diff options
262 files changed, 2987 insertions, 1159 deletions
diff --git a/Documentation/devicetree/bindings/net/brcm,amac.txt b/Documentation/devicetree/bindings/net/brcm,amac.txt index 2fefa1a44afd..ad16c1f481f7 100644 --- a/Documentation/devicetree/bindings/net/brcm,amac.txt +++ b/Documentation/devicetree/bindings/net/brcm,amac.txt @@ -11,6 +11,7 @@ Required properties: - reg-names: Names of the registers. "amac_base": Address and length of the GMAC registers "idm_base": Address and length of the GMAC IDM registers + (required for NSP and Northstar2) "nicpm_base": Address and length of the NIC Port Manager registers (required for Northstar2) - interrupts: Interrupt number diff --git a/Documentation/devicetree/bindings/net/brcm,bgmac-nsp.txt b/Documentation/devicetree/bindings/net/brcm,bgmac-nsp.txt deleted file mode 100644 index 022946caa7e2..000000000000 --- a/Documentation/devicetree/bindings/net/brcm,bgmac-nsp.txt +++ /dev/null @@ -1,24 +0,0 @@ -Broadcom GMAC Ethernet Controller Device Tree Bindings -------------------------------------------------------------- - -Required properties: - - compatible: "brcm,bgmac-nsp" - - reg: Address and length of the GMAC registers, - Address and length of the GMAC IDM registers - - reg-names: Names of the registers. Must have both "gmac_base" and - "idm_base" - - interrupts: Interrupt number - -Optional properties: -- mac-address: See ethernet.txt file in the same directory - -Examples: - -gmac0: ethernet@18022000 { - compatible = "brcm,bgmac-nsp"; - reg = <0x18022000 0x1000>, - <0x18110000 0x1000>; - reg-names = "gmac_base", "idm_base"; - interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>; - status = "disabled"; -}; diff --git a/Documentation/devicetree/bindings/ptp/brcm,ptp-dte.txt b/Documentation/devicetree/bindings/ptp/brcm,ptp-dte.txt index 07590bcdad15..7c04e22a5d6a 100644 --- a/Documentation/devicetree/bindings/ptp/brcm,ptp-dte.txt +++ b/Documentation/devicetree/bindings/ptp/brcm,ptp-dte.txt @@ -1,13 +1,20 @@ -* Broadcom Digital Timing Engine(DTE) based PTP clock driver +* Broadcom Digital Timing Engine(DTE) based PTP clock Required properties: -- compatible: should be "brcm,ptp-dte" +- compatible: should contain the core compatibility string + and the SoC compatibility string. The SoC + compatibility string is to handle SoC specific + hardware differences. + Core compatibility string: + "brcm,ptp-dte" + SoC compatibility strings: + "brcm,iproc-ptp-dte" - for iproc based SoC's - reg: address and length of the DTE block's NCO registers Example: -ptp_dte: ptp_dte@180af650 { - compatible = "brcm,ptp-dte"; +ptp: ptp-dte@180af650 { + compatible = "brcm,iproc-ptp-dte", "brcm,ptp-dte"; reg = <0x180af650 0x10>; status = "okay"; }; diff --git a/MAINTAINERS b/MAINTAINERS index 02994f42aacb..2784ac59801d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7730,6 +7730,7 @@ Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm.git S: Supported F: drivers/nvdimm/* +F: drivers/acpi/nfit/* F: include/linux/nd.h F: include/linux/libnvdimm.h F: include/uapi/linux/ndctl.h @@ -7741,7 +7742,6 @@ Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ S: Supported F: drivers/nvdimm/blk.c F: drivers/nvdimm/region_devs.c -F: drivers/acpi/nfit* LIBNVDIMM BTT: BLOCK TRANSLATION TABLE M: Vishal Verma <vishal.l.verma@intel.com> @@ -10684,7 +10684,6 @@ F: drivers/ptp/* F: include/linux/ptp_cl* PTRACE SUPPORT -M: Roland McGrath <roland@hack.frob.com> M: Oleg Nesterov <oleg@redhat.com> S: Maintained F: include/asm-generic/syscall.h @@ -10692,7 +10691,12 @@ F: include/linux/ptrace.h F: include/linux/regset.h F: include/linux/tracehook.h F: include/uapi/linux/ptrace.h +F: include/uapi/linux/ptrace.h +F: include/asm-generic/ptrace.h F: kernel/ptrace.c +F: arch/*/ptrace*.c +F: arch/*/*/ptrace*.c +F: arch/*/include/asm/ptrace*.h PULSE8-CEC DRIVER M: Hans Verkuil <hverkuil@xs4all.nl> diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h index 4e6e88a6b2f4..2244a94ed9c9 100644 --- a/arch/arm/include/asm/bug.h +++ b/arch/arm/include/asm/bug.h @@ -37,7 +37,7 @@ do { \ ".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \ "2:\t.asciz " #__file "\n" \ ".popsection\n" \ - ".pushsection __bug_table,\"a\"\n" \ + ".pushsection __bug_table,\"aw\"\n" \ ".align 2\n" \ "3:\t.word 1b, 2b\n" \ "\t.hword " #__line ", 0\n" \ diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index d69bebf697e7..74504b154256 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -116,7 +116,7 @@ struct cpu_cache_fns { void (*dma_unmap_area)(const void *, size_t, int); void (*dma_flush_range)(const void *, const void *); -}; +} __no_randomize_layout; /* * Select the calling method diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h index 366448eb0fb7..a02a57186f56 100644 --- a/arch/arm64/include/asm/bug.h +++ b/arch/arm64/include/asm/bug.h @@ -36,7 +36,7 @@ #ifdef CONFIG_GENERIC_BUG #define __BUG_ENTRY(flags) \ - ".pushsection __bug_table,\"a\"\n\t" \ + ".pushsection __bug_table,\"aw\"\n\t" \ ".align 2\n\t" \ "0: .long 1f - 0b\n\t" \ _BUGVERBOSE_LOCATION(__FILE__, __LINE__) \ diff --git a/arch/blackfin/include/asm/bug.h b/arch/blackfin/include/asm/bug.h index 8d9b1eba89c4..76b2e82ee730 100644 --- a/arch/blackfin/include/asm/bug.h +++ b/arch/blackfin/include/asm/bug.h @@ -21,7 +21,7 @@ #define _BUG_OR_WARN(flags) \ asm volatile( \ "1: .hword %0\n" \ - " .section __bug_table,\"a\",@progbits\n" \ + " .section __bug_table,\"aw\",@progbits\n" \ "2: .long 1b\n" \ " .long %1\n" \ " .short %2\n" \ @@ -38,7 +38,7 @@ #define _BUG_OR_WARN(flags) \ asm volatile( \ "1: .hword %0\n" \ - " .section __bug_table,\"a\",@progbits\n" \ + " .section __bug_table,\"aw\",@progbits\n" \ "2: .long 1b\n" \ " .short %1\n" \ " .org 2b + %2\n" \ diff --git a/arch/blackfin/include/asm/flat.h b/arch/blackfin/include/asm/flat.h index 296d7f56fbfd..f1d6ba7afbf2 100644 --- a/arch/blackfin/include/asm/flat.h +++ b/arch/blackfin/include/asm/flat.h @@ -44,8 +44,7 @@ flat_get_relocate_addr (unsigned long relval) return relval & 0x03ffffff; /* Mask out top 6 bits */ } -static inline int flat_set_persistent(unsigned long relval, - unsigned long *persistent) +static inline int flat_set_persistent(u32 relval, u32 *persistent) { int type = (relval >> 26) & 7; if (type == 3) { diff --git a/arch/blackfin/kernel/flat.c b/arch/blackfin/kernel/flat.c index d29ab6a2e909..8ebc54daaa8e 100644 --- a/arch/blackfin/kernel/flat.c +++ b/arch/blackfin/kernel/flat.c @@ -32,7 +32,7 @@ unsigned long bfin_get_addr_from_rp(u32 *ptr, break; case FLAT_BFIN_RELOC_TYPE_32_BIT: - pr_debug("*ptr = %lx", get_unaligned(ptr)); + pr_debug("*ptr = %x", get_unaligned(ptr)); val = get_unaligned(ptr); break; @@ -77,7 +77,7 @@ void bfin_put_addr_at_rp(u32 *ptr, u32 addr, u32 relval) case FLAT_BFIN_RELOC_TYPE_32_BIT: put_unaligned(addr, ptr); - pr_debug("new ptr =%lx", get_unaligned(ptr)); + pr_debug("new ptr =%x", get_unaligned(ptr)); break; } } diff --git a/arch/h8300/include/asm/flat.h b/arch/h8300/include/asm/flat.h index 18d024251738..7e0bd6fa1532 100644 --- a/arch/h8300/include/asm/flat.h +++ b/arch/h8300/include/asm/flat.h @@ -24,7 +24,7 @@ static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, u32 *addr, u32 *persistent) { u32 val = get_unaligned((__force u32 *)rp); - if (!(flags & FLAT_FLAG_GOTPIC) + if (!(flags & FLAT_FLAG_GOTPIC)) val &= 0x00ffffff; *addr = val; return 0; diff --git a/arch/m68k/include/asm/flat.h b/arch/m68k/include/asm/flat.h index 48b62790fe70..b2a41f5b3890 100644 --- a/arch/m68k/include/asm/flat.h +++ b/arch/m68k/include/asm/flat.h @@ -30,8 +30,7 @@ static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) } #define flat_get_relocate_addr(rel) (rel) -static inline int flat_set_persistent(unsigned long relval, - unsigned long *persistent) +static inline int flat_set_persistent(u32 relval, u32 *persistent) { return 0; } diff --git a/arch/mn10300/include/asm/bug.h b/arch/mn10300/include/asm/bug.h index aa6a38886391..811414fb002d 100644 --- a/arch/mn10300/include/asm/bug.h +++ b/arch/mn10300/include/asm/bug.h @@ -21,7 +21,7 @@ do { \ asm volatile( \ " syscall 15 \n" \ "0: \n" \ - " .section __bug_table,\"a\" \n" \ + " .section __bug_table,\"aw\" \n" \ " .long 0b,%0,%1 \n" \ " .previous \n" \ : \ diff --git a/arch/parisc/include/asm/bug.h b/arch/parisc/include/asm/bug.h index d2742273a685..07ea467f22fc 100644 --- a/arch/parisc/include/asm/bug.h +++ b/arch/parisc/include/asm/bug.h @@ -27,7 +27,7 @@ do { \ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ - "\t.pushsection __bug_table,\"a\"\n" \ + "\t.pushsection __bug_table,\"aw\"\n" \ "2:\t" ASM_WORD_INSN "1b, %c0\n" \ "\t.short %c1, %c2\n" \ "\t.org 2b+%c3\n" \ @@ -50,7 +50,7 @@ do { \ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ - "\t.pushsection __bug_table,\"a\"\n" \ + "\t.pushsection __bug_table,\"aw\"\n" \ "2:\t" ASM_WORD_INSN "1b, %c0\n" \ "\t.short %c1, %c2\n" \ "\t.org 2b+%c3\n" \ @@ -64,7 +64,7 @@ do { \ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ - "\t.pushsection __bug_table,\"a\"\n" \ + "\t.pushsection __bug_table,\"aw\"\n" \ "2:\t" ASM_WORD_INSN "1b\n" \ "\t.short %c0\n" \ "\t.org 2b+%c1\n" \ diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 0ce513f2926f..36fc7bfe9e11 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -91,6 +91,7 @@ static inline int hash__pgd_bad(pgd_t pgd) } #ifdef CONFIG_STRICT_KERNEL_RWX extern void hash__mark_rodata_ro(void); +extern void hash__mark_initmem_nx(void); #endif extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index c0737c86a362..d1da415e283c 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1192,5 +1192,6 @@ static inline const int pud_pfn(pud_t pud) BUILD_BUG(); return 0; } + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 487709ff6875..544440b5aff3 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -118,6 +118,7 @@ #ifdef CONFIG_STRICT_KERNEL_RWX extern void radix__mark_rodata_ro(void); +extern void radix__mark_initmem_nx(void); #endif static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr, diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 0151af6c2a50..87fcc1948817 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -18,7 +18,7 @@ #include <asm/asm-offsets.h> #ifdef CONFIG_DEBUG_BUGVERBOSE .macro EMIT_BUG_ENTRY addr,file,line,flags - .section __bug_table,"a" + .section __bug_table,"aw" 5001: PPC_LONG \addr, 5002f .short \line, \flags .org 5001b+BUG_ENTRY_SIZE @@ -29,7 +29,7 @@ .endm #else .macro EMIT_BUG_ENTRY addr,file,line,flags - .section __bug_table,"a" + .section __bug_table,"aw" 5001: PPC_LONG \addr .short \flags .org 5001b+BUG_ENTRY_SIZE @@ -42,14 +42,14 @@ sizeof(struct bug_entry), respectively */ #ifdef CONFIG_DEBUG_BUGVERBOSE #define _EMIT_BUG_ENTRY \ - ".section __bug_table,\"a\"\n" \ + ".section __bug_table,\"aw\"\n" \ "2:\t" PPC_LONG "1b, %0\n" \ "\t.short %1, %2\n" \ ".org 2b+%3\n" \ ".previous\n" #else #define _EMIT_BUG_ENTRY \ - ".section __bug_table,\"a\"\n" \ + ".section __bug_table,\"aw\"\n" \ "2:\t" PPC_LONG "1b\n" \ "\t.short %2\n" \ ".org 2b+%3\n" \ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index dd01212935ac..afae9a336136 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -80,6 +80,13 @@ unsigned long vmalloc_to_phys(void *vmalloc_addr); void pgtable_cache_add(unsigned shift, void (*ctor)(void *)); void pgtable_cache_init(void); + +#ifdef CONFIG_STRICT_KERNEL_RWX +void mark_initmem_nx(void); +#else +static inline void mark_initmem_nx(void) { } +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PGTABLE_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e6d8354d79ef..9029afd1fa2a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -824,7 +824,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * r3 volatile parameter and return value for status * r4-r10 volatile input and output value * r11 volatile hypercall number and output value - * r12 volatile + * r12 volatile input and output value * r13-r31 nonvolatile * LR nonvolatile * CTR volatile @@ -834,25 +834,26 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * Other registers nonvolatile * * The intersection of volatile registers that don't contain possible - * inputs is: r12, cr0, xer, ctr. We may use these as scratch regs - * upon entry without saving. + * inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry + * without saving, though xer is not a good idea to use, as hardware may + * interpret some bits so it may be costly to change them. */ #ifdef CONFIG_KVM_BOOK3S_64_HANDLER /* * There is a little bit of juggling to get syscall and hcall - * working well. Save r10 in ctr to be restored in case it is a - * hcall. + * working well. Save r13 in ctr to avoid using SPRG scratch + * register. * * Userspace syscalls have already saved the PPR, hcalls must save * it before setting HMT_MEDIUM. */ #define SYSCALL_KVMTEST \ - mr r12,r13; \ + mtctr r13; \ GET_PACA(r13); \ - mtctr r10; \ + std r10,PACA_EXGEN+EX_R10(r13); \ KVMTEST_PR(0xc00); /* uses r10, branch to do_kvm_0xc00_system_call */ \ HMT_MEDIUM; \ - mr r9,r12; \ + mfctr r9; #else #define SYSCALL_KVMTEST \ @@ -935,8 +936,8 @@ EXC_VIRT_END(system_call, 0x4c00, 0x100) * This is a hcall, so register convention is as above, with these * differences: * r13 = PACA - * r12 = orig r13 - * ctr = orig r10 + * ctr = orig r13 + * orig r10 saved in PACA */ TRAMP_KVM_BEGIN(do_kvm_0xc00) /* @@ -944,14 +945,13 @@ TRAMP_KVM_BEGIN(do_kvm_0xc00) * HMT_MEDIUM. That allows the KVM code to save that value into the * guest state (it is the guest's PPR value). */ - OPT_GET_SPR(r0, SPRN_PPR, CPU_FTR_HAS_PPR) + OPT_GET_SPR(r10, SPRN_PPR, CPU_FTR_HAS_PPR) HMT_MEDIUM - OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r0, CPU_FTR_HAS_PPR) + OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r10, CPU_FTR_HAS_PPR) mfctr r10 - SET_SCRATCH0(r12) + SET_SCRATCH0(r10) std r9,PACA_EXGEN+EX_R9(r13) mfcr r9 - std r10,PACA_EXGEN+EX_R10(r13) KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00) #endif diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 5adb390e773b..516ebef905c0 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -30,6 +30,7 @@ * Use unused space in the interrupt stack to save and restore * registers for winkle support. */ +#define _MMCR0 GPR0 #define _SDR1 GPR3 #define _PTCR GPR3 #define _RPR GPR4 @@ -272,6 +273,14 @@ power_enter_stop: b pnv_wakeup_noloss .Lhandle_esl_ec_set: + /* + * POWER9 DD2 can incorrectly set PMAO when waking up after a + * state-loss idle. Saving and restoring MMCR0 over idle is a + * workaround. + */ + mfspr r4,SPRN_MMCR0 + std r4,_MMCR0(r1) + /* * Check if the requested state is a deep idle state. */ @@ -450,10 +459,14 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) pnv_restore_hyp_resource_arch300: /* * Workaround for POWER9, if we lost resources, the ERAT - * might have been mixed up and needs flushing. + * might have been mixed up and needs flushing. We also need + * to reload MMCR0 (see comment above). */ blt cr3,1f PPC_INVALIDATE_ERAT + ld r1,PACAR1(r13) + ld r4,_MMCR0(r1) + mtspr SPRN_MMCR0,r4 1: /* * POWER ISA 3. Use PSSCR to determine if we diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8541f18694a4..46b4e67d2372 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -402,6 +402,7 @@ void __init mem_init(void) void free_initmem(void) { ppc_md.progress = ppc_printk_progress; + mark_initmem_nx(); free_initmem_default(POISON_FREE_INITMEM); } diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c index 188b4107584d..443a2c66a304 100644 --- a/arch/powerpc/mm/pgtable-hash64.c +++ b/arch/powerpc/mm/pgtable-hash64.c @@ -425,33 +425,51 @@ int hash__has_transparent_hugepage(void) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_STRICT_KERNEL_RWX -void hash__mark_rodata_ro(void) +static bool hash__change_memory_range(unsigned long start, unsigned long end, + unsigned long newpp) { - unsigned long start = (unsigned long)_stext; - unsigned long end = (unsigned long)__init_begin; unsigned long idx; unsigned int step, shift; - unsigned long newpp = PP_RXXX; shift = mmu_psize_defs[mmu_linear_psize].shift; step = 1 << shift; - start = ((start + step - 1) >> shift) << shift; - end = (end >> shift) << shift; + start = ALIGN_DOWN(start, step); + end = ALIGN(end, step); // aligns up - pr_devel("marking ro start %lx, end %lx, step %x\n", - start, end, step); + if (start >= end) + return false; - if (start == end) { - pr_warn("could not set rodata ro, relocate the start" - " of the kernel to a 0x%x boundary\n", step); - return; - } + pr_debug("Changing page protection on range 0x%lx-0x%lx, to 0x%lx, step 0x%x\n", + start, end, newpp, step); for (idx = start; idx < end; idx += step) /* Not sure if we can do much with the return value */ mmu_hash_ops.hpte_updateboltedpp(newpp, idx, mmu_linear_psize, mmu_kernel_ssize); + return true; +} + +void hash__mark_rodata_ro(void) +{ + unsigned long start, end; + + start = (unsigned long)_stext; + end = (unsigned long)__init_begin; + + WARN_ON(!hash__change_memory_range(start, end, PP_RXXX)); +} + +void hash__mark_initmem_nx(void) +{ + unsigned long start, end, pp; + + start = (unsigned long)__init_begin; + end = (unsigned long)__init_end; + + pp = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL)); + + WARN_ON(!hash__change_memory_range(start, end, pp)); } #endif diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 8c13e4282308..5cc50d47ce3f 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -112,10 +112,9 @@ set_the_pte: } #ifdef CONFIG_STRICT_KERNEL_RWX -void radix__mark_rodata_ro(void) +void radix__change_memory_range(unsigned long start, unsigned long end, + unsigned long clear) { - unsigned long start = (unsigned long)_stext; - unsigned long end = (unsigned long)__init_begin; unsigned long idx; pgd_t *pgdp; pud_t *pudp; @@ -125,7 +124,8 @@ void radix__mark_rodata_ro(void) start = ALIGN_DOWN(start, PAGE_SIZE); end = PAGE_ALIGN(end); // aligns up - pr_devel("marking ro start %lx, end %lx\n", start, end); + pr_debug("Changing flags on range %lx-%lx removing 0x%lx\n", + start, end, clear); for (idx = start; idx < end; idx += PAGE_SIZE) { pgdp = pgd_offset_k(idx); @@ -147,11 +147,29 @@ void radix__mark_rodata_ro(void) if (!ptep) continue; update_the_pte: - radix__pte_update(&init_mm, idx, ptep, _PAGE_WRITE, 0, 0); + radix__pte_update(&init_mm, idx, ptep, clear, 0, 0); } radix__flush_tlb_kernel_range(start, end); } + +void radix__mark_rodata_ro(void) +{ + unsigned long start, end; + + start = (unsigned long)_stext; + end = (unsigned long)__init_begin; + + radix__change_memory_range(start, end, _PAGE_WRITE); +} + +void radix__mark_initmem_nx(void) +{ + unsigned long start = (unsigned long)__init_begin; + unsigned long end = (unsigned long)__init_end; + + radix__change_memory_range(start, end, _PAGE_EXEC); +} #endif /* CONFIG_STRICT_KERNEL_RWX */ static inline void __meminit print_mapping(unsigned long start, diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 5c0b795d656c..0736e94c7615 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -505,4 +505,12 @@ void mark_rodata_ro(void) else hash__mark_rodata_ro(); } + +void mark_initmem_nx(void) +{ + if (radix_enabled()) + radix__mark_initmem_nx(); + else + hash__mark_initmem_nx(); +} #endif diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 9b87abb178f0..cad6b57ce494 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -78,7 +78,7 @@ void opal_configure_cores(void) * ie. Host hash supports hash guests * Host radix supports hash/radix guests */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (early_cpu_has_feature(CPU_FTR_ARCH_300)) { reinit_flags |= OPAL_REINIT_CPUS_MMU_HASH; if (early_radix_enabled()) reinit_flags |= OPAL_REINIT_CPUS_MMU_RADIX; diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 1bbd9dbfe4e0..ce9cc123988b 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -14,7 +14,7 @@ ".section .rodata.str,\"aMS\",@progbits,1\n" \ "2: .asciz \""__FILE__"\"\n" \ ".previous\n" \ - ".section __bug_table,\"a\"\n" \ + ".section __bug_table,\"aw\"\n" \ "3: .long 1b-3b,2b-3b\n" \ " .short %0,%1\n" \ " .org 3b+%2\n" \ @@ -30,7 +30,7 @@ asm volatile( \ "0: j 0b+2\n" \ "1:\n" \ - ".section __bug_table,\"a\"\n" \ + ".section __bug_table,\"aw\"\n" \ "2: .long 1b-2b\n" \ " .short %0\n" \ " .org 2b+%1\n" \ diff --git a/arch/sh/include/asm/bug.h b/arch/sh/include/asm/bug.h index c9828f785ca0..5b5086367639 100644 --- a/arch/sh/include/asm/bug.h +++ b/arch/sh/include/asm/bug.h @@ -24,14 +24,14 @@ */ #ifdef CONFIG_DEBUG_BUGVERBOSE #define _EMIT_BUG_ENTRY \ - "\t.pushsection __bug_table,\"a\"\n" \ + "\t.pushsection __bug_table,\"aw\"\n" \ "2:\t.long 1b, %O1\n" \ "\t.short %O2, %O3\n" \ "\t.org 2b+%O4\n" \ "\t.popsection\n" #else #define _EMIT_BUG_ENTRY \ - "\t.pushsection __bug_table,\"a\"\n" \ + "\t.pushsection __bug_table,\"aw\"\n" \ "2:\t.long 1b\n" \ "\t.short %O3\n" \ "\t.org 2b+%O4\n" \ diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h index ec9c04de3664..ff05992dae7a 100644 --- a/arch/sparc/include/asm/trap_block.h +++ b/arch/sparc/include/asm/trap_block.h @@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS]; void init_cur_cpu_trap(struct thread_info *); void setup_tba(void); extern int ncpus_probed; +extern u64 cpu_mondo_counter[NR_CPUS]; unsigned long real_hard_smp_processor_id(void); diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 24f21c726dfa..f10e2f712394 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -673,12 +673,14 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, static int dma_4v_supported(struct device *dev, u64 device_mask) { struct iommu *iommu = dev->archdata.iommu; - u64 dma_addr_mask; + u64 dma_addr_mask = iommu->dma_addr_mask; - if (device_mask > DMA_BIT_MASK(32) && iommu->atu) - dma_addr_mask = iommu->atu->dma_addr_mask; - else - dma_addr_mask = iommu->dma_addr_mask; + if (device_mask > DMA_BIT_MASK(32)) { + if (iommu->atu) + dma_addr_mask = iommu->atu->dma_addr_mask; + else + return 0; + } if ((device_mask & dma_addr_mask) == dma_addr_mask) return 1; diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index fdf31040a7dc..3218bc43302e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -622,22 +622,48 @@ retry: } } -/* Multi-cpu list version. */ +#define CPU_MONDO_COUNTER(cpuid) (cpu_mondo_counter[cpuid]) +#define MONDO_USEC_WAIT_MIN 2 +#define MONDO_USEC_WAIT_MAX 100 +#define MONDO_RETRY_LIMIT 500000 + +/* Multi-cpu list version. + * + * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'. + * Sometimes not all cpus receive the mondo, requiring us to re-send + * the mondo until all cpus have received, or cpus are truly stuck + * unable to receive mondo, and we timeout. + * Occasionally a target cpu strand is borrowed briefly by hypervisor to + * perform guest service, such as PCIe error handling. Consider the + * service time, 1 second overall wait is reasonable for 1 cpu. + * Here two in-between mondo check wait time are defined: 2 usec for + * single cpu quick turn around and up to 100usec for large cpu count. + * Deliver mondo to large number of cpus could take longer, we adjusts + * the retry count as long as target cpus are making forward progress. + */ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) { - int retries, this_cpu, prev_sent, i, saw_cpu_error; + int this_cpu, tot_cpus, prev_sent, i, rem; + int usec_wait, retries, tot_retries; + u16 first_cpu = 0xffff; + unsigned long xc_rcvd = 0; unsigned long status; + int ecpuerror_id = 0; + int enocpu_id = 0; u16 *cpu_list; + u16 cpu; this_cpu = smp_processor_id(); - cpu_list = __va(tb->cpu_list_pa); - - saw_cpu_error = 0; - retries = 0; + usec_wait = cnt * MONDO_USEC_WAIT_MIN; + if (usec_wait > MONDO_USEC_WAIT_MAX) + usec_wait = MONDO_USEC_WAIT_MAX; + retries = tot_retries = 0; + tot_cpus = cnt; prev_sent = 0; + do { - int forward_progress, n_sent; + int n_sent, mondo_delivered, target_cpu_busy; status = sun4v_cpu_mondo_send(cnt, tb->cpu_list_pa, @@ -645,94 +671,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) /* HV_EOK means all cpus received the xcall, we're done. */ if (likely(status == HV_EOK)) - break; + goto xcall_done; + + /* If not these non-fatal errors, panic */ + if (unlikely((status != HV_EWOULDBLOCK) && + (status != HV_ECPUERROR) && + (status != HV_ENOCPU))) + goto fatal_errors; /* First, see if we made any forward progress. * + * Go through the cpu_list, count the target cpus that have + * received our mondo (n_sent), and those that did not (rem). + * Re-pack cpu_list with the cpus remain to be retried in the + * front - this simplifies tracking the truly stalled cpus. + * * The hypervisor indicates successful sends by setting * cpu list entries to the value 0xffff. + * + * EWOULDBLOCK means some target cpus did not receive the + * mondo and retry usually helps. + * + * ECPUERROR means at least one target cpu is in error state, + * it's usually safe to skip the faulty cpu and retry. + * + * ENOCPU means one of the target cpu doesn't belong to the + * domain, perhaps offlined which is unexpected, but not + * fatal and it's okay to skip the offlined cpu. */ + rem = 0; n_sent = 0; for (i = 0; i < cnt; i++) { - if (likely(cpu_list[i] == 0xffff)) + cpu = cpu_list[i]; + if (likely(cpu == 0xffff)) { n_sent++; + } else if ((status == HV_ECPUERROR) && + (sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) { + ecpuerror_id = cpu + 1; + } else if (status == HV_ENOCPU && !cpu_online(cpu)) { + enocpu_id = cpu + 1; + } else { + cpu_list[rem++] = cpu; + } } - forward_progress = 0; - if (n_sent > prev_sent) - forward_progress = 1; + /* No cpu remained, we're done. */ + if (rem == 0) + break; - prev_sent = n_sent; + /* Otherwise, update the cpu count for retry. */ + cnt = rem; - /* If we get a HV_ECPUERROR, then one or more of the cpus - * in the list are in error state. Use the cpu_state() - * hypervisor call to find out which cpus are in error state. + /* Record the overall number of mondos received by the + * first of the remaining cpus. */ - if (unlikely(status == HV_ECPUERROR)) { - for (i = 0; i < cnt; i++) { - long err; - u16 cpu; + if (first_cpu != cpu_list[0]) { + first_cpu = cpu_list[0]; + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); + } - cpu = cpu_list[i]; - if (cpu == 0xffff) - continue; + /* Was any mondo delivered successfully? */ + mondo_delivered = (n_sent > prev_sent); + prev_sent = n_sent; - err = sun4v_cpu_state(cpu); - if (err == HV_CPU_STATE_ERROR) { - saw_cpu_error = (cpu + 1); - cpu_list[i] = 0xffff; - } - } - } else if (unlikely(status != HV_EWOULDBLOCK)) - goto fatal_mondo_error; + /* or, was any target cpu busy processing other mondos? */ + target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu)); + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); - /* Don't bother rewriting the CPU list, just leave the - * 0xffff and non-0xffff entries in there and the - * hypervisor will do the right thing. - * - * Only advance timeout state if we didn't make any - * forward progress. + /* Retry count is for no progress. If we're making progress, + * reset the retry count. */ - if (unlikely(!forward_progress)) { - if (unlikely(++retries > 10000)) - goto fatal_mondo_timeout; - - /* Delay a little bit to let other cpus catch up - * on their cpu mondo queue work. - */ - udelay(2 * cnt); + if (likely(mondo_delivered || target_cpu_busy)) { + tot_retries += retries; + retries = 0; + } else if (unlikely(retries > MONDO_RETRY_LIMIT)) { + goto fatal_mondo_timeout; } - } while (1); - if (unlikely(saw_cpu_error)) - goto fatal_mondo_cpu_error; + /* Delay a little bit to let other cpus catch up on + * their cpu mondo queue work. + */ + if (!mondo_delivered) + udelay(usec_wait); - return; + retries++; + } while (1); -fatal_mondo_cpu_error: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus " - "(including %d) were in error state\n", - this_cpu, saw_cpu_error - 1); +xcall_done: + if (unlikely(ecpuerror_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n", + this_cpu, ecpuerror_id - 1); + } else if (unlikely(enocpu_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n", + this_cpu, enocpu_id - 1); + } return; +fatal_errors: + /* fatal errors include bad alignment, etc */ + pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n", + this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa); + panic("Unexpected SUN4V mondo error %lu\n", status); + fatal_mondo_timeout: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward " - " progress after %d retries.