diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 881582f75c9c..bd4370487b07 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB) ... unused hole ... +ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks +... unused hole ... ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls diff --git a/Makefile b/Makefile index f9f6ee59c61a..b94f00938acc 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 10 -SUBLEVEL = 51 +SUBLEVEL = 52 EXTRAVERSION = NAME = TOSSUG Baby Fish diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 83cb3ac27095..c61d2373408c 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -24,6 +24,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, pr_warning("Failed to allocate identity pmd.\n"); return; } + /* + * Copy the original PMD to ensure that the PMD entries for + * the kernel image are preserved. + */ + if (!pud_none(*pud)) + memcpy(pmd, pmd_offset(pud, 0), + PTRS_PER_PMD * sizeof(pmd_t)); pud_populate(&init_mm, pud, pmd); pmd += pmd_index(addr); } else diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index af88b27ce313..a649cb686692 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -952,10 +952,27 @@ config VM86 default y depends on X86_32 ---help--- - This option is required by programs like DOSEMU to run 16-bit legacy - code on X86 processors. It also may be needed by software like - XFree86 to initialize some video cards via BIOS. Disabling this - option saves about 6k. + This option is required by programs like DOSEMU to run + 16-bit real mode legacy code on x86 processors. It also may + be needed by software like XFree86 to initialize some video + cards via BIOS. Disabling this option saves about 6K. + +config X86_16BIT + bool "Enable support for 16-bit segments" if EXPERT + default y + ---help--- + This option is required by programs like Wine to run 16-bit + protected mode legacy code on x86 processors. Disabling + this option saves about 300 bytes on i386, or around 6K text + plus 16K runtime memory on x86-64, + +config X86_ESPFIX32 + def_bool y + depends on X86_16BIT && X86_32 + +config X86_ESPFIX64 + def_bool y + depends on X86_16BIT && X86_64 config TOSHIBA tristate "Toshiba Laptop support" diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h new file mode 100644 index 000000000000..99efebb2f69d --- /dev/null +++ b/arch/x86/include/asm/espfix.h @@ -0,0 +1,16 @@ +#ifndef _ASM_X86_ESPFIX_H +#define _ASM_X86_ESPFIX_H + +#ifdef CONFIG_X86_64 + +#include + +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +extern void init_espfix_bsp(void); +extern void init_espfix_ap(void); + +#endif /* CONFIG_X86_64 */ + +#endif /* _ASM_X86_ESPFIX_H */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index bba3cf88e624..0a8b519226b8 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void) #define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */ -#define INTERRUPT_RETURN iretq +#define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ sysretq; diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 2d883440cb9a..b1609f2c524c 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t; #define MODULES_VADDR _AC(0xffffffffa0000000, UL) #define MODULES_END _AC(0xffffffffff000000, UL) #define MODULES_LEN (MODULES_END - MODULES_VADDR) +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) #define EARLY_DYNAMIC_PAGE_TABLES 64 diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index b7bf3505e1ec..2e327f114a1b 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -62,6 +62,8 @@ static inline void x86_ce4100_early_setup(void) { } #ifndef _SETUP +#include + /* * This is set up by the setup-routine at boot-time */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 7bd3bd310106..111eb356dbea 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-y += syscall_$(BITS).o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 08fa44443a01..5c38e2b298cd 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -532,6 +532,7 @@ syscall_exit: restore_all: TRACE_IRQS_IRET restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS # Warning: PT_OLDSS(%esp) contains the wrong/random values if we # are returning to the kernel. @@ -542,6 +543,7 @@ restore_all_notrace: cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS +#endif restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code irq_return: @@ -554,6 +556,7 @@ ENTRY(iret_exc) .previous _ASM_EXTABLE(irq_return,iret_exc) +#ifdef CONFIG_X86_ESPFIX32 CFI_RESTORE_STATE ldt_ss: #ifdef CONFIG_PARAVIRT @@ -597,6 +600,7 @@ ldt_ss: lss (%esp), %esp /* switch to espfix segment */ CFI_ADJUST_CFA_OFFSET -8 jmp restore_nocheck +#endif CFI_ENDPROC ENDPROC(system_call) @@ -709,6 +713,7 @@ END(syscall_badsys) * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. */ +#ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ @@ -718,8 +723,10 @@ END(syscall_badsys) pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 +#endif .endm .macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax @@ -730,6 +737,7 @@ END(syscall_badsys) /* switch to normal stack */ FIXUP_ESPFIX_STACK 27: +#endif .endm /* @@ -1337,11 +1345,13 @@ END(debug) ENTRY(nmi) RING0_INT_FRAME ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax popl_cfi %eax je nmi_espfix_stack +#endif cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup pushl_cfi %eax @@ -1381,6 +1391,7 @@ nmi_debug_stack_check: FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct +#ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: /* We have a RING0_INT_FRAME here. * @@ -1402,6 +1413,7 @@ nmi_espfix_stack: lss 12+4(%esp), %esp # back to espfix stack CFI_ADJUST_CFA_OFFSET -24 jmp irq_return +#endif CFI_ENDPROC END(nmi) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 7ac938a4bfab..39ba6914bbc6 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -58,6 +58,7 @@ #include #include #include +#include #include /* Avoid __ASSEMBLER__'ifying just for this. */ @@ -1056,12 +1057,45 @@ restore_args: irq_return: INTERRUPT_RETURN - _ASM_EXTABLE(irq_return, bad_iret) -#ifdef CONFIG_PARAVIRT ENTRY(native_iret) + /* + * Are we returning to a stack segment from the LDT? Note: in + * 64-bit mode SS:RSP on the exception stack is always valid. + */ +#ifdef CONFIG_X86_ESPFIX64 + testb $4,(SS-RIP)(%rsp) + jnz native_irq_return_ldt +#endif + +native_irq_return_iret: iretq - _ASM_EXTABLE(native_iret, bad_iret) + _ASM_EXTABLE(native_irq_return_iret, bad_iret) + +#ifdef CONFIG_X86_ESPFIX64 +native_irq_return_ldt: + pushq_cfi %rax + pushq_cfi %rdi + SWAPGS + movq PER_CPU_VAR(espfix_waddr),%rdi + movq %rax,(0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp),%rax /* RIP */ + movq %rax,(1*8)(%rdi) + movq (3*8)(%rsp),%rax /* CS */ + movq %rax,(2*8)(%rdi) + movq (4*8)(%rsp),%rax /* RFLAGS */ + movq %rax,(3*8)(%rdi) + movq (6*8)(%rsp),%rax /* SS */ + movq %rax,(5*8)(%rdi) + movq (5*8)(%rsp),%rax /* RSP */ + movq %rax,(4*8)(%rdi) + andl $0xffff0000,%eax + popq_cfi %rdi + orq PER_CPU_VAR(espfix_stack),%rax + SWAPGS + movq %rax,%rsp + popq_cfi %rax + jmp native_irq_return_iret #endif .section .fixup,"ax" @@ -1127,9 +1161,40 @@ ENTRY(retint_kernel) call preempt_schedule_irq jmp exit_intr #endif - CFI_ENDPROC END(common_interrupt) + + /* + * If IRET takes a fault on the espfix stack, then we + * end up promoting it to a doublefault. In that case, + * modify the stack to make it look like we just entered + * the #GP handler from user space, similar to bad_iret. + */ +#ifdef CONFIG_X86_ESPFIX64 + ALIGN +__do_double_fault: + XCPT_FRAME 1 RDI+8 + movq RSP(%rdi),%rax /* Trap on the espfix stack? */ + sarq $PGDIR_SHIFT,%rax + cmpl $ESPFIX_PGD_ENTRY,%eax + jne do_double_fault /* No, just deliver the fault */ + cmpl $__KERNEL_CS,CS(%rdi) + jne do_double_fault + movq RIP(%rdi),%rax + cmpq $native_irq_return_iret,%rax + jne do_double_fault /* This shouldn't happen... */ + movq PER_CPU_VAR(kernel_stack),%rax + subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */ + movq %rax,RSP(%rdi) + movq $0,(%rax) /* Missing (lost) #GP error code */ + movq $general_protection,RIP(%rdi) + retq + CFI_ENDPROC +END(__do_double_fault) +#else +# define __do_double_fault do_double_fault +#endif + /* * End of kprobes section */ @@ -1298,7 +1363,7 @@ zeroentry overflow do_overflow zeroentry bounds do_bounds zeroentry invalid_op do_invalid_op zeroentry device_not_available do_device_not_available -paranoiderrorentry double_fault do_double_fault +paranoiderrorentry double_fault __do_double_fault zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun errorentry invalid_TSS do_invalid_TSS errorentry segment_not_present do_segment_not_present @@ -1585,7 +1650,7 @@ error_sti: */ error_kernelspace: incl %ebx - leaq irq_return(%rip),%rcx + leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) je error_swapgs movl %ecx,%eax /* zero extend */ diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c new file mode 100644 index 000000000000..94d857fb1033 --- /dev/null +++ b/arch/x86/kernel/espfix_64.c @@ -0,0 +1,208 @@ +/* ----------------------------------------------------------------------- * + * + * Copyright 2014 Intel Corporation; author: H. Peter Anvin + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * ----------------------------------------------------------------------- */ + +/* + * The IRET instruction, when returning to a 16-bit segment, only + * restores the bottom 16 bits of the user space stack pointer. This + * causes some 16-bit software to break, but it also leaks kernel state + * to user space. + * + * This works around this by creating percpu "ministacks", each of which + * is mapped 2^16 times 64K apart. When we detect that the return SS is + * on the LDT, we copy the IRET frame to the ministack and use the + * relevant alias to return to userspace. The ministacks are mapped + * readonly, so if the IRET fault we promote #GP to #DF which is an IST + * vector and thus has its own stack; we then do the fixup in the #DF + * handler. + * + * This file sets up the ministacks and the related page tables. The + * actual ministack invocation is in entry_64.S. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Note: we only need 6*8 = 48 bytes for the espfix stack, but round + * it up to a cache line to avoid unnecessary sharing. + */ +#define ESPFIX_STACK_SIZE (8*8UL) +#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) + +/* There is address space for how many espfix pages? */ +#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) + +#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) +#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS +# error "Need more than one PGD for the ESPFIX hack" +#endif + +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) + +/* This contains the *bottom* address of the espfix stack */ +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +/* Initialization mutex - should this be a spinlock? */ +static DEFINE_MUTEX(espfix_init_mutex); + +/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */ +#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE) +static void *espfix_pages[ESPFIX_MAX_PAGES]; + +static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD] + __aligned(PAGE_SIZE); + +static unsigned int page_random, slot_random; + +/* + * This returns the bottom address of the espfix stack for a specific CPU. + * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case + * we have to account for some amount of padding at the end of each page. + */ +static inline unsigned long espfix_base_addr(unsigned int cpu) +{ + unsigned long page, slot; + unsigned long addr; + + page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random; + slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE; + addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE); + addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16); + addr += ESPFIX_BASE_ADDR; + return addr; +} + +#define PTE_STRIDE (65536/PAGE_SIZE) +#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE) +#define ESPFIX_PMD_CLONES PTRS_PER_PMD +#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES)) + +#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX) + +static void init_espfix_random(void) +{ + unsigned long rand; + + /* + * This is run before the entropy pools are initialized, + * but this is hopefully better than nothing. + */ + if (!arch_get_random_long(&rand)) { + /* The constant is an arbitrary large prime */ + rdtscll(rand); + rand *= 0xc345c6b72fd16123UL; + } + + slot_random = rand % ESPFIX_STACKS_PER_PAGE; + page_random = (rand / ESPFIX_STACKS_PER_PAGE) + & (ESPFIX_PAGE_SPACE - 1); +} + +void __init init_espfix_bsp(void) +{ + pgd_t *pgd_p; + pteval_t ptemask; + + ptemask = __supported_pte_mask; + + /* Install the espfix pud into the kernel page directory */ + pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + + /* Randomize the locations */ + init_espfix_random(); + + /* The rest is the same as for any other processor */ + init_espfix_ap(); +} + +void init_espfix_ap(void) +{ + unsigned int cpu, page; + unsigned long addr; + pud_t pud, *pud_p; + pmd_t pmd, *pmd_p; + pte_t pte, *pte_p; + int n; + void *stack_page; + pteval_t ptemask; + + /* We only have to do this once... */ + if (likely(this_cpu_read(espfix_stack))) + return; /* Already initialized */ + + cpu = smp_processor_id(); + addr = espfix_base_addr(cpu); + page = cpu/ESPFIX_STACKS_PER_PAGE; + + /* Did another CPU already set this up? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (likely(stack_page)) + goto done; + + mutex_lock(&espfix_init_mutex); + + /* Did we race on the lock? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (stack_page) + goto unlock_done; + + ptemask = __supported_pte_mask; + + pud_p = &espfix_pud_page[pud_index(addr)]; + pud = *pud_p; + if (!pud_present(pud)) { + pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); + pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PUD_CLONES; n++) + set_pud(&pud_p[n], pud); + } + + pmd_p = pmd_offset(&pud, addr); + pmd = *pmd_p; + if (!pmd_present(pmd)) { + pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); + pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PMD_CLONES; n++) + set_pmd(&pmd_p[n], pmd); + } + + pte_p = pte_offset_kernel(&pmd, addr); + stack_page = (void *)__get_free_page(GFP_KERNEL); + pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + for (n = 0; n < ESPFIX_PTE_CLONES; n++) + set_pte(&pte_p[n*PTE_STRIDE], pte); + + /* Job is done for this CPU and any CPU which shares this page */ + ACCESS_ONCE(espfix_pages[page]) = stack_page; + +unlock_done: + mutex_unlock(&espfix_init_mutex); +done: + this_cpu_write(espfix_stack, addr); + this_cpu_write(espfix_waddr, (unsigned long)stack_page + + (addr & ~PAGE_MASK)); +} diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index dcbbaa165bde..c37886d759cc 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -20,8 +20,6 @@ #include #include -int sysctl_ldt16 = 0; - #ifdef CONFIG_SMP static void flush_ldt(void *current_mm) { @@ -231,16 +229,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } } - /* - * On x86-64 we do not support 16-bit segments due to - * IRET leaking the high bits of the kernel stack address. - */ -#ifdef CONFIG_X86_64 - if (!ldt_info.seg_32bit && !sysctl_ldt16) { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { error = -EINVAL; goto out_unlock; } -#endif fill_ldt(&ldt, &ldt_info); if (oldmode) diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 3f08f34f93eb..a1da6737ba5b 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq"); DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); -DEF_NATIVE(pv_cpu_ops, iret, "iretq"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); @@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, iret); PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index bfd348e99369..fe862750583b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -265,6 +265,13 @@ notrace static void __cpuinit start_secondary(void *unused) check_tsc_sync_target(); /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(); +#endif + + /* * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0002a3a33081..e04e67753238 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -30,11 +30,13 @@ struct pg_state { unsigned long start_address; unsigned long current_address; const struct addr_marker *marker; + unsigned long lines; }; struct addr_marker { unsigned long start_address; const char *name; + unsigned long max_lines; }; /* indices for address_markers; keep sync'd w/ address_markers below */ @@ -45,6 +47,7 @@ enum address_markers_idx { LOW_KERNEL_NR, VMALLOC_START_NR, VMEMMAP_START_NR, + ESPFIX_START_NR, HIGH_KERNEL_NR, MODULES_VADDR_NR, MODULES_END_NR, @@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = { { PAGE_OFFSET, "Low Kernel Mapping" }, { VMALLOC_START, "vmalloc() Area" }, { VMEMMAP_START, "Vmemmap" }, + { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, { __START_KERNEL_map, "High Kernel Mapping" }, { MODULES_VADDR, "Modules" }, { MODULES_END, "End Modules" }, @@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, pgprot_t new_prot, int level) { pgprotval_t prot, cur; - static const char units[] = "KMGTPE"; + static const char units[] = "BKMGTPE"; /* * If we have a "break" in the series, we need to flush the state that @@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->current_prot = new_prot; st->level = level; st->marker = address_markers; + st->lines = 0; seq_printf(m, "---[ %s ]---\n", st->marker->name); } else if (prot != cur || level != st->level || st->current_address >= st->marker[1].start_address) { @@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st, /* * Now print the actual finished series */ - seq_printf(m, "0x%0*lx-0x%0*lx ", - width, st->start_address, - width, st->current_address); - - delta = (st->current_address - st->start_address) >> 10; - while (!(delta & 1023) && unit[1]) { - delta >>= 10; - unit++; + if (!st->marker->max_lines || + st->lines < st->marker->max_lines) { + seq_printf(m, "0x%0*lx-0x%0*lx ", + width, st->start_address, + width, st->current_address); + + delta = (st->current_address - st->start_address); + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + seq_printf(m, "%9lu%c ", delta, *unit); + printk_prot(m, st->current_prot, st->level); } - seq_printf(m, "%9lu%c ", delta, *unit); - printk_prot(m, st->current_prot, st->level); + st->lines++; /* * We print markers for special areas of address space, @@ -206,7 +215,15 @@ static void note_page(struct seq_file *m, struct pg_state *st, * This helps in the interpretation. */ if (st->current_address >= st->marker[1].start_address) { + if (st->marker->max_lines && + st->lines > st->marker->max_lines) { + unsigned long nskip = + st->lines - st->marker->max_lines; + seq_printf(m, "... %lu entr%s skipped ... \n", + nskip, nskip == 1 ? "y" : "ies"); + } st->marker++; + st->lines = 0; seq_printf(m, "---[ %s ]---\n", st->marker->name); } diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 0f134c7cfc24..0faad646f5fd 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -41,7 +41,6 @@ enum { #ifdef CONFIG_X86_64 #define vdso_enabled sysctl_vsyscall32 #define arch_setup_additional_pages syscall32_setup_pages -extern int sysctl_ldt16; #endif /* @@ -381,13 +380,6 @@ static ctl_table abi_table2[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "ldt16", - .data = &sysctl_ldt16, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, {} }; diff --git a/crypto/af_alg.c b/crypto/af_alg.c index ac33d5f30778..bf948e134981 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -21,6 +21,7 @@ #include #include #include +#include struct alg_type_list { const struct af_alg_type *type; @@ -243,6 +244,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) sock_init_data(newsock, sk2); sock_graft(sk2, newsock); + security_sk_clone(sk, sk2); err = type->accept(ask->private, sk2); if (err) { diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index d344cf3ac9e3..e13c5f4b12cb 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -849,7 +849,7 @@ static int iio_buffer_update_demux(struct iio_dev *indio_dev, /* Now we have the two masks, work from least sig and build up sizes */ for_each_set_bit(out_ind, - indio_dev->active_scan_mask, + buffer->scan_mask, indio_dev->masklength) { in_ind = find_next_bit(indio_dev->active_scan_mask, indio_dev->masklength, diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 658613021919..f8821ce27802 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -99,16 +99,56 @@ #define MVNETA_CPU_RXQ_ACCESS_ALL_MASK 0x000000ff #define MVNETA_CPU_TXQ_ACCESS_ALL_MASK 0x0000ff00 #define MVNETA_RXQ_TIME_COAL_REG(q) (0x2580 + ((q) << 2)) + +/* Exception Interrupt Port/Queue Cause register */ + #define MVNETA_INTR_NEW_CAUSE 0x25a0 -#define MVNETA_RX_INTR_MASK(nr_rxqs) (((1 << nr_rxqs) - 1) << 8) #define MVNETA_INTR_NEW_MASK 0x25a4 + +/* bits 0..7 = TXQ SENT, one bit per queue. + * bits 8..15 = RXQ OCCUP, one bit per queue. + * bits 16..23 = RXQ FREE, one bit per queue. + * bit 29 = OLD_REG_SUM, see old reg ? + * bit 30 = TX_ERR_SUM, one bit for 4 ports + * bit 31 = MISC_SUM, one bit for 4 ports + */ +#define MVNETA_TX_INTR_MASK(nr_txqs) (((1 << nr_txqs) - 1) << 0) +#define MVNETA_TX_INTR_MASK_ALL (0xff << 0) +#define MVNETA_RX_INTR_MASK(nr_rxqs) (((1 << nr_rxqs) - 1) << 8) +#define