diff options
171 files changed, 1886 insertions, 671 deletions
@@ -1172,7 +1172,7 @@ headers_check_all: headers_install_all PHONY += headers_check headers_check: headers_install $(Q)$(MAKE) $(hdr-inst)=include/uapi HDRCHECK=1 - $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi/ $(hdr-dst) HDRCHECK=1 + $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi $(hdr-dst) HDRCHECK=1 # --------------------------------------------------------------------------- # Kernel selftest diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index c6e53580aefe..71f930501ade 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -253,8 +253,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) */ off = offsetof(struct bpf_array, ptrs); emit_a64_mov_i64(tmp, off, ctx); - emit(A64_LDR64(tmp, r2, tmp), ctx); - emit(A64_LDR64(prg, tmp, r3), ctx); + emit(A64_ADD(1, tmp, r2, tmp), ctx); + emit(A64_LSL(1, prg, r3, 3), ctx); + emit(A64_LDR64(prg, tmp, prg), ctx); emit(A64_CBZ(1, prg, jmp_offset), ctx); /* goto *(prog->bpf_func + prologue_size); */ diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 53885512b8d3..6c0132c7212f 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -14,6 +14,10 @@ #include <asm-generic/module.h> +#ifdef CC_USING_MPROFILE_KERNEL +#define MODULE_ARCH_VERMAGIC "mprofile-kernel" +#endif + #ifndef __powerpc64__ /* * Thanks to Paul M for explaining this. diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 2a32483c7b6c..8da5d4c1cab2 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -132,7 +132,19 @@ extern long long virt_phys_offset; #define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) + +#ifdef CONFIG_PPC_BOOK3S_64 +/* + * On hash the vmalloc and other regions alias to the kernel region when passed + * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can + * return true for some vmalloc addresses, which is incorrect. So explicitly + * check that the address is in the kernel region. + */ +#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \ + pfn_valid(virt_to_pfn(kaddr))) +#else #define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) +#endif /* * On Book-E parts we need __va to parse the device tree and we can't diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 07d4e0ad60db..4898d676dcae 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -416,7 +416,7 @@ power9_dd1_recover_paca: * which needs to be restored from the stack. */ li r3, 1 - stb r0,PACA_NAPSTATELOST(r13) + stb r3,PACA_NAPSTATELOST(r13) blr /* diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 160ae0fa7d0d..fc4343514bed 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -305,16 +305,17 @@ int kprobe_handler(struct pt_regs *regs) save_previous_kprobe(kcb); set_current_kprobe(p, regs, kcb); kprobes_inc_nmissed_count(p); - prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_REENTER; if (p->ainsn.boostable >= 0) { ret = try_to_emulate(p, regs); if (ret > 0) { restore_previous_kprobe(kcb); + preempt_enable_no_resched(); return 1; } } + prepare_singlestep(p, regs); return 1; } else { if (*addr != BREAKPOINT_INSTRUCTION) { diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index d645da302bf2..baae104b16c7 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -864,6 +864,25 @@ static void tm_reclaim_thread(struct thread_struct *thr, if (!MSR_TM_SUSPENDED(mfmsr())) return; + /* + * If we are in a transaction and FP is off then we can't have + * used FP inside that transaction. Hence the checkpointed + * state is the same as the live state. We need to copy the + * live state to the checkpointed state so that when the + * transaction is restored, the checkpointed state is correct + * and the aborted transaction sees the correct state. We use + * ckpt_regs.msr here as that's what tm_reclaim will use to + * determine if it's going to write the checkpointed state or + * not. So either this will write the checkpointed registers, + * or reclaim will. Similarly for VMX. + */ + if ((thr->ckpt_regs.msr & MSR_FP) == 0) + memcpy(&thr->ckfp_state, &thr->fp_state, + sizeof(struct thread_fp_state)); + if ((thr->ckpt_regs.msr & MSR_VEC) == 0) + memcpy(&thr->ckvr_state, &thr->vr_state, + sizeof(struct thread_vr_state)); + giveup_all(container_of(thr, struct task_struct, thread)); tm_reclaim(thr, thr->ckpt_regs.msr, cause); diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c index d659345a98d6..44fe4833910f 100644 --- a/arch/powerpc/mm/dump_linuxpagetables.c +++ b/arch/powerpc/mm/dump_linuxpagetables.c @@ -16,6 +16,7 @@ */ #include <linux/debugfs.h> #include <linux/fs.h> +#include <linux/hugetlb.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/sched.h> @@ -391,7 +392,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { addr = start + i * PMD_SIZE; - if (!pmd_none(*pmd)) + if (!pmd_none(*pmd) && !pmd_huge(*pmd)) /* pmd exists */ walk_pte(st, pmd, addr); else @@ -407,7 +408,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) for (i = 0; i < PTRS_PER_PUD; i++, pud++) { addr = start + i * PUD_SIZE; - if (!pud_none(*pud)) + if (!pud_none(*pud) && !pud_huge(*pud)) /* pud exists */ walk_pmd(st, pud, addr); else @@ -427,7 +428,7 @@ static void walk_pagetables(struct pg_state *st) */ for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { addr = KERN_VIRT_START + i * PGDIR_SIZE; - if (!pgd_none(*pgd)) + if (!pgd_none(*pgd) && !pgd_huge(*pgd)) /* pgd exists */ walk_pud(st, pgd, addr); else diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 0206c8052328..df7b54ea956d 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -10,6 +10,7 @@ #include <linux/spinlock.h> #include <linux/kernel.h> #include <linux/time.h> +#include <linux/refcount.h> #include <uapi/asm/debug.h> #define DEBUG_MAX_LEVEL 6 /* debug levels range from 0 to 6 */ @@ -31,7 +32,7 @@ struct debug_view; typedef struct debug_info { struct debug_info* next; struct debug_info* prev; - atomic_t ref_count; + refcount_t ref_count; spinlock_t lock; int level; int nr_areas; diff --git a/arch/s390/include/asm/dis.h b/arch/s390/include/asm/dis.h index 60323c21938b..37f617dfbede 100644 --- a/arch/s390/include/asm/dis.h +++ b/arch/s390/include/asm/dis.h @@ -40,6 +40,8 @@ static inline int insn_length(unsigned char code) return ((((int) code + 64) >> 7) + 1) << 1; } +struct pt_regs; + void show_code(struct pt_regs *regs); void print_fn_code(unsigned char *code, unsigned long len); int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len); diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index 1293c4066cfc..28792ef82c83 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -27,12 +27,21 @@ * 2005-Dec Used as a template for s390 by Mike Grundy * <grundym@us.ibm.com> */ +#include <linux/types.h> #include <asm-generic/kprobes.h> #define BREAKPOINT_INSTRUCTION 0x0002 +#define FIXUP_PSW_NORMAL 0x08 +#define FIXUP_BRANCH_NOT_TAKEN 0x04 +#define FIXUP_RETURN_REGISTER 0x02 +#define FIXUP_NOT_REQUIRED 0x01 + +int probe_is_prohibited_opcode(u16 *insn); +int probe_get_fixup_type(u16 *insn); +int probe_is_insn_relative_long(u16 *insn); + #ifdef CONFIG_KPROBES -#include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> #include <linux/sched/task_stack.h> @@ -56,11 +65,6 @@ typedef u16 kprobe_opcode_t; #define KPROBE_SWAP_INST 0x10 -#define FIXUP_PSW_NORMAL 0x08 -#define FIXUP_BRANCH_NOT_TAKEN 0x04 -#define FIXUP_RETURN_REGISTER 0x02 -#define FIXUP_NOT_REQUIRED 0x01 - /* Architecture specific copy of original instruction */ struct arch_specific_insn { /* copy of original instruction */ @@ -90,10 +94,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr); int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); -int probe_is_prohibited_opcode(u16 *insn); -int probe_get_fixup_type(u16 *insn); -int probe_is_insn_relative_long(u16 *insn); - #define flush_insn_slot(p) do { } while (0) #endif /* CONFIG_KPROBES */ diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h index 73bff45ced55..e784bed6ed7f 100644 --- a/arch/s390/include/asm/sysinfo.h +++ b/arch/s390/include/asm/sysinfo.h @@ -146,7 +146,7 @@ extern int topology_max_mnest; * Returns the maximum nesting level supported by the cpu topology code. * The current maximum level is 4 which is the drawer level. */ -static inline int topology_mnest_limit(void) +static inline unsigned char topology_mnest_limit(void) { return min(topology_max_mnest, 4); } diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 530226b6cb19..86b3e74f569e 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -277,7 +277,7 @@ debug_info_alloc(const char *name, int pages_per_area, int nr_areas, memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *)); memset(rc->debugfs_entries, 0 ,DEBUG_MAX_VIEWS * sizeof(struct dentry*)); - atomic_set(&(rc->ref_count), 0); + refcount_set(&(rc->ref_count), 0); return rc; @@ -361,7 +361,7 @@ debug_info_create(const char *name, int pages_per_area, int nr_areas, debug_area_last = rc; rc->next = NULL; - debug_info_get(rc); + refcount_set(&rc->ref_count, 1); out: return rc; } @@ -416,7 +416,7 @@ static void debug_info_get(debug_info_t * db_info) { if (db_info) - atomic_inc(&db_info->ref_count); + refcount_inc(&db_info->ref_count); } /* @@ -431,7 +431,7 @@ debug_info_put(debug_info_t *db_info) if (!db_info) return; - if (atomic_dec_and_test(&db_info->ref_count)) { + if (refcount_dec_and_test(&db_info->ref_count)) { for (i = 0; i < DEBUG_MAX_VIEWS; i++) { if (!db_info->views[i]) continue; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index a5f5d3bb3dbc..e408d9cc5b96 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -312,6 +312,7 @@ ENTRY(system_call) lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) +.Lsysc_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER lmg %r11,%r15,__PT_R11(%r11) @@ -623,6 +624,7 @@ ENTRY(io_int_handler) lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) +.Lio_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER lmg %r11,%r15,__PT_R11(%r11) @@ -1174,15 +1176,23 @@ cleanup_critical: br %r14 .Lcleanup_sysc_restore: + # check if stpt has been executed clg %r9,BASED(.Lcleanup_sysc_restore_insn) + jh 0f + mvc __LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER + cghi %r11,__LC_SAVE_AREA_ASYNC je 0f + mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER +0: clg %r9,BASED(.Lcleanup_sysc_restore_insn+8) + je 1f lg %r9,24(%r11) # get saved pointer to pt_regs mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) -0: lmg %r8,%r9,__LC_RETURN_PSW +1: lmg %r8,%r9,__LC_RETURN_PSW br %r14 .Lcleanup_sysc_restore_insn: + .quad .Lsysc_exit_timer .quad .Lsysc_done - 4 .Lcleanup_io_tif: @@ -1190,15 +1200,20 @@ cleanup_critical: br %r14 .Lcleanup_io_restore: + # check if stpt has been executed clg %r9,BASED(.Lcleanup_io_restore_insn) - je 0f + jh 0f + mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER +0: clg %r9,BASED(.Lcleanup_io_restore_insn+8) + je 1f lg %r9,24(%r11) # get saved r11 pointer to pt_regs mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) -0: lmg %r8,%r9,__LC_RETURN_PSW +1: lmg %r8,%r9,__LC_RETURN_PSW br %r14 .Lcleanup_io_restore_insn: + .quad .Lio_exit_timer .quad .Lio_done - 4 .Lcleanup_idle: diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 27477f34cc0a..d03a6d12c4bd 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -173,6 +173,8 @@ int __init ftrace_dyn_arch_init(void) return 0; } +#ifdef CONFIG_MODULES + static int __init ftrace_plt_init(void) { unsigned int *ip; @@ -191,6 +193,8 @@ static int __init ftrace_plt_init(void) } device_initcall(ftrace_plt_init); +#endif /* CONFIG_MODULES */ + #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * Hook the return address and push it in the stack of return addresses diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 72307f108c40..6e2c42bd1c3b 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -31,8 +31,14 @@ SECTIONS { . = 0x00000000; .text : { - _text = .; /* Text and read-only data */ + /* Text and read-only data */ HEAD_TEXT + /* + * E.g. perf doesn't like symbols starting at address zero, + * therefore skip the initial PSW and channel program located + * at address zero and let _text start at 0x200. + */ + _text = 0x200; TEXT_TEXT SCHED_TEXT CPUIDLE_TEXT diff --git a/arch/s390/lib/probes.c b/arch/s390/lib/probes.c index ae90e1ae3607..1963ddbf4ab3 100644 --- a/arch/s390/lib/probes.c +++ b/arch/s390/lib/probes.c @@ -4,6 +4,7 @@ * Copyright IBM Corp. 2014 */ +#include <linux/errno.h> #include <asm/kprobes.h> #include <asm/dis.h> diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index 1e5bb2b86c42..b3bd3f23b8e8 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -337,8 +337,8 @@ long __strncpy_from_user(char *dst, const char __user *src, long size) return 0; done = 0; do { - offset = (size_t)src & ~PAGE_MASK; - len = min(size - done, PAGE_SIZE - offset); + offset = (size_t)src & (L1_CACHE_BYTES - 1); + len = min(size - done, L1_CACHE_BYTES - offset); if (copy_from_user(dst, src, len)) return -EFAULT; len_str = strnlen(dst, len); diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index dcbf985ab243..d1f837dc77a4 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -24,9 +24,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { - if (len & ~HPAGE_MASK) + struct hstate *h = hstate_file(file); + + if (len & ~huge_page_mask(h)) return -EINVAL; - if (addr & ~HPAGE_MASK) + if (addr & ~huge_page_mask(h)) return -EINVAL; return 0; } diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index ce6f56980aef..cf190728360b 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -91,9 +91,9 @@ extern unsigned long pfn_base; * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ -extern unsigned long empty_zero_page; +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page)) +#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) /* * In general all page table modifications should use the V8 atomic diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h index 478bf6bb4598..3fae200dd251 100644 --- a/arch/sparc/include/asm/setup.h +++ b/arch/sparc/include/asm/setup.h @@ -16,7 +16,7 @@ extern char reboot_command[]; */ extern unsigned char boot_cpu_id; -extern unsigned long empty_zero_page; +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; extern int serial_console; static inline int con_is_present(void) diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c index 6bcff698069b..cec54dc4ab81 100644 --- a/arch/sparc/kernel/ftrace.c +++ b/arch/sparc/kernel/ftrace.c @@ -130,17 +130,16 @@ unsigned long prepare_ftrace_return(unsigned long parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) return parent + 8UL; - if (ftrace_push_return_trace(parent, self_addr, &trace.depth, - frame_pointer, NULL) == -EBUSY) - return parent + 8UL; - trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; + if (!ftrace_graph_entry(&trace)) + return parent + 8UL; + + if (ftrace_push_return_trace(parent, self_addr, &trace.depth, + frame_pointer, NULL) == -EBUSY) return parent + 8UL; - } return return_hooker; } diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index c6afe98de4d9..3bd0d513bddb 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -290,7 +290,7 @@ void __init mem_init(void) /* Saves us work later. */ - memset((void *)&empty_zero_page, 0, PAGE_SIZE); + memset((void *)empty_zero_page, 0, PAGE_SIZE); i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5); i += 1; diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 82dab1692264..3aea55698165 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -782,24 +782,26 @@ static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan) static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl) { - u32 *dcsb = ctrl ? pvt->csels[1].csbases : pvt->csels[0].csbases; - int dimm, size0, size1; + int dimm, size0, size1, cs0, cs1; edac_printk(KERN_DEBUG, EDAC_MC, "UMC%d chip selects:\n", ctrl); for (dimm = 0; dimm < 4; dimm++) { size0 = 