\n", - this_cpu, retries); - goto dump_cpu_list_and_out; - -fatal_mondo_error: - printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n", - this_cpu, status); - printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) " - "mondo_block_pa(%lx)\n", - this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa); - -dump_cpu_list_and_out: - printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu); - for (i = 0; i < cnt; i++) - printk("%u ", cpu_list[i]); - printk("]\n"); + /* some cpus being non-responsive to the cpu mondo */ + pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n", + this_cpu, first_cpu, (tot_retries + retries), tot_cpus); + panic("SUN4V mondo timeout panic\n"); } static void (*xcall_deliver_impl)(struct trap_per_cpu *, int); diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S index 559bc5e9c199..34631995859a 100644 --- a/arch/sparc/kernel/sun4v_ivec.S +++ b/arch/sparc/kernel/sun4v_ivec.S @@ -26,6 +26,21 @@ sun4v_cpu_mondo: ldxa [%g0] ASI_SCRATCHPAD, %g4 sub %g4, TRAP_PER_CPU_FAULT_INFO, %g4 + /* Get smp_processor_id() into %g3 */ + sethi %hi(trap_block), %g5 + or %g5, %lo(trap_block), %g5 + sub %g4, %g5, %g3 + srlx %g3, TRAP_BLOCK_SZ_SHIFT, %g3 + + /* Increment cpu_mondo_counter[smp_processor_id()] */ + sethi %hi(cpu_mondo_counter), %g5 + or %g5, %lo(cpu_mondo_counter), %g5 + sllx %g3, 3, %g3 + add %g5, %g3, %g5 + ldx [%g5], %g3 + add %g3, 1, %g3 + stx %g3, [%g5] + /* Get CPU mondo queue base phys address into %g7. */ ldx [%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7 diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 196ee5eb4d48..ad31af1dd726 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2733,6 +2733,7 @@ void do_getpsr(struct pt_regs *regs) } } +u64 cpu_mondo_counter[NR_CPUS] = {0}; struct trap_per_cpu trap_block[NR_CPUS]; EXPORT_SYMBOL(trap_block); diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index fcb7604172ce..cd20ca0b4043 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -348,6 +348,7 @@ config X86_DEBUG_FPU config PUNIT_ATOM_DEBUG tristate "ATOM Punit debug driver" + depends on PCI select DEBUG_FS select IOSF_MBI ---help--- diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 0d810fb15eac..d88a2fddba8c 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -73,12 +73,13 @@ UBSAN_SANITIZE := n $(obj)/bzImage: asflags-y := $(SVGA_MODE) quiet_cmd_image = BUILD $@ +silent_redirect_image = >/dev/null cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \ - $(obj)/zoffset.h $@ + $(obj)/zoffset.h $@ $($(quiet)redirect_image) $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) - @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' + @$(kecho) 'Kernel: $@ is ready' ' (#'`cat .version`')' OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 6cf79e1a6830..0eb9f92f3717 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1,5 +1,4 @@ # CONFIG_64BIT is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -125,7 +124,6 @@ CONFIG_NF_CONNTRACK_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_IP_NF_TARGET_ULOG=y CONFIG_NF_NAT=y CONFIG_IP_NF_TARGET_MASQUERADE=y CONFIG_IP_NF_MANGLE=y @@ -255,7 +253,6 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_UHCI_HCD=y CONFIG_USB_PRINTER=y CONFIG_USB_STORAGE=y -CONFIG_USB_LIBUSUAL=y CONFIG_EDAC=y CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index de45f57b410d..4a4b16e56d35 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1,4 +1,3 @@ -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -124,7 +123,6 @@ CONFIG_NF_CONNTRACK_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_IP_NF_TARGET_ULOG=y CONFIG_NF_NAT=y CONFIG_IP_NF_TARGET_MASQUERADE=y CONFIG_IP_NF_MANGLE=y @@ -251,7 +249,6 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_UHCI_HCD=y CONFIG_USB_PRINTER=y CONFIG_USB_STORAGE=y -CONFIG_USB_LIBUSUAL=y CONFIG_EDAC=y CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index ff1ea2fb9705..8e3db8f642a7 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -191,8 +191,8 @@ static void release_pmc_hardware(void) {} static bool check_hw_exists(void) { - u64 val, val_fail, val_new= ~0; - int i, reg, reg_fail, ret = 0; + u64 val, val_fail = -1, val_new= ~0; + int i, reg, reg_fail = -1, ret = 0; int bios_fail = 0; int reg_safe = -1; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index aa62437d1aa1..98b0f0729527 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -1708,6 +1708,120 @@ static __initconst const u64 glm_hw_cache_extra_regs }, }; +static __initconst const u64 glp_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [C(RESULT_MISS)] = 0x0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [C(RESULT_MISS)] = 0x0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0380, /* ICACHE.ACCESSES */ + [C(RESULT_MISS)] = 0x0280, /* ICACHE.MISSES */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [C(RESULT_MISS)] = 0xe08, /* DTLB_LOAD_MISSES.WALK_COMPLETED */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [C(RESULT_MISS)] = 0xe49, /* DTLB_STORE_MISSES.WALK_COMPLETED */ + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c0, /* INST_RETIRED.ANY_P */ + [C(RESULT_MISS)] = 0x0481, /* ITLB.MISS */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [C(RESULT_MISS)] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, +}; + +static __initconst const u64 glp_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_READ| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_READ| + GLM_LLC_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_WRITE| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_WRITE| + GLM_LLC_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, +}; + #define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ #define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ #define KNL_MCDRAM_LOCAL BIT_ULL(21) @@ -3016,6 +3130,9 @@ static int hsw_hw_config(struct perf_event *event) return 0; } +static struct event_constraint counter0_constraint = + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1); + static struct event_constraint counter2_constraint = EVENT_CONSTRAINT(0, 0x4, 0); @@ -3037,6 +3154,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return c; } +static struct event_constraint * +glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c; + + /* :ppp means to do reduced skid PEBS which is PMC0 only. */ + if (event->attr.precise_ip == 3) + return &counter0_constraint; + + c = intel_get_event_constraints(cpuc, idx, event); + + return c; +} + /* * Broadwell: * @@ -3265,10 +3397,8 @@ static void intel_pmu_cpu_dying(int cpu) static void intel_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) { - if (x86_pmu.pebs_active) - intel_pmu_pebs_sched_task(ctx, sched_in); - if (x86_pmu.lbr_nr) - intel_pmu_lbr_sched_task(ctx, sched_in); + intel_pmu_pebs_sched_task(ctx, sched_in); + intel_pmu_lbr_sched_task(ctx, sched_in); } PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); @@ -3838,6 +3968,32 @@ __init int intel_pmu_init(void) pr_cont("Goldmont events, "); break; + case INTEL_FAM6_ATOM_GEMINI_LAKE: + memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints; + x86_pmu.extra_regs = intel_glm_extra_regs; + /* + * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS + * for precise cycles. + */ + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.get_event_constraints = glp_get_event_constraints; + x86_pmu.cpu_events = glm_events_attrs; + /* Goldmont Plus has 4-wide pipeline */ + event_attr_td_total_slots_scale_glm.event_str = "4"; + pr_cont("Goldmont plus events, "); + break; + case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 238ae3248ba5..4cf100ff2a37 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,16 +40,16 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT + * Available model: SLM,AMT,GLM * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 - * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL + * SKL,KNL,GLM * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 @@ -57,16 +57,17 @@ * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 - * Available model: SNB,IVB,HSW,BDW,SKL,KNL + * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL + * GLM * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL + * SKL,KNL,GLM * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 @@ -82,7 +83,7 @@ * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT only + * Available model: HSW ULT, GLM * Scope: Package (physical package) * */ @@ -504,6 +505,17 @@ static const struct cstate_model knl_cstates __initconst = { }; +static const struct cstate_model glm_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | + BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C10_RES), +}; + #define X86_CSTATES_MODEL(model, states) \ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) } @@ -546,6 +558,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index c6d23ffe422d..a322fed5f8ed 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -606,12 +606,6 @@ static inline void intel_pmu_drain_pebs_buffer(void) x86_pmu.drain_pebs(®s); } -void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) -{ - if (!sched_in) - intel_pmu_drain_pebs_buffer(); -} - /* * PEBS */ @@ -651,6 +645,12 @@ struct event_constraint intel_glm_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_glp_pebs_event_constraints[] = { + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), + EVENT_CONSTRAINT_END +}; + struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ @@ -816,6 +816,14 @@ static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc) return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs); } +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + if (!sched_in && pebs_needs_sched_cb(cpuc)) + intel_pmu_drain_pebs_buffer(); +} + static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) { struct debug_store *ds = cpuc->ds; @@ -889,6 +897,8 @@ void intel_pmu_pebs_enable(struct perf_event *event) if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { ds->pebs_event_reset[hwc->idx] = (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; + } else { + ds->pebs_event_reset[hwc->idx] = 0; } } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index eb261656a320..955457a30197 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -380,8 +380,12 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; + if (!cpuc->lbr_users) + return; + /* * If LBR callstack feature is enabled and the stack was saved when * the task was scheduled out, restore the stack. Otherwise flush diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 53728eea1bed..476aec3a4cab 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -879,6 +879,8 @@ extern struct event_constraint intel_slm_pebs_event_constraints[]; extern struct event_constraint intel_glm_pebs_event_constraints[]; +extern struct event_constraint intel_glp_pebs_event_constraints[]; + extern struct event_constraint intel_nehalem_pebs_event_constraints[]; extern struct event_constraint intel_westmere_pebs_event_constraints[]; diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 39e702d90cdb..aa6b2023d8f8 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -35,7 +35,7 @@ #define _BUG_FLAGS(ins, flags) \ do { \ asm volatile("1:\t" ins "\n" \ - ".pushsection __bug_table,\"a\"\n" \ + ".pushsection __bug_table,\"aw\"\n" \ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \ "\t.word %c1" "\t# bug_entry::line\n" \ @@ -52,7 +52,7 @@ do { \ #define _BUG_FLAGS(ins, flags) \ do { \ asm volatile("1:\t" ins "\n" \ - ".pushsection __bug_table,\"a\"\n" \ + ".pushsection __bug_table,\"aw\"\n" \ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ "\t.word %c0" "\t# bug_entry::flags\n" \ "\t.org 2b+%c1\n" \ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 7afb0e2f07f4..48febf07e828 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -328,13 +328,13 @@ static inline unsigned type in##bwl##_p(int port) \ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ { \ asm volatile("rep; outs" #bwl \ - : "+S"(addr), "+c"(count) : "d"(port)); \ + : "+S"(addr), "+c"(count) : "d"(port) : "memory"); \ } \ \ static inline void ins##bwl(int port, void *addr, unsigned long count) \ { \ asm volatile("rep; ins" #bwl \ - : "+D"(addr), "+c"(count) : "d"(port)); \ + : "+D"(addr), "+c"(count) : "d"(port) : "memory"); \ } BUILDIO(b, b, char) diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 34b984c60790..6cf65437b5e5 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -52,10 +52,10 @@ typedef u8 kprobe_opcode_t; #define flush_insn_slot(p) do { } while (0) /* optinsn template addresses */ -extern __visible kprobe_opcode_t optprobe_template_entry; -extern __visible kprobe_opcode_t optprobe_template_val; -extern __visible kprobe_opcode_t optprobe_template_call; -extern __visible kprobe_opcode_t optprobe_template_end; +extern __visible kprobe_opcode_t optprobe_template_entry[]; +extern __visible kprobe_opcode_t optprobe_template_val[]; +extern __visible kprobe_opcode_t optprobe_template_call[]; +extern __visible kprobe_opcode_t optprobe_template_end[]; #define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE) #define MAX_OPTINSN_SIZE \ (((unsigned long)&optprobe_template_end - \ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index ecfcb6643c9b..265c907d7d4c 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -293,7 +293,7 @@ static inline unsigned long __get_current_cr3_fast(void) unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); /* For now, be very restrictive about when this can be called. */ - VM_WARN_ON(in_nmi() || !in_atomic()); + VM_WARN_ON(in_nmi() || preemptible()); VM_BUG_ON(cr3 != __read_cr3()); return cr3; diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index cb976bab6299..9ffc36bfe4cd 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -84,7 +84,7 @@ struct pv_init_ops { */ unsigned (*patch)(u8 type, u16 clobber, void *insnbuf, unsigned long addr, unsigned len); -}; +} __no_randomize_layout; struct pv_lazy_ops { @@ -92,12 +92,12 @@ struct pv_lazy_ops { void (*enter)(void); void (*leave)(void); void (*flush)(void); -}; +} __no_randomize_layout; struct pv_time_ops { unsigned long long (*sched_clock)(void); unsigned long long (*steal_clock)(int cpu); -}; +} __no_randomize_layout; struct pv_cpu_ops { /* hooks for various privileged instructions */ @@ -176,7 +176,7 @@ struct pv_cpu_ops { void (*start_context_switch)(struct task_struct *prev); void (*end_context_switch)(struct task_struct *next); -}; +} __no_randomize_layout; struct pv_irq_ops { /* @@ -199,7 +199,7 @@ struct pv_irq_ops { #ifdef CONFIG_X86_64 void (*adjust_exception_frame)(void); #endif -}; +} __no_randomize_layout; struct pv_mmu_ops { unsigned long (*read_cr2)(void); @@ -305,7 +305,7 @@ struct pv_mmu_ops { an mfn. We can tell which is which from the index. */ void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags); -}; +} __no_randomize_layout; struct arch_spinlock; #ifdef CONFIG_SMP @@ -322,7 +322,7 @@ struct pv_lock_ops { void (*kick)(int cpu); struct paravirt_callee_save vcpu_is_preempted; -}; +} __no_randomize_layout; /* This contains all the paravirt structures: we get a convenient * number for each function using the offset which we use to indicate @@ -334,7 +334,7 @@ struct paravirt_patch_template { struct pv_irq_ops pv_irq_ops; struct pv_mmu_ops pv_mmu_ops; struct pv_lock_ops pv_lock_ops; -}; +} __no_randomize_layout; extern struct pv_info pv_info; extern struct pv_init_ops pv_init_ops; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6a79547e8ee0..028245e1c42b 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -129,7 +129,7 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; -}; +} __randomize_layout; struct cpuid_regs { u32 eax, ebx, ecx, edx; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 6bb680671088..7491e73d9253 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -347,6 +347,14 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, struct mpc_intsrc mp_irq; /* + * Check bus_irq boundary. + */ + if (bus_irq >= NR_IRQS_LEGACY) { + pr_warn("Invalid bus_irq %u for legacy override\n", bus_irq); + return; + } + + /* * Convert 'gsi' to 'ioapic.pin'. */ ioapic = mp_find_ioapic(gsi); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index b4f5f73febdb..237e9c2341c7 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2093,7 +2093,7 @@ static inline void __init check_timer(void) int idx; idx = find_irq_entry(apic1, pin1, mp_INT); if (idx != -1 && irq_trigger(idx)) - unmask_ioapic_irq(irq_get_chip_data(0)); + unmask_ioapic_irq(irq_get_irq_data(0)); } irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bb5abe8f5fd4..3b9e220621f8 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -134,6 +134,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) n = K6_BUG_LOOP; f_vide = vide; + OPTIMIZER_HIDE_VAR(f_vide); d = rdtsc(); while (n--) f_vide(); diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 3fe45f84ced4..cbf1f6ba39a8 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -235,8 +235,7 @@ static void __init dtb_add_ioapic(struct device_node *dn) ret = of_address_to_resource(dn, 0, &r); if (ret) { - printk(KERN_ERR "Can't obtain address from node %s.\n", - dn->full_name); + printk(KERN_ERR "Can't obtain address from device node %pOF.\n", dn); return; } mp_register_ioapic(++ioapic_id, r.start, gsi_top, &cfg); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 760433b2574a..2688c7dc5323 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -22,7 +22,7 @@ config KVM depends on HAVE_KVM depends on HIGH_RES_TIMERS # for TASKSTATS/TASK_DELAY_ACCT: - depends on NET + depends on NET && MULTIUSER select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 2695a34fa1c5..337b6d2730fa 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -649,9 +649,10 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu) } if ((stimer->config & HV_STIMER_ENABLE) && - stimer->count) - stimer_start(stimer); - else + stimer->count) { + if (!stimer->msg_pending) + stimer_start(stimer); + } else stimer_cleanup(stimer); } } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 84e62acf2dd8..29fd8af5c347 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -198,7 +198,8 @@ struct loaded_vmcs { struct vmcs *vmcs; struct vmcs *shadow_vmcs; int cpu; - int launched; + bool launched; + bool nmi_known_unmasked; struct list_head loaded_vmcss_on_cpu_link; }; @@ -2326,6 +2327,11 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) __vmx_load_host_state(to_vmx(vcpu)); } +static bool emulation_required(struct kvm_vcpu *vcpu) +{ + return emulate_invalid_guest_state && !guest_state_valid(vcpu); +} + static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); /* @@ -2363,6 +2369,8 @@ static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { + unsigned long old_rflags = vmx_get_rflags(vcpu); + __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); to_vmx(vcpu)->rflags = rflags; if (to_vmx(vcpu)->rmode.vm86_active) { @@ -2370,6 +2378,9 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; } vmcs_writel(GUEST_RFLAGS, rflags); + + if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM) + to_vmx(vcpu)->emulation_required = emulation_required(vcpu); } static u32 vmx_get_pkru(struct kvm_vcpu *vcpu) @@ -3857,11 +3868,6 @@ static __init int alloc_kvm_area(void) return 0; } -static bool emulation_required(struct kvm_vcpu *vcpu) -{ - return emulate_invalid_guest_state && !guest_state_valid(vcpu); -} - static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment *save) { @@ -5510,10 +5516,8 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!is_guest_mode(vcpu)) { - ++vcpu->stat.nmi_injections; - vmx->nmi_known_unmasked = false; - } + ++vcpu->stat.nmi_injections; + vmx->loaded_vmcs->nmi_known_unmasked = false; if (vmx->rmode.vm86_active) { if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE) @@ -5527,16 +5531,21 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) { - if (to_vmx(vcpu)->nmi_known_unmasked) + struct vcpu_vmx *vmx = to_vmx(vcpu); + bool masked; + + if (vmx->loaded_vmcs->nmi_known_unmasked) return false; - return vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; + masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; + vmx->loaded_vmcs->nmi_known_unmasked = !masked; + return masked; } static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) { struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx->nmi_known_unmasked = !masked; + vmx->loaded_vmcs->nmi_known_unmasked = !masked; if (masked) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); @@ -8736,7 +8745,7 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK; - if (vmx->nmi_known_unmasked) + if (vmx->loaded_vmcs->nmi_known_unmasked) return; /* * Can't use vmx->exit_intr_info since we're not sure what @@ -8760,7 +8769,7 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); else - vmx->nmi_known_unmasked = + vmx->loaded_vmcs->nmi_known_unmasked = !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI); } @@ -10488,6 +10497,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); u32 exit_qual; int ret; @@ -10512,6 +10522,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * for misconfigurations which will anyway be caught by the processor * when using the merged vmcs02. */ + if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS) { + nested_vmx_failValid(vcpu, + VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS); + goto out; + } + if (vmcs12->launch_state == launch) { nested_vmx_failValid(vcpu, launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5b8f07889f6a..82a63c59f77b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -597,8 +597,8 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) (unsigned long *)&vcpu->arch.regs_avail)) return true; - gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT; - offset = (kvm_read_cr3(vcpu) & ~31u) & (PAGE_SIZE - 1); + gfn = (kvm_read_cr3(vcpu) & ~31ul) >> PAGE_SHIFT; + offset = (kvm_read_cr3(vcpu) & ~31ul) & (PAGE_SIZE - 1); r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), PFERR_USER_MASK | PFERR_WRITE_MASK); if (r < 0) diff --git a/arch/x86/math-emu/Makefile b/arch/x86/math-emu/Makefile index 9b0c63b60302..1b2dac174321 100644 --- a/arch/x86/math-emu/Makefile +++ b/arch/x86/math-emu/Makefile @@ -5,8 +5,8 @@ #DEBUG = -DDEBUGGING DEBUG = PARANOID = -DPARANOID -EXTRA_CFLAGS := $(PARANOID) $(DEBUG) -fno-builtin $(MATH_EMULATION) -EXTRA_AFLAGS := $(PARANOID) +ccflags-y += $(PARANOID) $(DEBUG) -fno-builtin $(MATH_EMULATION) +asflags-y += $(PARANOID) # From 'C' language sources: C_OBJS =fpu_entry.o errors.o \ diff --git a/arch/x86/math-emu/fpu_emu.h b/arch/x86/math-emu/fpu_emu.h index afbc4d805d66..c9c320dccca1 100644 --- a/arch/x86/math-emu/fpu_emu.h +++ b/arch/x86/math-emu/fpu_emu.h @@ -157,7 +157,7 @@ extern u_char const data_sizes_16[32]; #define signbyte(a) (((u_char *)(a))[9]) #define getsign(a) (signbyte(a) & 0x80) -#define setsign(a,b) { if (b) signbyte(a) |= 0x80; else signbyte(a) &= 0x7f; } +#define setsign(a,b) { if ((b) != 0) signbyte(a) |= 0x80; else signbyte(a) &= 0x7f; } #define copysign(a,b) { if (getsign(a)) signbyte(b) |= 0x80; \ else signbyte(b) &= 0x7f; } #define changesign(a) { signbyte(a) ^= 0x80; } diff --git a/arch/x86/math-emu/reg_compare.c b/arch/x86/math-emu/reg_compare.c index b77360fdbf4a..19b33b50adfa 100644 --- a/arch/x86/math-emu/reg_compare.c +++ b/arch/x86/math-emu/reg_compare.c @@ -168,7 +168,7 @@ static int compare(FPU_REG const *b, int tagb) /* This function requires that st(0) is not empty */ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag) { - int f = 0, c; + int f, c; c = compare(loaded_data, loaded_tag); @@ -189,12 +189,12 @@ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag) case COMP_No_Comp: f = SW_C3 | SW_C2 | SW_C0; break; -#ifdef PARANOID default: +#ifdef PARANOID EXCEPTION(EX_INTERNAL | 0x121); +#endif /* PARANOID */ f = SW_C3 | SW_C2 | SW_C0; break; -#endif /* PARANOID */ } setcc(f); if (c & COMP_Denormal) { @@ -205,7 +205,7 @@ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag) static int compare_st_st(int nr) { - int f = 0, c; + int f, c; FPU_REG *st_ptr; if (!NOT_EMPTY(0) || !NOT_EMPTY(nr)) { @@ -235,12 +235,12 @@ static int compare_st_st(int nr) case COMP_No_Comp: f = SW_C3 | SW_C2 | SW_C0; break; -#ifdef PARANOID default: +#ifdef PARANOID EXCEPTION(EX_INTERNAL | 0x122); +#endif /* PARANOID */ f = SW_C3 | SW_C2 | SW_C0; break; -#endif /* PARANOID */ } setcc(f); if (c & COMP_Denormal) { @@ -283,12 +283,12 @@ static int compare_i_st_st(int nr) case COMP_No_Comp: f = X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF; break; -#ifdef PARANOID default: +#ifdef PARANOID EXCEPTION(EX_INTERNAL | 0x122); +#endif /* PARANOID */ f = 0; break; -#endif /* PARANOID */ } FPU_EFLAGS = (FPU_EFLAGS & ~(X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF)) | f; if (c & COMP_Denormal) { diff --git a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c index 6e075afa7877..58337b2bc682 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c @@ -38,8 +38,10 @@ static void __init *max7315_platform_data(void *info) */ strcpy(i2c_info->type, "max7315"); if (nr++) { - sprintf(base_pin_name, "max7315_%d_base", nr); - sprintf(intr_pin_name, "max7315_%d_int", nr); + snprintf(base_pin_name, sizeof(base_pin_name), + "max7315_%d_base", nr); + snprintf(intr_pin_name, sizeof(intr_pin_name), + "max7315_%d_int", nr); } else { strcpy(base_pin_name, "max7315_base"); strcpy(intr_pin_name, "max7315_int"); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index d4a61ddf9e62..3e4bdb442fbc 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -40,7 +40,6 @@ static int timeout_base_ns[] = { static int timeout_us; static bool nobau = true; static int nobau_perm; -static cycles_t congested_cycles; /* tunables: */ static int max_concurr = MAX_BAU_CONCURRENT; @@ -829,10 +828,10 @@ static void record_send_stats(cycles_t time1, cycles_t time2, if ((completion_status == FLUSH_COMPLETE) && (try == 1)) { bcp->period_requests++; bcp->period_time += elapsed; - if ((elapsed > congested_cycles) && + if ((elapsed > usec_2_cycles(bcp->cong_response_us)) && (bcp->period_requests > bcp->cong_reps) && ((bcp->period_time / bcp->period_requests) > - congested_cycles)) { + usec_2_cycles(bcp->cong_response_us))) { stat->s_congested++; disable_for_period(bcp, stat); } @@ -2222,14 +2221,17 @@ static int __init uv_bau_init(void) else if (is_uv1_hub()) ops = uv1_bau_ops; + nuvhubs = uv_num_possible_blades(); + if (nuvhubs < 2) { + pr_crit("UV: BAU disabled - insufficient hub count\n"); + goto err_bau_disable; + } + for_each_possible_cpu(cur_cpu) { mask = &per_cpu(uv_flush_tlb_mask, cur_cpu); zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu)); } - nuvhubs = uv_num_possible_blades(); - congested_cycles = usec_2_cycles(congested_respns_us); - uv_base_pnode = 0x7fffffff; for (uvhub = 0; uvhub < nuvhubs; uvhub++) { cpus = uv_blade_nr_possible_cpus(uvhub); @@ -2242,9 +2244,8 @@ static int __init uv_bau_init(void) enable_timeouts(); if (init_per_cpu(nuvhubs, uv_base_pnode)) { - set_bau_off(); - nobau_perm = 1; - return 0; + pr_crit("UV: BAU disabled - per CPU init failed\n"); + goto err_bau_disable; } vector = UV_BAU_MESSAGE; @@ -2270,6 +2271,16 @@ static int __init uv_bau_init(void) } return 0; + +err_bau_disable: + + for_each_possible_cpu(cur_cpu) + free_cpumask_var(per_cpu(uv_flush_tlb_mask, cur_cpu)); + + set_bau_off(); + nobau_perm = 1; + + return -EINVAL; } core_initcall(uv_bau_init); fs_initcall(uv_ptc_init); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index b75b734ee73a..19182d091587 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3160,6 +3160,8 @@ static struct acpi_driver acpi_nfit_driver = { static __init int nfit_init(void) { + int ret; + BUILD_BUG_ON(sizeof(struct acpi_table_nfit) != 40); BUILD_BUG_ON(sizeof(struct acpi_nfit_system_address) != 56); BUILD_BUG_ON(sizeof(struct acpi_nfit_memory_map) != 48); @@ -3187,8 +3189,14 @@ static __init int nfit_init(void) return -ENOMEM; nfit_mce_register(); + ret = acpi_bus_register_driver(&acpi_nfit_driver); + if (ret) { + nfit_mce_unregister(); + destroy_workqueue(nfit_wq); + } + + return ret; - return acpi_bus_register_driver(&acpi_nfit_driver); } static __exit void nfit_exit(void) diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index 292dec18ffb8..07bdd51b3b9a 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1613,7 +1613,7 @@ static int zatm_init_one(struct pci_dev *pci_dev, ret = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32)); if (ret < 0) - goto out_disable; + goto out_release; zatm_dev->pci_dev = pci_dev; dev->dev_data = zatm_dev; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 3b8210ebb50e..60303aa28587 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1222,8 +1222,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev, spin_unlock_irq(&dev->power.lock); - dev_pm_domain_set(dev, &genpd->domain); - return gpd_data; err_free: @@ -1237,8 +1235,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev, static void genpd_free_dev_data(struct device *dev, struct generic_pm_domain_data *gpd_data) { - dev_pm_domain_set(dev, NULL); - spin_lock_irq(&dev->power.lock); dev->power.subsys_data->domain_data = NULL; @@ -1275,6 +1271,8 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (ret) goto out; + dev_pm_domain_set(dev, &genpd->domain); + genpd->device_count++; genpd->max_off_time_changed = true; @@ -1336,6 +1334,8 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, if (genpd->detach_dev) genpd->detach_dev(genpd, dev); + dev_pm_domain_set(dev, NULL); + list_del_init(&pdd->list_node); genpd_unlock(genpd); diff --git a/drivers/base/regmap/regmap-w1.c b/drivers/base/regmap/regmap-w1.c index 5f04e7bf063e..e6c64b0be5b2 100644 --- a/drivers/base/regmap/regmap-w1.c +++ b/drivers/base/regmap/regmap-w1.c @@ -1,7 +1,7 @@ /* * Register map access API - W1 (1-Wire) support * - * Copyright (C) 2017 OAO Radioavionica + * Copyright (c) 2017 Radioavionica Corporation * Author: Alex A. Mihaylov <minimumlaw@rambler.ru> * * This program is free software; you can redistribute it and/or modify @@ -11,7 +11,7 @@ #include <linux/regmap.h> #include <linux/module.h> -#include "../../w1/w1.h" +#include <linux/w1.h> #include "internal.h" diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c index f6e7491c873c..d509b500a7b5 100644 --- a/drivers/clocksource/timer-of.c +++ b/drivers/clocksource/timer-of.c @@ -41,8 +41,16 @@ static __init int timer_irq_init(struct device_node *np, struct timer_of *to = container_of(of_irq, struct timer_of, of_irq); struct clock_event_device *clkevt = &to->clkevt; - of_irq->irq = of_irq->name ? of_irq_get_byname(np, of_irq->name): - irq_of_parse_and_map(np, of_irq->index); + if (of_irq->name) { + of_irq->irq = ret = of_irq_get_byname(np, of_irq->name); + if (ret < 0) { + pr_err("Failed to get interrupt %s for %s\n", + of_irq->name, np->full_name); + return ret; + } + } else { + of_irq->irq = irq_of_parse_and_map(np, of_irq->index); + } if (!of_irq->irq) { pr_err("Failed to map interrupt for %s\n", np->full_name); return -EINVAL; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b7fb8b7c980d..6cd503525638 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -225,6 +225,9 @@ struct global_params { * @vid: Stores VID limits for this CPU * @pid: Stores PID parameters for this CPU * @last_sample_time: Last Sample time + * @aperf_mperf_shift: Number of clock cycles after aperf, merf is incremented + * This shift is a multiplier to mperf delta to + * calculate CPU busy. * @prev_aperf: Last APERF value read from APERF MSR * @prev_mperf: Last MPERF value read from MPERF MSR * @prev_tsc: Last timestamp counter (TSC) value @@ -259,6 +262,7 @@ struct cpudata { u64 last_update; u64 last_sample_time; + u64 aperf_mperf_shift; u64 prev_aperf; u64 prev_mperf; u64 prev_tsc; @@ -321,6 +325,7 @@ struct pstate_funcs { int (*get_min)(void); int (*get_turbo)(void); int (*get_scaling)(void); + int (*get_aperf_mperf_shift)(void); u64 (*get_val)(struct cpudata*, int pstate); void (*get_vid)(struct cpudata *); void (*update_util)(struct update_util_data *data, u64 time, @@ -1486,6 +1491,11 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) return val; } +static int knl_get_aperf_mperf_shift(void) +{ + return 10; +} + static int knl_get_turbo_pstate(void) { u64 value; @@ -1543,6 +1553,9 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + if (pstate_funcs.get_aperf_mperf_shift) + cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift(); + if (pstate_funcs.get_vid) pstate_funcs.get_vid(cpu); @@ -1616,7 +1629,8 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) int32_t busy_frac, boost; int target, avg_pstate; - busy_frac = div_fp(sample->mperf, sample->tsc); + busy_frac = div_fp(sample->mperf << cpu->aperf_mperf_shift, + sample->tsc); boost = cpu->iowait_boost; cpu->iowait_boost >>= 1; @@ -1675,7 +1689,8 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) sample_ratio = div_fp(pid_params.sample_rate_ns, duration_ns); perf_scaled = mul_fp(perf_scaled, sample_ratio); } else { - sample_ratio = div_fp(100 * cpu->sample.mperf, cpu->sample.tsc); + sample_ratio = div_fp(100 * (cpu->sample.mperf << cpu->aperf_mperf_shift), + cpu->sample.tsc); if (sample_ratio < int_tofp(1)) perf_scaled = 0; } @@ -1807,6 +1822,7 @@ static const struct pstate_funcs knl_funcs = { .get_max_physical = core_get_max_pstate_physical, .get_min = core_get_min_pstate, .get_turbo = knl_get_turbo_pstate, + .get_aperf_mperf_shift = knl_get_aperf_mperf_shift, .get_scaling = core_get_scaling, .get_val = core_get_val, .update_util = intel_pstate_update_util_pid, @@ -2403,6 +2419,7 @@ static void __init copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.get_val = funcs->get_val; pstate_funcs.get_vid = funcs->get_vid; pstate_funcs.update_util = funcs->update_util; + pstate_funcs.get_aperf_mperf_shift = funcs->get_aperf_mperf_shift; intel_pstate_use_acpi_profile(); } diff --git a/drivers/dax/device-dax.h b/drivers/dax/device-dax.h index fdcd9769ffde..688b051750bd 100644 --- a/drivers/dax/device-dax.h +++ b/drivers/dax/device-dax.h @@ -21,5 +21,5 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id, struct resource *res, unsigned int align, void *addr, unsigned long flags); struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, - struct resource *res, int count); + int id, struct resource *res, int count); #endif /* __DEVICE_DAX_H__ */ diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 12943d19bfc4..e9f3b3e4bbf4 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -529,7 +529,8 @@ static void dev_dax_release(struct device *dev) struct dax_region *dax_region = dev_dax->region; struct dax_device *dax_dev = dev_dax->dax_dev; - ida_simple_remove(&dax_region->ida, dev_dax->id); + if (dev_dax->id >= 0) + ida_simple_remove(&dax_region->ida, dev_dax->id); dax_region_put(dax_region); put_dax(dax_dev); kfree(dev_dax); @@ -559,7 +560,7 @@ static void unregister_dev_dax(void *dev) } struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, - struct resource *res, int count) + int id, struct resource *res, int count) { struct device *parent = dax_region->dev; struct dax_device *dax_dev; @@ -567,7 +568,10 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, struct inode *inode; struct device *dev; struct cdev *cdev; - int rc = 0, i; + int rc, i; + + if (!count) + return ERR_PTR(-EINVAL); dev_dax = kzalloc(sizeof(*dev_dax) + sizeof(*res) * count, GFP_KERNEL); if (!dev_dax) @@ -587,10 +591,16 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, if (i < count) goto err_id; - dev_dax->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL); - if (dev_dax->id < 0) { - rc = dev_dax->id; - goto err_id; + if (id < 0) { + id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL); + dev_dax->id = id; + if (id < 0) { + rc = id; + goto err_id; + } + } else { + /* region provider owns @id lifetime */ + dev_dax->id = -1; } /* @@ -598,8 +608,10 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, * device outside of mmap of the resulting character device. */ dax_dev = alloc_dax(dev_dax, NULL, NULL); - if (!dax_dev) + if (!dax_dev) { + rc = -ENOMEM; goto err_dax; + } /* from here on we're committed to teardown via dax_dev_release() */ dev = &dev_dax->dev; @@ -620,7 +632,7 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, dev->parent = parent; dev->groups = dax_attribute_groups; dev->release = dev_dax_release; - dev_set_name(dev, "dax%d.