MVNETA_RX_INTR_MASK_ALL (0xff << 8) + #define MVNETA_INTR_OLD_CAUSE 0x25a8 #define MVNETA_INTR_OLD_MASK 0x25ac + +/* Data Path Port/Queue Cause Register */ #define MVNETA_INTR_MISC_CAUSE 0x25b0 #define MVNETA_INTR_MISC_MASK 0x25b4 + +#define MVNETA_CAUSE_PHY_STATUS_CHANGE BIT(0) +#define MVNETA_CAUSE_LINK_CHANGE BIT(1) +#define MVNETA_CAUSE_PTP BIT(4) + +#define MVNETA_CAUSE_INTERNAL_ADDR_ERR BIT(7) +#define MVNETA_CAUSE_RX_OVERRUN BIT(8) +#define MVNETA_CAUSE_RX_CRC_ERROR BIT(9) +#define MVNETA_CAUSE_RX_LARGE_PKT BIT(10) +#define MVNETA_CAUSE_TX_UNDERUN BIT(11) +#define MVNETA_CAUSE_PRBS_ERR BIT(12) +#define MVNETA_CAUSE_PSC_SYNC_CHANGE BIT(13) +#define MVNETA_CAUSE_SERDES_SYNC_ERR BIT(14) + +#define MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT 16 +#define MVNETA_CAUSE_BMU_ALLOC_ERR_ALL_MASK (0xF << MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT) +#define MVNETA_CAUSE_BMU_ALLOC_ERR_MASK(pool) (1 << (MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT + (pool))) + +#define MVNETA_CAUSE_TXQ_ERROR_SHIFT 24 +#define MVNETA_CAUSE_TXQ_ERROR_ALL_MASK (0xFF << MVNETA_CAUSE_TXQ_ERROR_SHIFT) +#define MVNETA_CAUSE_TXQ_ERROR_MASK(q) (1 << (MVNETA_CAUSE_TXQ_ERROR_SHIFT + (q))) + #define MVNETA_INTR_ENABLE 0x25b8 #define MVNETA_TXQ_INTR_ENABLE_ALL_MASK 0x0000ff00 -#define MVNETA_RXQ_INTR_ENABLE_ALL_MASK 0xff000000 +#define MVNETA_RXQ_INTR_ENABLE_ALL_MASK 0xff000000 // note: neta says it's 0x000000FF + #define MVNETA_RXQ_CMD 0x2680 #define MVNETA_RXQ_DISABLE_SHIFT 8 #define MVNETA_RXQ_ENABLE_MASK 0x000000ff @@ -174,9 +214,6 @@ #define MVNETA_RX_COAL_PKTS 32 #define MVNETA_RX_COAL_USEC 100 -/* Timer */ -#define MVNETA_TX_DONE_TIMER_PERIOD 10 - /* Napi polling weight */ #define MVNETA_RX_POLL_WEIGHT 64 @@ -219,10 +256,12 @@ #define MVNETA_RX_BUF_SIZE(pkt_size) ((pkt_size) + NET_SKB_PAD) -struct mvneta_stats { +struct mvneta_pcpu_stats { struct u64_stats_sync syncp; - u64 packets; - u64 bytes; + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; }; struct mvneta_port { @@ -230,16 +269,11 @@ struct mvneta_port { void __iomem *base; struct mvneta_rx_queue *rxqs; struct mvneta_tx_queue *txqs; - struct timer_list tx_done_timer; struct net_device *dev; u32 cause_rx_tx; struct napi_struct napi; - /* Flags */ - unsigned long flags; -#define MVNETA_F_TX_DONE_TIMER_BIT 0 - /* Napi weight */ int weight; @@ -248,8 +282,7 @@ struct mvneta_port { u8 mcast_count[256]; u16 tx_ring_size; u16 rx_ring_size; - struct mvneta_stats tx_stats; - struct mvneta_stats rx_stats; + struct mvneta_pcpu_stats *stats; struct mii_bus *mii_bus; struct phy_device *phy_dev; @@ -428,21 +461,29 @@ struct rtnl_link_stats64 *mvneta_get_stats64(struct net_device *dev, { struct mvneta_port *pp = netdev_priv(dev); unsigned int start; + int cpu; - memset(stats, 0, sizeof(struct rtnl_link_stats64)); - - do { - start = u64_stats_fetch_begin_bh(&pp->rx_stats.syncp); - stats->rx_packets = pp->rx_stats.packets; - stats->rx_bytes = pp->rx_stats.bytes; - } while (u64_stats_fetch_retry_bh(&pp->rx_stats.syncp, start)); + for_each_possible_cpu(cpu) { + struct mvneta_pcpu_stats *cpu_stats; + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + cpu_stats = per_cpu_ptr(pp->stats, cpu); + do { + start = u64_stats_fetch_begin_bh(&cpu_stats->syncp); + rx_packets = cpu_stats->rx_packets; + rx_bytes = cpu_stats->rx_bytes; + tx_packets = cpu_stats->tx_packets; + tx_bytes = cpu_stats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&cpu_stats->syncp, start)); - do { - start = u64_stats_fetch_begin_bh(&pp->tx_stats.syncp); - stats->tx_packets = pp->tx_stats.packets; - stats->tx_bytes = pp->tx_stats.bytes; - } while (u64_stats_fetch_retry_bh(&pp->tx_stats.syncp, start)); + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; + stats->tx_packets += tx_packets; + stats->tx_bytes += tx_bytes; + } stats->rx_errors = dev->stats.rx_errors; stats->rx_dropped = dev->stats.rx_dropped; @@ -1063,17 +1104,6 @@ static void mvneta_tx_done_pkts_coal_set(struct mvneta_port *pp, txq->done_pkts_coal = value; } -/* Trigger tx done timer in MVNETA_TX_DONE_TIMER_PERIOD msecs */ -static void mvneta_add_tx_done_timer(struct mvneta_port *pp) -{ - if (test_and_set_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags) == 0) { - pp->tx_done_timer.expires = jiffies + - msecs_to_jiffies(MVNETA_TX_DONE_TIMER_PERIOD); - add_timer(&pp->tx_done_timer); - } -} - - /* Handle rx descriptor fill by setting buf_cookie and buf_phys_addr */ static void mvneta_rx_desc_fill(struct mvneta_rx_desc *rx_desc, u32 phys_addr, u32 cookie) @@ -1354,6 +1384,8 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo, { struct net_device *dev = pp->dev; int rx_done, rx_filled; + u32 rcvd_pkts = 0; + u32 rcvd_bytes = 0; /* Get number of received packets */ rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq); @@ -1391,10 +1423,8 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo, rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE); - u64_stats_update_begin(&pp->rx_stats.syncp); - pp->rx_stats.packets++; - pp->rx_stats.bytes += rx_bytes; - u64_stats_update_end(&pp->rx_stats.syncp); + rcvd_pkts++; + rcvd_bytes += rx_bytes; /* Linux processing */ skb_reserve(skb, MVNETA_MH_SIZE); @@ -1415,6 +1445,15 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo, } } + if (rcvd_pkts) { + struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); + + u64_stats_update_begin(&stats->syncp); + stats->rx_packets += rcvd_pkts; + stats->rx_bytes += rcvd_bytes; + u64_stats_update_end(&stats->syncp); + } + /* Update rxq management counters */ mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_filled); @@ -1545,25 +1584,17 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev) out: if (frags > 0) { - u64_stats_update_begin(&pp->tx_stats.syncp); - pp->tx_stats.packets++; - pp->tx_stats.bytes += skb->len; - u64_stats_update_end(&pp->tx_stats.syncp); + struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); + u64_stats_update_begin(&stats->syncp); + stats->tx_packets++; + stats->tx_bytes += skb->len; + u64_stats_update_end(&stats->syncp); } else { dev->stats.tx_dropped++; dev_kfree_skb_any(skb); } - if (txq->count >= MVNETA_TXDONE_COAL_PKTS) - mvneta_txq_done(pp, txq); - - /* If after calling mvneta_txq_done, count equals - * frags, we need to set the timer - */ - if (txq->count == frags && frags > 0) - mvneta_add_tx_done_timer(pp); - return NETDEV_TX_OK; } @@ -1839,14 +1870,22 @@ static int mvneta_poll(struct napi_struct *napi, int budget) /* Read cause register */ cause_rx_tx = mvreg_read(pp, MVNETA_INTR_NEW_CAUSE) & - MVNETA_RX_INTR_MASK(rxq_number); + (MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number)); + + /* Release Tx descriptors */ + if (cause_rx_tx & MVNETA_TX_INTR_MASK_ALL) { + int tx_todo = 0; + + mvneta_tx_done_gbe(pp, (cause_rx_tx & MVNETA_TX_INTR_MASK_ALL), &tx_todo); + cause_rx_tx &= ~MVNETA_TX_INTR_MASK_ALL; + } /* For the case where the last mvneta_poll did not process all * RX packets */ cause_rx_tx |= pp->cause_rx_tx; if (rxq_number > 1) { - while ((cause_rx_tx != 0) && (budget > 0)) { + while ((cause_rx_tx & MVNETA_RX_INTR_MASK_ALL) && (budget > 0)) { int count; struct mvneta_rx_queue *rxq; /* get rx queue number from cause_rx_tx */ @@ -1878,7 +1917,7 @@ static int mvneta_poll(struct napi_struct *napi, int budget) napi_complete(napi); local_irq_save(flags); mvreg_write(pp, MVNETA_INTR_NEW_MASK, - MVNETA_RX_INTR_MASK(rxq_number)); + MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number)); local_irq_restore(flags); } @@ -1886,26 +1925,6 @@ static int mvneta_poll(struct napi_struct *napi, int budget) return rx_done; } -/* tx done timer callback */ -static void mvneta_tx_done_timer_callback(unsigned long data) -{ - struct net_device *dev = (struct net_device *)data; - struct mvneta_port *pp = netdev_priv(dev); - int tx_done = 0, tx_todo = 0; - - if (!netif_running(dev)) - return ; - - clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags); - - tx_done = mvneta_tx_done_gbe(pp, - (((1 << txq_number) - 1) & - MVNETA_CAUSE_TXQ_SENT_DESC_ALL_MASK), - &tx_todo); - if (tx_todo > 0) - mvneta_add_tx_done_timer(pp); -} - /* Handle rxq fill: allocates rxq skbs; called when initializing a port */ static int mvneta_rxq_fill(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, int num) @@ -2155,7 +2174,7 @@ static void mvneta_start_dev(struct mvneta_port *pp) /* Unmask interrupts */ mvreg_write(pp, MVNETA_INTR_NEW_MASK, - MVNETA_RX_INTR_MASK(rxq_number)); + MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number)); phy_start(pp->phy_dev); netif_tx_start_all_queues(pp->dev); @@ -2188,16 +2207,6 @@ static void mvneta_stop_dev(struct mvneta_port *pp) mvneta_rx_reset(pp); } -/* tx timeout callback - display a message and stop/start the network device */ -static void mvneta_tx_timeout(struct net_device *dev) -{ - struct mvneta_port *pp = netdev_priv(dev); - - netdev_info(dev, "tx timeout\n"); - mvneta_stop_dev(pp); - mvneta_start_dev(pp); -} - /* Return positive if MTU is valid */ static int mvneta_check_mtu_valid(struct net_device *dev, int mtu) { @@ -2426,8 +2435,6 @@ static int mvneta_stop(struct net_device *dev) free_irq(dev->irq, pp); mvneta_cleanup_rxqs(pp); mvneta_cleanup_txqs(pp); - del_timer(&pp->tx_done_timer); - clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags); return 0; } @@ -2548,7 +2555,6 @@ static const struct net_device_ops mvneta_netdev_ops = { .ndo_set_rx_mode = mvneta_set_rx_mode, .ndo_set_mac_address = mvneta_set_mac_addr, .ndo_change_mtu = mvneta_change_mtu, - .ndo_tx_timeout = mvneta_tx_timeout, .ndo_get_stats64 = mvneta_get_stats64, }; @@ -2729,10 +2735,6 @@ static int mvneta_probe(struct platform_device *pdev) pp = netdev_priv(dev); - pp->tx_done_timer.function = mvneta_tx_done_timer_callback; - init_timer(&pp->tx_done_timer); - clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags); - pp->weight = MVNETA_RX_POLL_WEIGHT; pp->phy_node = phy_node; pp->phy_interface = phy_mode; @@ -2751,7 +2753,12 @@ static int mvneta_probe(struct platform_device *pdev) clk_prepare_enable(pp->clk); - pp->tx_done_timer.data = (unsigned long)dev; + /* Alloc per-cpu stats */ + pp->stats = alloc_percpu(struct mvneta_pcpu_stats); + if (!pp->stats) { + err = -ENOMEM; + goto err_clk; + } pp->tx_ring_size = MVNETA_MAX_TXD; pp->rx_ring_size = MVNETA_MAX_RXD; @@ -2762,7 +2769,7 @@ static int mvneta_probe(struct platform_device *pdev) err = mvneta_init(pp, phy_addr); if (err < 0) { dev_err(&pdev->dev, "can't init eth hal\n"); - goto err_clk; + goto err_free_stats; } mvneta_port_power_up(pp, phy_mode); @@ -2791,6 +2798,8 @@ static int mvneta_probe(struct platform_device *pdev) err_deinit: mvneta_deinit(pp); +err_free_stats: + free_percpu(pp->stats); err_clk: clk_disable_unprepare(pp->clk); err_unmap: @@ -2811,6 +2820,7 @@ static int mvneta_remove(struct platform_device *pdev) unregister_netdev(dev); mvneta_deinit(pp); clk_disable_unprepare(pp->clk); + free_percpu(pp->stats); iounmap(pp->base); irq_dispose_mapping(dev->irq); free_netdev(dev); diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c index 91245f5dbe81..47257b6eea84 100644 --- a/drivers/rapidio/devices/tsi721_dma.c +++ b/drivers/rapidio/devices/tsi721_dma.c @@ -287,6 +287,12 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan) "desc %p not ACKed\n", tx_desc); } + if (ret == NULL) { + dev_dbg(bdma_chan->dchan.device->dev, + "%s: unable to obtain tx descriptor\n", __func__); + goto err_out; + } + i = bdma_chan->wr_count_next % bdma_chan->bd_num; if (i == bdma_chan->bd_num - 1) { i = 0; @@ -297,7 +303,7 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan) tx_desc->txd.phys = bdma_chan->bd_phys + i * sizeof(struct tsi721_dma_desc); tx_desc->hw_desc = &((struct tsi721_dma_desc *)bdma_chan->bd_base)[i]; - +err_out: spin_unlock_bh(&bdma_chan->lock); return ret; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 86d522004a20..e5953c8018c5 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -815,6 +815,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) scsi_next_command(cmd); return; } + } else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) { + /* + * Certain non BLOCK_PC requests are commands that don't + * actually transfer anything (FLUSH), so cannot use + * good_bytes != blk_rq_bytes(req) as the signal for an error. + * This sets the error explicitly for the problem case. + */ + error = __scsi_error_from_host_byte(cmd, result); } /* no bidi support for !REQ_TYPE_BLOCK_PC yet */ diff --git a/drivers/staging/vt6655/bssdb.c b/drivers/staging/vt6655/bssdb.c index f983915168b7..3496a77612ba 100644 --- a/drivers/staging/vt6655/bssdb.c +++ b/drivers/staging/vt6655/bssdb.c @@ -1026,7 +1026,7 @@ start: pDevice->byERPFlag &= ~(WLAN_SET_ERP_USE_PROTECTION(1)); } - { + if (pDevice->eCommandState == WLAN_ASSOCIATE_WAIT) { pDevice->byReAssocCount++; if ((pDevice->byReAssocCount > 10) && (pDevice->bLinkPass != true)) { //10 sec timeout printk("Re-association timeout!!!\n"); diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c index 08b250f01dae..d170b6f9db7c 100644 --- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -2434,6 +2434,7 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { int handled = 0; unsigned char byData = 0; int ii = 0; + unsigned long flags; // unsigned char byRSSI; MACvReadISR(pDevice->PortOffset, &pDevice->dwIsr); @@ -2459,7 +2460,8 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { handled = 1; MACvIntDisable(pDevice->PortOffset); - spin_lock_irq(&pDevice->lock); + + spin_lock_irqsave(&pDevice->lock, flags); //Make sure current page is 0 VNSvInPortB(pDevice->PortOffset + MAC_REG_PAGE1SEL, &byOrgPageSel); @@ -2700,7 +2702,8 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { MACvSelectPage1(pDevice->PortOffset); } - spin_unlock_irq(&pDevice->lock); + spin_unlock_irqrestore(&pDevice->lock, flags); + MACvIntEnable(pDevice->PortOffset, IMR_MASK_VALUE); return IRQ_RETVAL(handled); diff --git a/include/linux/printk.h b/include/linux/printk.h index 22c7052e9372..708b8a84f6c0 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -124,9 +124,9 @@ asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* - * Special printk facility for scheduler use only, _DO_NOT_USE_ ! + * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ -__printf(1, 2) __cold int printk_sched(const char *fmt, ...); +__printf(1, 2) __cold int printk_deferred(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -161,7 +161,7 @@ int printk(const char *s, ...) return 0; } static inline __printf(1, 2) __cold -int printk_sched(const char *s, ...) +int printk_deferred(const char *s, ...) { return 0; } diff --git a/init/main.c b/init/main.c index e83ac04fda97..2132ffd5e031 100644 --- a/init/main.c +++ b/init/main.c @@ -606,6 +606,10 @@ asmlinkage void __init start_kernel(void) if (efi_enabled(EFI_RUNTIME_SERVICES)) efi_enter_virtual_mode(); #endif +#ifdef CONFIG_X86_ESPFIX64 + /* Should be run before the first non-init thread is created */ + init_espfix_bsp(); +#endif thread_info_cache_init(); cred_init(); fork_init(totalram_pages); diff --git a/kernel/printk.c b/kernel/printk.c index d37d45c90ae6..f7aff4bd5454 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -2485,7 +2485,7 @@ void wake_up_klogd(void) preempt_enable(); } -int printk_sched(const char *fmt, ...) +int printk_deferred(const char *fmt, ...) { unsigned long flags; va_list args; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2672eca82a2b..c771f2547bef 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1235,7 +1235,7 @@ out: * leave kernel. */ if (p->mm && printk_ratelimit()) { - printk_sched("process %d (%s) no longer affine to cpu%d\n", + printk_deferred("process %d (%s) no longer affine to cpu%d\n", task_pid_nr(p), p->comm, cpu); } } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 15334e6de832..2dffc7b5d469 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -892,7 +892,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) if (!once) { once = true; - printk_sched("sched: RT throttling activated\n"); + printk_deferred("sched: RT throttling activated\n"); } } else { /* diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 9df0e3b19f09..58e8430165b5 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -138,7 +138,8 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev) { /* Nothing to do if we already reached the limit */ if (dev->min_delta_ns >= MIN_DELTA_LIMIT) { - printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n"); + printk_deferred(KERN_WARNING + "CE: Reprogramming failure. Giving up\n"); dev->next_event.tv64 = KTIME_MAX; return -ETIME; } @@ -151,9 +152,10 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev) if (dev->min_delta_ns > MIN_DELTA_LIMIT) dev->min_delta_ns = MIN_DELTA_LIMIT; - printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", - dev->name ? dev->name : "?", - (unsigned long long) dev->min_delta_ns); + printk_deferred(KERN_WARNING + "CE: %s increased min_delta_ns to %llu nsec\n", + dev->name ? dev->name : "?", + (unsigned long long) dev->min_delta_ns); return 0; } diff --git a/lib/btree.c b/lib/btree.c index f9a484676cb6..4264871ea1a0 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -198,6 +198,7 @@ EXPORT_SYMBOL_GPL(btree_init); void btree_destroy(struct btree_head *head) { + mempool_free(head->node, head->mempool); mempool_destroy(head->mempool); head->mempool = NULL; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0ab02fb8e9b1..71305c6aba5b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2339,7 +2339,7 @@ static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const gfp_t wait = gfp_mask & __GFP_WAIT; + const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -2348,20 +2348,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (!wait) { + if (atomic) { /* - * Not worth trying to allocate harder for - * __GFP_NOMEMALLOC even if it can't schedule. + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. */ - if (!(gfp_mask & __GFP_NOMEMALLOC)) + if (!(gfp_mask & __GFP_NOMEMALLOC)) alloc_flags |= ALLOC_HARDER; /* - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the + * comment for __cpuset_node_allowed_softwall(). */ alloc_flags &= ~ALLOC_CPUSET; } else if (unlikely(rt_task(current)) && !in_interrupt()) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 9a0e5874e73e..164fa9dcd97d 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1365,7 +1365,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, int err; if (level != SOL_PPPOL2TP) - return udp_prot.setsockopt(sk, level, optname, optval, optlen); + return -EINVAL; if (optlen < sizeof(int)) return -EINVAL; @@ -1491,7 +1491,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, struct pppol2tp_session *ps; if (level != SOL_PPPOL2TP) - return udp_prot.getsockopt(sk, level, optname, optval, optlen); + return -EINVAL; if (get_user(len, optlen)) return -EFAULT; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index d566cdba24ec..10eea2326022 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -398,6 +398,9 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (ieee80211_has_order(hdr->frame_control)) return TX_CONTINUE; + if (ieee80211_is_probe_req(hdr->frame_control)) + return TX_CONTINUE; + /* no stations in PS mode */ if (!atomic_read(&ps->num_sta_ps)) return TX_CONTINUE; @@ -447,6 +450,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) { struct sta_info *sta = tx->sta; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; struct ieee80211_local *local = tx->local; if (unlikely(!sta)) @@ -457,6 +461,15 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) { int ac = skb_get_queue_mapping(tx->skb); + /* only deauth, disassoc and action are bufferable MMPDUs */ + if (ieee80211_is_mgmt(hdr->frame_control) && + !ieee80211_is_deauth(hdr->frame_control) && + !ieee80211_is_disassoc(hdr->frame_control) && + !ieee80211_is_action(hdr->frame_control)) { + info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; + return TX_CONTINUE; + } + ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n", sta->sta.addr, sta->sta.aid, ac); if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) @@ -514,22 +527,8 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) static ieee80211_tx_result debug_noinline ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; - if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED)) return TX_CONTINUE; - - /* only deauth, disassoc and action are bufferable MMPDUs */ - if (ieee80211_is_mgmt(hdr->frame_control) && - !ieee80211_is_deauth(hdr->frame_control) && - !ieee80211_is_disassoc(hdr->frame_control) && - !ieee80211_is_action(hdr->frame_control)) { - if (tx->flags & IEEE80211_TX_UNICAST) - info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; - return TX_CONTINUE; - } - if (tx->flags & IEEE80211_TX_UNICAST) return ieee80211_tx_h_unicast_ps_buf(tx); else diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 5755bc14abbd..bc5a75b1aef8 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1972,7 +1972,8 @@ TRACE_EVENT(cfg80211_michael_mic_failure, MAC_ASSIGN(addr, addr); __entry->key_type = key_type; __entry->key_id = key_id; - memcpy(__entry->tsc, tsc, 6); + if (tsc) + memcpy(__entry->tsc, tsc, 6); ), TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm", NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type,