0; + cs0 = dimm * 2; - if (dcsb[dimm*2] & DCSB_CS_ENABLE) - size0 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, dimm); + if (csrow_enabled(cs0, ctrl, pvt)) + size0 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs0); size1 = 0; - if (dcsb[dimm*2 + 1] & DCSB_CS_ENABLE) - size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, dimm); + cs1 = dimm * 2 + 1; + + if (csrow_enabled(cs1, ctrl, pvt)) + size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs1); amd64_info(EDAC_MC ": %d: %5dMB %d: %5dMB\n", - dimm * 2, size0, - dimm * 2 + 1, size1); + cs0, size0, + cs1, size1); } } @@ -2756,26 +2758,22 @@ skip: * encompasses * */ -static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr) +static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr_orig) { - u32 cs_mode, nr_pages; u32 dbam = dct ? pvt->dbam1 : pvt->dbam0; + int csrow_nr = csrow_nr_orig; + u32 cs_mode, nr_pages; + if (!pvt->umc) + csrow_nr >>= 1; - /* - * The math on this doesn't look right on the surface because x/2*4 can - * be simplified to x*2 but this expression makes use of the fact that - * it is integral math where 1/2=0. This intermediate value becomes the - * number of bits to shift the DBAM register to extract the proper CSROW - * field. - */ - cs_mode = DBAM_DIMM(csrow_nr / 2, dbam); + cs_mode = DBAM_DIMM(csrow_nr, dbam); - nr_pages = pvt->ops->dbam_to_cs(pvt, dct, cs_mode, (csrow_nr / 2)) - << (20 - PAGE_SHIFT); + nr_pages = pvt->ops->dbam_to_cs(pvt, dct, cs_mode, csrow_nr); + nr_pages <<= 20 - PAGE_SHIFT; edac_dbg(0, "csrow: %d, channel: %d, DBAM idx: %d\n", - csrow_nr, dct, cs_mode); + csrow_nr_orig, dct, cs_mode); edac_dbg(0, "nr_pages/channel: %u\n", nr_pages); return nr_pages; diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index ed3137c1ceb0..ab3a951a17e6 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -155,19 +155,14 @@ static int efi_pstore_scan_sysfs_exit(struct efivar_entry *pos, * efi_pstore_sysfs_entry_iter * * @record: pstore record to pass to callback - * @pos: entry to begin iterating from * * You MUST call efivar_enter_iter_begin() before this function, and * efivar_entry_iter_end() afterwards. * - * It is possible to begin iteration from an arbitrary entry within - * the list by passing @pos. @pos is updated on return to point to - * the next entry of the last one passed to efi_pstore_read_func(). - * To begin iterating from the beginning of the list @pos must be %NULL. */ -static int efi_pstore_sysfs_entry_iter(struct pstore_record *record, - struct efivar_entry **pos) +static int efi_pstore_sysfs_entry_iter(struct pstore_record *record) { + struct efivar_entry **pos = (struct efivar_entry **)&record->psi->data; struct efivar_entry *entry, *n; struct list_head *head = &efivar_sysfs_list; int size = 0; @@ -218,7 +213,6 @@ static int efi_pstore_sysfs_entry_iter(struct pstore_record *record, */ static ssize_t efi_pstore_read(struct pstore_record *record) { - struct efivar_entry *entry = (struct efivar_entry *)record->psi->data; ssize_t size; record->buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL); @@ -229,7 +223,7 @@ static ssize_t efi_pstore_read(struct pstore_record *record) size = -EINTR; goto out; } - size = efi_pstore_sysfs_entry_iter(record, &entry); + size = efi_pstore_sysfs_entry_iter(record); efivar_entry_iter_end(); out: diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 3ac4c03ba77b..c13a4fd86b3c 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -605,6 +605,13 @@ static int coretemp_cpu_online(unsigned int cpu) struct platform_data *pdata; /* + * Don't execute this on resume as the offline callback did + * not get executed on suspend. + */ + if (cpuhp_tasks_frozen) + return 0; + + /* * CPUID.06H.EAX[0] indicates whether the CPU has thermal * sensors. We check this bit only, all the early CPUs * without thermal sensors will be filtered out. @@ -654,6 +661,13 @@ static int coretemp_cpu_offline(unsigned int cpu) struct temp_data *tdata; int indx, target; + /* + * Don't execute this on suspend as the device remove locks + * up the machine. + */ + if (cpuhp_tasks_frozen) + return 0; + /* If the physical CPU device does not exist, just return */ if (!pdev) return 0; diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index cf737ec8563b..5c4db65c5019 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -819,7 +819,6 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data, rc = -EINVAL; goto out; } - drv_data->irq = irq_of_parse_and_map(np, 0); drv_data->rstc = devm_reset_control_get_optional(dev, NULL); if (IS_ERR(drv_data->rstc)) { @@ -902,10 +901,11 @@ mv64xxx_i2c_probe(struct platform_device *pd) if (!IS_ERR(drv_data->clk)) clk_prepare_enable(drv_data->clk); + drv_data->irq = platform_get_irq(pd, 0); + if (pdata) { drv_data->freq_m = pdata->freq_m; drv_data->freq_n = pdata->freq_n; - drv_data->irq = platform_get_irq(pd, 0); drv_data->adapter.timeout = msecs_to_jiffies(pdata->timeout); drv_data->offload_enabled = false; memcpy(&drv_data->reg_offsets, &mv64xxx_i2c_regs_mv64xxx, sizeof(drv_data->reg_offsets)); @@ -915,7 +915,7 @@ mv64xxx_i2c_probe(struct platform_device *pd) goto exit_clk; } if (drv_data->irq < 0) { - rc = -ENXIO; + rc = drv_data->irq; goto exit_reset; } diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c index dbe7e44c9321..6ba6c83ca8f1 100644 --- a/drivers/i2c/busses/i2c-xgene-slimpro.c +++ b/drivers/i2c/busses/i2c-xgene-slimpro.c @@ -416,6 +416,7 @@ static int xgene_slimpro_i2c_probe(struct platform_device *pdev) adapter->class = I2C_CLASS_HWMON; adapter->dev.parent = &pdev->dev; adapter->dev.of_node = pdev->dev.of_node; + ACPI_COMPANION_SET(&adapter->dev, ACPI_COMPANION(&pdev->dev)); i2c_set_adapdata(adapter, ctx); rc = i2c_add_adapter(adapter); if (rc) { diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 26f7237558ba..9669ca4937b8 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -395,18 +395,20 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc, if (force_nr) { priv->adap.nr = force_nr; ret = i2c_add_numbered_adapter(&priv->adap); - dev_err(&parent->dev, - "failed to add mux-adapter %u as bus %u (error=%d)\n", - chan_id, force_nr, ret); + if (ret < 0) { + dev_err(&parent->dev, + "failed to add mux-adapter %u as bus %u (error=%d)\n", + chan_id, force_nr, ret); + goto err_free_priv; + } } else { ret = i2c_add_adapter(&priv->adap); - dev_err(&parent->dev, - "failed to add mux-adapter %u (error=%d)\n", - chan_id, ret); - } - if (ret < 0) { - kfree(priv); - return ret; + if (ret < 0) { + dev_err(&parent->dev, + "failed to add mux-adapter %u (error=%d)\n", + chan_id, ret); + goto err_free_priv; + } } WARN(sysfs_create_link(&priv->adap.dev.kobj, &muxc->dev->kobj, @@ -422,6 +424,10 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc, muxc->adapter[muxc->num_adapters++] = &priv->adap; return 0; + +err_free_priv: + kfree(priv); + return ret; } EXPORT_SYMBOL_GPL(i2c_mux_add_adapter); diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c index 406d5059072c..d97031804de8 100644 --- a/drivers/i2c/muxes/i2c-mux-reg.c +++ b/drivers/i2c/muxes/i2c-mux-reg.c @@ -196,20 +196,25 @@ static int i2c_mux_reg_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); mux->data.reg_size = resource_size(res); mux->data.reg = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(mux->data.reg)) - return PTR_ERR(mux->data.reg); + if (IS_ERR(mux->data.reg)) { + ret = PTR_ERR(mux->data.reg); + goto err_put_parent; + } } if (mux->data.reg_size != 4 && mux->data.reg_size != 2 && mux->data.reg_size != 1) { dev_err(&pdev->dev, "Invalid register size\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put_parent; } muxc = i2c_mux_alloc(parent, &pdev->dev, mux->data.n_values, 0, 0, i2c_mux_reg_select, NULL); - if (!muxc) - return -ENOMEM; + if (!muxc) { + ret = -ENOMEM; + goto err_put_parent; + } muxc->priv = mux; platform_set_drvdata(pdev, muxc); @@ -223,7 +228,7 @@ static int i2c_mux_reg_probe(struct platform_device *pdev) ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], class); if (ret) - goto add_adapter_failed; + goto err_del_mux_adapters; } dev_dbg(&pdev->dev, "%d port mux on %s adapter\n", @@ -231,8 +236,10 @@ static int i2c_mux_reg_probe(struct platform_device *pdev) return 0; -add_adapter_failed: +err_del_mux_adapters: i2c_mux_del_adapters(muxc); +err_put_parent: + i2c_put_adapter(parent); return ret; } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 5db11a405129..cd8139593ccd 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -218,7 +218,7 @@ static DEFINE_SPINLOCK(param_spinlock); * Buffers are freed after this timeout */ static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS; -static unsigned dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES; +static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES; static unsigned long dm_bufio_peak_allocated; static unsigned long dm_bufio_allocated_kmem_cache; @@ -1558,10 +1558,10 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp) return true; } -static unsigned get_retain_buffers(struct dm_bufio_client *c) +static unsigned long get_retain_buffers(struct dm_bufio_client *c) { - unsigned retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); - return retain_bytes / c->block_size; + unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); + return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT); } static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, @@ -1571,7 +1571,7 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, struct dm_buffer *b, *tmp; unsigned long freed = 0; unsigned long count = nr_to_scan; - unsigned retain_target = get_retain_buffers(c); + unsigned long retain_target = get_retain_buffers(c); for (l = 0; l < LIST_SIZE; l++) { list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) { @@ -1794,8 +1794,8 @@ static bool older_than(struct dm_buffer *b, unsigned long age_hz) static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz) { struct dm_buffer *b, *tmp; - unsigned retain_target = get_retain_buffers(c); - unsigned count; + unsigned long retain_target = get_retain_buffers(c); + unsigned long count; LIST_HEAD(write_list); dm_bufio_lock(c); @@ -1955,7 +1955,7 @@ MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache"); module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds"); -module_param_named(retain_bytes, dm_bufio_retain_bytes, uint, S_IRUGO | S_IWUSR); +module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory"); module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR); diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c index 9b1afdfb13f0..707233891291 100644 --- a/drivers/md/dm-cache-background-tracker.c +++ b/drivers/md/dm-cache-background-tracker.c @@ -33,6 +33,11 @@ struct background_tracker *btracker_create(unsigned max_work) { struct background_tracker *b = kmalloc(sizeof(*b), GFP_KERNEL); + if (!b) { + DMERR("couldn't create background_tracker"); + return NULL; + } + b->max_work = max_work; atomic_set(&b->pending_promotes, 0); atomic_set(&b->pending_writebacks, 0); diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index 72479bd61e11..e5eb9c9b4bc8 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1120,8 +1120,6 @@ static bool clean_target_met(struct smq_policy *mq, bool idle) * Cache entries may not be populated. So we cannot rely on the * size of the clean queue. */ - unsigned nr_clean; - if (idle) { /* * We'd like to clean everything. @@ -1129,18 +1127,16 @@ static bool clean_target_met(struct smq_policy *mq, bool idle) return q_size(&mq->dirty) == 0u; } - nr_clean = from_cblock(mq->cache_size) - q_size(&mq->dirty); - return (nr_clean + btracker_nr_writebacks_queued(mq->bg_work)) >= - percent_to_target(mq, CLEAN_TARGET); + /* + * If we're busy we don't worry about cleaning at all. + */ + return true; } -static bool free_target_met(struct smq_policy *mq, bool idle) +static bool free_target_met(struct smq_policy *mq) { unsigned nr_free; - if (!idle) - return true; - nr_free = from_cblock(mq->cache_size) - mq->cache_alloc.nr_allocated; return (nr_free + btracker_nr_demotions_queued(mq->bg_work)) >= percent_to_target(mq, FREE_TARGET); @@ -1190,9 +1186,9 @@ static void queue_demotion(struct smq_policy *mq) if (unlikely(WARN_ON_ONCE(!mq->migrations_allowed))) return; - e = q_peek(&mq->clean, mq->clean.nr_levels, true); + e = q_peek(&mq->clean, mq->clean.nr_levels / 2, true); if (!e) { - if (!clean_target_met(mq, false)) + if (!clean_target_met(mq, true)) queue_writeback(mq); return; } @@ -1220,7 +1216,7 @@ static void queue_promotion(struct smq_policy *mq, dm_oblock_t oblock, * We always claim to be 'idle' to ensure some demotions happen * with continuous loads. */ - if (!free_target_met(mq, true)) + if (!free_target_met(mq)) queue_demotion(mq); return; } @@ -1421,14 +1417,10 @@ static int smq_get_background_work(struct dm_cache_policy *p, bool idle, spin_lock_irqsave(&mq->lock, flags); r = btracker_issue(mq->bg_work, result); if (r == -ENODATA) { - /* find some writeback work to do */ - if (mq->migrations_allowed && !free_target_met(mq, idle)) - queue_demotion(mq); - - else if (!clean_target_met(mq, idle)) + if (!clean_target_met(mq, idle)) { queue_writeback(mq); - - r = btracker_issue(mq->bg_work, result); + r = btracker_issue(mq->bg_work, result); + } } spin_unlock_irqrestore(&mq->lock, flags); @@ -1452,6 +1444,7 @@ static void __complete_background_work(struct smq_policy *mq, clear_pending(mq, e); if (success) { e->oblock = work->oblock; + e->level = NR_CACHE_LEVELS - 1; push(mq, e); // h, q, a } else { diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 1db375f50a13..d682a0511381 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -94,6 +94,9 @@ static void iot_io_begin(struct io_tracker *iot, sector_t len) static void __iot_io_end(struct io_tracker *iot, sector_t len) { + if (!len) + return; + iot->in_flight -= len; if (!iot->in_flight) iot->idle_time = jiffies; @@ -474,7 +477,7 @@ struct cache { spinlock_t invalidation_lock; struct list_head invalidation_requests; - struct io_tracker origin_tracker; + struct io_tracker tracker; struct work_struct commit_ws; struct batcher committer; @@ -901,8 +904,7 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio) static bool accountable_bio(struct cache *cache, struct bio *bio) { - return ((bio->bi_bdev == cache->origin_dev->bdev) && - bio_op(bio) != REQ_OP_DISCARD); + return bio_op(bio) != REQ_OP_DISCARD; } static void accounted_begin(struct cache *cache, struct bio *bio) @@ -912,7 +914,7 @@ static void accounted_begin(struct cache *cache, struct bio *bio) if (accountable_bio(cache, bio)) { pb->len = bio_sectors(bio); - iot_io_begin(&cache->origin_tracker, pb->len); + iot_io_begin(&cache->tracker, pb->len); } } @@ -921,7 +923,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio) size_t pb_data_size = get_per_bio_data_size(cache); struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); - iot_io_end(&cache->origin_tracker, pb->len); + iot_io_end(&cache->tracker, pb->len); } static void accounted_request(struct cache *cache, struct bio *bio) @@ -1716,20 +1718,19 @@ static int invalidate_start(struct cache *cache, dm_cblock_t cblock, enum busy { IDLE, - MODERATE, BUSY }; static enum busy spare_migration_bandwidth(struct cache *cache) { - bool idle = iot_idle_for(&cache->origin_tracker, HZ); + bool idle = iot_idle_for(&cache->tracker, HZ); sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) * cache->sectors_per_block; - if (current_volume <= cache->migration_threshold) - return idle ? IDLE : MODERATE; + if (idle && current_volume <= cache->migration_threshold) + return IDLE; else - return idle ? MODERATE : BUSY; + return BUSY; } static void inc_hit_counter(struct cache *cache, struct bio *bio) @@ -2045,8 +2046,6 @@ static void check_migrations(struct work_struct *ws) for (;;) { b = spare_migration_bandwidth(cache); - if (b == BUSY) - break; r = policy_get_background_work(cache->policy, b == IDLE, &op); if (r == -ENODATA) @@ -2717,7 +2716,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) batcher_init(&cache->committer, commit_op, cache, issue_op, cache, cache->wq); - iot_init(&cache->origin_tracker); + iot_init(&cache->tracker); init_rwsem(&cache->background_work_lock); prevent_background_work(cache); @@ -2941,7 +2940,7 @@ static void cache_postsuspend(struct dm_target *ti) cancel_delayed_work(&cache->waker); flush_workqueue(cache->wq); - WARN_ON(cache->origin_tracker.in_flight); + WARN_ON(cache->tracker.in_flight); /* * If it's a flush suspend there won't be any deferred bios, so this diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 926a6bcb32c8..3df056b73b66 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -447,7 +447,7 @@ failed: * it has been invoked. */ #define dm_report_EIO(m) \ -({ \ +do { \ struct mapped_device *md = dm_table_get_md((m)->ti->table); \ \ pr_debug("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d\n", \ @@ -455,8 +455,7 @@ failed: test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags), \ test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags), \ dm_noflush_suspending((m)->ti)); \ - -EIO; \ -}) +} while (0) /* * Map cloned requests (request-based multipath) @@ -481,7 +480,8 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, if (!pgpath) { if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) return DM_MAPIO_DELAY_REQUEUE; - return dm_report_EIO(m); /* Failed */ + dm_report_EIO(m); /* Failed */ + return DM_MAPIO_KILL; } else if (test_bit(MPATHF_QUEUE_IO, &m->flags) || test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags)) { if (pg_init_all_paths(m)) @@ -558,7 +558,8 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m if (!pgpath) { if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) return DM_MAPIO_REQUEUE; - return dm_report_EIO(m); + dm_report_EIO(m); + return -EIO; } mpio->pgpath = pgpath; @@ -1493,7 +1494,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone, if (atomic_read(&m->nr_valid_paths) == 0 && !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { if (error == -EIO) - error = dm_report_EIO(m); + dm_report_EIO(m); /* complete with the original error */ r = DM_ENDIO_DONE; } @@ -1524,8 +1525,10 @@ static int do_end_io_bio(struct multipath *m, struct bio *clone, fail_path(mpio->pgpath); if (atomic_read(&m->nr_valid_paths) == 0 && - !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) - return dm_report_EIO(m); + !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { + dm_report_EIO(m); + return -EIO; + } /* Queue for the daemon to resubmit */ dm_bio_restore(get_bio_details_from_bio(clone), clone); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 2af27026aa2e..b639fa7246ee 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -507,6 +507,7 @@ static int map_request(struct dm_rq_target_io *tio) case DM_MAPIO_KILL: /* The target wants to complete the I/O */ dm_kill_unmapped_request(rq, -EIO); + break; default: DMWARN("unimplemented target map return value: %d", r); BUG(); diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 0f0251d0d337..d31d18d9727c 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -484,11 +484,11 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd) if (r < 0) return r; - r = save_sm_roots(pmd); + r = dm_tm_pre_commit(pmd->tm); if (r < 0) return r; - r = dm_tm_pre_commit(pmd->tm); + r = save_sm_roots(pmd); if (r < 0) return r; diff --git a/drivers/md/md.c b/drivers/md/md.c index 82f798be964f..10367ffe92e3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8022,18 +8022,15 @@ EXPORT_SYMBOL(md_write_end); * may proceed without blocking. It is important to call this before * attempting a GFP_KERNEL allocation while holding the mddev lock. * Must be called with mddev_lock held. - * - * In the ->external case MD_SB_CHANGE_PENDING can not be cleared until mddev->lock - * is dropped, so return -EAGAIN after notifying userspace. */ -int md_allow_write(struct mddev *mddev) +void md_allow_write(struct mddev *mddev) { if (!mddev->pers) - return 0; + return; if (mddev->ro) - return 0; + return; if (!mddev->pers->sync_request) - return 0; + return; spin_lock(&mddev->lock); if (mddev->in_sync) { @@ -8046,13 +8043,12 @@ int md_allow_write(struct mddev *mddev) spin_unlock(&mddev->lock); md_update_sb(mddev, 0); sysfs_notify_dirent_safe(mddev->sysfs_state); + /* wait for the dirty state to be recorded in the metadata */ + wait_event(mddev->sb_wait, + !test_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags) && + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); } else spin_unlock(&mddev->lock); - - if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) - return -EAGAIN; - else - return 0; } EXPORT_SYMBOL_GPL(md_allow_write); diff --git a/drivers/md/md.h b/drivers/md/md.h index 4e75d121bfcc..11f15146ce51 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -665,7 +665,7 @@ extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, bool metadata_op); extern void md_do_sync(struct md_thread *thread); extern void md_new_event(struct mddev *mddev); -extern int md_allow_write(struct mddev *mddev); +extern void md_allow_write(struct mddev *mddev); extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c index ebb280a14325..32adf6b4a9c7 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.c +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -142,10 +142,23 @@ static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b) static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b) { + int r; + uint32_t old_count; enum allocation_event ev; struct sm_disk *smd = container_of(sm, struct sm_disk, sm); - return sm_ll_dec(&smd->ll, b, &ev); + r = sm_ll_dec(&smd->ll, b, &ev); + if (!r && (ev == SM_FREE)) { + /* + * It's only free if it's also free in the last + * transaction. + */ + r = sm_ll_lookup(&smd->old_ll, b, &old_count); + if (!r && !old_count) + smd->nr_allocated_this_transaction--; + } + + return r; } static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 84e58596594d..d6c0bc76e837 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -385,7 +385,7 @@ static int raid0_run(struct mddev *mddev) blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_discard_sectors(mddev->queue, UINT_MAX); blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); blk_queue_io_opt(mddev->queue, @@ -459,6 +459,95 @@ static inline int is_io_in_chunk_boundary(struct mddev *mddev, } } +static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) +{ + struct r0conf *conf = mddev->private; + struct strip_zone *zone; + sector_t start = bio->bi_iter.bi_sector; + sector_t end; + unsigned int stripe_size; + sector_t first_stripe_index, last_stripe_index; + sector_t start_disk_offset; + unsigned int start_disk_index; + sector_t end_disk_offset; + unsigned int end_disk_index; + unsigned int disk; + + zone = find_zone(conf, &start); + + if (bio_end_sector(bio) > zone->zone_end) { + struct bio *split = bio_split(bio, + zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO, + mddev->bio_set); + bio_chain(split, bio); + generic_make_request(bio); + bio = split; + end = zone->zone_end; + } else + end = bio_end_sector(bio); + + if (zone != conf->strip_zone) + end = end - zone[-1].zone_end; + + /* Now start and end is the offset in zone */ + stripe_size = zone->nb_dev * mddev->chunk_sectors; + + first_stripe_index = start; + sector_div(first_stripe_index, stripe_size); + last_stripe_index = end; + sector_div(last_stripe_index, stripe_size); + + start_disk_index = (int)(start - first_stripe_index * stripe_size) / + mddev->chunk_sectors; + start_disk_offset = ((int)(start - first_stripe_index * stripe_size) % + mddev->chunk_sectors) + + first_stripe_index * mddev->chunk_sectors; + end_disk_index = (int)(end - last_stripe_index * stripe_size) / + mddev->chunk_sectors; + end_disk_offset = ((int)(end - last_stripe_index * stripe_size) % + mddev->chunk_sectors) + + last_stripe_index * mddev->chunk_sectors; + + for (disk = 0; disk < zone->nb_dev; disk++) { + sector_t dev_start, dev_end; + struct bio *discard_bio = NULL; + struct md_rdev *rdev; + + if (disk < start_disk_index) + dev_start = (first_stripe_index + 1) * + mddev->chunk_sectors; + else if (disk > start_disk_index) + dev_start = first_stripe_index * mddev->chunk_sectors; + else + dev_start = start_disk_offset; + + if (disk < end_disk_index) + dev_end = (last_stripe_index + 1) * mddev->chunk_sectors; + else if (disk > end_disk_index) + dev_end = last_stripe_index * mddev->chunk_sectors; + else + dev_end = end_disk_offset; + + if (dev_end <= dev_start) + continue; + + rdev = conf->devlist[(zone - conf->strip_zone) * + conf->strip_zone[0].nb_dev + disk]; + if (__blkdev_issue_discard(rdev->bdev, + dev_start + zone->dev_start + rdev->data_offset, + dev_end - dev_start, GFP_NOIO, 0, &discard_bio) || + !discard_bio) + continue; + bio_chain(discard_bio, bio); + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(rdev->bdev), + discard_bio, disk_devt(mddev->gendisk), + bio->bi_iter.bi_sector); + generic_make_request(discard_bio); + } + bio_endio(bio); +} + static void raid0_make_request(struct mddev *mddev, struct bio *bio) { struct strip_zone *zone; @@ -473,6 +562,11 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) return; } + if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) { + raid0_handle_discard(mddev, bio); + return; + } + bio_sector = bio->bi_iter.bi_sector; sector = bio_sector; chunk_sects = mddev->chunk_sectors; @@ -498,19 +592,13 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) bio->bi_iter.bi_sector = sector + zone->dev_start + tmp_dev->data_offset; - if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) { - /* Just ignore it */ - bio_endio(bio); - } else { - if (mddev->gendisk) - trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), - bio, disk_devt(mddev->gendisk), - bio_sector); - mddev_check_writesame(mddev, bio); - mddev_check_write_zeroes(mddev, bio); - generic_make_request(bio); - } + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), + bio, disk_devt(mddev->gendisk), + bio_sector); + mddev_check_writesame(mddev, bio); + mddev_check_write_zeroes(mddev, bio); + generic_make_request(bio); } static void raid0_status(struct seq_file *seq, struct mddev *mddev) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 7ed59351fe97..af5056d56878 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -666,8 +666,11 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect break; } continue; - } else + } else { + if ((sectors > best_good_sectors) && (best_disk >= 0)) + best_disk = -1; best_good_sectors = sectors; + } if (best_disk >= 0) /* At least two disks to choose from so failfast is OK */ @@ -1529,17 +1532,16 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, plug = container_of(cb, struct raid1_plug_cb, cb); else plug = NULL; - spin_lock_irqsave(&conf->device_lock, flags); if (plug) { bio_list_add(&plug->pending, mbio); plug->pending_cnt++; } else { + spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; - } - spin_unlock_irqrestore(&conf->device_lock, flags); - if (!plug) + spin_unlock_irqrestore(&conf->device_lock, flags); md_wakeup_thread(mddev->thread); + } } r1_bio_write_done(r1_bio); @@ -3197,7 +3199,7 @@ static int raid1_reshape(struct mddev *mddev) struct r1conf *conf = mddev->private; int cnt, raid_disks; unsigned long flags; - int d, d2, err; + int d, d2; /* Cannot change chunk_size, layout, or level */ if (mddev->chunk_sectors != mddev->new_chunk_sectors || @@ -3209,11 +3211,8 @@ static int raid1_reshape(struct mddev *mddev) return -EINVAL; } - if (!mddev_is_clustered(mddev)) { - err = md_allow_write(mddev); - if (err) - return err; - } + if (!mddev_is_clustered(mddev)) + md_allow_write(mddev); raid_disks = mddev->raid_disks + mddev->delta_disks; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 6b86a0032cf8..4343d7ff9916 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1282,17 +1282,16 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, plug = container_of(cb, struct raid10_plug_cb, cb); else plug = NULL; - spin_lock_irqsave(&conf->device_lock, flags); if (plug) { bio_list_add(&plug->pending, mbio); plug->pending_cnt++; } else { + spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; - } - spin_unlock_irqrestore(&conf->device_lock, flags); - if (!plug) + spin_unlock_irqrestore(&conf->device_lock, flags); md_wakeup_thread(mddev->thread); + } } static void raid10_write_request(struct mddev *mddev, struct bio *bio, diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 26ba09282e7c..4c00bc248287 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -24,6 +24,7 @@ #include "md.h" #include "raid5.h" #include "bitmap.h" +#include "raid5-log.h" /* * metadata/data stored in disk with 4k size unit (a block) regardless @@ -622,20 +623,30 @@ static void r5l_do_submit_io(struct r5l_log *log, struct r5l_io_unit *io) __r5l_set_io_unit_state(io, IO_UNIT_IO_START); spin_unlock_irqrestore(&log->io_list_lock, flags); + /* + * In case of journal device failures, submit_bio will get error + * and calls endio, then active stripes will continue write + * process. Therefore, it is not necessary to check Faulty bit + * of journal device here. + * + * We can't check split_bio after current_bio is submitted. If + * io->split_bio is null, after current_bio is submitted, current_bio + * might already be completed and the io_unit is freed. We submit + * split_bio first to avoid the issue. + */ + if (io->split_bio) { + if (io->has_flush) + io->split_bio->bi_opf |= REQ_PREFLUSH; + if (io->has_fua) + io->split_bio->bi_opf |= REQ_FUA; + submit_bio(io->split_bio); + } + if (io->has_flush) io->current_bio->bi_opf |= REQ_PREFLUSH; if (io->has_fua) io->current_bio->bi_opf |= REQ_FUA; submit_bio(io->current_bio); - - if (!io->split_bio) - return; - - if (io->has_flush) - io->split_bio->bi_opf |= REQ_PREFLUSH; - if (io->has_fua) - io->split_bio->bi_opf |= REQ_FUA; - submit_bio(io->split_bio); } /* deferred io_unit will be dispatched here */ @@ -670,6 +681,11 @@ static void r5c_disable_writeback_async(struct work_struct *work) return; pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n", mdname(mddev)); + + /* wait superblock change before suspend */ + wait_event(mddev->sb_wait, + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); + mddev_suspend(mddev); log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; mddev_resume(mddev); @@ -2621,8 +2637,11 @@ int r5c_try_caching_write(struct r5conf *conf, * When run in degraded mode, array is set to write-through mode. * This check helps drain pending write safely in the transition to * write-through mode. + * + * When a stripe is syncing, the write is also handled in write + * through mode. */ - if (s->failed) { + if (s->failed || test_bit(STRIPE_SYNCING, &sh->state)) { r5c_make_stripe_write_out(sh); return -EAGAIN; } @@ -2825,6 +2844,9 @@ void r5c_finish_stripe_write_out(struct r5conf *conf, } r5l_append_flush_payload(log, sh->sector); + /* stripe is flused to raid disks, we can do resync now */ + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) + set_bit(STRIPE_HANDLE, &sh->state); } int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh) @@ -2973,7 +2995,7 @@ ioerr: return ret; } -void r5c_update_on_rdev_error(struct mddev *mddev) +void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev) { struct r5conf *conf = mddev->private; struct r5l_log *log = conf->log; @@ -2981,7 +3003,8 @@ void r5c_update_on_rdev_error(struct mddev *mddev) if (!log) return; - if (raid5_calc_degraded(conf) > 0 && + if ((raid5_calc_degraded(conf) > 0 || + test_bit(Journal, &rdev->flags)) && conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK) schedule_work(&log->disable_writeback_work); } diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h