%d", dax_region->id, dev_dax->id); + dev_set_name(dev, "dax%d.%d", dax_region->id, id); rc = cdev_device_add(cdev, dev); if (rc) { @@ -636,7 +648,8 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, return dev_dax; err_dax: - ida_simple_remove(&dax_region->ida, dev_dax->id); + if (dev_dax->id >= 0) + ida_simple_remove(&dax_region->ida, dev_dax->id); err_id: kfree(dev_dax); diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index 9f2a0b4fd801..8d8c852ba8f2 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -58,13 +58,12 @@ static void dax_pmem_percpu_kill(void *data) static int dax_pmem_probe(struct device *dev) { - int rc; void *addr; struct resource res; + int rc, id, region_id; struct nd_pfn_sb *pfn_sb; struct dev_dax *dev_dax; struct dax_pmem *dax_pmem; - struct nd_region *nd_region; struct nd_namespace_io *nsio; struct dax_region *dax_region; struct nd_namespace_common *ndns; @@ -123,14 +122,17 @@ static int dax_pmem_probe(struct device *dev) /* adjust the dax_region resource to the start of data */ res.start += le64_to_cpu(pfn_sb->dataoff); - nd_region = to_nd_region(dev->parent); - dax_region = alloc_dax_region(dev, nd_region->id, &res, + rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", ®ion_id, &id); + if (rc != 2) + return -EINVAL; + + dax_region = alloc_dax_region(dev, region_id, &res, le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP); if (!dax_region) return -ENOMEM; /* TODO: support for subdividing a dax region... */ - dev_dax = devm_create_dev_dax(dax_region, &res, 1); + dev_dax = devm_create_dev_dax(dax_region, id, &res, 1); /* child dev_dax instances now own the lifetime of the dax_region */ dax_region_put(dax_region); diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 57da14c15987..56e0a0e1b600 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -75,11 +75,6 @@ int dma_fence_signal_locked(struct dma_fence *fence) if (WARN_ON(!fence)) return -EINVAL; - if (!ktime_to_ns(fence->timestamp)) { - fence->timestamp = ktime_get(); - smp_mb__before_atomic(); - } - if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { ret = -EINVAL; @@ -87,8 +82,11 @@ int dma_fence_signal_locked(struct dma_fence *fence) * we might have raced with the unlocked dma_fence_signal, * still run through all callbacks */ - } else + } else { + fence->timestamp = ktime_get(); + set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); trace_dma_fence_signaled(fence); + } list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) { list_del_init(&cur->node); @@ -115,14 +113,11 @@ int dma_fence_signal(struct dma_fence *fence) if (!fence) return -EINVAL; - if (!ktime_to_ns(fence->timestamp)) { - fence->timestamp = ktime_get(); - smp_mb__before_atomic(); - } - if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) return -EINVAL; + fence->timestamp = ktime_get(); + set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); trace_dma_fence_signaled(fence); if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags)) { diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c index 82a6e7f6d37f..59a3b2f8ee91 100644 --- a/drivers/dma-buf/sync_debug.c +++ b/drivers/dma-buf/sync_debug.c @@ -84,7 +84,7 @@ static void sync_print_fence(struct seq_file *s, show ? "_" : "", sync_status_str(status)); - if (status) { + if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) { struct timespec64 ts64 = ktime_to_timespec64(fence->timestamp); diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 545e2c5c4815..d7e219d2669d 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -391,7 +391,13 @@ static void sync_fill_fence_info(struct dma_fence *fence, sizeof(info->driver_name)); info->status = dma_fence_get_status(fence); - info->timestamp_ns = ktime_to_ns(fence->timestamp); + while (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && + !test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) + cpu_relax(); + info->timestamp_ns = + test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ? + ktime_to_ns(fence->timestamp) : + ktime_set(0, 0); } static long sync_file_ioctl_fence_info(struct sync_file *sync_file, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 5f8ada1d872b..37971d9402e3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -101,7 +101,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) if (adev->kfd) { struct kgd2kfd_shared_resources gpu_resources = { .compute_vmid_bitmap = 0xFF00, - .num_mec = adev->gfx.mec.num_mec, .num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec, .num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe }; @@ -122,7 +121,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) /* According to linux/bitmap.h we shouldn't use bitmap_clear if * nbits is not compile time constant */ - last_valid_bit = adev->gfx.mec.num_mec + last_valid_bit = 1 /* only first MEC can have compute queues */ * adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; for (i = last_valid_bit; i < KGD_MAX_QUEUES; ++i) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 88187bfc5ea3..3f95f7cb4019 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -226,10 +226,6 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, kfd->shared_resources = *gpu_resources; - /* We only use the first MEC */ - if (kfd->shared_resources.num_mec > 1) - kfd->shared_resources.num_mec = 1; - /* calculate max size of mqds needed for queues */ size = max_num_of_queues_per_device * kfd->device_info->mqd_size_aligned; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 955aa304ff48..602769ced3bd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -77,13 +77,6 @@ static bool is_pipe_enabled(struct device_queue_manager *dqm, int mec, int pipe) return false; } -unsigned int get_mec_num(struct device_queue_manager *dqm) -{ - BUG_ON(!dqm || !dqm->dev); - - return dqm->dev->shared_resources.num_mec; -} - unsigned int get_queues_num(struct device_queue_manager *dqm) { BUG_ON(!dqm || !dqm->dev); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index 66b9615bc3c1..faf820a06400 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -180,7 +180,6 @@ void device_queue_manager_init_cik(struct device_queue_manager_asic_ops *ops); void device_queue_manager_init_vi(struct device_queue_manager_asic_ops *ops); void program_sh_mem_settings(struct device_queue_manager *dqm, struct qcm_process_device *qpd); -unsigned int get_mec_num(struct device_queue_manager *dqm); unsigned int get_queues_num(struct device_queue_manager *dqm); unsigned int get_queues_per_pipe(struct device_queue_manager *dqm); unsigned int get_pipes_per_mec(struct device_queue_manager *dqm); diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index 91ef1484b3bb..36f376677a53 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -63,9 +63,6 @@ struct kgd2kfd_shared_resources { /* Bit n == 1 means VMID n is available for KFD. */ unsigned int compute_vmid_bitmap; - /* number of mec available from the hardware */ - uint32_t num_mec; - /* number of pipes per mec */ uint32_t num_pipe_per_mec; diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index bfd237c15e76..ae5f06895562 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -330,6 +330,13 @@ static bool drm_dp_sideband_msg_build(struct drm_dp_sideband_msg_rx *msg, return false; } + /* + * ignore out-of-order messages or messages that are part of a + * failed transaction + */ + if (!recv_hdr.somt && !msg->have_somt) + return false; + /* get length contained in this portion */ msg->curchunk_len = recv_hdr.msg_len; msg->curchunk_hdrlen = hdrlen; @@ -2164,7 +2171,7 @@ out_unlock: } EXPORT_SYMBOL(drm_dp_mst_topology_mgr_resume); -static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) +static bool drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) { int len; u8 replyblock[32]; @@ -2179,12 +2186,12 @@ static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) replyblock, len); if (ret != len) { DRM_DEBUG_KMS("failed to read DPCD down rep %d %d\n", len, ret); - return; + return false; } ret = drm_dp_sideband_msg_build(msg, replyblock, len, true); if (!ret) { DRM_DEBUG_KMS("sideband msg build failed %d\n", replyblock[0]); - return; + return false; } replylen = msg->curchunk_len + msg->curchunk_hdrlen; @@ -2196,21 +2203,32 @@ static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up) ret = drm_dp_dpcd_read(mgr->aux, basereg + curreply, replyblock, len); if (ret != len) { - DRM_DEBUG_KMS("failed to read a chunk\n"); + DRM_DEBUG_KMS("failed to read a chunk (len %d, ret %d)\n", + len, ret); + return false; } + ret = drm_dp_sideband_msg_build(msg, replyblock, len, false); - if (ret == false) + if (!ret) { DRM_DEBUG_KMS("failed to build sideband msg\n"); + return false; + } + curreply += len; replylen -= len; } + return true; } static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) { int ret = 0; - drm_dp_get_one_sb_msg(mgr, false); + if (!drm_dp_get_one_sb_msg(mgr, false)) { + memset(&mgr->down_rep_recv, 0, + sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } if (mgr->down_rep_recv.have_eomt) { struct drm_dp_sideband_msg_tx *txmsg; @@ -2266,7 +2284,12 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) { int ret = 0; - drm_dp_get_one_sb_msg(mgr, true); + + if (!drm_dp_get_one_sb_msg(mgr, true)) { + memset(&mgr->up_req_recv, 0, + sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } if (mgr->up_req_recv.have_eomt) { struct drm_dp_sideband_msg_req_body msg; @@ -2318,7 +2341,9 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) DRM_DEBUG_KMS("Got RSN: pn: %d avail_pbn %d\n", msg.u.resource_stat.port_number, msg.u.resource_stat.available_pbn); } - drm_dp_put_mst_branch_device(mstb); + if (mstb) + drm_dp_put_mst_branch_device(mstb); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); } return ret; diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 49546222c6d3..6276bb834b4f 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -54,7 +54,7 @@ static const uint32_t ipu_plane_formats[] = { DRM_FORMAT_RGBA8888, DRM_FORMAT_RGBX8888, DRM_FORMAT_BGRA8888, - DRM_FORMAT_BGRA8888, + DRM_FORMAT_BGRX8888, DRM_FORMAT_UYVY, DRM_FORMAT_VYUY, DRM_FORMAT_YUYV, diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 636031a30e17..8aca20209cb8 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -237,7 +237,7 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) /* port@1 is the output port */ ret = drm_of_find_panel_or_bridge(np, 1, 0, &imxpd->panel, &imxpd->bridge); - if (ret) + if (ret && ret != -ENODEV) return ret; imxpd->dev = dev; diff --git a/drivers/gpu/drm/radeon/radeon_kfd.c b/drivers/gpu/drm/radeon/radeon_kfd.c index 699fe7f9b8bf..a2ab6dcdf4a2 100644 --- a/drivers/gpu/drm/radeon/radeon_kfd.c +++ b/drivers/gpu/drm/radeon/radeon_kfd.c @@ -184,7 +184,6 @@ void radeon_kfd_device_init(struct radeon_device *rdev) if (rdev->kfd) { struct kgd2kfd_shared_resources gpu_resources = { .compute_vmid_bitmap = 0xFF00, - .num_mec = 1, .num_pipe_per_mec = 4, .num_queue_per_pipe = 8 }; diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 403bbd5f99a9..a12cc7ea99b6 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -520,6 +520,34 @@ static void vc4_crtc_disable(struct drm_crtc *crtc) SCALER_DISPSTATX_EMPTY); } +static void vc4_crtc_update_dlist(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); + struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state); + + if (crtc->state->event) { + unsigned long flags; + + crtc->state->event->pipe = drm_crtc_index(crtc); + + WARN_ON(drm_crtc_vblank_get(crtc) != 0); + + spin_lock_irqsave(&dev->event_lock, flags); + vc4_crtc->event = crtc->state->event; + crtc->state->event = NULL; + + HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), + vc4_state->mm.start); + + spin_unlock_irqrestore(&dev->event_lock, flags); + } else { + HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), + vc4_state->mm.start); + } +} + static void vc4_crtc_enable(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; @@ -530,6 +558,12 @@ static void vc4_crtc_enable(struct drm_crtc *crtc) require_hvs_enabled(dev); + /* Enable vblank irq handling before crtc is started otherwise + * drm_crtc_get_vblank() fails in vc4_crtc_update_dlist(). + */ + drm_crtc_vblank_on(crtc); + vc4_crtc_update_dlist(crtc); + /* Turn on the scaler, which will wait for vstart to start * compositing. */ @@ -541,9 +575,6 @@ static void vc4_crtc_enable(struct drm_crtc *crtc) /* Turn on the pixel valve, which will emit the vstart signal. */ CRTC_WRITE(PV_V_CONTROL, CRTC_READ(PV_V_CONTROL) | PV_VCONTROL_VIDEN); - - /* Enable vblank irq handling after crtc is started. */ - drm_crtc_vblank_on(crtc); } static bool vc4_crtc_mode_fixup(struct drm_crtc *crtc, @@ -598,7 +629,6 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc, { struct drm_device *dev = crtc->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); - struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state); struct drm_plane *plane; bool debug_dump_regs = false; @@ -620,25 +650,15 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc, WARN_ON_ONCE(dlist_next - dlist_start != vc4_state->mm.size); - if (crtc->state->event) { - unsigned long flags; - - crtc->state->event->pipe = drm_crtc_index(crtc); - - WARN_ON(drm_crtc_vblank_get(crtc) != 0); - - spin_lock_irqsave(&dev->event_lock, flags); - vc4_crtc->event = crtc->state->event; - crtc->state->event = NULL; - - HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), - vc4_state->mm.start); - - spin_unlock_irqrestore(&dev->event_lock, flags); - } else { - HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), - vc4_state->mm.start); - } + /* Only update DISPLIST if the CRTC was already running and is not + * being disabled. + * vc4_crtc_enable() takes care of updating the dlist just after + * re-enabling VBLANK interrupts and before enabling the engine. + * If the CRTC is being disabled, there's no point in updating this + * information. + */ + if (crtc->state->active && old_state->active) + vc4_crtc_update_dlist(crtc); if (debug_dump_regs) { DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc)); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 41b39464ded8..501e16a9227d 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -2732,6 +2732,9 @@ static int hidpp_initialize_battery(struct hidpp_device *hidpp) hidpp_battery_props, sizeof(hidpp_battery_props), GFP_KERNEL); + if (!battery_props) + return -ENOMEM; + num_battery_props = ARRAY_SIZE(hidpp_battery_props) - 2; if (hidpp->capabilities & HIDPP_CAPABILITY_BATTERY_MILEAGE) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index f3e35e7a189d..aff20f4b6d97 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -620,16 +620,6 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, return 0; } -static int mt_touch_input_mapped(struct hid_device *hdev, struct hid_input *hi, - struct hid_field *field, struct hid_usage *usage, - unsigned long **bit, int *max) -{ - if (usage->type == EV_KEY || usage->type == EV_ABS) - set_bit(usage->type, hi->input->evbit); - - return -1; -} - static int mt_compute_slot(struct mt_device *td, struct input_dev *input) { __s32 quirks = td->mtclass.quirks; @@ -969,8 +959,10 @@ static int mt_input_mapped(struct hid_device *hdev, struct hid_input *hi, return 0; if (field->application == HID_DG_TOUCHSCREEN || - field->application == HID_DG_TOUCHPAD) - return mt_touch_input_mapped(hdev, hi, field, usage, bit, max); + field->application == HID_DG_TOUCHPAD) { + /* We own these mappings, tell hid-input to ignore them */ + return -1; + } /* let hid-core decide for the others */ return 0; diff --git a/drivers/ide/ide-timings.c b/drivers/ide/ide-timings.c index 0e05f75934c9..1858e3ce3993 100644 --- a/drivers/ide/ide-timings.c +++ b/drivers/ide/ide-timings.c @@ -104,19 +104,19 @@ u16 ide_pio_cycle_time(ide_drive_t *drive, u8 pio) EXPORT_SYMBOL_GPL(ide_pio_cycle_time); #define ENOUGH(v, unit) (((v) - 1) / (unit) + 1) -#define EZ(v, unit) ((v) ? ENOUGH(v, unit) : 0) +#define EZ(v, unit) ((v) ? ENOUGH((v) * 1000, unit) : 0) static void ide_timing_quantize(struct ide_timing *t, struct ide_timing *q, int T, int UT) { - q->setup = EZ(t->setup * 1000, T); - q->act8b = EZ(t->act8b * 1000, T); - q->rec8b = EZ(t->rec8b * 1000, T); - q->cyc8b = EZ(t->cyc8b * 1000, T); - q->active = EZ(t->active * 1000, T); - q->recover = EZ(t->recover * 1000, T); - q->cycle = EZ(t->cycle * 1000, T); - q->udma = EZ(t->udma * 1000, UT); + q->setup = EZ(t->setup, T); + q->act8b = EZ(t->act8b, T); + q->rec8b = EZ(t->rec8b, T); + q->cyc8b = EZ(t->cyc8b, T); + q->active = EZ(t->active, T); + q->recover = EZ(t->recover, T); + q->cycle = EZ(t->cycle, T); + q->udma = EZ(t->udma, UT); } void ide_timing_merge(struct ide_timing *a, struct ide_timing *b, diff --git a/drivers/irqchip/irq-digicolor.c b/drivers/irqchip/irq-digicolor.c index dad85e74c37c..3aae015469a5 100644 --- a/drivers/irqchip/irq-digicolor.c +++ b/drivers/irqchip/irq-digicolor.c @@ -71,7 +71,7 @@ static void __init digicolor_set_gc(void __iomem *reg_base, unsigned irq_base, static int __init digicolor_of_init(struct device_node *node, struct device_node *parent) { - static void __iomem *reg_base; + void __iomem *reg_base; unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; struct regmap *ucregs; int ret; diff --git a/drivers/irqchip/irq-gic-realview.c b/drivers/irqchip/irq-gic-realview.c index 54c296401525..18d58d2b4ffe 100644 --- a/drivers/irqchip/irq-gic-realview.c +++ b/drivers/irqchip/irq-gic-realview.c @@ -43,7 +43,7 @@ static const struct of_device_id syscon_pldset_of_match[] = { static int __init realview_gic_of_init(struct device_node *node, struct device_node *parent) { - static struct regmap *map; + struct regmap *map; struct device_node *np; const struct of_device_id *gic_id; u32 pld1_ctrl; diff --git a/drivers/irqchip/irq-mips-cpu.c b/drivers/irqchip/irq-mips-cpu.c index 0a8ed1c05518..14461cbfab2f 100644 --- a/drivers/irqchip/irq-mips-cpu.c +++ b/drivers/irqchip/irq-mips-cpu.c @@ -154,7 +154,7 @@ asmlinkage void __weak plat_irq_dispatch(void) static int mips_cpu_intc_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { - static struct irq_chip *chip; + struct irq_chip *chip; if (hw < 2 && cpu_has_mipsmt) { /* Software interrupts are used for MT/CMT IPI */ diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 832ebf4062f7..6ab1d3afec02 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -950,7 +950,6 @@ static void __init __gic_init(unsigned long gic_base_addr, &gic_irq_domain_ops, NULL); if (!gic_irq_domain) panic("Failed to add GIC IRQ domain"); - gic_irq_domain->name = "mips-gic-irq"; gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain, IRQ_DOMAIN_FLAG_IPI_PER_CPU, @@ -959,7 +958,6 @@ static void __init __gic_init(unsigned long gic_base_addr, if (!gic_ipi_domain) panic("Failed to add GIC IPI domain"); - gic_ipi_domain->name = "mips-gic-ipi"; irq_domain_update_bus_token(gic_ipi_domain, DOMAIN_BUS_IPI); if (node && diff --git a/drivers/isdn/divert/isdn_divert.c b/drivers/isdn/divert/isdn_divert.c index 060d357f107f..6f423bc49d0d 100644 --- a/drivers/isdn/divert/isdn_divert.c +++ b/drivers/isdn/divert/isdn_divert.c @@ -485,18 +485,19 @@ static int isdn_divert_icall(isdn_ctrl *ic) cs->deflect_dest[0] = '\0'; retval = 4; /* only proceed */ } - sprintf(cs->info, "%d 0x%lx %s %s %s %s 0x%x 0x%x %d %d %s\n", - cs->akt_state, - cs->divert_id, - divert_if.drv_to_name(cs->ics.driver), - (ic->command == ISDN_STAT_ICALLW) ? "1" : "0", - cs->ics.parm.setup.phone, - cs->ics.parm.setup.eazmsn, - cs->ics.parm.setup.si1, - cs->ics.parm.setup.si2, - cs->ics.parm.setup.screen, - dv->rule.waittime, - cs->deflect_dest); + snprintf(cs->info, sizeof(cs->info), + "%d 0x%lx %s %s %s %s 0x%x 0x%x %d %d %s\n", + cs->akt_state, + cs->divert_id, + divert_if.drv_to_name(cs->ics.driver), + (ic->command == ISDN_STAT_ICALLW) ? "1" : "0", + cs->ics.parm.setup.phone, + cs->ics.parm.setup.eazmsn, + cs->ics.parm.setup.si1, + cs->ics.parm.setup.si2, + cs->ics.parm.setup.screen, + dv->rule.waittime, + cs->deflect_dest); if ((dv->rule.action == DEFLECT_REPORT) || (dv->rule.action == DEFLECT_REJECT)) { put_info_buffer(cs->info); diff --git a/drivers/isdn/hardware/avm/c4.c b/drivers/isdn/hardware/avm/c4.c index 40c7e2cf423b..034cabac699d 100644 --- a/drivers/isdn/hardware/avm/c4.c +++ b/drivers/isdn/hardware/avm/c4.c @@ -42,7 +42,7 @@ static char *revision = "$Revision: 1.1.2.2 $"; static bool suppress_pollack; -static struct pci_device_id c4_pci_tbl[] = { +static const struct pci_device_id c4_pci_tbl[] = { { PCI_VENDOR_ID_DEC, PCI_DEVICE_ID_DEC_21285, PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_C4, 0, 0, (unsigned long)4 }, { PCI_VENDOR_ID_DEC, PCI_DEVICE_ID_DEC_21285, PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_C2, 0, 0, (unsigned long)2 }, { } /* Terminating entry */ diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c index 8b7ad4f1ab01..b2023e08dcd2 100644 --- a/drivers/isdn/hardware/eicon/divasmain.c +++ b/drivers/isdn/hardware/eicon/divasmain.c @@ -110,7 +110,7 @@ typedef struct _diva_os_thread_dpc { /* This table should be sorted by PCI device ID */ -static struct pci_device_id divas_pci_tbl[] = { +static const struct pci_device_id divas_pci_tbl[] = { /* Diva Server BRI-2M PCI 0xE010 */ { PCI_VDEVICE(EICON, PCI_DEVICE_ID_EICON_MAESTRA), CARDTYPE_MAESTRA_PCI }, diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c index e3fa1cd64470..dce6632daae1 100644 --- a/drivers/isdn/hardware/mISDN/avmfritz.c +++ b/drivers/isdn/hardware/mISDN/avmfritz.c @@ -1142,7 +1142,7 @@ fritz_remove_pci(struct pci_dev *pdev) pr_info("%s: drvdata already removed\n", __func__); } -static struct pci_device_id fcpci_ids[] = { +static const struct pci_device_id fcpci_ids[] = { { PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (unsigned long) "Fritz!Card PCI"}, { PCI_VENDOR_ID_AVM, PCI_DEVICE_ID_AVM_A1_V2, PCI_ANY_ID, PCI_ANY_ID, diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index aea0c9616ea5..3cf07b8ced1c 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -5348,7 +5348,7 @@ static const struct hm_map hfcm_map[] = { #undef H #define H(x) ((unsigned long)&hfcm_map[x]) -static struct pci_device_id hfmultipci_ids[] = { +static const struct pci_device_id hfmultipci_ids[] = { /* Cards with HFC-4S Chip */ { PCI_VENDOR_ID_CCD, PCI_DEVICE_ID_CCD_HFC4S, PCI_VENDOR_ID_CCD, diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index 5dc246d71c16..d2e401a8090e 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -2161,7 +2161,7 @@ static const struct _hfc_map hfc_map[] = {}, }; -static struct pci_device_id hfc_ids[] = +static const struct pci_device_id hfc_ids[] = { { PCI_VDEVICE(CCD, PCI_DEVICE_ID_CCD_2BD0), (unsigned long) &hfc_map[0] }, diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index afde4edef9ae..6a6d848bd18e 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -1137,7 +1137,7 @@ static void nj_remove(struct pci_dev *pdev) /* We cannot select cards with PCI_SUB... IDs, since here are cards with * SUB IDs set to PCI_ANY_ID, so we need to match all and reject * known other cards which not work with this driver - see probe function */ -static struct pci_device_id nj_pci_ids[] = { +static const struct pci_device_id nj_pci_ids[] = { { PCI_VENDOR_ID_TIGERJET, PCI_DEVICE_ID_TIGERJET_300, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, { } diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c index 3052c836b89f..d80072fef434 100644 --- a/drivers/isdn/hardware/mISDN/w6692.c +++ b/drivers/isdn/hardware/mISDN/w6692.c @@ -1398,7 +1398,7 @@ w6692_remove_pci(struct pci_dev *pdev) pr_notice("%s: drvdata already removed\n", __func__); } -static struct pci_device_id w6692_ids[] = { +static const struct pci_device_id w6692_ids[] = { { PCI_VENDOR_ID_DYNALINK, PCI_DEVICE_ID_DYNALINK_IS64PH, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (ulong)&w6692_map[0]}, { PCI_VENDOR_ID_WINBOND2, PCI_DEVICE_ID_WINBOND2_6692, diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c index c7d68675b028..7108bdb8742e 100644 --- a/drivers/isdn/hisax/config.c +++ b/drivers/isdn/hisax/config.c @@ -1909,7 +1909,7 @@ static void EChannel_proc_rcv(struct hisax_d_if *d_if) #ifdef CONFIG_PCI #include <linux/pci.h> -static struct pci_device_id hisax_pci_tbl[] __used = { +static const struct pci_device_id hisax_pci_tbl[] __used = { #ifdef CONFIG_HISAX_FRITZPCI {PCI_VDEVICE(AVM, PCI_DEVICE_ID_AVM_A1) }, #endif diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c index 90f051ce0259..9090cc1e1f29 100644 --- a/drivers/isdn/hisax/hfc4s8s_l1.c +++ b/drivers/isdn/hisax/hfc4s8s_l1.c @@ -86,7 +86,7 @@ typedef struct { char *device_name; } hfc4s8s_param; -static struct pci_device_id hfc4s8s_ids[] = { +static const struct pci_device_id hfc4s8s_ids[] = { {.vendor = PCI_VENDOR_ID_CCD, .device = PCI_DEVICE_ID_4S, .subvendor = 0x1397, diff --git a/drivers/isdn/hisax/hisax_fcpcipnp.c b/drivers/isdn/hisax/hisax_fcpcipnp.c index 5a9f39ed1d5d..e4f7573ba9bf 100644 --- a/drivers/isdn/hisax/hisax_fcpcipnp.c +++ b/drivers/isdn/hisax/hisax_fcpcipnp.c @@ -52,7 +52,7 @@ module_param(debug, int, 0); MODULE_AUTHOR("Kai Germaschewski <kai.germaschewski@gmx.de>/Karsten Keil <kkeil@suse.de>"); MODULE_DESCRIPTION("AVM Fritz!PCI/PnP ISDN driver"); -static struct pci_device_id fcpci_ids[] = { +static const struct pci_device_id fcpci_ids[] = { { .vendor = PCI_VENDOR_ID_AVM, .device = PCI_DEVICE_ID_AVM_A1, .subvendor = PCI_ANY_ID, diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index f4eace5ea184..40f3cd7eab0f 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -156,7 +156,8 @@ static int read_sb_page(struct mddev *mddev, loff_t offset, rdev_for_each(rdev, mddev) { if (! test_bit(In_sync, &rdev->flags) - || test_bit(Faulty, &rdev->flags)) + || test_bit(Faulty, &rdev->flags) + || test_bit(Bitmap_sync, &rdev->flags)) continue; target = offset + index * (PAGE_SIZE/512); diff --git a/drivers/md/md.h b/drivers/md/md.h index 991f0fe2dcc6..b50eb4ac1b82 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -134,7 +134,9 @@ enum flag_bits { Faulty, /* device is known to have a fault */ In_sync, /* device is in_sync with rest of array */ Bitmap_sync, /* ..actually, not quite In_sync. Need a - * bitmap-based recovery to get fully in sync + * bitmap-based recovery to get fully in sync. + * The bit is only meaningful before device + * has been passed to pers->hot_add_disk. */ WriteMostly, /* Avoid reading if at all possible */ AutoDetected, /* added by auto-detect */ diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 77cce3573aa8..44ad5baf3206 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1150,7 +1150,7 @@ int ppl_init_log(struct r5conf *conf) goto err; } - ppl_conf->bs = bioset_create(conf->raid_disks, 0, 0); + ppl_conf->bs = bioset_create(conf->raid_disks, 0, BIOSET_NEED_BVECS); if (!ppl_conf->bs) { ret = -ENOMEM; goto err; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2ceb338b094b..aeeb8d6854e2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7951,12 +7951,10 @@ static void end_reshape(struct r5conf *conf) { if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { - struct md_rdev *rdev; spin_lock_irq(&conf->device_lock); conf->previous_raid_disks = conf->raid_disks; - rdev_for_each(rdev, conf->mddev) - rdev->data_offset = rdev->new_data_offset; + md_finish_reshape(conf->mddev); smp_wmb(); conf->reshape_progress = MaxSector; conf->mddev->reshape_position = MaxSector; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 14ff622190a5..181839d6fbea 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4596,7 +4596,7 @@ static int bond_check_params(struct bond_params *params) } ad_user_port_key = valptr->value; - if (bond_mode == BOND_MODE_TLB) { + if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) { bond_opt_initstr(&newval, "default"); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index e68d368e20ac..7f36d3e3c98b 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1665,6 +1665,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .dev_name = "BCM53125", .vlans = 4096, .enabled_ports = 0xff, + .arl_entries = 4, .