for Tegra ...
Test results for stable-v5.15:
11 builds: 11 pass, 0 fail
28 boots: 28 pass, 0 fail
114 tests: 114 pass, 0 failLinux version: 5.15.91-rc1-g5605d15db022
Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000,
tegra194-p2972-0000, tegra194-p3509-0000+p3668-0000,
tegra20-ventana, tegra210-p2371-2180,
tegra210-p3450-0000, tegra30-cardhu-a04Jon
Quoted 9 lines
This is the start of the stable review cycle for the 5.15.91 release. There are 204 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 01 Feb 2023 13:42:39 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
Quoted 9 lines
https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.91-rc1.gzor in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.gitlinux-5.15.y
and the diffstat can be found below.thanks,
greg k-h
Compiled and booted on my x86_64 and ARM64 test systems. No errors or regressions.
Thanks.