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 53b088166c28..5bcdd33101b0 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3178,6 +3178,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .port_set_jumbo_size = mv88e6165_port_set_jumbo_size, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_limit = mv88e6390_port_pause_limit, + .port_set_cmode = mv88e6390x_port_set_cmode, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .stats_snapshot = mv88e6390_g1_stats_snapshot, diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index d3906f6b01bd..86058a9f3417 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1785,16 +1785,18 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) xgene_enet_gpiod_get(pdata); - pdata->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(pdata->clk)) { - /* Abort if the clock is defined but couldn't be retrived. - * Always abort if the clock is missing on DT system as - * the driver can't cope with this case. - */ - if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node) - return PTR_ERR(pdata->clk); - /* Firmware may have set up the clock already. */ - dev_info(dev, "clocks have been setup already\n"); + if (pdata->phy_mode != PHY_INTERFACE_MODE_SGMII) { + pdata->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(pdata->clk)) { + /* Abort if the clock is defined but couldn't be + * retrived. Always abort if the clock is missing on + * DT system as the driver can't cope with this case. + */ + if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node) + return PTR_ERR(pdata->clk); + /* Firmware may have set up the clock already. */ + dev_info(dev, "clocks have been setup already\n"); + } } if (pdata->phy_mode != PHY_INTERFACE_MODE_XGMII) diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 73aca97a96bc..d937083db9a4 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -50,11 +50,14 @@ static u32 platform_bgmac_idm_read(struct bgmac *bgmac, u16 offset) static void platform_bgmac_idm_write(struct bgmac *bgmac, u16 offset, u32 value) { - return writel(value, bgmac->plat.idm_base + offset); + writel(value, bgmac->plat.idm_base + offset); } static bool platform_bgmac_clk_enabled(struct bgmac *bgmac) { + if (!bgmac->plat.idm_base) + return true; + if ((bgmac_idm_read(bgmac, BCMA_IOCTL) & BGMAC_CLK_EN) != BGMAC_CLK_EN) return false; if (bgmac_idm_read(bgmac, BCMA_RESET_CTL) & BCMA_RESET_CTL_RESET) @@ -66,6 +69,9 @@ static void platform_bgmac_clk_enable(struct bgmac *bgmac, u32 flags) { u32 val; + if (!bgmac->plat.idm_base) + return; + /* The Reset Control register only contains a single bit to show if the * controller is currently in reset. Do a sanity check here, just in * case the bootloader happened to leave the device in reset. @@ -180,6 +186,7 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->feature_flags |= BGMAC_FEAT_CMDCFG_SR_REV4; bgmac->feature_flags |= BGMAC_FEAT_TX_MASK_SETUP; bgmac->feature_flags |= BGMAC_FEAT_RX_MASK_SETUP; + bgmac->feature_flags |= BGMAC_FEAT_IDM_MASK; bgmac->dev = &pdev->dev; bgmac->dma_dev = &pdev->dev; @@ -207,15 +214,13 @@ static int bgmac_probe(struct platform_device *pdev) return PTR_ERR(bgmac->plat.base); regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base"); - if (!regs) { - dev_err(&pdev->dev, "Unable to obtain idm resource\n"); - return -EINVAL; + if (regs) { + bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); + if (IS_ERR(bgmac->plat.idm_base)) + return PTR_ERR(bgmac->plat.idm_base); + bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; } - bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(bgmac->plat.idm_base)) - return PTR_ERR(bgmac->plat.idm_base); - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base"); if (regs) { bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev, diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index ba4d2e145bb9..48d672b204a4 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -622,9 +622,11 @@ static int bgmac_dma_alloc(struct bgmac *bgmac) BUILD_BUG_ON(BGMAC_MAX_TX_RINGS > ARRAY_SIZE(ring_base)); BUILD_BUG_ON(BGMAC_MAX_RX_RINGS > ARRAY_SIZE(ring_base)); - if (!(bgmac_idm_read(bgmac, BCMA_IOST) & BCMA_IOST_DMA64)) { - dev_err(bgmac->dev, "Core does not report 64-bit DMA\n"); - return -ENOTSUPP; + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { + if (!(bgmac_idm_read(bgmac, BCMA_IOST) & BCMA_IOST_DMA64)) { + dev_err(bgmac->dev, "Core does not report 64-bit DMA\n"); + return -ENOTSUPP; + } } for (i = 0; i < BGMAC_MAX_TX_RINGS; i++) { @@ -855,9 +857,11 @@ static void bgmac_mac_speed(struct bgmac *bgmac) static void bgmac_miiconfig(struct bgmac *bgmac) { if (bgmac->feature_flags & BGMAC_FEAT_FORCE_SPEED_2500) { - bgmac_idm_write(bgmac, BCMA_IOCTL, - bgmac_idm_read(bgmac, BCMA_IOCTL) | 0x40 | - BGMAC_BCMA_IOCTL_SW_CLKEN); + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { + bgmac_idm_write(bgmac, BCMA_IOCTL, + bgmac_idm_read(bgmac, BCMA_IOCTL) | + 0x40 | BGMAC_BCMA_IOCTL_SW_CLKEN); + } bgmac->mac_speed = SPEED_2500; bgmac->mac_duplex = DUPLEX_FULL; bgmac_mac_speed(bgmac); @@ -874,11 +878,36 @@ static void bgmac_miiconfig(struct bgmac *bgmac) } } +static void bgmac_chip_reset_idm_config(struct bgmac *bgmac) +{ + u32 iost; + + iost = bgmac_idm_read(bgmac, BCMA_IOST); + if (bgmac->feature_flags & BGMAC_FEAT_IOST_ATTACHED) + iost &= ~BGMAC_BCMA_IOST_ATTACHED; + + /* 3GMAC: for BCM4707 & BCM47094, only do core reset at bgmac_probe() */ + if (!(bgmac->feature_flags & BGMAC_FEAT_NO_RESET)) { + u32 flags = 0; + + if (iost & BGMAC_BCMA_IOST_ATTACHED) { + flags = BGMAC_BCMA_IOCTL_SW_CLKEN; + if (!bgmac->has_robosw) + flags |= BGMAC_BCMA_IOCTL_SW_RESET; + } + bgmac_clk_enable(bgmac, flags); + } + + if (iost & BGMAC_BCMA_IOST_ATTACHED && !bgmac->has_robosw) + bgmac_idm_write(bgmac, BCMA_IOCTL, + bgmac_idm_read(bgmac, BCMA_IOCTL) & + ~BGMAC_BCMA_IOCTL_SW_RESET); +} + /* http://bcm-v4.sipsolutions.net/mac-gbit/gmac/chipreset */ static void bgmac_chip_reset(struct bgmac *bgmac) { u32 cmdcfg_sr; - u32 iost; int i; if (bgmac_clk_enabled(bgmac)) { @@ -899,20 +928,8 @@ static void bgmac_chip_reset(struct bgmac *bgmac) /* TODO: Clear software multicast filter list */ } - iost = bgmac_idm_read(bgmac, BCMA_IOST); - if (bgmac->feature_flags & BGMAC_FEAT_IOST_ATTACHED) - iost &= ~BGMAC_BCMA_IOST_ATTACHED; - - /* 3GMAC: for BCM4707 & BCM47094, only do core reset at bgmac_probe() */ - if (!(bgmac->feature_flags & BGMAC_FEAT_NO_RESET)) { - u32 flags = 0; - if (iost & BGMAC_BCMA_IOST_ATTACHED) { - flags = BGMAC_BCMA_IOCTL_SW_CLKEN; - if (!bgmac->has_robosw) - flags |= BGMAC_BCMA_IOCTL_SW_RESET; - } - bgmac_clk_enable(bgmac, flags); - } + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) + bgmac_chip_reset_idm_config(bgmac); /* Request Misc PLL for corerev > 2 */ if (bgmac->feature_flags & BGMAC_FEAT_MISC_PLL_REQ) { @@ -970,11 +987,6 @@ static void bgmac_chip_reset(struct bgmac *bgmac) BGMAC_CHIPCTL_7_IF_TYPE_RGMII); } - if (iost & BGMAC_BCMA_IOST_ATTACHED && !bgmac->has_robosw) - bgmac_idm_write(bgmac, BCMA_IOCTL, - bgmac_idm_read(bgmac, BCMA_IOCTL) & - ~BGMAC_BCMA_IOCTL_SW_RESET); - /* http://bcm-v4.sipsolutions.net/mac-gbit/gmac/gmac_reset * Specs don't say about using BGMAC_CMDCFG_SR, but in this routine * BGMAC_CMDCFG is read _after_ putting chip in a reset. So it has to @@ -1497,8 +1509,10 @@ int bgmac_enet_probe(struct bgmac *bgmac) bgmac_clk_enable(bgmac, 0); /* This seems to be fixing IRQ by assigning OOB #6 to the core */ - if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6) - bgmac_idm_write(bgmac, BCMA_OOB_SEL_OUT_A30, 0x86); + if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { + if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6) + bgmac_idm_write(bgmac, BCMA_OOB_SEL_OUT_A30, 0x86); + } bgmac_chip_reset(bgmac); diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index c1818766c501..443d57b10264 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -425,6 +425,7 @@ #define BGMAC_FEAT_CC4_IF_SW_TYPE BIT(17) #define BGMAC_FEAT_CC4_IF_SW_TYPE_RGMII BIT(18) #define BGMAC_FEAT_CC7_IF_TYPE_RGMII BIT(19) +#define BGMAC_FEAT_IDM_MASK BIT(20) struct bgmac_slot_info { union { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 43423744fdfa..1e33abde4a3e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -2886,7 +2886,7 @@ static int bnx2x_test_nvram_tbl(struct bnx2x *bp, static int bnx2x_test_nvram(struct bnx2x *bp) { - const struct crc_pair nvram_tbl[] = { + static const struct crc_pair nvram_tbl[] = { { 0, 0x14 }, /* bootstrap */ { 0x14, 0xec }, /* dir */ { 0x100, 0x350 }, /* manuf_info */ @@ -2895,7 +2895,7 @@ static int bnx2x_test_nvram(struct bnx2x *bp) { 0x708, 0x70 }, /* manuf_key_info */ { 0, 0 } }; - const struct crc_pair nvram_tbl2[] = { + static const struct crc_pair nvram_tbl2[] = { { 0x7e8, 0x350 }, /* manuf_info2 */ { 0xb38, 0xf0 }, /* feature_info */ { 0, 0 } @@ -3162,7 +3162,8 @@ static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf) if (is_multi(bp)) { for_each_eth_queue(bp, i) { memset(queue_name, 0, sizeof(queue_name)); - sprintf(queue_name, "%d", i); + snprintf(queue_name, sizeof(queue_name), + "%d", i); for (j = 0; j < BNX2X_NUM_Q_STATS; j++) snprintf(buf + (k + j)*ETH_GSTRING_LEN, ETH_GSTRING_LEN, diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index daca1c9d254b..7b0b399aaedd 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1202,12 +1202,21 @@ static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv, return tx_cb_ptr; } -/* Simple helper to free a control block's resources */ -static void bcmgenet_free_cb(struct enet_cb *cb) +static struct enet_cb *bcmgenet_put_txcb(struct bcmgenet_priv *priv, + struct bcmgenet_tx_ring *ring) { - dev_kfree_skb_any(cb->skb); - cb->skb = NULL; - dma_unmap_addr_set(cb, dma_addr, 0); + struct enet_cb *tx_cb_ptr; + + tx_cb_ptr = ring->cbs; + tx_cb_ptr += ring->write_ptr - ring->cb_ptr; + + /* Rewinding local write pointer */ + if (ring->write_ptr == ring->cb_ptr) + ring->write_ptr = ring->end_ptr; + else + ring->write_ptr--; + + return tx_cb_ptr; } static inline void bcmgenet_rx_ring16_int_disable(struct bcmgenet_rx_ring *ring) @@ -1260,18 +1269,72 @@ static inline void bcmgenet_tx_ring_int_disable(struct bcmgenet_tx_ring *ring) INTRL2_CPU_MASK_SET); } +/* Simple helper to free a transmit control block's resources + * Returns an skb when the last transmit control block associated with the + * skb is freed. The skb should be freed by the caller if necessary. + */ +static struct sk_buff *bcmgenet_free_tx_cb(struct device *dev, + struct enet_cb *cb) +{ + struct sk_buff *skb; + + skb = cb->skb; + + if (skb) { + cb->skb = NULL; + if (cb == GENET_CB(skb)->first_cb) + dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), + DMA_TO_DEVICE); + else + dma_unmap_page(dev, dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), + DMA_TO_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + + if (cb == GENET_CB(skb)->last_cb) + return skb; + + } else if (dma_unmap_addr(cb, dma_addr)) { + dma_unmap_page(dev, + dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), + DMA_TO_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + } + + return 0; +} + +/* Simple helper to free a receive control block's resources */ +static struct sk_buff *bcmgenet_free_rx_cb(struct device *dev, + struct enet_cb *cb) +{ + struct sk_buff *skb; + + skb = cb->skb; + cb->skb = NULL; + + if (dma_unmap_addr(cb, dma_addr)) { + dma_unmap_single(dev, dma_unmap_addr(cb, dma_addr), + dma_unmap_len(cb, dma_len), DMA_FROM_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + } + + return skb; +} + /* Unlocked version of the reclaim routine */ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, struct bcmgenet_tx_ring *ring) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct device *kdev = &priv->pdev->dev; - struct enet_cb *tx_cb_ptr; - unsigned int pkts_compl = 0; + unsigned int txbds_processed = 0; unsigned int bytes_compl = 0; - unsigned int c_index; + unsigned int pkts_compl = 0; unsigned int txbds_ready; - unsigned int txbds_processed = 0; + unsigned int c_index; + struct sk_buff *skb; /* Clear status before servicing to reduce spurious interrupts */ if (ring->index == DESC_INDEX) @@ -1292,21 +1355,12 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, /* Reclaim transmitted buffers */ while (txbds_processed < txbds_ready) { - tx_cb_ptr = &priv->tx_cbs[ring->clean_ptr]; - if (tx_cb_ptr->skb) { + skb = bcmgenet_free_tx_cb(&priv->pdev->dev, + &priv->tx_cbs[ring->clean_ptr]); + if (skb) { pkts_compl++; - bytes_compl += GENET_CB(tx_cb_ptr->skb)->bytes_sent; - dma_unmap_single(kdev, - dma_unmap_addr(tx_cb_ptr, dma_addr), - dma_unmap_len(tx_cb_ptr, dma_len), - DMA_TO_DEVICE); - bcmgenet_free_cb(tx_cb_ptr); - } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { - dma_unmap_page(kdev, - dma_unmap_addr(tx_cb_ptr, dma_addr), - dma_unmap_len(tx_cb_ptr, dma_len), - DMA_TO_DEVICE); - dma_unmap_addr_set(tx_cb_ptr, dma_addr, 0); + bytes_compl += GENET_CB(skb)->bytes_sent; + dev_kfree_skb_any(skb); } txbds_processed++; @@ -1380,95 +1434,6 @@ static void bcmgenet_tx_reclaim_all(struct net_device *dev) bcmgenet_tx_reclaim(dev, &priv->tx_rings[DESC_INDEX]); } -/* Transmits a single SKB (either head of a fragment or a single SKB) - * caller must hold priv->lock - */ -static int bcmgenet_xmit_single(struct net_device *dev, - struct sk_buff *skb, - u16 dma_desc_flags, - struct bcmgenet_tx_ring *ring) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device *kdev = &priv->pdev->dev; - struct enet_cb *tx_cb_ptr; - unsigned int skb_len; - dma_addr_t mapping; - u32 length_status; - int ret; - - tx_cb_ptr = bcmgenet_get_txcb(priv, ring); - - if (unlikely(!tx_cb_ptr)) - BUG(); - - tx_cb_ptr->skb = skb; - - skb_len = skb_headlen(skb); - - mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE); - ret = dma_mapping_error(kdev, mapping); - if (ret) { - priv->mib.tx_dma_failed++; - netif_err(priv, tx_err, dev, "Tx DMA map failed\n"); - dev_kfree_skb(skb); - return ret; - } - - dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); - dma_unmap_len_set(tx_cb_ptr, dma_len, skb_len); - length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags | - (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) | - DMA_TX_APPEND_CRC; - - if (skb->ip_summed == CHECKSUM_PARTIAL) - length_status |= DMA_TX_DO_CSUM; - - dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, length_status); - - return 0; -} - -/* Transmit a SKB fragment */ -static int bcmgenet_xmit_frag(struct net_device *dev, - skb_frag_t *frag, - u16 dma_desc_flags, - struct bcmgenet_tx_ring *ring) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device *kdev = &priv->pdev->dev; - struct enet_cb *tx_cb_ptr; - unsigned int frag_size; - dma_addr_t mapping; - int ret; - - tx_cb_ptr = bcmgenet_get_txcb(priv, ring); - - if (unlikely(!tx_cb_ptr)) - BUG(); - - tx_cb_ptr->skb = NULL; - - frag_size = skb_frag_size(frag); - - mapping = skb_frag_dma_map(kdev, frag, 0, frag_size, DMA_TO_DEVICE); - ret = dma_mapping_error(kdev, mapping); - if (ret) { - priv->mib.tx_dma_failed++; - netif_err(priv, tx_err, dev, "%s: Tx DMA map failed\n", - __func__); - return ret; - } - - dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); - dma_unmap_len_set(tx_cb_ptr, dma_len, frag_size); - - dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, - (frag_size << DMA_BUFLENGTH_SHIFT) | dma_desc_flags | - (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT)); - - return 0; -} - /* Reallocate the SKB to put enough headroom in front of it and insert * the transmit checksum offsets in the descriptors */ @@ -1535,11 +1500,16 @@ static struct sk_buff *bcmgenet_put_tx_csum(struct net_device *dev, static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device *kdev = &priv->pdev->dev; struct bcmgenet_tx_ring *ring = NULL; + struct enet_cb *tx_cb_ptr; struct netdev_queue *txq; unsigned long flags = 0; int nr_frags, index; - u16 dma_desc_flags; + dma_addr_t mapping; + unsigned int size; + skb_frag_t *frag; + u32 len_stat; int ret; int i; @@ -1592,29 +1562,53 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) } } - dma_desc_flags = DMA_SOP; - if (nr_frags == 0) - dma_desc_flags |= DMA_EOP; + for (i = 0; i <= nr_frags; i++) { + tx_cb_ptr = bcmgenet_get_txcb(priv, ring); - /* Transmit single SKB or head of fragment list */ - ret = bcmgenet_xmit_single(dev, skb, dma_desc_flags, ring); - if (ret) { - ret = NETDEV_TX_OK; - goto out; - } + if (unlikely(!tx_cb_ptr)) + BUG(); + + if (!i) { + /* Transmit single SKB or head of fragment list */ + GENET_CB(skb)->first_cb = tx_cb_ptr; + size = skb_headlen(skb); + mapping = dma_map_single(kdev, skb->data, size, + DMA_TO_DEVICE); + } else { + /* xmit fragment */ + frag = &skb_shinfo(skb)->frags[i - 1]; + size = skb_frag_size(frag); + mapping = skb_frag_dma_map(kdev, frag, 0, size, + DMA_TO_DEVICE); + } - /* xmit fragment */ - for (i = 0; i < nr_frags; i++) { - ret = bcmgenet_xmit_frag(dev, - &skb_shinfo(skb)->frags[i], - (i == nr_frags - 1) ? DMA_EOP : 0, - ring); + ret = dma_mapping_error(kdev, mapping); if (ret) { + priv->mib.tx_dma_failed++; + netif_err(priv, tx_err, dev, "Tx DMA map failed\n"); ret = NETDEV_TX_OK; - goto out; + goto out_unmap_frags; + } + dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); + dma_unmap_len_set(tx_cb_ptr, dma_len, size); + + tx_cb_ptr->skb = skb; + + len_stat = (size << DMA_BUFLENGTH_SHIFT) | + (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT); + + if (!i) { + len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; + if (skb->ip_summed == CHECKSUM_PARTIAL) + len_stat |= DMA_TX_DO_CSUM; } + if (i == nr_frags) + len_stat |= DMA_EOP; + + dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, len_stat); } + GENET_CB(skb)->last_cb = tx_cb_ptr; skb_tx_timestamp(skb); /* Decrement total BD count and advance our write pointer */ @@ -1635,6 +1629,19 @@ out: spin_unlock_irqrestore(&ring->lock, flags); return ret; + +out_unmap_frags: + /* Back up for failed control block mapping */ + bcmgenet_put_txcb(priv, ring); + + /* Unmap successfully mapped control blocks */ + while (i-- > 0) { + tx_cb_ptr = bcmgenet_put_txcb(priv, ring); + bcmgenet_free_tx_cb(kdev, tx_cb_ptr); + } + + dev_kfree_skb(skb); + goto out; } static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv, @@ -1666,14 +1673,12 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv, } /* Grab the current Rx skb from the ring and DMA-unmap it */ - rx_skb = cb->skb; - if (likely(rx_skb)) - dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr), - priv->rx_buf_len, DMA_FROM_DEVICE); + rx_skb = bcmgenet_free_rx_cb(kdev, cb); /* Put the new Rx skb on the ring */ cb->skb = skb; dma_unmap_addr_set(cb, dma_addr, mapping); + dma_unmap_len_set(cb, dma_len, priv->rx_buf_len); dmadesc_set_addr(priv, cb->bd_addr, mapping); /* Return the current Rx skb to caller */ @@ -1880,22 +1885,16 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv, static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) { - struct device *kdev = &priv->pdev->dev; + struct sk_buff *skb; struct enet_cb *cb; int i; for (i = 0; i < priv->num_rx_bds; i++) { cb = &priv->rx_cbs[i]; - if (dma_unmap_addr(cb, dma_addr)) { - dma_unmap_single(kdev, - dma_unmap_addr(cb, dma_addr), - priv->rx_buf_len, DMA_FROM_DEVICE); - dma_unmap_addr_set(cb, dma_addr, 0); - } - - if (cb->skb) - bcmgenet_free_cb(cb); + skb = bcmgenet_free_rx_cb(&priv->pdev->dev, cb); + if (skb) + dev_kfree_skb_any(skb); } } @@ -2479,8 +2478,10 @@ static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv) static void bcmgenet_fini_dma(struct bcmgenet_priv *priv) { - int i; struct netdev_queue *txq; + struct sk_buff *skb; + struct enet_cb *cb; + int i; bcmgenet_fini_rx_napi(priv); bcmgenet_fini_tx_napi(priv); @@ -2489,10 +2490,10 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv) bcmgenet_dma_teardown(priv); for (i = 0; i < priv->num_tx_bds; i++) { - if (priv->tx_cbs[i].skb != NULL) { - dev_kfree_skb(priv->tx_cbs[i].skb); - priv->tx_cbs[i].skb = NULL; - } + cb = priv->tx_cbs + i; + skb = bcmgenet_free_tx_cb(&priv->pdev->dev, cb); + if (skb) + dev_kfree_skb(skb); } for (i = 0; i < priv->hw_params->tx_queues; i++) { diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index efd07020b89f..b9344de669f8 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -544,6 +544,8 @@ struct bcmgenet_hw_params { }; struct bcmgenet_skb_cb { + struct enet_cb *first_cb; /* First control block of SKB */ + struct enet_cb *last_cb; /* Last control block of SKB */ unsigned int bytes_sent; /* bytes on the wire (no TSB) */ }; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 28ecda3d3404..ebd353bc78ff 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -335,7 +335,7 @@ lio_ethtool_get_channels(struct net_device *dev, static int lio_get_eeprom_len(struct net_device *netdev) { - u8 buf[128]; + u8 buf[192]; struct lio *lio = GET_LIO(netdev); struct octeon_device *oct_dev = lio->oct_dev; struct octeon_board_info *board_info; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index a0ca68ce3fbb..79112563a25a 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1008,7 +1008,7 @@ static void bgx_print_qlm_mode(struct bgx *bgx, u8 lmacid) { struct device *dev = &bgx->pdev->dev; struct lmac *lmac; - char str[20]; + char str[27]; if (!bgx->is_dlm && lmacid) return; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c index 50517cfd9671..9f9d6cae39d5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c @@ -441,7 +441,8 @@ void cxgb4_ptp_init(struct adapter *adapter) adapter->ptp_clock = ptp_clock_register(&adapter->ptp_clock_info, &adapter->pdev->dev); - if (!adapter->ptp_clock) { + if (IS_ERR_OR_NULL(adapter->ptp_clock)) { + adapter->ptp_clock = NULL; dev_err(adapter->pdev_dev, "PTP %s Clock registration has failed\n", __func__); return; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 99987d8e437e..aa28299aef5f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -174,6 +174,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x50a0), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a1), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a2), /* Custom T540-KR4 */ + CH_PCI_ID_TABLE_FENTRY(0x50a3), /* Custom T580-KR4 */ + CH_PCI_ID_TABLE_FENTRY(0x50a4), /* Custom 2x T540-CR */ /* T6 adapters: */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index ff864a187d5a..a37166ee577b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -776,8 +776,9 @@ void hns_ae_update_led_status(struct hnae_handle *handle) assert(handle); mac_cb = hns_get_mac_cb(handle); - if (!mac_cb->cpld_ctrl) + if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) return; + hns_set_led_opt(mac_cb); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 7a8addda726e..408b63faf9a8 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -53,6 +53,34 @@ static u32 dsaf_read_sub(struct dsaf_device *dsaf_dev, u32 reg) return ret; } +static void hns_dsaf_acpi_ledctrl_by_port(struct hns_mac_cb *mac_cb, u8 op_type, + u32 link, u32 port, u32 act) +{ + union acpi_object *obj; + union acpi_object obj_args[3], argv4; + + obj_args[0].integer.type = ACPI_TYPE_INTEGER; + obj_args[0].integer.value = link; + obj_args[1].integer.type = ACPI_TYPE_INTEGER; + obj_args[1].integer.value = port; + obj_args[2].integer.type = ACPI_TYPE_INTEGER; + obj_args[2].integer.value = act; + + argv4.type = ACPI_TYPE_PACKAGE; + argv4.package.count = 3; + argv4.package.elements = obj_args; + + obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), + &hns_dsaf_acpi_dsm_guid, 0, op_type, &argv4); + if (!obj) { + dev_warn(mac_cb->dev, "ledctrl fail, link:%d port:%d act:%d!\n", + link, port, act); + return; + } + + ACPI_FREE(obj); +} + static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, u16 speed, int data) { @@ -93,6 +121,18 @@ static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, } } +static void hns_cpld_set_led_acpi(struct hns_mac_cb *mac_cb, int link_status, + u16 speed, int data) +{ + if (!mac_cb) { + pr_err("cpld_led_set mac_cb is null!\n"); + return; + } + + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + link_status, mac_cb->mac_id, data); +} + static void cpld_led_reset(struct hns_mac_cb *mac_cb) { if (!mac_cb || !mac_cb->cpld_ctrl) @@ -103,6 +143,20 @@ static void cpld_led_reset(struct hns_mac_cb *mac_cb) mac_cb->cpld_led_value = CPLD_LED_DEFAULT_VALUE; } +static void cpld_led_reset_acpi(struct hns_mac_cb *mac_cb) +{ + if (!mac_cb) { + pr_err("cpld_led_reset mac_cb is null!\n"); + return; + } + + if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) + return; + + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + 0, mac_cb->mac_id, 0); +} + static int cpld_set_led_id(struct hns_mac_cb *mac_cb, enum hnae_led_state status) { @@ -604,8 +658,8 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev) misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback; } else if (is_acpi_node(dsaf_dev->dev->fwnode)) { - misc_op->cpld_set_led = hns_cpld_set_led; - misc_op->cpld_reset_led = cpld_led_reset; + misc_op->cpld_set_led = hns_cpld_set_led_acpi; + misc_op->cpld_reset_led = cpld_led_reset_acpi; misc_op->cpld_set_led_id = cpld_set_led_id; misc_op->dsaf_reset = hns_dsaf_rst_acpi; diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c index d94b3744a5b9..b651c1210555 100644 --- a/drivers/net/ethernet/mellanox/mlx4/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c @@ -283,7 +283,7 @@ int mlx4_zone_add_one(struct mlx4_zone_allocator *zone_alloc, } /* Should be called under a lock */ -static int __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry) +static void __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry) { struct mlx4_zone_allocator *zone_alloc = entry->allocator; @@ -315,8 +315,6 @@ static int __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry) } zone_alloc->mask = mask; } - - return 0; } void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc) @@ -457,7 +455,7 @@ struct mlx4_bitmap *mlx4_zone_get_bitmap(struct mlx4_zone_allocator *zones, u32 int mlx4_zone_remove_one(struct mlx4_zone_allocator *zones, u32 uid) { struct mlx4_zone_entry *zone; - int res; + int res = 0; spin_lock(&zones->lock); @@ -468,7 +466,7 @@ int mlx4_zone_remove_one(struct mlx4_zone_allocator *zones, u32 uid) goto out; } - res = __mlx4_zone_remove_one_entry(zone); + __mlx4_zone_remove_one_entry(zone); out: spin_unlock(&zones->lock); diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 746d94e28470..60850bfa3d32 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -766,11 +766,13 @@ static void emac_shutdown(struct platform_device *pdev) struct emac_adapter *adpt = netdev_priv(netdev); struct emac_sgmii *sgmii = &adpt->phy; - /* Closing the SGMII turns off its interrupts */ - sgmii->close(adpt); + if (netdev->flags & IFF_UP) { + /* Closing the SGMII turns off its interrupts */ + sgmii->close(adpt); - /* Resetting the MAC turns off all DMA and its interrupts */ - emac_mac_reset(adpt); + /* Resetting the MAC turns off all DMA and its interrupts */ + emac_mac_reset(adpt); + } } static struct platform_driver emac_platform_driver = { diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index b607936e1b3e..9c0488e0f08e 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -90,17 +90,13 @@ struct ioc3_private { spinlock_t ioc3_lock; struct mii_if_info mii; + struct net_device *dev; struct pci_dev *pdev; /* Members used by autonegotiation */ struct timer_list ioc3_timer; }; -static inline struct net_device *priv_netdev(struct ioc3_private *dev) -{ - return (void *)dev - ((sizeof(struct net_device) + 31) & ~31); -} - static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); static void ioc3_set_multicast_list(struct net_device *dev); static int ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev); @@ -427,7 +423,7 @@ static void ioc3_get_eaddr_nic(struct ioc3_private *ip) nic[i] = nic_read_byte(ioc3); for (i = 2; i < 8; i++) - priv_netdev(ip)->dev_addr[i - 2] = nic[i]; + ip->dev->dev_addr[i - 2] = nic[i]; } /* @@ -439,7 +435,7 @@ static void ioc3_get_eaddr(struct ioc3_private *ip) { ioc3_get_eaddr_nic(ip); - printk("Ethernet address is %pM.\n", priv_netdev(ip)->dev_addr); + printk("Ethernet address is %pM.\n", ip->dev->dev_addr); } static void __ioc3_set_mac_address(struct net_device *dev) @@ -790,13 +786,12 @@ static void ioc3_timer(unsigned long data) */ static int ioc3_mii_init(struct ioc3_private *ip) { - struct net_device *dev = priv_netdev(ip); int i, found = 0, res = 0; int ioc3_phy_workaround = 1; u16 word; for (i = 0; i < 32; i++) { - word = ioc3_mdio_read(dev, i, MII_PHYSID1); + word = ioc3_mdio_read(ip->dev, i, MII_PHYSID1); if (word != 0xffff && word != 0x0000) { found = 1; @@ -1276,6 +1271,7 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) SET_NETDEV_DEV(dev, &pdev->dev); ip = netdev_priv(dev); + ip->dev = dev; dev->irq = pdev->irq; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f233bf8b4ebb..c4407e8e39a3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -117,7 +117,7 @@ static void dwmac4_tx_queue_routing(struct mac_device_info *hw, void __iomem *ioaddr = hw->pcsr; u32 value; - const struct stmmac_rx_routing route_possibilities[] = { + static const struct stmmac_rx_routing route_possibilities[] = { { GMAC_RXQCTRL_AVCPQ_MASK, GMAC_RXQCTRL_AVCPQ_SHIFT }, { GMAC_RXQCTRL_PTPQ_MASK, GMAC_RXQCTRL_PTPQ_SHIFT }, { GMAC_RXQCTRL_DCBCPQ_MASK, GMAC_RXQCTRL_DCBCPQ_SHIFT }, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1853f7ff6657..1763e48c84e2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4120,8 +4120,15 @@ int stmmac_dvr_probe(struct device *device, if ((phyaddr >= 0) && (phyaddr <= 31)) priv->plat->phy_addr = phyaddr; - if (priv->plat->stmmac_rst) + if (priv->plat->stmmac_rst) { + ret = reset_control_assert(priv->plat->stmmac_rst); reset_control_deassert(priv->plat->stmmac_rst); + /* Some reset controllers have only reset callback instead of + * assert + deassert callbacks pair. + */ + if (ret == -ENOTSUPP) + reset_control_reset(priv->plat->stmmac_rst); + } /* Init MAC and get the capabilities */ ret = stmmac_hw_init(priv); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 46cb7f8955a2..4bb04aaf9650 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9532,7 +9532,7 @@ static struct niu_parent *niu_get_parent(struct niu *np, p = niu_new_parent(np, id, ptype); if (p) { - char port_name[6]; + char port_name[8]; int err; sprintf(port_name, "port%d", port); @@ -9553,7 +9553,7 @@ static void niu_put_parent(struct niu *np) { struct niu_parent *p = np->parent; u8 port = np->port; - char port_name[6]; + char port_name[8]; BUG_ON(!p || p->ports[port] != np); diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 711fbbbc4b1f..163d8d16bc24 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -654,6 +654,8 @@ static int bdx_ioctl_priv(struct net_device *ndev, struct ifreq *ifr, int cmd) RET(-EFAULT); } DBG("%d 0x%x 0x%x\n", data[0], data[1], data[2]); + } else { + return -EOPNOTSUPP; } if (!capable(CAP_SYS_RAWIO)) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 1850e348f555..badd0a8caeb9 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -3089,6 +3089,31 @@ static int cpsw_probe(struct platform_device *pdev) cpsw->quirk_irq = true; } + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + ndev->netdev_ops = &cpsw_netdev_ops; + ndev->ethtool_ops = &cpsw_ethtool_ops; + netif_napi_add(ndev, &cpsw->napi_rx, cpsw_rx_poll, CPSW_POLL_WEIGHT); + netif_tx_napi_add(ndev, &cpsw->napi_tx, cpsw_tx_poll, CPSW_POLL_WEIGHT); + cpsw_split_res(ndev); + + /* register the network device */ + SET_NETDEV_DEV(ndev, &pdev->dev); + ret = register_netdev(ndev); + if (ret) { + dev_err(priv->dev, "error registering net device\n"); + ret = -ENODEV; + goto clean_ale_ret; + } + + if (cpsw->data.dual_emac) { + ret = cpsw_probe_dual_emac(priv); + if (ret) { + cpsw_err(priv, probe, "error probe slave 2 emac interface\n"); + goto clean_unregister_netdev_ret; + } + } + /* Grab RX and TX IRQs. Note that we also have RX_THRESHOLD and * MISC IRQs which are always kept disabled with this driver so * we will not request them. @@ -3127,33 +3152,9 @@ static int cpsw_probe(struct platform_device *pdev) goto clean_ale_ret; } - ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - - ndev->netdev_ops = &cpsw_netdev_ops; - ndev->ethtool_ops = &cpsw_ethtool_ops; - netif_napi_add(ndev, &cpsw->napi_rx, cpsw_rx_poll, CPSW_POLL_WEIGHT); - netif_tx_napi_add(ndev, &cpsw->napi_tx, cpsw_tx_poll, CPSW_POLL_WEIGHT); - cpsw_split_res(ndev); - - /* register the network device */ - SET_NETDEV_DEV(ndev, &pdev->dev); - ret = register_netdev(ndev); - if (ret) { - dev_err(priv->dev, "error registering net device\n"); - ret = -ENODEV; - goto clean_ale_ret; - } - cpsw_notice(priv, probe, "initialized device (regs %pa, irq %d, pool size %d)\n", &ss_res->start, ndev->irq, dma_params.descs_pool_size); - if (cpsw->data.dual_emac) { - ret = cpsw_probe_dual_emac(priv); - if (ret) { - cpsw_err(priv, probe, "error probe slave 2 emac interface\n"); - goto clean_unregister_netdev_ret; - } - } pm_runtime_put(&pdev->dev); diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 00755b6a42cf..c608e1dfaf09 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -135,8 +135,8 @@ int mdio_mux_init(struct device *dev, for_each_available_child_of_node(dev->of_node, child_bus_node) { int v; - v = of_mdio_parse_addr(dev, child_bus_node); - if (v < 0) { + r = of_property_read_u32(child_bus_node, "reg", &v); + if (r) { dev_err(dev, "Error: Failed to find reg for child %s\n", of_node_full_name(child_bus_node)); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 13028833bee3..bd4303944e44 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -120,6 +120,7 @@ struct ppp { int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ + int *xmit_recursion __percpu; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ @@ -1025,6 +1026,7 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev, struct ppp *ppp = netdev_priv(dev); int indx; int err; + int cpu; ppp->dev = dev; ppp->ppp_net = src_net; @@ -1039,6 +1041,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev, INIT_LIST_HEAD(&ppp->channels); spin_lock_init(&ppp->rlock); spin_lock_init(&ppp->wlock); + + ppp->xmit_recursion = alloc_percpu(int); + if (!ppp->xmit_recursion) { + err = -ENOMEM; + goto err1; + } + for_each_possible_cpu(cpu) + (*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0; + #ifdef CONFIG_PPP_MULTILINK ppp->minseq = -1; skb_queue_head_init(&ppp->mrq); @@ -1050,11 +1061,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev, err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set); if (err < 0) - return err; + goto err2; conf->file->private_data = &ppp->file; return 0; +err2: + free_percpu(ppp->xmit_recursion); +err1: + return err; } static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = { @@ -1400,18 +1415,16 @@ static void __ppp_xmit_process(struct ppp *ppp) ppp_xmit_unlock(ppp); } -static DEFINE_PER_CPU(int, ppp_xmit_recursion); - static void ppp_xmit_process(struct ppp *ppp) { local_bh_disable(); - if (unlikely(__this_cpu_read(ppp_xmit_recursion))) + if (unlikely(*this_cpu_ptr(ppp->xmit_recursion))) goto err; - __this_cpu_inc(ppp_xmit_recursion); + (*this_cpu_ptr(ppp->xmit_recursion))++; __ppp_xmit_process(ppp); - __this_cpu_dec(ppp_xmit_recursion); + (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); @@ -1905,7 +1918,7 @@ static void __ppp_channel_push(struct channel *pch) read_lock(&pch->upl); ppp = pch->ppp; if (ppp) - __ppp_xmit_process(ppp); + ppp_xmit_process(ppp); read_unlock(&pch->upl); } } @@ -1914,9 +1927,7 @@ static void ppp_channel_push(struct channel *pch) { local_bh_disable(); - __this_cpu_inc(ppp_xmit_recursion); __ppp_channel_push(pch); - __this_cpu_dec(ppp_xmit_recursion); local_bh_enable(); } @@ -3057,6 +3068,7 @@ static void ppp_destroy_interface(struct ppp *ppp) #endif /* CONFIG_PPP_FILTER */ kfree_skb(ppp->xmit_pending); + free_percpu(ppp->xmit_recursion); free_netdev(ppp->dev); } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index d103a1d4fb36..8f572b9f3625 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -768,8 +768,10 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ u8 *buf; int len; int temp; + int err; u8 iface_no; struct usb_cdc_parsed_header hdr; + u16 curr_ntb_format; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -874,6 +876,32 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ goto error2; } + /* + * Some Huawei devices have been observed to come out of reset in NDP32 mode. + * Let's check if this is the case, and set the device to NDP16 mode again if + * needed. + */ + if (ctx->drvflags & CDC_NCM_FLAG_RESET_NTB16) { + err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_FORMAT, + USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE, + 0, iface_no, &curr_ntb_format, 2); + if (err < 0) { + goto error2; + } + + if (curr_ntb_format == USB_CDC_NCM_NTB32_FORMAT) { + dev_info(&intf->dev, "resetting NTB format to 16-bit"); + err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT, + USB_TYPE_CLASS | USB_DIR_OUT + | USB_RECIP_INTERFACE, + USB_CDC_NCM_NTB16_FORMAT, + iface_no, NULL, 0); + + if (err < 0) + goto error2; + } + } + cdc_ncm_find_endpoints(dev, ctx->data); cdc_ncm_find_endpoints(dev, ctx->control); if (!dev->in || !dev->out || !dev->status) { diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c index 2680a65cd5e4..63f28908afda 100644 --- a/drivers/net/usb/huawei_cdc_ncm.c +++ b/drivers/net/usb/huawei_cdc_ncm.c @@ -80,6 +80,12 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev, * be at the end of the frame. */ drvflags |= CDC_NCM_FLAG_NDP_TO_END; + + /* Additionally, it has been reported that some Huawei E3372H devices, with + * firmware version 21.318.01.00.541, come out of reset in NTB32 format mode, hence + * needing to be set to the NTB16 one again. + */ + drvflags |= CDC_NCM_FLAG_RESET_NTB16; ret = cdc_ncm_bind_common(usbnet_dev, intf, 1, drvflags); if (ret) goto err; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 2dfca96a63b6..340c13484e5c 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -898,6 +898,7 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .set_wol = smsc95xx_ethtool_set_wol, .get_link_ksettings = smsc95xx_get_link_ksettings, .set_link_ksettings = smsc95xx_set_link_ksettings, + .get_ts_info = ethtool_op_get_ts_info, }; static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index ba1c9f93592b..9c51b8be0038 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -311,7 +311,7 @@ struct vmxnet3_intr { u8 num_intrs; /* # of intr vectors */ u8 event_intr_idx; /* idx of the intr vector for event */ u8 mod_levels[VMXNET3_LINUX_MAX_MSIX_VECT]; /* moderation level */ - char event_msi_vector_name[IFNAMSIZ+11]; + char event_msi_vector_name[IFNAMSIZ+17]; #ifdef CONFIG_PCI_MSI struct msix_entry msix_entries[VMXNET3_LINUX_MAX_MSIX_VECT]; #endif diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 6e2e760d98b1..0b75def39c6c 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -5704,7 +5704,7 @@ static void rt2800_init_freq_calibration(struct rt2x00_dev *rt2x00dev) static void rt2800_init_bbp_5592_glrt(struct rt2x00_dev *rt2x00dev) { - const u8 glrt_table[] = { + static const u8 glrt_table[] = { 0xE0, 0x1F, 0X38, 0x32, 0x08, 0x28, 0x19, 0x0A, 0xFF, 0x00, /* 128 ~ 137 */ 0x16, 0x10, 0x10, 0x0B, 0x36, 0x2C, 0x26, 0x24, 0x42, 0x36, /* 138 ~ 147 */ 0x30, 0x2D, 0x4C, 0x46, 0x3D, 0x40, 0x3E, 0x42, 0x3D, 0x40, /* 148 ~ 157 */ diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 7cd99b1f8596..75bc08c6838c 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -421,14 +421,15 @@ static void set_badblock(struct badblocks *bb, sector_t s, int num) static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len) { const unsigned int sector_size = 512; - sector_t start_sector; + sector_t start_sector, end_sector; u64 num_sectors; u32 rem; start_sector = div_u64(ns_offset, sector_size); - num_sectors = div_u64_rem(len, sector_size, &rem); + end_sector = div_u64_rem(ns_offset + len, sector_size, &rem); if (rem) - num_sectors++; + end_sector++; + num_sectors = end_sector - start_sector; if (unlikely(num_sectors > (u64)INT_MAX)) { u64 remaining = num_sectors; diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 077f62e208aa..6a4367cc9caa 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3401,9 +3401,10 @@ static int cxlflash_afu_debug(struct cxlflash_cfg *cfg, if (is_write) { req_flags |= SISL_REQ_FLAGS_HOST_WRITE; - rc = copy_from_user(kbuf, ubuf, ulen); - if (unlikely(rc)) + if (copy_from_user(kbuf, ubuf, ulen)) { + rc = -EFAULT; goto out; + } } } @@ -3431,8 +3432,10 @@ static int cxlflash_afu_debug(struct cxlflash_cfg *cfg, goto out; } - if (ulen && !is_write) - rc = copy_to_user(ubuf, kbuf, ulen); + if (ulen && !is_write) { + if (copy_to_user(ubuf, kbuf, ulen)) + rc = -EFAULT; + } out: kfree(buf); dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 551d103c27f1..2bfea7082e3a 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -1693,7 +1693,7 @@ static int prep_ssp_v2_hw(struct hisi_hba *hisi_hba, static int parse_trans_tx_err_code_v2_hw(u32 err_msk) { - const u8 trans_tx_err_code_prio[] = { + static const u8 trans_tx_err_code_prio[] = { TRANS_TX_OPEN_FAIL_WITH_IT_NEXUS_LOSS, TRANS_TX_ERR_PHY_NOT_ENABLE, TRANS_TX_OPEN_CNX_ERR_WRONG_DESTINATION, @@ -1738,7 +1738,7 @@ static int parse_trans_tx_err_code_v2_hw(u32 err_msk) static int parse_trans_rx_err_code_v2_hw(u32 err_msk) { - const u8 trans_rx_err_code_prio[] = { + static const u8 trans_rx_err_code_prio[] = { TRANS_RX_ERR_WITH_RXFRAME_CRC_ERR, TRANS_RX_ERR_WITH_RXFIS_8B10B_DISP_ERR, TRANS_RX_ERR_WITH_RXFRAME_HAVE_ERRPRM, @@ -1784,7 +1784,7 @@ static int parse_trans_rx_err_code_v2_hw(u32 err_msk) static int parse_dma_tx_err_code_v2_hw(u32 err_msk) { - const u8 dma_tx_err_code_prio[] = { + static const u8 dma_tx_err_code_prio[] = { DMA_TX_UNEXP_XFER_ERR, DMA_TX_UNEXP_RETRANS_ERR, DMA_TX_XFER_LEN_OVERFLOW, @@ -1810,7 +1810,7 @@ static int parse_dma_tx_err_code_v2_hw(u32 err_msk) static int parse_sipc_rx_err_code_v2_hw(u32 err_msk) { - const u8 sipc_rx_err_code_prio[] = { + static const u8 sipc_rx_err_code_prio[] = { SIPC_RX_FIS_STATUS_ERR_BIT_VLD, SIPC_RX_PIO_WRSETUP_STATUS_DRQ_ERR, SIPC_RX_FIS_STATUS_BSY_BIT_ERR, @@ -1836,7 +1836,7 @@ static int parse_sipc_rx_err_code_v2_hw(u32 err_msk) static int parse_dma_rx_err_code_v2_hw(u32 err_msk) { - const u8 dma_rx_err_code_prio[] = { + static const u8 dma_rx_err_code_prio[] = { DMA_RX_UNKNOWN_FRM_ERR, DMA_RX_DATA_LEN_OVERFLOW, DMA_RX_DATA_LEN_UNDERFLOW, diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c index 47f66e949745..ed197bc8e801 100644 --- a/drivers/scsi/isci/request.c +++ b/drivers/scsi/isci/request.c @@ -213,7 +213,7 @@ static void sci_task_request_build_ssp_task_iu(struct isci_request *ireq) * @task_context: * */ -static void scu_ssp_reqeust_construct_task_context( +static void scu_ssp_request_construct_task_context( struct isci_request *ireq, struct scu_task_context *task_context) { @@ -425,7 +425,7 @@ static void scu_ssp_io_request_construct_task_context(struct isci_request *ireq, u8 prot_type = scsi_get_prot_type(scmd); u8 prot_op = scsi_get_prot_op(scmd); - scu_ssp_reqeust_construct_task_context(ireq, task_context); + scu_ssp_request_construct_task_context(ireq, task_context); task_context->ssp_command_iu_length = sizeof(struct ssp_cmd_iu) / sizeof(u32); @@ -472,7 +472,7 @@ static void scu_ssp_task_request_construct_task_context(struct isci_request *ire { struct scu_task_context *task_context = ireq->tc; - scu_ssp_reqeust_construct_task_context(ireq, task_context); + scu_ssp_request_construct_task_context(ireq, task_context); task_context->control_frame = 1; task_context->priority = SCU_TASK_PRIORITY_HIGH; @@ -495,7 +495,7 @@ static void scu_ssp_task_request_construct_task_context(struct isci_request *ire * the command buffer is complete. none Revisit task context construction to * determine what is common for SSP/SMP/STP task context structures. */ -static void scu_sata_reqeust_construct_task_context( +static void scu_sata_request_construct_task_context( struct isci_request *ireq, struct scu_task_context *task_context) { @@ -562,7 +562,7 @@ static void scu_stp_raw_request_construct_task_context(struct isci_request *ireq { struct scu_task_context *task_context = ireq->tc; - scu_sata_reqeust_construct_task_context(ireq, task_context); + scu_sata_request_construct_task_context(ireq, task_context); task_context->control_frame = 0; task_context->priority = SCU_TASK_PRIORITY_NORMAL; @@ -613,7 +613,7 @@ static void sci_stp_optimized_request_construct(struct isci_request *ireq, struct scu_task_context *task_context = ireq->tc; /* Build the STP task context structure */ - scu_sata_reqeust_construct_task_context(ireq, task_context); + scu_sata_request_construct_task_context(ireq, task_context); /* Copy over the SGL elements */ sci_request_build_sgl(ireq); @@ -1401,7 +1401,7 @@ static enum sci_status sci_stp_request_pio_data_out_transmit_data(struct isci_re * @data_buffer: The buffer of data to be copied. * @length: The length of the data transfer. * - * Copy the data from the buffer for the length specified to the IO reqeust SGL + * Copy the data from the buffer for the length specified to the IO request SGL * specified data region. enum sci_status */ static enum sci_status diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c index fd501f8dbb11..8660f923ace0 100644 --- a/drivers/scsi/libfc/fc_disc.c +++ b/drivers/scsi/libfc/fc_disc.c @@ -573,7 +573,7 @@ static void fc_disc_gpn_ft_resp(struct fc_seq *sp, struct fc_frame *fp, event = DISC_EV_FAILED; } if (error) - fc_disc_error(disc, fp); + fc_disc_error(disc, ERR_PTR(error)); else if (event != DISC_EV_NONE) fc_disc_done(disc, event); fc_frame_free(fp); diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index b58bba4604e8..7786c97e033f 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -1227,7 +1227,7 @@ static void qedf_rport_event_handler(struct fc_lport *lport, if (rdata->spp_type != FC_TYPE_FCP) { QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, - "Not offlading since since spp type isn't FCP\n"); + "Not offloading since spp type isn't FCP\n"); break; } if (!(rdata->ids.roles & FC_RPORT_ROLE_FCP_TARGET)) { diff --git a/drivers/scsi/qedi/qedi.h b/drivers/scsi/qedi/qedi.h index 32632c9b2276..91d2f51c351b 100644 --- a/drivers/scsi/qedi/qedi.h +++ b/drivers/scsi/qedi/qedi.h @@ -23,11 +23,17 @@ #include <linux/qed/qed_iscsi_if.h> #include <linux/qed/qed_ll2_if.h> #include "qedi_version.h" +#include "qedi_nvm_iscsi_cfg.h" #define QEDI_MODULE_NAME "qedi" struct qedi_endpoint; +#ifndef GET_FIELD2 +#define GET_FIELD2(value, name) \ + (((value) & (name ## _MASK)) >> (name ## _OFFSET)) +#endif + /* * PCI function probe defines */ @@ -66,6 +72,11 @@ struct qedi_endpoint; #define QEDI_HW_DMA_BOUNDARY 0xfff #define QEDI_PATH_HANDLE 0xFE0000000UL +enum qedi_nvm_tgts { + QEDI_NVM_TGT_PRI, + QEDI_NVM_TGT_SEC, +}; + struct qedi_uio_ctrl { /* meta data */ u32 uio_hsi_version; @@ -283,6 +294,8 @@ struct qedi_ctx { void *bdq_pbl_list; dma_addr_t bdq_pbl_list_dma; u8 bdq_pbl_list_num_entries; + struct nvm_iscsi_cfg *iscsi_cfg; + dma_addr_t nvm_buf_dma; void __iomem *bdq_primary_prod; void __iomem *bdq_secondary_prod; u16 bdq_prod_idx; @@ -337,6 +350,10 @@ struct qedi_ctx { bool use_fast_sge; atomic_t num_offloads; +#define SYSFS_FLAG_FW_SEL_BOOT 2 +#define IPV6_LEN 41 +#define IPV4_LEN 17 + struct iscsi_boot_kset *boot_kset; }; struct qedi_work { diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index 19254bd739d9..93d54acd4a22 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -1411,7 +1411,7 @@ static void qedi_tmf_work(struct work_struct *work) list_work = kzalloc(sizeof(*list_work), GFP_ATOMIC); if (!list_work) { - QEDI_ERR(&qedi->dbg_ctx, "Memory alloction failed\n"); + QEDI_ERR(&qedi->dbg_ctx, "Memory allocation failed\n"); goto abort_ret; } diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 5f5a4ef2e529..2c3783684815 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <linux/if_vlan.h> #include <linux/cpu.h> +#include <linux/iscsi_boot_sysfs.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_device.h> @@ -1143,6 +1144,30 @@ exit_setup_int: return rc; } +static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi) +{ + if (qedi->iscsi_cfg) + dma_free_coherent(&qedi->pdev->dev, + sizeof(struct nvm_iscsi_cfg), + qedi->iscsi_cfg, qedi->nvm_buf_dma); +} + +static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi) +{ + qedi->iscsi_cfg = dma_zalloc_coherent(&qedi->pdev->dev, + sizeof(struct nvm_iscsi_cfg), + &qedi->nvm_buf_dma, GFP_KERNEL); + if (!qedi->iscsi_cfg) { + QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n"); + return -ENOMEM; + } + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_cfg, + qedi->nvm_buf_dma); + + return 0; +} + static void qedi_free_bdq(struct qedi_ctx *qedi) { int i; @@ -1183,6 +1208,7 @@ static void qedi_free_global_queues(struct qedi_ctx *qedi) kfree(gl[i]); } qedi_free_bdq(qedi); + qedi_free_nvm_iscsi_cfg(qedi); } static int qedi_alloc_bdq(struct qedi_ctx *qedi) @@ -1309,6 +1335,11 @@ static int qedi_alloc_global_queues(struct qedi_ctx *qedi) if (rc) goto mem_alloc_failure; + /* Allocate DMA coherent buffers for NVM_ISCSI_CFG */ + rc = qedi_alloc_nvm_iscsi_cfg(qedi); + if (rc) + goto mem_alloc_failure; + /* Allocate a CQ and an associated PBL for each MSI-X * vector. */ @@ -1671,6 +1702,387 @@ void qedi_reset_host_mtu(struct qedi_ctx *qedi, u16 mtu) qedi_ops->ll2->start(qedi->cdev, ¶ms); } +/** + * qedi_get_nvram_block: - Scan through the iSCSI NVRAM block (while accounting + * for gaps) for the matching absolute-pf-id of the QEDI device. + */ +static struct nvm_iscsi_block * +qedi_get_nvram_block(struct qedi_ctx *qedi) +{ + int i; + u8 pf; + u32 flags; + struct nvm_iscsi_block *block; + + pf = qedi->dev_info.common.abs_pf_id; + block = &qedi->iscsi_cfg->block[0]; + for (i = 0; i < NUM_OF_ISCSI_PF_SUPPORTED; i++, block++) { + flags = ((block->id) & NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK) >> + NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET; + if (flags & (NVM_ISCSI_CFG_BLK_CTRL_FLAG_IS_NOT_EMPTY | + NVM_ISCSI_CFG_BLK_CTRL_FLAG_PF_MAPPED) && + (pf == (block->id & NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_MASK) + >> NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_OFFSET)) + return block; + } + return NULL; +} + +static ssize_t qedi_show_boot_eth_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + struct nvm_iscsi_initiator *initiator; + char *str = buf; + int rc = 1; + u32 ipv6_en, dhcp_en, ip_len; + struct nvm_iscsi_block *block; + char *fmt, *ip, *sub, *gw; + + block = qedi_get_nvram_block(qedi); + if (!block) + return 0; + + initiator = &block->initiator; + ipv6_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_IPV6_ENABLED; + dhcp_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_DHCP_TCPIP_CONFIG_ENABLED; + /* Static IP assignments. */ + fmt = ipv6_en ? "%pI6\n" : "%pI4\n"; + ip = ipv6_en ? initiator->ipv6.addr.byte : initiator->ipv4.addr.byte; + ip_len = ipv6_en ? IPV6_LEN : IPV4_LEN; + sub = ipv6_en ? initiator->ipv6.subnet_mask.byte : + initiator->ipv4.subnet_mask.byte; + gw = ipv6_en ? initiator->ipv6.gateway.byte : + initiator->ipv4.gateway.byte; + /* DHCP IP adjustments. */ + fmt = dhcp_en ? "%s\n" : fmt; + if (dhcp_en) { + ip = ipv6_en ? "0::0" : "0.0.0.0"; + sub = ip; + gw = ip; + ip_len = ipv6_en ? 5 : 8; + } + + switch (type) { + case ISCSI_BOOT_ETH_IP_ADDR: + rc = snprintf(str, ip_len, fmt, ip); + break; + case ISCSI_BOOT_ETH_SUBNET_MASK: + rc = snprintf(str, ip_len, fmt, sub); + break; + case ISCSI_BOOT_ETH_GATEWAY: + rc = snprintf(str, ip_len, fmt, gw); + break; + case ISCSI_BOOT_ETH_FLAGS: + rc = snprintf(str, 3, "%hhd\n", + SYSFS_FLAG_FW_SEL_BOOT); + break; + case ISCSI_BOOT_ETH_INDEX: + rc = snprintf(str, 3, "0\n"); + break; + case ISCSI_BOOT_ETH_MAC: + rc = sysfs_format_mac(str, qedi->mac, ETH_ALEN); + break; + case ISCSI_BOOT_ETH_VLAN: + rc = snprintf(str, 12, "%d\n", + GET_FIELD2(initiator->generic_cont0, + NVM_ISCSI_CFG_INITIATOR_VLAN)); + break; + case ISCSI_BOOT_ETH_ORIGIN: + if (dhcp_en) + rc = snprintf(str, 3, "3\n"); + break; + default: + rc = 0; + break; + } + + return rc; +} + +static umode_t qedi_eth_get_attr_visibility(void *data, int type) +{ + int rc = 1; + + switch (type) { + case ISCSI_BOOT_ETH_FLAGS: + case ISCSI_BOOT_ETH_MAC: + case ISCSI_BOOT_ETH_INDEX: + case ISCSI_BOOT_ETH_IP_ADDR: + case ISCSI_BOOT_ETH_SUBNET_MASK: + case ISCSI_BOOT_ETH_GATEWAY: + case ISCSI_BOOT_ETH_ORIGIN: + case ISCSI_BOOT_ETH_VLAN: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static ssize_t qedi_show_boot_ini_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + struct nvm_iscsi_initiator *initiator; + char *str = buf; + int rc; + struct nvm_iscsi_block *block; + + block = qedi_get_nvram_block(qedi); + if (!block) + return 0; + + initiator = &block->initiator; + + switch (type) { + case ISCSI_BOOT_INI_INITIATOR_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + initiator->initiator_name.byte); + break; + default: + rc = 0; + break; + } + return rc; +} + +static umode_t qedi_ini_get_attr_visibility(void *data, int type) +{ + int rc; + + switch (type) { + case ISCSI_BOOT_INI_INITIATOR_NAME: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static ssize_t +qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type, + char *buf, enum qedi_nvm_tgts idx) +{ + char *str = buf; + int rc = 1; + u32 ctrl_flags, ipv6_en, chap_en, mchap_en, ip_len; + struct nvm_iscsi_block *block; + char *chap_name, *chap_secret; + char *mchap_name, *mchap_secret; + + block = qedi_get_nvram_block(qedi); + if (!block) + goto exit_show_tgt_info; + + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_EVT, + "Port:%d, tgt_idx:%d\n", + GET_FIELD2(block->id, NVM_ISCSI_CFG_BLK_MAPPED_PF_ID), idx); + + ctrl_flags = block->target[idx].ctrl_flags & + NVM_ISCSI_CFG_TARGET_ENABLED; + + if (!ctrl_flags) { + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_EVT, + "Target disabled\n"); + goto exit_show_tgt_info; + } + + ipv6_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_IPV6_ENABLED; + ip_len = ipv6_en ? IPV6_LEN : IPV4_LEN; + chap_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_CHAP_ENABLED; + chap_name = chap_en ? block->initiator.chap_name.byte : NULL; + chap_secret = chap_en ? block->initiator.chap_password.byte : NULL; + + mchap_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_CHAP_MUTUAL_ENABLED; + mchap_name = mchap_en ? block->target[idx].chap_name.byte : NULL; + mchap_secret = mchap_en ? block->target[idx].chap_password.byte : NULL; + + switch (type) { + case ISCSI_BOOT_TGT_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + block->target[idx].target_name.byte); + break; + case ISCSI_BOOT_TGT_IP_ADDR: + if (ipv6_en) + rc = snprintf(str, ip_len, "%pI6\n", + block->target[idx].ipv6_addr.byte); + else + rc = snprintf(str, ip_len, "%pI4\n", + block->target[idx].ipv4_addr.byte); + break; + case ISCSI_BOOT_TGT_PORT: + rc = snprintf(str, 12, "%d\n", + GET_FIELD2(block->target[idx].generic_cont0, + NVM_ISCSI_CFG_TARGET_TCP_PORT)); + break; + case ISCSI_BOOT_TGT_LUN: + rc = snprintf(str, 22, "%.*d\n", + block->target[idx].lun.value[1], + block->target[idx].lun.value[0]); + break; + case ISCSI_BOOT_TGT_CHAP_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", + chap_name); + break; + case ISCSI_BOOT_TGT_CHAP_SECRET: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", + chap_secret); + break; + case ISCSI_BOOT_TGT_REV_CHAP_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", + mchap_name); + break; + case ISCSI_BOOT_TGT_REV_CHAP_SECRET: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", + mchap_secret); + break; + case ISCSI_BOOT_TGT_FLAGS: + rc = snprintf(str, 3, "%hhd\n", SYSFS_FLAG_FW_SEL_BOOT); + break; + case ISCSI_BOOT_TGT_NIC_ASSOC: + rc = snprintf(str, 3, "0\n"); + break; + default: + rc = 0; + break; + } + +exit_show_tgt_info: + return rc; +} + +static ssize_t qedi_show_boot_tgt_pri_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + + return qedi_show_boot_tgt_info(qedi, type, buf, QEDI_NVM_TGT_PRI); +} + +static ssize_t qedi_show_boot_tgt_sec_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + + return qedi_show_boot_tgt_info(qedi, type, buf, QEDI_NVM_TGT_SEC); +} + +static umode_t qedi_tgt_get_attr_visibility(void *data, int type) +{ + int rc; + + switch (type) { + case ISCSI_BOOT_TGT_NAME: + case ISCSI_BOOT_TGT_IP_ADDR: + case ISCSI_BOOT_TGT_PORT: + case ISCSI_BOOT_TGT_LUN: + case ISCSI_BOOT_TGT_CHAP_NAME: + case ISCSI_BOOT_TGT_CHAP_SECRET: + case ISCSI_BOOT_TGT_REV_CHAP_NAME: + case ISCSI_BOOT_TGT_REV_CHAP_SECRET: + case ISCSI_BOOT_TGT_NIC_ASSOC: + case ISCSI_BOOT_TGT_FLAGS: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static void qedi_boot_release(void *data) +{ + struct qedi_ctx *qedi = data; + + scsi_host_put(qedi->shost); +} + +static int qedi_get_boot_info(struct qedi_ctx *qedi) +{ + int ret = 1; + u16 len; + + len = sizeof(struct nvm_iscsi_cfg); + + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "Get NVM iSCSI CFG image\n"); + ret = qedi_ops->common->nvm_get_image(qedi->cdev, + QED_NVM_IMAGE_ISCSI_CFG, + (char *)qedi->iscsi_cfg, len); + if (ret) + QEDI_ERR(&qedi->dbg_ctx, + "Could not get NVM image. ret = %d\n", ret); + + return ret; +} + +static int qedi_setup_boot_info(struct qedi_ctx *qedi) +{ + struct iscsi_boot_kobj *boot_kobj; + + if (qedi_get_boot_info(qedi)) + return -EPERM; + + qedi->boot_kset = iscsi_boot_create_host_kset(qedi->shost->host_no); + if (!qedi->boot_kset) + goto kset_free; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_target(qedi->boot_kset, 0, qedi, + qedi_show_boot_tgt_pri_info, + qedi_tgt_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_target(qedi->boot_kset, 1, qedi, + qedi_show_boot_tgt_sec_info, + qedi_tgt_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_initiator(qedi->boot_kset, 0, qedi, + qedi_show_boot_ini_info, + qedi_ini_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_ethernet(qedi->boot_kset, 0, qedi, + qedi_show_boot_eth_info, + qedi_eth_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + return 0; + +put_host: + scsi_host_put(qedi->shost); +kset_free: + iscsi_boot_destroy_kset(qedi->boot_kset); + return -ENOMEM; +} + static void __qedi_remove(struct pci_dev *pdev, int mode) { struct qedi_ctx *qedi = pci_get_drvdata(pdev); @@ -1724,6 +2136,9 @@ static void __qedi_remove(struct pci_dev *pdev, int mode) qedi->ll2_recv_thread = NULL; } qedi_ll2_free_skbs(qedi); + + if (qedi->boot_kset) + iscsi_boot_destroy_kset(qedi->boot_kset); } } @@ -1967,6 +2382,10 @@ static int __qedi_probe(struct pci_dev *pdev, int mode) /* F/w needs 1st task context memory entry for performance */ set_bit(QEDI_RESERVE_TASK_ID, qedi->task_idx_map); atomic_set(&qedi->num_offloads, 0); + + if (qedi_setup_boot_info(qedi)) + QEDI_ERR(&qedi->dbg_ctx, + "No iSCSI boot target configured\n"); } return 0; diff --git a/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h b/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h new file mode 100644 index 000000000000..df39b69b366d --- /dev/null +++ b/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h @@ -0,0 +1,210 @@ +/* + * QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef NVM_ISCSI_CFG_H +#define NVM_ISCSI_CFG_H + +#define NUM_OF_ISCSI_TARGET_PER_PF 4 /* Defined as per the + * ISCSI IBFT constraint + */ +#define NUM_OF_ISCSI_PF_SUPPORTED 4 /* One PF per Port - + * assuming 4 port card + */ + +#define NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN 256 + +union nvm_iscsi_dhcp_vendor_id { + u32 value[NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_IPV4_ADDR_BYTE_LEN 4 +union nvm_iscsi_ipv4_addr { + u32 addr; + u8 byte[NVM_ISCSI_IPV4_ADDR_BYTE_LEN]; +}; + +#define NVM_ISCSI_IPV6_ADDR_BYTE_LEN 16 +union nvm_iscsi_ipv6_addr { + u32 addr[4]; + u8 byte[NVM_ISCSI_IPV6_ADDR_BYTE_LEN]; +}; + +struct nvm_iscsi_initiator_ipv4 { + union nvm_iscsi_ipv4_addr addr; /* 0x0 */ + union nvm_iscsi_ipv4_addr subnet_mask; /* 0x4 */ + union nvm_iscsi_ipv4_addr gateway; /* 0x8 */ + union nvm_iscsi_ipv4_addr primary_dns; /* 0xC */ + union nvm_iscsi_ipv4_addr secondary_dns; /* 0x10 */ + union nvm_iscsi_ipv4_addr dhcp_addr; /* 0x14 */ + + union nvm_iscsi_ipv4_addr isns_server; /* 0x18 */ + union nvm_iscsi_ipv4_addr slp_server; /* 0x1C */ + union nvm_iscsi_ipv4_addr primay_radius_server; /* 0x20 */ + union nvm_iscsi_ipv4_addr secondary_radius_server; /* 0x24 */ + + union nvm_iscsi_ipv4_addr rsvd[4]; /* 0x28 */ +}; + +struct nvm_iscsi_initiator_ipv6 { + union nvm_iscsi_ipv6_addr addr; /* 0x0 */ + union nvm_iscsi_ipv6_addr subnet_mask; /* 0x10 */ + union nvm_iscsi_ipv6_addr gateway; /* 0x20 */ + union nvm_iscsi_ipv6_addr primary_dns; /* 0x30 */ + union nvm_iscsi_ipv6_addr secondary_dns; /* 0x40 */ + union nvm_iscsi_ipv6_addr dhcp_addr; /* 0x50 */ + + union nvm_iscsi_ipv6_addr isns_server; /* 0x60 */ + union nvm_iscsi_ipv6_addr slp_server; /* 0x70 */ + union nvm_iscsi_ipv6_addr primay_radius_server; /* 0x80 */ + union nvm_iscsi_ipv6_addr secondary_radius_server; /* 0x90 */ + + union nvm_iscsi_ipv6_addr rsvd[3]; /* 0xA0 */ + + u32 config; /* 0xD0 */ +#define NVM_ISCSI_CFG_INITIATOR_IPV6_SUBNET_MASK_PREFIX_MASK 0x000000FF +#define NVM_ISCSI_CFG_INITIATOR_IPV6_SUBNET_MASK_PREFIX_OFFSET 0 + + u32 rsvd_1[3]; +}; + +#define NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN 256 +union nvm_iscsi_name { + u32 value[NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN 256 +union nvm_iscsi_chap_name { + u32 value[NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN 16 /* md5 need per RFC1996 + * is 16 octets + */ +union nvm_iscsi_chap_password { + u32 value[NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN]; +}; + +union nvm_iscsi_lun { + u8 byte[8]; + u32 value[2]; +}; + +struct nvm_iscsi_generic { + u32 ctrl_flags; /* 0x0 */ +#define NVM_ISCSI_CFG_GEN_CHAP_ENABLED BIT(0) +#define NVM_ISCSI_CFG_GEN_DHCP_TCPIP_CONFIG_ENABLED BIT(1) +#define NVM_ISCSI_CFG_GEN_DHCP_ISCSI_CONFIG_ENABLED BIT(2) +#define NVM_ISCSI_CFG_GEN_IPV6_ENABLED BIT(3) +#define NVM_ISCSI_CFG_GEN_IPV4_FALLBACK_ENABLED BIT(4) +#define NVM_ISCSI_CFG_GEN_ISNS_WORLD_LOGIN BIT(5) +#define NVM_ISCSI_CFG_GEN_ISNS_SELECTIVE_LOGIN BIT(6) +#define NVM_ISCSI_CFG_GEN_ADDR_REDIRECT_ENABLED BIT(7) +#define NVM_ISCSI_CFG_GEN_CHAP_MUTUAL_ENABLED BIT(8) + + u32 timeout; /* 0x4 */ +#define NVM_ISCSI_CFG_GEN_DHCP_REQUEST_TIMEOUT_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_GEN_DHCP_REQUEST_TIMEOUT_OFFSET 0 +#define NVM_ISCSI_CFG_GEN_PORT_LOGIN_TIMEOUT_MASK 0xFFFF0000 +#define NVM_ISCSI_CFG_GEN_PORT_LOGIN_TIMEOUT_OFFSET 16 + + union nvm_iscsi_dhcp_vendor_id dhcp_vendor_id; /* 0x8 */ + u32 rsvd[62]; /* 0x108 */ +}; + +struct nvm_iscsi_initiator { + struct nvm_iscsi_initiator_ipv4 ipv4; /* 0x0 */ + struct nvm_iscsi_initiator_ipv6 ipv6; /* 0x38 */ + + union nvm_iscsi_name initiator_name; /* 0x118 */ + union nvm_iscsi_chap_name chap_name; /* 0x218 */ + union nvm_iscsi_chap_password chap_password; /* 0x318 */ + + u32 generic_cont0; /* 0x398 */ +#define NVM_ISCSI_CFG_INITIATOR_VLAN_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_INITIATOR_VLAN_OFFSET 0 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_MASK 0x00030000 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_OFFSET 16 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_4 1 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_6 2 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_4_AND_6 3 + + u32 ctrl_flags; +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_PRIORITY_V6 BIT(0) +#define NVM_ISCSI_CFG_INITIATOR_VLAN_ENABLED BIT(1) + + u32 rsvd[116]; /* 0x32C */ +}; + +struct nvm_iscsi_target { + u32 ctrl_flags; /* 0x0 */ +#define NVM_ISCSI_CFG_TARGET_ENABLED BIT(0) +#define NVM_ISCSI_CFG_BOOT_TIME_LOGIN_STATUS BIT(1) + + u32 generic_cont0; /* 0x4 */ +#define NVM_ISCSI_CFG_TARGET_TCP_PORT_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_TARGET_TCP_PORT_OFFSET 0 + + u32 ip_ver; +#define NVM_ISCSI_CFG_IPv4 4 +#define NVM_ISCSI_CFG_IPv6 6 + + u32 rsvd_1[7]; /* 0x24 */ + union nvm_iscsi_ipv4_addr ipv4_addr; /* 0x28 */ + union nvm_iscsi_ipv6_addr ipv6_addr; /* 0x2C */ + union nvm_iscsi_lun lun; /* 0x3C */ + + union nvm_iscsi_name target_name; /* 0x44 */ + union nvm_iscsi_chap_name chap_name; /* 0x144 */ + union nvm_iscsi_chap_password chap_password; /* 0x244 */ + + u32 rsvd_2[107]; /* 0x2C4 */ +}; + +struct nvm_iscsi_block { + u32 id; /* 0x0 */ +#define NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_MASK 0x0000000F +#define NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_OFFSET 0 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK 0x00000FF0 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET 4 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_IS_NOT_EMPTY BIT(0) +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_PF_MAPPED BIT(1) + + u32 rsvd_1[5]; /* 0x4 */ + + struct nvm_iscsi_generic generic; /* 0x18 */ + struct nvm_iscsi_initiator initiator; /* 0x218 */ + struct nvm_iscsi_target target[NUM_OF_ISCSI_TARGET_PER_PF]; + /* 0x718 */ + + u32 rsvd_2[58]; /* 0x1718 */ + /* total size - 0x1800 - 6K block */ +}; + +struct nvm_iscsi_cfg { + u32 id; /* 0x0 */ +#define NVM_ISCSI_CFG_BLK_VERSION_MINOR_MASK 0x000000FF +#define NVM_ISCSI_CFG_BLK_VERSION_MAJOR_MASK 0x0000FF00 +#define NVM_ISCSI_CFG_BLK_SIGNATURE_MASK 0xFFFF0000 +#define NVM_ISCSI_CFG_BLK_SIGNATURE 0x49430000 /* IC - Iscsi + * Config + */ + +#define NVM_ISCSI_CFG_BLK_VERSION_MAJOR 0 +#define NVM_ISCSI_CFG_BLK_VERSION_MINOR 10 +#define NVM_ISCSI_CFG_BLK_VERSION ((NVM_ISCSI_CFG_BLK_VERSION_MAJOR << 8) | \ + NVM_ISCSI_CFG_BLK_VERSION_MINOR) + + struct nvm_iscsi_block block[NUM_OF_ISCSI_PF_SUPPORTED]; /* 0x4 */ +}; + +#endif diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index c2dc836dc484..e101cd3043b9 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3727,7 +3727,7 @@ static struct qla_tgt_cmd *qlt_ctio_to_cmd(struct scsi_qla_host *vha, h &= QLA_CMD_HANDLE_MASK; if (h != QLA_TGT_NULL_HANDLE) { - if (unlikely(h > req->num_outstanding_cmds)) { + if (unlikely(h >= req->num_outstanding_cmds)) { ql_dbg(ql_dbg_tgt, vha, 0xe052, "qla_target(%d): Wrong handle %x received\n", vha->vp_idx, handle); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 21225d62b0c1..1e82d4128a84 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -758,8 +758,11 @@ static bool sg_is_valid_dxfer(sg_io_hdr_t *hp) if (hp->dxferp || hp->dxfer_len > 0) return false; return true; - case SG_DXFER_TO_DEV: case SG_DXFER_FROM_DEV: + if (hp->dxfer_len < 0) + return false; + return true; + case SG_DXFER_TO_DEV: case SG_DXFER_TO_FROM_DEV: if (!hp->dxferp || hp->dxfer_len == 0) return false; diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 8b93197daefe..9be211d68b15 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -837,6 +837,7 @@ static struct scsi_host_template virtscsi_host_template_multi = { .eh_abort_handler = virtscsi_abort, .eh_device_reset_handler = virtscsi_device_reset, .eh_timed_out = virtscsi_eh_timed_out, + .slave_alloc = virtscsi_device_alloc, .can_queue = 1024, .dma_boundary = UINT_MAX, diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 69ec23daa25e..a1e6860b6f46 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -574,7 +574,7 @@ static int load_flat_file(struct linux_binprm *bprm, MAX_SHARED_LIBS * sizeof(unsigned long), FLAT_DATA_ALIGN); - pr_debug("Allocated data+bss+stack (%ld bytes): %lx\n", + pr_debug("Allocated data+bss+stack (%u bytes): %lx\n", data_len + bss_len + stack_len, datapos); fpos = ntohl(hdr->data_start); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index e071d23f6148..ef7240ace576 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -271,6 +271,11 @@ out: if (ret < 0) err = ret; dput(last); + /* last_name no longer match cache index */ + if (fi->readdir_cache_idx >= 0) { + fi->readdir_cache_idx = -1; + fi->dir_release_count = 0; + } } return err; } diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 79dafa71effd..51f0aea70cb4 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -175,11 +175,8 @@ ext2_get_acl(struct inode *inode, int type) return acl; } -/* - * inode->i_mutex: down - */ -int -ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +static int +__ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) { int name_index; void *value = NULL; @@ -189,13 +186,6 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) switch(type) { case ACL_TYPE_ACCESS: name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (error) - return error; - inode->i_ctime = current_time(inode); - mark_inode_dirty(inode); - } break; case ACL_TYPE_DEFAULT: @@ -222,6 +212,31 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) } /* + * inode->i_mutex: down + */ +int +ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int error; + int update_mode = 0; + umode_t mode = inode->i_mode; + + if (type == ACL_TYPE_ACCESS && acl) { + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) + return error; + update_mode = 1; + } + error = __ext2_set_acl(inode, acl, type); + if (!error && update_mode) { + inode->i_mode = mode; + inode->i_ctime = current_time(inode); + mark_inode_dirty(inode); + } + return error; +} + +/* * Initialize the ACLs of a new inode. Called from ext2_new_inode. * * dir->i_mutex: down @@ -238,12 +253,12 @@ ext2_init_acl(struct inode *inode, struct inode *dir) return error; if (default_acl) { - error = ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + error = __ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); posix_acl_release(default_acl); } if (acl) { if (!error) - error = ext2_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __ext2_set_acl(inode, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); } return error; diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index a140c5e3dc54..b4b8438c42ef 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -211,7 +211,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { + if (acl && !ipage) { error = posix_acl_update_mode(inode, &inode->i_mode, &acl); if (error) return error; diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 56bbf592e487..5b876f6d3f6b 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -879,6 +879,7 @@ int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) struct inode *inode; struct f2fs_inode_info *fi; bool is_dir = (type == DIR_INODE); + unsigned long ino = 0; trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir, get_pages(sbi, is_dir ? @@ -901,8 +902,17 @@ retry: inode = igrab(&fi->vfs_inode); spin_unlock(&sbi->inode_lock[type]); if (inode) { + unsigned long cur_ino = inode->i_ino; + filemap_fdatawrite(inode->i_mapping); iput(inode); + /* We need to give cpu to another writers. */ + if (ino == cur_ino) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + cond_resched(); + } else { + ino = cur_ino; + } } else { /* * We should submit bio, since it exists several diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index a0e6d2c65a9e..2706130c261b 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1538,7 +1538,6 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) { - inode_unlock(inode); ret = -EPERM; goto unlock_out; } @@ -1549,9 +1548,8 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) { if (!capable(CAP_LINUX_IMMUTABLE)) { - inode_unlock(inode); ret = -EPERM; - goto out; + goto unlock_out; } } @@ -1564,7 +1562,6 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) f2fs_mark_inode_dirty_sync(inode, false); unlock_out: inode_unlock(inode); -out: mnt_drop_write_file(filp); return ret; } diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 9adc202fcd6f..71191d89917d 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -11,6 +11,7 @@ */ #include <linux/proc_fs.h> #include <linux/f2fs_fs.h> +#include <linux/seq_file.h> #include "f2fs.h" #include "segment.h" diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index 9b92058a1240..6bb5d7c42888 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -51,8 +51,8 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type) return acl; } -int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, - int type) +static int __hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, + int type) { int err; char *xattr_name; @@ -64,12 +64,6 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, switch (type) { case ACL_TYPE_ACCESS: xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - err = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (err) - return err; - } - err = 0; break; case ACL_TYPE_DEFAULT: @@ -105,6 +99,18 @@ end_set_acl: return err; } +int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int err; + + if (type == ACL_TYPE_ACCESS && acl) { + err = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (err) + return err; + } + return __hfsplus_set_posix_acl(inode, acl, type); +} + int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir) { int err = 0; @@ -122,15 +128,15 @@ int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir) return err; if (default_acl) { - err = hfsplus_set_posix_acl(inode, default_acl, - ACL_TYPE_DEFAULT); + err = __hfsplus_set_posix_acl(inode, default_acl, + ACL_TYPE_DEFAULT); posix_acl_release(default_acl); } if (acl) { if (!err) - err = hfsplus_set_posix_acl(inode, acl, - ACL_TYPE_ACCESS); + err = __hfsplus_set_posix_acl(inode, acl, + ACL_TYPE_ACCESS); posix_acl_release(acl); } return err; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 8cf898a59730..217a5e7815da 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -410,7 +410,11 @@ static int parse_options(char *options, struct iso9660_options *popt) if (match_int(&args[0], &option)) return 0; n = option; - if (n > 99) + /* + * Track numbers are supposed to be in range 1-99, the + * mount option starts indexing at 0. + */ + if (n >= 99) return 0; popt->session = n + 1; break; @@ -543,7 +547,7 @@ static unsigned int isofs_get_last_session(struct super_block *sb, s32 session) vol_desc_start=0; ms_info.addr_format=CDROM_LBA; - if(session >= 0 && session <= 99) { + if (session > 0) { struct cdrom_tocentry Te; Te.cdte_track=session; Te.cdte_format=CDROM_LBA; diff --git a/fs/mount.h b/fs/mount.h index de45d9e76748..6790767d1883 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -16,7 +16,7 @@ struct mnt_namespace { u64 event; unsigned int mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; -}; +} __randomize_layout; struct mnt_pcp { int mnt_count; @@ -69,7 +69,7 @@ struct mount { struct hlist_head mnt_pins; struct fs_pin mnt_umount; struct dentry *mnt_ex_mountpoint; -}; +} __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ diff --git a/fs/namei.c b/fs/namei.c index 88fd38d1e3e7..ddb6a7c2b3d4 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -524,7 +524,7 @@ struct nameidata { struct inode *link_inode; unsigned root_seq; int dfd; -}; +} __randomize_layout; static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) { diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index b45083c0f9ae..49b0a9e7ff18 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -720,8 +720,8 @@ static const struct rpc_version nfs_cb_version4 = { .counts = nfs4_cb_counts, }; -static const struct rpc_version *nfs_cb_version[] = { - &nfs_cb_version4, +static const struct rpc_version *nfs_cb_version[2] = { + [1] = &nfs_cb_version4, }; static const struct rpc_program cb_program; @@ -795,7 +795,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c .saddress = (struct sockaddr *) &conn->cb_saddr, .timeout = &timeparms, .program = &cb_program, - .version = 0, + .version = 1, .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET), }; struct rpc_clnt *client; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 18694598bebf..aa2b89071630 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -51,7 +51,7 @@ struct proc_dir_entry { spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ u8 namelen; char name[]; -}; +} __randomize_layout; union proc_op { int (*proc_get_link)(struct dentry *, struct path *); @@ -70,7 +70,7 @@ struct proc_inode { struct hlist_node sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; -}; +} __randomize_layout; /* * General functions @@ -279,7 +279,7 @@ struct proc_maps_private { #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif -}; +} __randomize_layout; struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode); diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 3d2256a425ee..54415f0e3d18 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -23,7 +23,8 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) struct reiserfs_transaction_handle th; size_t jcreate_blocks; int size = acl ? posix_acl_xattr_size(acl->a_count) : 0; - + int update_mode = 0; + umode_t mode = inode->i_mode; /* * Pessimism: We can't assume that anything from the xattr root up @@ -37,7 +38,16 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) error = journal_begin(&th, inode->i_sb, jcreate_blocks); reiserfs_write_unlock(inode->i_sb); if (error == 0) { + if (type == ACL_TYPE_ACCESS && acl) { + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) + goto unlock; + update_mode = 1; + } error = __reiserfs_set_acl(&th, inode, type, acl); + if (!error && update_mode) + inode->i_mode = mode; +unlock: reiserfs_write_lock(inode->i_sb); error2 = journal_end(&th); reiserfs_write_unlock(inode->i_sb); @@ -241,11 +251,6 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (error) - return error; - } break; case ACL_TYPE_DEFAULT: name = XATTR_NAME_POSIX_ACL_DEFAULT; diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 05488da3aee9..3ae9013eeaaa 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -46,7 +46,7 @@ struct linux_binprm { unsigned interp_flags; unsigned interp_data; unsigned long loader, exec; -}; +} __randomize_layout; #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) @@ -81,7 +81,7 @@ struct linux_binfmt { int (*load_shlib)(struct file *); int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ -}; +} __randomize_layout; extern void __register_binfmt(struct linux_binfmt *fmt, int insert); diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 360c082e885c..d41d40ac3efd 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -85,7 +85,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __ret = 0; \ if (cgroup_bpf_enabled && (sock_ops)->sk) { \ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ - if (sk_fullsock(__sk)) \ + if (__sk && sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ sock_ops, \ BPF_CGROUP_SOCK_OPS); \ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 621076f56251..8e5d31f6faef 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -43,6 +43,7 @@ struct bpf_reg_state { u32 min_align; u32 aux_off; u32 aux_off_align; + bool value_from_signed; }; enum bpf_stack_slot_type { diff --git a/include/linux/cdev.h b/include/linux/cdev.h index 408bc09ce497..cb28eb21e3ca 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -17,7 +17,7 @@ struct cdev { struct list_head list; dev_t dev; unsigned int count; -}; +} __randomize_layout; void cdev_init(struct cdev *, const struct file_operations *); diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index f0f6c537b64c..040dd105c3e7 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -10,14 +10,14 @@ #define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL #define DEFINE_CEPH_FEATURE(bit, incarnation, name) \ - const static uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ - const static uint64_t CEPH_FEATUREMASK_##name = \ + static const uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* this bit is ignored but still advertised by release *when* */ #define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \ - const static uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ - const static uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ + static const uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cd4bbe8242bd..bdb80c4aef6e 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -235,6 +235,7 @@ #endif /* GCC_VERSION >= 40500 */ #if GCC_VERSION >= 40600 + /* * When used with Link Time Optimization, gcc can optimize away C functions or * variables which are referenced only from assembly code. __visible tells the @@ -242,7 +243,17 @@ * this. */ #define __visible __attribute__((externally_visible)) -#endif + +/* + * RANDSTRUCT_PLUGIN wants to use an anonymous struct, but it is only + * possible since GCC 4.6. To provide as much build testing coverage + * as possible, this is used for all GCC 4.6+ builds, and not just on + * RANDSTRUCT_PLUGIN builds. + */ +#define randomized_struct_fields_start struct { +#define randomized_struct_fields_end } __randomize_layout; + +#endif /* GCC_VERSION >= 40600 */ #if GCC_VERSION >= 40900 && !defined(__CHECKER__) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 219f82f3ec1a..eca8ad75e28b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -452,6 +452,11 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s # define __no_randomize_layout #endif +#ifndef randomized_struct_fields_start +# define randomized_struct_fields_start +# define randomized_struct_fields_end +#endif + /* * Tell gcc if a function is cold. The compiler will assume any path * directly leading to the call is unlikely. diff --git a/include/linux/cred.h b/include/linux/cred.h index c728d515e5e2..099058e1178b 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -31,7 +31,7 @@ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; -}; +} __randomize_layout; /** * get_group_info - Get a reference to a group info structure @@ -145,7 +145,7 @@ struct cred { struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ struct rcu_head rcu; /* RCU deletion hook */ -}; +} __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 3f3ff4ccdc3f..aae1cdb76851 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -118,7 +118,7 @@ struct dentry { struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; -}; +} __randomize_layout; /* * dentry->d_lock spinlock nesting subclasses: diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index a5195a7d6f77..0a186c4f3981 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -55,6 +55,7 @@ struct dma_fence_cb; * of the time. * * DMA_FENCE_FLAG_SIGNALED_BIT - fence is already signaled + * DMA_FENCE_FLAG_TIMESTAMP_BIT - timestamp recorded for fence signaling * DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT - enable_signaling might have been called * DMA_FENCE_FLAG_USER_BITS - start of the unused bits, can be used by the * implementer of the fence for its own purposes. Can be used in different @@ -84,6 +85,7 @@ struct dma_fence { enum dma_fence_flag_bits { DMA_FENCE_FLAG_SIGNALED_BIT, + DMA_FENCE_FLAG_TIMESTAMP_BIT, DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, DMA_FENCE_FLAG_USER_BITS, /* must always be last member */ }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 7b5d6816542b..6e1fd5d21248 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -296,7 +296,7 @@ struct kiocb { void *private; int ki_flags; enum rw_hint ki_hint; -}; +} __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) { @@ -404,7 +404,7 @@ struct address_space { struct list_head private_list; /* ditto */ void *private_data; /* ditto */ errseq_t wb_err; -} __attribute__((aligned(sizeof(long)))); +} __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit @@ -447,7 +447,7 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -}; +} __randomize_layout; /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache @@ -666,7 +666,7 @@ struct inode { #endif void *i_private; /* fs or device private pointer */ -}; +} __randomize_layout; static inline unsigned int i_blocksize(const struct inode *node) { @@ -883,7 +883,8 @@ struct file { #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; -} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ +} __randomize_layout + __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; @@ -1020,7 +1021,7 @@ struct file_lock { int state; /* state of grant or error if -ve */ } afs; } fl_u; -}; +} __randomize_layout; struct file_lock_context { spinlock_t flc_lock; @@ -1412,7 +1413,7 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ -}; +} __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can @@ -1698,7 +1699,7 @@ struct file_operations { u64); ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, u64); -}; +} __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 0efc3e62843a..7a026240cbb1 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -12,7 +12,7 @@ struct fs_struct { int umask; int in_exec; struct path root, pwd; -}; +} __randomize_layout; extern struct kmem_cache *fs_cachep; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 5857390ac35a..6383115e9d2c 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -145,8 +145,8 @@ enum { #ifdef CONFIG_DYNAMIC_FTRACE /* The hash used to know what functions callbacks trace */ struct ftrace_ops_hash { - struct ftrace_hash *notrace_hash; - struct ftrace_hash *filter_hash; + struct ftrace_hash __rcu *notrace_hash; + struct ftrace_hash __rcu *filter_hash; struct mutex regex_lock; }; @@ -168,7 +168,7 @@ static inline void ftrace_free_init_mem(void) { } */ struct ftrace_ops { ftrace_func_t func; - struct ftrace_ops *next; + struct ftrace_ops __rcu *next; unsigned long flags; void *private; ftrace_func_t saved_func; diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 5591f055e13f..fadd579d577d 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -23,6 +23,6 @@ struct kern_ipc_perm { struct rcu_head rcu; atomic_t refcount; -} ____cacheline_aligned_in_smp; +} ____cacheline_aligned_in_smp __randomize_layout; #endif /* _LINUX_IPC_H */ diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 848e5796400e..65327ee0936b 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -61,7 +61,7 @@ struct ipc_namespace { struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct ipc_namespace init_ipc_ns; extern spinlock_t mq_lock; diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 348c6f47e4cc..8037850f3104 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -85,19 +85,18 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) k += 12; } /* Last block: affect all 32 bits of (c) */ - /* All the case statements fall through */ switch (length) { - case 12: c += (u32)k[11]<<24; - case 11: c += (u32)k[10]<<16; - case 10: c += (u32)k[9]<<8; - case 9: c += k[8]; - case 8: b += (u32)k[7]<<24; - case 7: b += (u32)k[6]<<16; - case 6: b += (u32)k[5]<<8; - case 5: b += k[4]; - case 4: a += (u32)k[3]<<24; - case 3: a += (u32)k[2]<<16; - case 2: a += (u32)k[1]<<8; + case 12: c += (u32)k[11]<<24; /* fall through */ + case 11: c += (u32)k[10]<<16; /* fall through */ + case 10: c += (u32)k[9]<<8; /* fall through */ + case 9: c += k[8]; /* fall through */ + case 8: b += (u32)k[7]<<24; /* fall through */ + case 7: b += (u32)k[6]<<16; /* fall through */ + case 6: b += (u32)k[5]<<8; /* fall through */ + case 5: b += k[4]; /* fall through */ + case 4: a += (u32)k[3]<<24; /* fall through */ + case 3: a += (u32)k[2]<<16; /* fall through */ + case 2: a += (u32)k[1]<<8; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ @@ -131,10 +130,10 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) k += 3; } - /* Handle the last 3 u32's: all the case statements fall through */ + /* Handle the last 3 u32's */ switch (length) { - case 3: c += k[2]; - case 2: b += k[1]; + case 3: c += k[2]; /* fall through */ + case 2: b += k[1]; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 8496cf64575c..9520fc3c3b9a 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -45,7 +45,7 @@ struct key_preparsed_payload { size_t datalen; /* Raw datalen */ size_t quotalen; /* Quota length for proposed payload */ time_t expiry; /* Expiry time of key */ -}; +} __randomize_layout; typedef int (*request_key_actor_t)(struct key_construction *key, const char *op, void *aux); @@ -158,7 +158,7 @@ struct key_type { /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ -}; +} __randomize_layout; extern struct key_type key_type_keyring; diff --git a/include/linux/kmod.h b/include/linux/kmod.h index c4e441e00db5..655082c88fd9 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -64,7 +64,7 @@ struct subprocess_info { int (*init)(struct subprocess_info *info, struct cred *new); void (*cleanup)(struct subprocess_info *info); void *data; -}; +} __randomize_layout; extern int call_usermodehelper(const char *path, char **argv, char **envp, int wait); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index eeab34b0f589..4d800c79475a 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -172,7 +172,7 @@ struct kset { spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; -}; +} __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); diff --git a/include/linux/llist.h b/include/linux/llist.h index d11738110a7a..1957635e6d5f 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -93,6 +93,23 @@ static inline void init_llist_head(struct llist_head *list) container_of(ptr, type, member) /** + * member_address_is_nonnull - check whether the member address is not NULL + * @ptr: the object pointer (struct type * that contains the llist_node) + * @member: the name of the llist_node within the struct. + * + * This macro is conceptually the same as + * &ptr->member != NULL + * but it works around the fact that compilers can decide that taking a member + * address is never a NULL pointer. + * + * Real objects that start at a high address and have a member at NULL are + * unlikely to exist, but such pointers may be returned e.g. by the + * container_of() macro. + */ +#define member_address_is_nonnull(ptr, member) \ + ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) + +/** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries @@ -145,7 +162,7 @@ static inline void init_llist_head(struct llist_head *list) */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ - &(pos)->member != NULL; \ + member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** @@ -167,7 +184,7 @@ static inline void init_llist_head(struct llist_head *list) */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ - &pos->member != NULL && \ + member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 7a86925ba8f3..3a90febadbe2 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1912,7 +1912,7 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ -}; +} __randomize_layout; /* * Security module hook list structure. @@ -1923,7 +1923,7 @@ struct security_hook_list { struct list_head *head; union security_list_options hook; char *lsm; -}; +} __randomize_layout; /* * Initializing a security_hook_list structure takes diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 45cdb27791a3..ff151814a02d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -342,7 +342,7 @@ struct vm_area_struct { struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; -}; +} __randomize_layout; struct core_thread { struct task_struct *task; @@ -500,7 +500,7 @@ struct mm_struct { atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; -}; +} __randomize_layout; extern struct mm_struct init_mm; diff --git a/include/linux/module.h b/include/linux/module.h index 8eb9a1e693e5..e7bdd549e527 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -45,7 +45,7 @@ struct module_kobject { struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; -}; +} __randomize_layout; struct module_attribute { struct attribute attr; @@ -475,7 +475,7 @@ struct module { ctor_fn_t *ctors; unsigned int num_ctors; #endif -} ____cacheline_aligned; +} ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif diff --git a/include/linux/mount.h b/include/linux/mount.h index 8e0352af06b7..1ce85e6fd95f 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -67,7 +67,7 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; -}; +} __randomize_layout; struct file; /* forward dec */ struct path; diff --git a/include/linux/msg.h b/include/linux/msg.h index f3f302f9c197..a001305f5a79 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -29,7 +29,7 @@ struct msg_queue { struct list_head q_messages; struct list_head q_receivers; struct list_head q_senders; -}; +} __randomize_layout; /* Helper routines for sys_msgsnd and sys_msgrcv */ extern long do_msgsnd(int msqid, long mtype, void __user *mtext, diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index a4b97be30b28..22f081065d49 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -61,8 +61,6 @@ typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); struct nf_hook_ops { - struct list_head list; - /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; @@ -160,13 +158,6 @@ int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); -int nf_register_hook(struct nf_hook_ops *reg); -void nf_unregister_hook(struct nf_hook_ops *reg); -int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); -void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); -int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); -void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); - /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ int nf_register_sockopt(struct nf_sockopt_ops *reg); diff --git a/include/linux/path.h b/include/linux/path.h index d1372186f431..cde895cc4af4 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -7,7 +7,7 @@ struct vfsmount; struct path { struct vfsmount *mnt; struct dentry *dentry; -}; +} __randomize_layout; extern void path_get(const struct path *); extern void path_put(const struct path *); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index c2a989dee876..b09136f88cf4 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -52,7 +52,7 @@ struct pid_namespace { int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; -}; +} __randomize_layout; extern struct pid_namespace init_pid_ns; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 58ab28d81fc2..06844b54dfc1 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -21,7 +21,7 @@ struct proc_ns_operations { int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); -}; +} __randomize_layout; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; diff --git a/include/linux/sched.h b/include/linux/sched.h index 2ba9ec93423f..8337e2db0bb2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -426,7 +426,7 @@ struct sched_rt_entity { /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif -}; +} __randomize_layout; struct sched_dl_entity { struct rb_node rb_node; @@ -526,6 +526,13 @@ struct task_struct { #endif /* -1 unrunnable, 0 runnable, >0 stopped: */ volatile long state; + + /* + * This begins the randomizable portion of task_struct. Only + * scheduling-critical items should be added above here. + */ + randomized_struct_fields_start + void *stack; atomic_t usage; /* Per task flags (PF_*), defined further below: */ @@ -1079,6 +1086,13 @@ struct task_struct { /* Used by LSM modules for access restriction: */ void *security; #endif + + /* + * New fields for task_struct should be added above here, so that + * they are included in the randomized portion of task_struct. + */ + randomized_struct_fields_end + /* CPU-specific state of this task: */ struct thread_struct thread; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index c06d63b3a583..2a0dd40b15db 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -222,7 +222,7 @@ struct signal_struct { struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) */ -}; +} __randomize_layout; /* * Bits in flags field of signal_struct. diff --git a/include/linux/sem.h b/include/linux/sem.h index be5cf2ea14ad..de2deb8676bd 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -41,7 +41,7 @@ struct sem_array { unsigned int use_global_lock;/* >0: global lock required */ struct sem sems[]; -}; +} __randomize_layout; #ifdef CONFIG_SYSVIPC diff --git a/include/linux/shm.h b/include/linux/shm.h index 04e881829625..0fb7061ec54c 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -22,7 +22,7 @@ struct shmid_kernel /* private to the kernel */ /* The task created the shm object. NULL if the task is dead. */ struct task_struct *shm_creator; struct list_head shm_clist; /* list by creator */ -}; +} __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 3a89b9ff4cdc..1d4dba490fb6 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -120,7 +120,7 @@ struct ctl_table struct ctl_table_poll *poll; void *extra1; void *extra2; -}; +} __randomize_layout; struct ctl_node { struct rb_node node; diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index f73cedfa2e0b..536c80ff7ad9 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -338,7 +338,7 @@ enum { struct trace_event_file { struct list_head list; struct trace_event_call *event_call; - struct event_filter *filter; + struct event_filter __rcu *filter; struct dentry *dir; struct trace_array *tr; struct trace_subsystem_dir *system; diff --git a/include/linux/tty.h b/include/linux/tty.h index 69464c0d8068..79c30daf46a9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -332,7 +332,7 @@ struct tty_struct { /* If the tty has a pending do_SAK, queue it here - akpm */ struct work_struct SAK_work; struct tty_port *port; -}; +} __randomize_layout; /* Each of a tty's open files has private_data pointing to tty_file_private */ struct tty_file_private { diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index b742b5e47cc2..00b2213f6a35 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -291,7 +291,7 @@ struct tty_operations { void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif const struct file_operations *proc_fops; -}; +} __randomize_layout; struct tty_driver { int magic; /* magic number for this structure */ @@ -325,7 +325,7 @@ struct tty_driver { const struct tty_operations *ops; struct list_head tty_drivers; -}; +} __randomize_layout; extern struct list_head tty_drivers; diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 021f7a88f52c..1a59699cf82a 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -83,6 +83,7 @@ /* Driver flags */ #define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ #define CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE 0x04 /* Avoid altsetting toggle during init */ +#define CDC_NCM_FLAG_RESET_NTB16 0x08 /* set NDP16 one more time after altsetting switch */ #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 32354b4b4b2b..b3575ce29148 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -66,7 +66,7 @@ struct user_namespace { #endif struct ucounts *ucounts; int ucount_max[UCOUNT_COUNTS]; -}; +} __randomize_layout; struct ucounts { struct hlist_node node; diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 60f0bb83b313..da826ed059cf 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -26,7 +26,7 @@ struct uts_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct uts_namespace init_uts_ns; #ifdef CONFIG_UTS_NS diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 678e4d6fa317..53b1a2cca421 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -37,7 +37,7 @@ struct unix_skb_parms { u32 secid; /* Security ID */ #endif u32 consumed; -}; +} __randomize_layout; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index afc39e3a3f7c..9816df225af3 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -156,7 +156,7 @@ struct neighbour { struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; -}; +} __randomize_layout; struct neigh_ops { int family; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 31a2b51bef2c..1c401bd4c2e0 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -148,7 +148,7 @@ struct net { #endif struct sock *diag_nlsk; atomic_t fnhe_genid; -}; +} __randomize_layout; #include <linux/seq_file_net.h> diff --git a/include/net/netlink.h b/include/net/netlink.h index 01709172b3d3..ef8e6c3a80a6 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -98,8 +98,8 @@ * nla_put_u8(skb, type, value) add u8 attribute to skb * nla_put_u16(skb, type, value) add u16 attribute to skb * nla_put_u32(skb, type, value) add u32 attribute to skb - * nla_put_u64_64bits(skb, type, - * value, padattr) add u64 attribute to skb + * nla_put_u64_64bit(skb, type, + * value, padattr) add u64 attribute to skb * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a9519a06a23b..980807d7506f 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -469,6 +469,8 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member) #define _sctp_walk_params(pos, chunk, end, member)\ for (pos.v = chunk->member;\ + (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <\ + (void *)chunk + end) &&\ pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\ ntohs(pos.p->length) >= sizeof(struct sctp_paramhdr);\ pos.v += SCTP_PAD4(ntohs(pos.p->length))) @@ -479,6 +481,8 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length)) #define _sctp_walk_errors(err, chunk_hdr, end)\ for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \ sizeof(struct sctp_chunkhdr));\ + ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <\ + (void *)chunk_hdr + end) &&\ (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\ ntohs(err->length) >= sizeof(sctp_errhdr_t); \ err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length)))) diff --git a/include/net/sock.h b/include/net/sock.h index f69c8c2782df..7c0632c7e870 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1128,7 +1128,7 @@ struct proto { atomic_t socks; #endif int (*diag_destroy)(struct sock *sk, int err); -}; +} __randomize_layout; int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); diff --git a/kernel/audit.c b/kernel/audit.c index 833267bbd80b..6dd556931739 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -641,6 +641,7 @@ static int auditd_send_unicast_skb(struct sk_buff *skb) ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); + kfree_skb(skb); rc = -ECONNREFUSED; goto err; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6a86723c5b64..af9e84a4944e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -504,6 +504,7 @@ static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno) { regs[regno].min_value = BPF_REGISTER_MIN_RANGE; regs[regno].max_value = BPF_REGISTER_MAX_RANGE; + regs[regno].value_from_signed = false; regs[regno].min_align = 0; } @@ -777,12 +778,13 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, return -EACCES; } -static bool is_pointer_value(struct bpf_verifier_env *env, int regno) +static bool __is_pointer_value(bool allow_ptr_leaks, + const struct bpf_reg_state *reg) { - if (env->allow_ptr_leaks) + if (allow_ptr_leaks) return false; - switch (env->cur_state.regs[regno].type) { + switch (reg->type) { case UNKNOWN_VALUE: case CONST_IMM: return false; @@ -791,6 +793,11 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) } } +static bool is_pointer_value(struct bpf_verifier_env *env, int regno) +{ + return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]); +} + static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, int off, int size, bool strict) { @@ -1832,10 +1839,24 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, dst_align = dst_reg->min_align; /* We don't know anything about what was done to this register, mark it - * as unknown. + * as unknown. Also, if both derived bounds came from signed/unsigned + * mixed compares and one side is unbounded, we cannot really do anything + * with them as boundaries cannot be trusted. Thus, arithmetic of two + * regs of such kind will get invalidated bounds on the dst side. */ - if (min_val == BPF_REGISTER_MIN_RANGE && - max_val == BPF_REGISTER_MAX_RANGE) { + if ((min_val == BPF_REGISTER_MIN_RANGE && + max_val == BPF_REGISTER_MAX_RANGE) || + (BPF_SRC(insn->code) == BPF_X && + ((min_val != BPF_REGISTER_MIN_RANGE && + max_val == BPF_REGISTER_MAX_RANGE) || + (min_val == BPF_REGISTER_MIN_RANGE && + max_val != BPF_REGISTER_MAX_RANGE) || + (dst_reg->min_value != BPF_REGISTER_MIN_RANGE && + dst_reg->max_value == BPF_REGISTER_MAX_RANGE) || + (dst_reg->min_value == BPF_REGISTER_MIN_RANGE && + dst_reg->max_value != BPF_REGISTER_MAX_RANGE)) && + regs[insn->dst_reg].value_from_signed != + regs[insn->src_reg].value_from_signed)) { reset_reg_range_values(regs, insn->dst_reg); return; } @@ -2023,6 +2044,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) regs[insn->dst_reg].max_value = insn->imm; regs[insn->dst_reg].min_value = insn->imm; regs[insn->dst_reg].min_align = calc_align(insn->imm); + regs[insn->dst_reg].value_from_signed = false; } } else if (opcode > BPF_END) { @@ -2198,40 +2220,63 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u8 opcode) { + bool value_from_signed = true; + bool is_range = true; + switch (opcode) { case BPF_JEQ: /* If this is false then we know nothing Jon Snow, but if it is * true then we know for sure. */ true_reg->max_value = true_reg->min_value = val; + is_range = false; break; case BPF_JNE: /* If this is true we know nothing Jon Snow, but if it is false * we know the value for sure; */ false_reg->max_value = false_reg->min_value = val; + is_range = false; break; case BPF_JGT: - /* Unsigned comparison, the minimum value is 0. */ - false_reg->min_value = 0; + value_from_signed = false; /* fallthrough */ case BPF_JSGT: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGT) { + /* Unsigned comparison, the minimum value is 0. */ + false_reg->min_value = 0; + } /* If this is false then we know the maximum val is val, * otherwise we know the min val is val+1. */ false_reg->max_value = val; + false_reg->value_from_signed = value_from_signed; true_reg->min_value = val + 1; + true_reg->value_from_signed = value_from_signed; break; case BPF_JGE: - /* Unsigned comparison, the minimum value is 0. */ - false_reg->min_value = 0; + value_from_signed = false; /* fallthrough */ case BPF_JSGE: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGE) { + /* Unsigned comparison, the minimum value is 0. */ + false_reg->min_value = 0; + } /* If this is false then we know the maximum value is val - 1, * otherwise we know the mimimum value is val. */ false_reg->max_value = val - 1; + false_reg->value_from_signed = value_from_signed; true_reg->min_value = val; + true_reg->value_from_signed = value_from_signed; break; default: break; @@ -2239,6 +2284,12 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, check_reg_overflow(false_reg); check_reg_overflow(true_reg); + if (is_range) { + if (__is_pointer_value(false, false_reg)) + reset_reg_range_values(false_reg, 0); + if (__is_pointer_value(false, true_reg)) + reset_reg_range_values(true_reg, 0); + } } /* Same as above, but for the case that dst_reg is a CONST_IMM reg and src_reg @@ -2248,41 +2299,64 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u8 opcode) { + bool value_from_signed = true; + bool is_range = true; + switch (opcode) { case BPF_JEQ: /* If this is false then we know nothing Jon Snow, but if it is * true then we know for sure. */ true_reg->max_value = true_reg->min_value = val; + is_range = false; break; case BPF_JNE: /* If this is true we know nothing Jon Snow, but if it is false * we know the value for sure; */ false_reg->max_value = false_reg->min_value = val; + is_range = false; break; case BPF_JGT: - /* Unsigned comparison, the minimum value is 0. */ - true_reg->min_value = 0; + value_from_signed = false; /* fallthrough */ case BPF_JSGT: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGT) { + /* Unsigned comparison, the minimum value is 0. */ + true_reg->min_value = 0; + } /* * If this is false, then the val is <= the register, if it is * true the register <= to the val. */ false_reg->min_value = val; + false_reg->value_from_signed = value_from_signed; true_reg->max_value = val - 1; + true_reg->value_from_signed = value_from_signed; break; case BPF_JGE: - /* Unsigned comparison, the minimum value is 0. */ - true_reg->min_value = 0; + value_from_signed = false; /* fallthrough */ case BPF_JSGE: + if (true_reg->value_from_signed != value_from_signed) + reset_reg_range_values(true_reg, 0); + if (false_reg->value_from_signed != value_from_signed) + reset_reg_range_values(false_reg, 0); + if (opcode == BPF_JGE) { + /* Unsigned comparison, the minimum value is 0. */ + true_reg->min_value = 0; + } /* If this is false then constant < register, if it is true then * the register < constant. */ false_reg->min_value = val + 1; + false_reg->value_from_signed = value_from_signed; true_reg->max_value = val; + true_reg->value_from_signed = value_from_signed; break; default: break; @@ -2290,6 +2364,12 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, check_reg_overflow(false_reg); check_reg_overflow(true_reg); + if (is_range) { + if (__is_pointer_value(false, false_reg)) + reset_reg_range_values(false_reg, 0); + if (__is_pointer_value(false, true_reg)) + reset_reg_range_values(true_reg, 0); + } } static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, diff --git a/kernel/cpu.c b/kernel/cpu.c index ab860453841d..eee033134262 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -279,7 +279,8 @@ static int bringup_wait_for_ap(unsigned int cpu) /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_completion(&st->done); - BUG_ON(!cpu_online(cpu)); + if (WARN_ON_ONCE((!cpu_online(cpu)))) + return -ECANCELED; /* Unpark the stopper thread and the hotplug thread of the target cpu */ stop_machine_unpark(cpu); diff --git a/kernel/events/core.c b/kernel/events/core.c index 1538df9b2b65..426c2ffba16d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1452,6 +1452,13 @@ static enum event_type_t get_event_type(struct perf_event *event) lockdep_assert_held(&ctx->lock); + /* + * It's 'group type', really, because if our group leader is + * pinned, so are we. + */ + if (event->group_leader != event) + event = event->group_leader; + event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE; if (!ctx->task) event_type |= EVENT_CPU; @@ -4378,7 +4385,9 @@ EXPORT_SYMBOL_GPL(perf_event_read_value); static int __perf_read_group_add(struct perf_event *leader, u64 read_format, u64 *values) { + struct perf_event_context *ctx = leader->ctx; struct perf_event *sub; + unsigned long flags; int n = 1; /* skip @nr */ int ret; @@ -4408,12 +4417,15 @@ static int __perf_read_group_add(struct perf_event *leader, if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); + raw_spin_lock_irqsave(&ctx->lock, flags); + list_for_each_entry(sub, &leader->sibling_list, group_entry) { values[n++] += perf_event_count(sub); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); } + raw_spin_unlock_irqrestore(&ctx->lock, flags); return 0; } @@ -7321,21 +7333,6 @@ int perf_event_account_interrupt(struct perf_event *event) return __perf_event_account_interrupt(event, 1); } -static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs) -{ - /* - * Due to interrupt latency (AKA "skid"), we may enter the - * kernel before taking an overflow, even if the PMU is only - * counting user events. - * To avoid leaking information to userspace, we must always - * reject kernel samples when exclude_kernel is set. - */ - if (event->attr.exclude_kernel && !user_mode(regs)) - return false; - - return true; -} - /* * Generic event overflow handling, sampling. */ @@ -7357,12 +7354,6 @@ static int __perf_event_overflow(struct perf_event *event, ret = __perf_event_account_interrupt(event, throttle); /* - * For security, drop the skid kernel samples if necessary. - */ - if (!sample_is_allowed(event, regs)) - return ret; - - /* * XXX event_limit might not quite work as expected on inherited * events */ diff --git a/kernel/futex.c b/kernel/futex.c index c934689043b2..16dbe4c93895 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -212,7 +212,7 @@ struct futex_pi_state { atomic_t refcount; union futex_key key; -}; +} __randomize_layout; /** * struct futex_q - The hashed futex queue entry, one per waiting task @@ -246,7 +246,7 @@ struct futex_q { struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; -}; +} __randomize_layout; static const struct futex_q futex_q_init = { /* list gets initialized in queue_me()*/ diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index d171bc57e1e0..a3cc37c0c85e 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -170,21 +170,11 @@ static void irq_state_clr_disabled(struct irq_desc *desc) irqd_clear(&desc->irq_data, IRQD_IRQ_DISABLED); } -static void irq_state_set_disabled(struct irq_desc *desc) -{ - irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); -} - static void irq_state_clr_masked(struct irq_desc *desc) { irqd_clear(&desc->irq_data, IRQD_IRQ_MASKED); } -static void irq_state_set_masked(struct irq_desc *desc) -{ - irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); -} - static void irq_state_clr_started(struct irq_desc *desc) { irqd_clear(&desc->irq_data, IRQD_IRQ_STARTED); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index dbfba9933ed2..a2c48058354c 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -227,6 +227,16 @@ static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) return __irqd_to_state(d) & mask; } +static inline void irq_state_set_disabled(struct irq_desc *desc) +{ + irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); +} + +static inline void irq_state_set_masked(struct irq_desc *desc) +{ + irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); +} + #undef __irqd_to_state static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 5624b2dd6b58..1d1a5b945ab4 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1090,6 +1090,16 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. + * + * Locking rules: + * + * desc->request_mutex Provides serialization against a concurrent free_irq() + * chip_bus_lock Provides serialization for slow bus operations + * desc->lock Provides serialization against hard interrupts + * + * chip_bus_lock and desc->lock are sufficient for all other management and + * interrupt related functions. desc->request_mutex solely serializes + * request/free_irq(). */ static int __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) @@ -1167,20 +1177,35 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE) new->flags &= ~IRQF_ONESHOT; + /* + * Protects against a concurrent __free_irq() call which might wait + * for synchronize_irq() to complete without holding the optional + * chip bus lock and desc->lock. + */ mutex_lock(&desc->request_mutex); + + /* + * Acquire bus lock as the irq_request_resources() callback below + * might rely on the serialization or the magic power management + * functions which are abusing the irq_bus_lock() callback, + */ + chip_bus_lock(desc); + + /* First installed action requests resources. */ if (!desc->action) { ret = irq_request_resources(desc); if (ret) { pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", new->name, irq, desc->irq_data.chip->name); - goto out_mutex; + goto out_bus_unlock; } } - chip_bus_lock(desc); - /* * The following block of code has to be executed atomically + * protected against a concurrent interrupt and any of the other + * management calls which are not serialized via + * desc->request_mutex or the optional bus lock. */ raw_spin_lock_irqsave(&desc->lock, flags); old_ptr = &desc->action; @@ -1286,10 +1311,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) ret = __irq_set_trigger(desc, new->flags & IRQF_TRIGGER_MASK); - if (ret) { - irq_release_resources(desc); + if (ret) goto out_unlock; - } } desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ @@ -1385,12 +1408,10 @@ mismatch: out_unlock: raw_spin_unlock_irqrestore(&desc->lock, flags); - chip_bus_sync_unlock(desc); - if (!desc->action) irq_release_resources(desc); - -out_mutex: +out_bus_unlock: + chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); out_thread: @@ -1472,6 +1493,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) WARN(1, "Trying to free already-free IRQ %d\n", irq); raw_spin_unlock_irqrestore(&desc->lock, flags); chip_bus_sync_unlock(desc); + mutex_unlock(&desc->request_mutex); return NULL; } @@ -1498,6 +1520,20 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) #endif raw_spin_unlock_irqrestore(&desc->lock, flags); + /* + * Drop bus_lock here so the changes which were done in the chip + * callbacks above are synced out to the irq chips which hang + * behind a slow bus (I2C, SPI) before calling synchronize_irq(). + * + * Aside of that the bus_lock can also be taken from the threaded + * handler in irq_finalize_oneshot() which results in a deadlock + * because synchronize_irq() would wait forever for the thread to + * complete, which is blocked on the bus lock. + * + * The still held desc->request_mutex() protects against a + * concurrent request_irq() of this irq so the release of resources + * and timing data is properly serialized. + */ chip_bus_sync_unlock(desc); unregister_handler_proc(irq, action); @@ -1530,8 +1566,15 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) } } + /* Last action releases resources */ if (!desc->action) { + /* + * Reaquire bus lock as irq_release_resources() might + * require it to deallocate resources over the slow bus. + */ + chip_bus_lock(desc); irq_release_resources(desc); + chip_bus_sync_unlock(desc); irq_remove_timings(desc); } diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index cea1de0161f1..6bd9b58429cc 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -149,6 +149,8 @@ static void resume_irq(struct irq_desc *desc) /* Pretend that it got disabled ! */ desc->depth++; + irq_state_set_disabled(desc); + irq_state_set_masked(desc); resume: desc->istate &= ~IRQS_SUSPENDED; __enable_irq(desc); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 78069895032a..649dc9d3951a 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -963,7 +963,6 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, return -EDEADLK; raw_spin_lock(&task->pi_lock); - rt_mutex_adjust_prio(task); waiter->task = task; waiter->lock = lock; waiter->prio = task->prio; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 6e3ea4ac1bda..14d2dbf97c53 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -683,7 +683,7 @@ static u64 vtime_delta(struct vtime *vtime) { unsigned long long clock; - clock = sched_clock_cpu(smp_processor_id()); + clock = sched_clock(); if (clock < vtime->starttime) return 0; @@ -814,7 +814,7 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqcount_begin(&vtime->seqcount); vtime->state = VTIME_SYS; - vtime->starttime = sched_clock_cpu(smp_processor_id()); + vtime->starttime = sched_clock(); write_seqcount_end(&vtime->seqcount); } @@ -826,7 +826,7 @@ void vtime_init_idle(struct task_struct *t, int cpu) local_irq_save(flags); write_seqcount_begin(&vtime->seqcount); vtime->state = VTIME_SYS; - vtime->starttime = sched_clock_cpu(cpu); + vtime->starttime = sched_clock(); write_seqcount_end(&vtime->seqcount); local_irq_restore(flags); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index a84299f44b5d..755bd3f1a1a9 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1392,17 +1392,19 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) struct sched_dl_entity *pi_se = &p->dl; /* - * Use the scheduling parameters of the top pi-waiter - * task if we have one and its (absolute) deadline is - * smaller than our one... OTW we keep our runtime and - * deadline. + * Use the scheduling parameters of the top pi-waiter task if: + * - we have a top pi-waiter which is a SCHED_DEADLINE task AND + * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is + * smaller than our deadline OR we are a !SCHED_DEADLINE task getting + * boosted due to a SCHED_DEADLINE pi-waiter). + * Otherwise we keep our runtime and deadline. */ - if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio)) { + if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) { pi_se = &pi_task->dl; } else if (!dl_prio(p->normal_prio)) { /* * Special case in which we have a !SCHED_DEADLINE task - * that is going to be deboosted, but exceedes its + * that is going to be deboosted, but exceeds its * runtime while doing so. No point in replenishing * it, as it's going to return back to its original * scheduling class after this. diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 53f6b6401cf0..02004ae91860 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -113,7 +113,7 @@ static int ftrace_disabled __read_mostly; static DEFINE_MUTEX(ftrace_lock); -static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; @@ -169,8 +169,11 @@ int ftrace_nr_registered_ops(void) mutex_lock(&ftrace_lock); - for (ops = ftrace_ops_list; - ops != &ftrace_list_end; ops = ops->next) + for (ops = rcu_dereference_protected(ftrace_ops_list, + lockdep_is_held(&ftrace_lock)); + ops != &ftrace_list_end; + ops = rcu_dereference_protected(ops->next, + lockdep_is_held(&ftrace_lock))) cnt++; mutex_unlock(&ftrace_lock); @@ -275,10 +278,11 @@ static void update_ftrace_function(void) * If there's only one ftrace_ops registered, the ftrace_ops_list * will point to the ops we want. */ - set_function_trace_op = ftrace_ops_list; + set_function_trace_op = rcu_dereference_protected(ftrace_ops_list, + lockdep_is_held(&ftrace_lock)); /* If there's no ftrace_ops registered, just call the stub function */ - if (ftrace_ops_list == &ftrace_list_end) { + if (set_function_trace_op == &ftrace_list_end) { func = ftrace_stub; /* @@ -286,7 +290,8 @@ static void update_ftrace_function(void) * recursion safe and not dynamic and the arch supports passing ops, * then have the mcount trampoline call the function directly. */ - } else if (ftrace_ops_list->next == &ftrace_list_end) { + } else if (rcu_dereference_protected(ftrace_ops_list->next, + lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) { func = ftrace_ops_get_list_func(ftrace_ops_list); } else { @@ -348,9 +353,11 @@ int using_ftrace_ops_list_func(void) return ftrace_trace_function == ftrace_ops_list_func; } -static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) +static void add_ftrace_ops(struct ftrace_ops __rcu **list, + struct ftrace_ops *ops) { - ops->next = *list; + rcu_assign_pointer(ops->next, *list); + /* * We are entering ops into the list but another * CPU might be walking that list. We need to make sure @@ -360,7 +367,8 @@ static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) rcu_assign_pointer(*list, ops); } -static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) +static int remove_ftrace_ops(struct ftrace_ops __rcu **list, + struct ftrace_ops *ops) { struct ftrace_ops **p; @@ -368,7 +376,10 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) * If we are removing the last function, then simply point * to the ftrace_stub. */ - if (*list == ops && ops->next == &ftrace_list_end) { + if (rcu_dereference_protected(*list, + lockdep_is_held(&ftrace_lock)) == ops && + rcu_dereference_protected(ops->next, + lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) { *list = &ftrace_list_end; return 0; } @@ -1569,8 +1580,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) return 0; #endif - hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash); - hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash); + rcu_assign_pointer(hash.filter_hash, ops->func_hash->filter_hash); + rcu_assign_pointer(hash.notrace_hash, ops->func_hash->notrace_hash); if (hash_contains_ip(ip, &hash)) ret = 1; @@ -2840,7 +2851,8 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) * If there's no more ops registered with ftrace, run a * sanity check to make sure all rec flags are cleared. */ - if (ftrace_ops_list == &ftrace_list_end) { + if (rcu_dereference_protected(ftrace_ops_list, + lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) { struct ftrace_page *pg; struct dyn_ftrace *rec; @@ -6453,7 +6465,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, if (ftrace_enabled) { /* we are starting ftrace again */ - if (ftrace_ops_list != &ftrace_list_end) + if (rcu_dereference_protected(ftrace_ops_list, + lockdep_is_held(&ftrace_lock)) != &ftrace_list_end) update_ftrace_function(); ftrace_startup_sysctl(); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 4ae268e687fe..529cc50d7243 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1136,12 +1136,12 @@ static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu) for (i = 0; i < nr_pages; i++) { struct page *page; /* - * __GFP_NORETRY flag makes sure that the allocation fails - * gracefully without invoking oom-killer and the system is - * not destabilized. + * __GFP_RETRY_MAYFAIL flag makes sure that the allocation fails + * gracefully without invoking oom-killer and the system is not + * destabilized. */ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), - GFP_KERNEL | __GFP_NORETRY, + GFP_KERNEL | __GFP_RETRY_MAYFAIL, cpu_to_node(cpu)); if (!bpage) goto free_pages; @@ -1149,7 +1149,7 @@ static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu) list_add(&bpage->list, pages); page = alloc_pages_node(cpu_to_node(cpu), - GFP_KERNEL | __GFP_NORETRY, 0); + GFP_KERNEL | __GFP_RETRY_MAYFAIL, 0); if (!page) goto free_pages; bpage->page = page_address(page); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2d0ffcc49dba..42b9355033d4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7774,6 +7774,7 @@ static int instance_rmdir(const char *name) } kfree(tr->topts); + free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); kfree(tr); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6ade1c55cc3a..490ba229931d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1210,9 +1210,9 @@ struct ftrace_event_field { struct event_filter { int n_preds; /* Number assigned */ int a_preds; /* allocated */ - struct filter_pred *preds; - struct filter_pred *root; - char *filter_string; + struct filter_pred __rcu *preds; + struct filter_pred __rcu *root; + char *filter_string; }; struct event_subsystem { diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index f0f3447e8aa4..861ae2a165f4 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -34,11 +34,11 @@ static struct lock_class_key bridge_netdev_addr_lock_key; netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - const unsigned char *dest = skb->data; struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); const struct nf_br_ops *nf_ops; + const unsigned char *dest; u16 vid = 0; rcu_read_lock(); @@ -61,6 +61,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) goto out; + dest = eth_hdr(skb)->h_dest; if (is_broadcast_ether_addr(dest)) { br_flood(br, skb, BR_PKT_BROADCAST, false, true); } else if (is_multicast_ether_addr(dest)) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 013f2290bfa5..7637f58c1226 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -131,11 +131,11 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); - const unsigned char *dest = eth_hdr(skb)->h_dest; enum br_pkt_type pkt_type = BR_PKT_UNICAST; struct net_bridge_fdb_entry *dst = NULL; struct net_bridge_mdb_entry *mdst; bool local_rcv, mcast_hit = false; + const unsigned char *dest; struct net_bridge *br; u16 vid = 0; @@ -153,6 +153,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false); local_rcv = !!(br->dev->flags & IFF_PROMISC); + dest = eth_hdr(skb)->h_dest; if (is_multicast_ether_addr(dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(dest)) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 0c31035bbfee..b7cc615d42ef 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3203,8 +3203,10 @@ static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type) return NULL; data = kmem_cache_zalloc(ceph_msg_data_cache, GFP_NOFS); - if (data) - data->type = type; + if (!data) + return NULL; + + data->type = type; INIT_LIST_HEAD(&data->links); return data; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 86a9737d8e3f..901bb8221366 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -5310,7 +5310,10 @@ static int invalidate_authorizer(struct ceph_connection *con) static void osd_reencode_message(struct ceph_msg *msg) { - encode_request_finish(msg); + int type = le16_to_cpu(msg->hdr.type); + + if (type == CEPH_MSG_OSD_OP) + encode_request_finish(msg); } static int osd_sign_message(struct ceph_msg *msg) diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 864789c5974e..64ae9f89773a 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -338,7 +338,7 @@ static void crush_finalize(struct crush_map *c) static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; - int err = -EINVAL; + int err; int i, j; void **p = &pbyval; void *start = pbyval; @@ -407,7 +407,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) size = sizeof(struct crush_bucket_straw2); break; default: - err = -EINVAL; goto bad; } BUG_ON(size == 0); @@ -439,31 +438,31 @@ static struct crush_map *crush_decode(void *pbyval, void *end) err = crush_decode_uniform_bucket(p, end, (struct crush_bucket_uniform *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_LIST: err = crush_decode_list_bucket(p, end, (struct crush_bucket_list *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_TREE: err = crush_decode_tree_bucket(p, end, (struct crush_bucket_tree *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_STRAW: err = crush_decode_straw_bucket(p, end, (struct crush_bucket_straw *)b); if (err < 0) - goto bad; + goto fail; break; case CRUSH_BUCKET_STRAW2: err = crush_decode_straw2_bucket(p, end, (struct crush_bucket_straw2 *)b); if (err < 0) - goto bad; + goto fail; break; } } @@ -474,7 +473,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) u32 yes; struct crush_rule *r; - err = -EINVAL; ceph_decode_32_safe(p, end, yes, bad); if (!yes) { dout("crush_decode NO rule %d off %x %p to %p\n", @@ -489,7 +487,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) /* len */ ceph_decode_32_safe(p, end, yes, bad); #if BITS_PER_LONG == 32 - err = -EINVAL; if (yes > (ULONG_MAX - sizeof(*r)) / sizeof(struct crush_rule_step)) goto bad; @@ -557,7 +554,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end) if (*p != end) { err = decode_choose_args(p, end, c); if (err) - goto bad; + goto fail; } done: @@ -567,10 +564,14 @@ done: badmem: err = -ENOMEM; -bad: +fail: dout("crush_decode fail %d\n", err); crush_destroy(c); return ERR_PTR(err); + +bad: + err = -EINVAL; + goto fail; } int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs) @@ -1399,7 +1400,7 @@ static struct ceph_pg_mapping *__decode_pg_upmap_items(void **p, void *end, return ERR_PTR(-EINVAL); ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval); - pg = kzalloc(sizeof(*pg) + 2 * len * sizeof(u32), GFP_NOIO); + pg = alloc_pg_mapping(2 * len * sizeof(u32)); if (!pg) return ERR_PTR(-ENOMEM); @@ -1544,7 +1545,7 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map) if (struct_v >= 3) { /* erasure_code_profiles */ ceph_decode_skip_map_of_map(p, end, string, string, string, - bad); + e_inval); } if (struct_v >= 4) { @@ -1825,9 +1826,9 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, if (struct_v >= 3) { /* new_erasure_code_profiles */ ceph_decode_skip_map_of_map(p, end, string, string, string, - bad); + e_inval); /* old_erasure_code_profiles */ - ceph_decode_skip_set(p, end, string, bad); + ceph_decode_skip_set(p, end, string, e_inval); } if (struct_v >= 4) { diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 82fd4c9c4a1b..06b147d7d9e2 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -28,6 +28,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; + ifr.ifr_name[IFNAMSIZ-1] = 0; error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex); if (error) @@ -424,6 +425,8 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (copy_from_user(&iwr, arg, sizeof(iwr))) return -EFAULT; + iwr.ifr_name[sizeof(iwr.ifr_name) - 1] = 0; + return wext_handle_ioctl(net, &iwr, cmd, arg); } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index a0093e1b0235..fdcb1bcd2afa 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -400,6 +400,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, err = -ENOMEM; goto errout; } + refcount_set(&rule->refcnt, 1); rule->fr_net = net; rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) @@ -517,8 +518,6 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, last = r; } - refcount_set(&rule->refcnt, 1); - if (last) list_add_rcu(&rule->list, &last->list); else diff --git a/net/core/filter.c b/net/core/filter.c index c7f737058d89..f44fc22fd45a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2248,7 +2248,7 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) bpf_skb_net_grow(skb, len_diff_abs); bpf_compute_data_end(skb); - return 0; + return ret; } BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, diff --git a/net/core/netpoll.c b/net/core/netpoll.c index d3408a693166..8357f164c660 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -277,7 +277,7 @@ static void zap_completion_queue(void) struct sk_buff *skb = clist; clist = clist->next; if (!skb_irq_freeable(skb)) { - refcount_inc(&skb->users); + refcount_set(&skb->users, 1); dev_kfree_skb_any(skb); /* put this one back */ } else { __kfree_skb(skb); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d1ba90980be1..9201e3621351 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2031,7 +2031,8 @@ static int do_setlink(const struct sk_buff *skb, struct sockaddr *sa; int len; - len = sizeof(sa_family_t) + dev->addr_len; + len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len, + sizeof(*sa)); sa = kmalloc(len, GFP_KERNEL); if (!sa) { err = -ENOMEM; @@ -4241,6 +4242,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi switch (event) { case NETDEV_REBOOT: + case NETDEV_CHANGEADDR: case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: case NETDEV_BONDING_FAILOVER: diff --git a/net/dccp/input.c b/net/dccp/input.c index 4a05d7876850..fa6be9750bb4 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -126,7 +126,7 @@ static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) static u16 dccp_reset_code_convert(const u8 code) { - const u16 error_code[] = { + static const u16 error_code[] = { [DCCP_RESET_CODE_CLOSED] = 0, /* normal termination */ [DCCP_RESET_CODE_UNSPECIFIED] = 0, /* nothing known */ [DCCP_RESET_CODE_ABORTED] = ECONNRESET, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 4e678fa892dd..044d2a159a3c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1334,13 +1334,14 @@ static struct pernet_operations fib_net_ops = { void __init ip_fib_init(void) { - rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); - rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); + fib_trie_init(); register_pernet_subsys(&fib_net_ops); + register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); - fib_trie_init(); + rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); + rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7eb252dcecee..50c74cd890bc 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -599,6 +599,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, hlen = iph->ihl * 4; mtu = mtu - hlen; /* Size of data space */ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; + ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* When frag_list is given, use it. First, check its validity: * some transformers could create wrong frag_list or break existing @@ -614,14 +615,15 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (first_len - hlen > mtu || ((first_len - hlen) & 7) || ip_is_fragment(iph) || - skb_cloned(skb)) + skb_cloned(skb) || + skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || - skb_headroom(frag) < hlen) + skb_headroom(frag) < hlen + ll_rs) goto slow_path_clean; /* Partially cloned skb? */ @@ -711,8 +713,6 @@ slow_path: left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ - ll_rs = LL_RESERVED_SPACE(rt->dst.dev); - /* * Fragment the datagram. */ diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c index 805c8ddfe860..4bbc273b45e8 100644 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ b/net/ipv4/netfilter/nf_tables_arp.c @@ -72,8 +72,7 @@ static const struct nf_chain_type filter_arp = { .family = NFPROTO_ARP, .owner = THIS_MODULE, .hook_mask = (1 << NF_ARP_IN) | - (1 << NF_ARP_OUT) | - (1 << NF_ARP_FORWARD), + (1 << NF_ARP_OUT), }; static int __init nf_tables_arp_init(void) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 0905cf04c2a4..03ad8778c395 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -335,6 +335,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; + treq->txhash = net_tx_rndhash(); req->mss = mss; ireq->ir_num = ntohs(th->dest); ireq->ir_rmt_port = th->source; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index dbcc9352a48f..69ee877574d0 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -112,7 +112,8 @@ struct bbr { cwnd_gain:10, /* current gain for setting cwnd */ full_bw_cnt:3, /* number of rounds without large bw gains */ cycle_idx:3, /* current index in pacing_gain cycle array */ - unused_b:6; + has_seen_rtt:1, /* have we seen an RTT sample yet? */ + unused_b:5; u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ u32 full_bw; /* recent bw, to estimate if pipe is full */ }; @@ -211,6 +212,35 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) return rate >> BW_SCALE; } +/* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */ +static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain) +{ + u64 rate = bw; + + rate = bbr_rate_bytes_per_sec(sk, rate, gain); + rate = min_t(u64, rate, sk->sk_max_pacing_rate); + return rate; +} + +/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ +static void bbr_init_pacing_rate_from_rtt(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw; + u32 rtt_us; + + if (tp->srtt_us) { /* any RTT sample yet? */ + rtt_us = max(tp->srtt_us >> 3, 1U); + bbr->has_seen_rtt = 1; + } else { /* no RTT sample yet */ + rtt_us = USEC_PER_MSEC; /* use nominal default RTT */ + } + bw = (u64)tp->snd_cwnd * BW_UNIT; + do_div(bw, rtt_us); + sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain); +} + /* Pace using current bw estimate and a gain factor. In order to help drive the * network toward lower queues while maintaining high utilization and low * latency, the average pacing rate aims to be slightly (~1%) lower than the @@ -220,12 +250,13 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) */ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) { + struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - u64 rate = bw; + u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain); - rate = bbr_rate_bytes_per_sec(sk, rate, gain); - rate = min_t(u64, rate, sk->sk_max_pacing_rate); - if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate) + if (unlikely(!bbr->has_seen_rtt && tp->srtt_us)) + bbr_init_pacing_rate_from_rtt(sk); + if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate) sk->sk_pacing_rate = rate; } @@ -798,7 +829,6 @@ static void bbr_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - u64 bw; bbr->prior_cwnd = 0; bbr->tso_segs_goal = 0; /* default segs per skb until first ACK */ @@ -814,11 +844,8 @@ static void bbr_init(struct sock *sk) minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */ - /* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ - bw = (u64)tp->snd_cwnd * BW_UNIT; - do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC); - sk->sk_pacing_rate = 0; /* force an update of sk_pacing_rate */ - bbr_set_pacing_rate(sk, bw, bbr_high_gain); + bbr->has_seen_rtt = 0; + bbr_init_pacing_rate_from_rtt(sk); bbr->restore_cwnd = 0; bbr->round_start = 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 25294d43e147..b057653ceca9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1388,6 +1388,11 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) unlock_sock_fast(sk, slow); } + /* we cleared the head states previously only if the skb lacks any IP + * options, see __udp_queue_rcv_skb(). + */ + if (unlikely(IPCB(skb)->opt.optlen > 0)) + skb_release_head_state(skb); consume_stateless_skb(skb); } EXPORT_SYMBOL_GPL(skb_consume_udp); @@ -1779,8 +1784,12 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id_once(sk, skb); } - /* clear all pending head states while they are hot in the cache */ - skb_release_head_state(skb); + /* At recvmsg() time we need skb->dst to process IP options-related + * cmsg, elsewhere can we clear all pending head states while they are + * hot in the cache + */ + if (likely(IPCB(skb)->opt.optlen == 0)) + skb_release_head_state(skb); rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index e9065b8d3af8..abb2c307fbe8 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -78,7 +78,7 @@ EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { - u16 offset = sizeof(struct ipv6hdr); + unsigned int offset = sizeof(struct ipv6hdr); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; @@ -86,6 +86,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; + unsigned int len; switch (**nexthdr) { @@ -111,7 +112,10 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); - offset += ipv6_optlen(exthdr); + len = ipv6_optlen(exthdr); + if (len + offset >= IPV6_MAXPLEN) + return -EINVAL; + offset += len; *nexthdr = &exthdr->nexthdr; } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7b75b0620730..4e7817abc0b9 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -216,6 +216,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; + treq->txhash = net_tx_rndhash(); /* * We need to lookup the dst_entry to get the correct window size. diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 552d606e57ca..974cf2a3795a 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -227,114 +227,6 @@ void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, } EXPORT_SYMBOL(nf_unregister_net_hooks); -static LIST_HEAD(nf_hook_list); - -static int _nf_register_hook(struct nf_hook_ops *reg) -{ - struct net *net, *last; - int ret; - - for_each_net(net) { - ret = nf_register_net_hook(net, reg); - if (ret && ret != -ENOENT) - goto rollback; - } - list_add_tail(®->list, &nf_hook_list); - - return 0; -rollback: - last = net; - for_each_net(net) { - if (net == last) - break; - nf_unregister_net_hook(net, reg); - } - return ret; -} - -int nf_register_hook(struct nf_hook_ops *reg) -{ - int ret; - - rtnl_lock(); - ret = _nf_register_hook(reg); - rtnl_unlock(); - - return ret; -} -EXPORT_SYMBOL(nf_register_hook); - -static void _nf_unregister_hook(struct nf_hook_ops *reg) -{ - struct net *net; - - list_del(®->list); - for_each_net(net) - nf_unregister_net_hook(net, reg); -} - -void nf_unregister_hook(struct nf_hook_ops *reg) -{ - rtnl_lock(); - _nf_unregister_hook(reg); - rtnl_unlock(); -} -EXPORT_SYMBOL(nf_unregister_hook); - -int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - unsigned int i; - int err = 0; - - for (i = 0; i < n; i++) { - err = nf_register_hook(®[i]); - if (err) - goto err; - } - return err; - -err: - if (i > 0) - nf_unregister_hooks(reg, i); - return err; -} -EXPORT_SYMBOL(nf_register_hooks); - -/* Caller MUST take rtnl_lock() */ -int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - unsigned int i; - int err = 0; - - for (i = 0; i < n; i++) { - err = _nf_register_hook(®[i]); - if (err) - goto err; - } - return err; - -err: - if (i > 0) - _nf_unregister_hooks(reg, i); - return err; -} -EXPORT_SYMBOL(_nf_register_hooks); - -void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - while (n-- > 0) - nf_unregister_hook(®[n]); -} -EXPORT_SYMBOL(nf_unregister_hooks); - -/* Caller MUST take rtnl_lock */ -void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) -{ - while (n-- > 0) - _nf_unregister_hook(®[n]); -} -EXPORT_SYMBOL(_nf_unregister_hooks); - /* Returns 1 if okfn() needs to be executed by the caller, * -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, @@ -450,40 +342,9 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); EXPORT_SYMBOL(nf_nat_decode_session_hook); #endif -static int nf_register_hook_list(struct net *net) -{ - struct nf_hook_ops *elem; - int ret; - - rtnl_lock(); - list_for_each_entry(elem, &nf_hook_list, list) { - ret = nf_register_net_hook(net, elem); - if (ret && ret != -ENOENT) - goto out_undo; - } - rtnl_unlock(); - return 0; - -out_undo: - list_for_each_entry_continue_reverse(elem, &nf_hook_list, list) - nf_unregister_net_hook(net, elem); - rtnl_unlock(); - return ret; -} - -static void nf_unregister_hook_list(struct net *net) -{ - struct nf_hook_ops *elem; - - rtnl_lock(); - list_for_each_entry(elem, &nf_hook_list, list) - nf_unregister_net_hook(net, elem); - rtnl_unlock(); -} - static int __net_init netfilter_net_init(struct net *net) { - int i, h, ret; + int i, h; for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) { for (h = 0; h < NF_MAX_HOOKS; h++) @@ -500,16 +361,12 @@ static int __net_init netfilter_net_init(struct net *net) return -ENOMEM; } #endif - ret = nf_register_hook_list(net); - if (ret) - remove_proc_entry("netfilter", net->proc_net); - return ret; + return 0; } static void __net_exit netfilter_net_exit(struct net *net) { - nf_unregister_hook_list(net); remove_proc_entry("netfilter", net->proc_net); } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index e03d16ed550d..899c2c36da13 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -422,7 +422,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { if (expect_matches(i, expect)) { - if (nf_ct_remove_expect(expect)) + if (nf_ct_remove_expect(i)) break; } else if (expect_clash(i, expect)) { ret = -EBUSY; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 832c5a08d9a5..eb541786ccb7 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -222,20 +222,21 @@ find_appropriate_src(struct net *net, .tuple = tuple, .zone = zone }; - struct rhlist_head *hl; + struct rhlist_head *hl, *h; hl = rhltable_lookup(&nf_nat_bysource_table, &key, nf_nat_bysource_params); - if (!hl) - return 0; - ct = container_of(hl, typeof(*ct), nat_bysource); + rhl_for_each_entry_rcu(ct, h, hl, nat_bysource) { + nf_ct_invert_tuplepr(result, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + result->dst = tuple->dst; - nf_ct_invert_tuplepr(result, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - result->dst = tuple->dst; + if (in_range(l3proto, l4proto, result, range)) + return 1; + } - return in_range(l3proto, l4proto, result, range); + return 0; } /* For [FUTURE] fragmentation handling, we want the least-used diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 92b05e188fd1..733d3e4a30d8 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -472,8 +472,7 @@ static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) if (msglen > skb->len) msglen = skb->len; - if (nlh->nlmsg_len < NLMSG_HDRLEN || - skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) + if (skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) return; err = nla_parse(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy, @@ -500,7 +499,8 @@ static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < NLMSG_HDRLEN || + if (skb->len < NLMSG_HDRLEN || + nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 08679ebb3068..e3c4c6c3fef7 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -629,6 +629,34 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, return ct; } +static +struct nf_conn *ovs_ct_executed(struct net *net, + const struct sw_flow_key *key, + const struct ovs_conntrack_info *info, + struct sk_buff *skb, + bool *ct_executed) +{ + struct nf_conn *ct = NULL; + + /* If no ct, check if we have evidence that an existing conntrack entry + * might be found for this skb. This happens when we lose a skb->_nfct + * due to an upcall, or if the direction is being forced. If the + * connection was not confirmed, it is not cached and needs to be run + * through conntrack again. + */ + *ct_executed = (key->ct_state & OVS_CS_F_TRACKED) && + !(key->ct_state & OVS_CS_F_INVALID) && + (key->ct_zone == info->zone.id); + + if (*ct_executed || (!key->ct_state && info->force)) { + ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, + !!(key->ct_state & + OVS_CS_F_NAT_MASK)); + } + + return ct; +} + /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool skb_nfct_cached(struct net *net, const struct sw_flow_key *key, @@ -637,24 +665,17 @@ static bool skb_nfct_cached(struct net *net, { enum ip_conntrack_info ctinfo; struct nf_conn *ct; + bool ct_executed = true; ct = nf_ct_get(skb, &ctinfo); - /* If no ct, check if we have evidence that an existing conntrack entry - * might be found for this skb. This happens when we lose a skb->_nfct - * due to an upcall. If the connection was not confirmed, it is not - * cached and needs to be run through conntrack again. - */ - if (!ct && key->ct_state & OVS_CS_F_TRACKED && - !(key->ct_state & OVS_CS_F_INVALID) && - key->ct_zone == info->zone.id) { - ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, - !!(key->ct_state - & OVS_CS_F_NAT_MASK)); - if (ct) - nf_ct_get(skb, &ctinfo); - } if (!ct) + ct = ovs_ct_executed(net, key, info, skb, &ct_executed); + + if (ct) + nf_ct_get(skb, &ctinfo); + else return false; + if (!net_eq(net, read_pnet(&ct->ct_net))) return false; if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct))) @@ -679,7 +700,7 @@ static bool skb_nfct_cached(struct net *net, return false; } - return true; + return ct_executed; } #ifdef CONFIG_NF_NAT_NEEDED diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e3beb28203eb..008bb34ee324 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -214,6 +214,7 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *, static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); +static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb); struct packet_skb_cb { union { @@ -260,6 +261,7 @@ static int packet_direct_xmit(struct sk_buff *skb) if (skb != orig_skb) goto drop; + packet_pick_tx_queue(dev, skb); txq = skb_get_tx_queue(dev, skb); local_bh_disable(); @@ -2747,8 +2749,6 @@ tpacket_error: goto tpacket_error; } - packet_pick_tx_queue(dev, skb); - skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); @@ -2931,8 +2931,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = sk->sk_priority; skb->mark = sockc.mark; - packet_pick_tx_queue(dev, skb); - if (po->has_vnet_hdr) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) diff --git a/net/rds/send.c b/net/rds/send.c index e81aa176f4e2..41b9f0f5bb9c 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -170,8 +170,8 @@ restart: * The acquire_in_xmit() check above ensures that only one * caller can increment c_send_gen at any time. */ - cp->cp_send_gen++; - send_gen = cp->cp_send_gen; + send_gen = READ_ONCE(cp->cp_send_gen) + 1; + WRITE_ONCE(cp->cp_send_gen, send_gen); /* * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, @@ -431,7 +431,7 @@ over_batch: smp_mb(); if ((test_bit(0, &conn->c_map_queued) || !list_empty(&cp->cp_send_queue)) && - send_gen == cp->cp_send_gen) { + send_gen == READ_ONCE(cp->cp_send_gen)) { rds_stats_inc(s_send_lock_queue_raced); if (batch_count < send_batch_count) goto restart; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index aed6cf2e9fd8..f2e9ed34a963 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -835,7 +835,7 @@ out_nlmsg_trim: } static int -act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, +tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, struct list_head *actions, int event) { struct sk_buff *skb; @@ -1018,7 +1018,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, } if (event == RTM_GETACTION) - ret = act_get_notify(net, portid, n, &actions, event); + ret = tcf_get_notify(net, portid, n, &actions, event); else { /* delete */ ret = tcf_del_notify(net, n, &actions, portid); if (ret) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 4e16b02ed832..6110447fe51d 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -228,7 +228,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, sctp_adaptation_ind_param_t aiparam; sctp_supported_ext_param_t ext_param; int num_ext = 0; - __u8 extensions[3]; + __u8 extensions[4]; struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL; @@ -396,7 +396,7 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, sctp_adaptation_ind_param_t aiparam; sctp_supported_ext_param_t ext_param; int num_ext = 0; - __u8 extensions[3]; + __u8 extensions[4]; struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL, *auth_random = NULL; diff --git a/security/keys/internal.h b/security/keys/internal.h index 91bc6214ae57..1c02c6547038 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -198,7 +198,7 @@ struct request_key_auth { void *callout_info; size_t callout_len; pid_t pid; -}; +} __randomize_layout; extern struct key_type key_type_request_key_auth; extern struct key *request_key_auth_new(struct key *target, diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 7e0405e1651d..412a7c82995a 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -120,7 +120,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, int strict_alignment, const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz) + char *log_buf, size_t log_buf_sz, int log_level) { union bpf_attr attr; @@ -131,7 +131,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, attr.license = ptr_to_u64(license); attr.log_buf = ptr_to_u64(log_buf); attr.log_size = log_buf_sz; - attr.log_level = 2; + attr.log_level = log_level; log_buf[0] = 0; attr.kern_version = kern_version; attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 16de44a14b48..418c86e69bcb 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -38,7 +38,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, int strict_alignment, const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz); + char *log_buf, size_t log_buf_sz, int log_level); int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index a4d3762cd825..83874b0e266c 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -704,7 +704,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser, ui_browser__gotorc(browser, row, column + 1); SLsmg_draw_hline(2); - if (row++ == 0) + if (++row == 0) goto out; } else row = 0; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 87b431886670..413f74df08de 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -273,7 +273,7 @@ struct perf_evsel *perf_evsel__new_cycles(void) struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = 1, + .exclude_kernel = geteuid() != 0, }; struct perf_evsel *evsel; @@ -298,8 +298,10 @@ struct perf_evsel *perf_evsel__new_cycles(void) goto out; /* use asprintf() because free(evsel) assumes name is allocated */ - if (asprintf(&evsel->name, "cycles%.*s", - attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0) + if (asprintf(&evsel->name, "cycles%s%s%.*s", + (attr.precise_ip || attr.exclude_kernel) ? ":" : "", + attr.exclude_kernel ? "u" : "", + attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0) goto error_free; out: return evsel; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 5de2b86b9880..2e9eb6aa3ce2 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2209,7 +2209,7 @@ int machine__get_kernel_start(struct machine *machine) machine->kernel_start = 1ULL << 63; if (map) { err = map__load(map); - if (map->start) + if (!err) machine->kernel_start = map->start; } return err; diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c index bccebd935907..29793694cbc7 100644 --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@ -380,7 +380,7 @@ static int do_test_single(struct bpf_align_test *test) prog_len = probe_filter_length(prog); fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, 1, "GPL", 0, - bpf_vlog, sizeof(bpf_vlog)); + bpf_vlog, sizeof(bpf_vlog), 2); if (fd_prog < 0) { printf("Failed to load program.\n"); printf("%s", bpf_vlog); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 404aec520812..af7d173910f4 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -4969,7 +4969,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val), 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -4995,7 +4995,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) + 1, 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -5023,7 +5023,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 20, 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -5050,7 +5050,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 19, 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -5510,6 +5510,476 @@ static struct bpf_test tests[] = { .errstr = "invalid bpf_context access", .prog_type = BPF_PROG_TYPE_LWT_IN, }, + { + "bounds checks mixing signed and unsigned, positive bounds", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 2), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 4, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_ST_MEM(BPF_B, BPF_REG_8, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R8 invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 4), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_ST_MEM(BPF_B, BPF_REG_8, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R8 invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 4", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 5", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 4), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 invalid mem access", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 6", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -512), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_6, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_6, 5), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_4, 1, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_ST_MEM(BPF_H, BPF_REG_10, -512, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R4 min value is negative, either use unsigned", + .errstr = "R4 min value is negative, either use unsigned", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 7", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 8", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024 + 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 9", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 10", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_LD_IMM64(BPF_REG_2, -9223372036854775808ULL), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 11", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 12", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + /* Dead branch. */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 13", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -6), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 14", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 2), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_7, 1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, 4, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_7), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 15", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_MOV64_IMM(BPF_REG_8, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 42, 6), + BPF_JMP_REG(BPF_JSGT, BPF_REG_8, BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, -3), + BPF_JMP_IMM(BPF_JA, 0, 0, -7), + }, + .fixup_map1 = { 4 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 16", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -6), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, }; static int probe_filter_length(const struct bpf_insn *fp) @@ -5633,7 +6103,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT, - "GPL", 0, bpf_vlog, sizeof(bpf_vlog)); + "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1); expected_ret = unpriv && test->result_unpriv != UNDEF ? test->result_unpriv : test->result; |