index 27097101ccca..328d67aedda4 100644 --- a/drivers/md/raid5-log.h +++ b/drivers/md/raid5-log.h @@ -28,7 +28,8 @@ extern void r5c_flush_cache(struct r5conf *conf, int num); extern void r5c_check_stripe_cache_usage(struct r5conf *conf); extern void r5c_check_cached_full_stripe(struct r5conf *conf); extern struct md_sysfs_entry r5c_journal_mode; -extern void r5c_update_on_rdev_error(struct mddev *mddev); +extern void r5c_update_on_rdev_error(struct mddev *mddev, + struct md_rdev *rdev); extern bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect); extern struct dma_async_tx_descriptor * diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2e38cfac5b1d..9c4f7659f8b1 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -103,8 +103,7 @@ static inline void unlock_device_hash_lock(struct r5conf *conf, int hash) static inline void lock_all_device_hash_locks_irq(struct r5conf *conf) { int i; - local_irq_disable(); - spin_lock(conf->hash_locks); + spin_lock_irq(conf->hash_locks); for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++) spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks); spin_lock(&conf->device_lock); @@ -114,9 +113,9 @@ static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf) { int i; spin_unlock(&conf->device_lock); - for (i = NR_STRIPE_HASH_LOCKS; i; i--) - spin_unlock(conf->hash_locks + i - 1); - local_irq_enable(); + for (i = NR_STRIPE_HASH_LOCKS - 1; i; i--) + spin_unlock(conf->hash_locks + i); + spin_unlock_irq(conf->hash_locks); } /* Find first data disk in a raid6 stripe */ @@ -234,11 +233,15 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh, if (test_bit(R5_InJournal, &sh->dev[i].flags)) injournal++; /* - * When quiesce in r5c write back, set STRIPE_HANDLE for stripes with - * data in journal, so they are not released to cached lists + * In the following cases, the stripe cannot be released to cached + * lists. Therefore, we make the stripe write out and set + * STRIPE_HANDLE: + * 1. when quiesce in r5c write back; + * 2. when resync is requested fot the stripe. */ - if (conf->quiesce && r5c_is_writeback(conf->log) && - !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0) { + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) || + (conf->quiesce && r5c_is_writeback(conf->log) && + !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0)) { if (test_bit(STRIPE_R5C_CACHING, &sh->state)) r5c_make_stripe_write_out(sh); set_bit(STRIPE_HANDLE, &sh->state); @@ -714,12 +717,11 @@ static bool is_full_stripe_write(struct stripe_head *sh) static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) { - local_irq_disable(); if (sh1 > sh2) { - spin_lock(&sh2->stripe_lock); + spin_lock_irq(&sh2->stripe_lock); spin_lock_nested(&sh1->stripe_lock, 1); } else { - spin_lock(&sh1->stripe_lock); + spin_lock_irq(&sh1->stripe_lock); spin_lock_nested(&sh2->stripe_lock, 1); } } @@ -727,8 +729,7 @@ static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) { spin_unlock(&sh1->stripe_lock); - spin_unlock(&sh2->stripe_lock); - local_irq_enable(); + spin_unlock_irq(&sh2->stripe_lock); } /* Only freshly new full stripe normal write stripe can be added to a batch list */ @@ -2312,14 +2313,12 @@ static int resize_stripes(struct r5conf *conf, int newsize) struct stripe_head *osh, *nsh; LIST_HEAD(newstripes); struct disk_info *ndisks; - int err; + int err = 0; struct kmem_cache *sc; int i; int hash, cnt; - err = md_allow_write(conf->mddev); - if (err) - return err; + md_allow_write(conf->mddev); /* Step 1 */ sc = kmem_cache_create(conf->cache_name[1-conf->active_name], @@ -2694,7 +2693,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) bdevname(rdev->bdev, b), mdname(mddev), conf->raid_disks - mddev->degraded); - r5c_update_on_rdev_error(mddev); + r5c_update_on_rdev_error(mddev, rdev); } /* @@ -3055,6 +3054,11 @@ sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous) * When LOG_CRITICAL, stripes with injournal == 0 will be sent to * no_space_stripes list. * + * 3. during journal failure + * In journal failure, we try to flush all cached data to raid disks + * based on data in stripe cache. The array is read-only to upper + * layers, so we would skip all pending writes. + * */ static inline bool delay_towrite(struct r5conf *conf, struct r5dev *dev, @@ -3068,6 +3072,9 @@ static inline bool delay_towrite(struct r5conf *conf, if (test_bit(R5C_LOG_CRITICAL, &conf->cache_state) && s->injournal > 0) return true; + /* case 3 above */ + if (s->log_failed && s->injournal) + return true; return false; } @@ -4653,8 +4660,13 @@ static void handle_stripe(struct stripe_head *sh) if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) { spin_lock(&sh->stripe_lock); - /* Cannot process 'sync' concurrently with 'discard' */ - if (!test_bit(STRIPE_DISCARD, &sh->state) && + /* + * Cannot process 'sync' concurrently with 'discard'. + * Flush data in r5cache before 'sync'. + */ + if (!test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state) && + !test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) && + !test_bit(STRIPE_DISCARD, &sh->state) && test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { set_bit(STRIPE_SYNCING, &sh->state); clear_bit(STRIPE_INSYNC, &sh->state); @@ -4701,10 +4713,15 @@ static void handle_stripe(struct stripe_head *sh) " to_write=%d failed=%d failed_num=%d,%d\n", s.locked, s.uptodate, s.to_read, s.to_write, s.failed, s.failed_num[0], s.failed_num[1]); - /* check if the array has lost more than max_degraded devices and, + /* + * check if the array has lost more than max_degraded devices and, * if so, some requests might need to be failed. + * + * When journal device failed (log_failed), we will only process + * the stripe if there is data need write to raid disks */ - if (s.failed > conf->max_degraded || s.log_failed) { + if (s.failed > conf->max_degraded || + (s.log_failed && s.injournal == 0)) { sh->check_state = 0; sh->reconstruct_state = 0; break_stripe_batch_list(sh, 0); @@ -5277,8 +5294,10 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group) struct stripe_head *sh, *tmp; struct list_head *handle_list = NULL; struct r5worker_group *wg; - bool second_try = !r5c_is_writeback(conf->log); - bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state); + bool second_try = !r5c_is_writeback(conf->log) && + !r5l_log_disk_error(conf); + bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state) || + r5l_log_disk_error(conf); again: wg = NULL; @@ -6313,7 +6332,6 @@ int raid5_set_cache_size(struct mddev *mddev, int size) { struct r5conf *conf = mddev->private; - int err; if (size <= 16 || size > 32768) return -EINVAL; @@ -6325,10 +6343,7 @@ raid5_set_cache_size(struct mddev *mddev, int size) ; mutex_unlock(&conf->cache_size_mutex); - - err = md_allow_write(mddev); - if (err) - return err; + md_allow_write(mddev); mutex_lock(&conf->cache_size_mutex); while (size > conf->max_nr_stripes) @@ -7530,7 +7545,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) * neilb: there is no locking about new writes here, * so this cannot be safe. */ - if (atomic_read(&conf->active_stripes)) { + if (atomic_read(&conf->active_stripes) || + atomic_read(&conf->r5c_cached_full_stripes) || + atomic_read(&conf->r5c_cached_partial_stripes)) { return -EBUSY; } log_exit(conf); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 19581d783d8e..d034d8cd7d22 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -849,6 +849,9 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, mv88e6xxx_g1_stats_read(chip, reg, &low); if (s->sizeof_stat == 8) mv88e6xxx_g1_stats_read(chip, reg + 1, &high); + break; + default: + return UINT64_MAX; } value = (((u64)high) << 16) | low; return value; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 4ee15ff06a44..faeb4935ef3e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -200,29 +200,18 @@ err_exit: static int hw_atl_a0_hw_offload_set(struct aq_hw_s *self, struct aq_nic_cfg_s *aq_nic_cfg) { - int err = 0; - /* TX checksums offloads*/ tpo_ipv4header_crc_offload_en_set(self, 1); tpo_tcp_udp_crc_offload_en_set(self, 1); - if (err < 0) - goto err_exit; /* RX checksums offloads*/ rpo_ipv4header_crc_offload_en_set(self, 1); rpo_tcp_udp_crc_offload_en_set(self, 1); - if (err < 0) - goto err_exit; /* LSO offloads*/ tdm_large_send_offload_en_set(self, 0xFFFFFFFFU); - if (err < 0) - goto err_exit; - - err = aq_hw_err_from_flags(self); -err_exit: - return err; + return aq_hw_err_from_flags(self); } static int hw_atl_a0_hw_init_tx_path(struct aq_hw_s *self) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 42150708191d..1bceb7358e5c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -200,25 +200,18 @@ err_exit: static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self, struct aq_nic_cfg_s *aq_nic_cfg) { - int err = 0; unsigned int i; /* TX checksums offloads*/ tpo_ipv4header_crc_offload_en_set(self, 1); tpo_tcp_udp_crc_offload_en_set(self, 1); - if (err < 0) - goto err_exit; /* RX checksums offloads*/ rpo_ipv4header_crc_offload_en_set(self, 1); rpo_tcp_udp_crc_offload_en_set(self, 1); - if (err < 0) - goto err_exit; /* LSO offloads*/ tdm_large_send_offload_en_set(self, 0xFFFFFFFFU); - if (err < 0) - goto err_exit; /* LRO offloads */ { @@ -245,10 +238,7 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self, rpo_lro_en_set(self, aq_nic_cfg->is_lro ? 0xFFFFFFFFU : 0U); } - err = aq_hw_err_from_flags(self); - -err_exit: - return err; + return aq_hw_err_from_flags(self); } static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b56c54d68d5e..03f55daecb20 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7630,8 +7630,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->min_mtu = ETH_ZLEN; dev->max_mtu = BNXT_MAX_MTU; - bnxt_dcb_init(bp); - #ifdef CONFIG_BNXT_SRIOV init_waitqueue_head(&bp->sriov_cfg_wait); #endif @@ -7669,6 +7667,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bnxt_hwrm_func_qcfg(bp); bnxt_hwrm_port_led_qcaps(bp); bnxt_ethtool_init(bp); + bnxt_dcb_init(bp); bnxt_set_rx_skb_mode(bp, false); bnxt_set_tpa_flags(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index 46de2f8ff024..5c6dd0ce209f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -553,8 +553,10 @@ static u8 bnxt_dcbnl_setdcbx(struct net_device *dev, u8 mode) if ((mode & DCB_CAP_DCBX_VER_CEE) || !(mode & DCB_CAP_DCBX_VER_IEEE)) return 1; - if ((mode & DCB_CAP_DCBX_HOST) && BNXT_VF(bp)) - return 1; + if (mode & DCB_CAP_DCBX_HOST) { + if (BNXT_VF(bp) || (bp->flags & BNXT_FLAG_FW_LLDP_AGENT)) + return 1; + } if (mode == bp->dcbx_cap) return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h index fa376444e57c..3549d3876278 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h @@ -37,7 +37,7 @@ #define T4FW_VERSION_MAJOR 0x01 #define T4FW_VERSION_MINOR 0x10 -#define T4FW_VERSION_MICRO 0x21 +#define T4FW_VERSION_MICRO 0x2B #define T4FW_VERSION_BUILD 0x00 #define T4FW_MIN_VERSION_MAJOR 0x01 @@ -46,7 +46,7 @@ #define T5FW_VERSION_MAJOR 0x01 #define T5FW_VERSION_MINOR 0x10 -#define T5FW_VERSION_MICRO 0x21 +#define T5FW_VERSION_MICRO 0x2B #define T5FW_VERSION_BUILD 0x00 #define T5FW_MIN_VERSION_MAJOR 0x00 @@ -55,7 +55,7 @@ #define T6FW_VERSION_MAJOR 0x01 #define T6FW_VERSION_MINOR 0x10 -#define T6FW_VERSION_MICRO 0x21 +#define T6FW_VERSION_MICRO 0x2B #define T6FW_VERSION_BUILD 0x00 #define T6FW_MIN_VERSION_MAJOR 0x00 diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c index 6ac336b546e6..1536356e2ea8 100644 --- a/drivers/net/ethernet/faraday/ftmac100.c +++ b/drivers/net/ethernet/faraday/ftmac100.c @@ -1174,11 +1174,17 @@ static int ftmac100_remove(struct platform_device *pdev) return 0; } +static const struct of_device_id ftmac100_of_ids[] = { + { .compatible = "andestech,atmac100" }, + { } +}; + static struct platform_driver ftmac100_driver = { .probe = ftmac100_probe, .remove = ftmac100_remove, .driver = { .name = DRV_NAME, + .of_match_table = ftmac100_of_ids }, }; @@ -1202,3 +1208,4 @@ module_exit(ftmac100_exit); MODULE_AUTHOR("Po-Yu Chuang <ratbert@faraday-tech.com>"); MODULE_DESCRIPTION("FTMAC100 driver"); MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(of, ftmac100_of_ids); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 703205475524..83aab1e4c8c8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2862,12 +2862,10 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) int port = 0; if (msi_x) { - int nreq = dev->caps.num_ports * num_online_cpus() + 1; - - nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs, - nreq); - if (nreq > MAX_MSIX) - nreq = MAX_MSIX; + int nreq = min3(dev->caps.num_ports * + (int)num_online_cpus() + 1, + dev->caps.num_eqs - dev->caps.reserved_eqs, + MAX_MSIX); entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL); if (!entries) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index fc52d742b7f7..27251a78075c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -13,7 +13,7 @@ config MLX5_CORE config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" - depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE + depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE depends on IPV6=y || IPV6=n || MLX5_CORE=m imply PTP_1588_CLOCK default n diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0099a3e397bc..2fd044b23875 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1003,7 +1003,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv); void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv); void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt); -int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn); +int mlx5e_create_ttc_table(struct mlx5e_priv *priv); void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv); int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index ce7b09d72ff6..8209affa75c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -794,7 +794,6 @@ static void get_supported(u32 eth_proto_cap, ptys2ethtool_supported_port(link_ksettings, eth_proto_cap); ptys2ethtool_supported_link(supported, eth_proto_cap); ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause); - ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Asym_Pause); } static void get_advertising(u32 eth_proto_cap, u8 tx_pause, @@ -804,7 +803,7 @@ static void get_advertising(u32 eth_proto_cap, u8 tx_pause, unsigned long *advertising = link_ksettings->link_modes.advertising; ptys2ethtool_adver_link(advertising, eth_proto_cap); - if (tx_pause) + if (rx_pause) ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause); if (tx_pause ^ rx_pause) ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Asym_Pause); @@ -849,6 +848,8 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev, struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0}; + u32 rx_pause = 0; + u32 tx_pause = 0; u32 eth_proto_cap; u32 eth_proto_admin; u32 eth_proto_lp; @@ -871,11 +872,13 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev, an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); an_status = MLX5_GET(ptys_reg, out, an_status); + mlx5_query_port_pause(mdev, &rx_pause, &tx_pause); + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); get_supported(eth_proto_cap, link_ksettings); - get_advertising(eth_proto_admin, 0, 0, link_ksettings); + get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings); get_speed_duplex(netdev, eth_proto_oper, link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 576d6787b484..53ed58320a24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -800,7 +800,7 @@ void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv) mlx5e_destroy_flow_table(&ttc->ft); } -int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn) +int mlx5e_create_ttc_table(struct mlx5e_priv *priv) { struct mlx5e_ttc_table *ttc = &priv->fs.ttc; struct mlx5_flow_table_attr ft_attr = {}; @@ -810,7 +810,6 @@ int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn) ft_attr.max_fte = MLX5E_TTC_TABLE_SIZE; ft_attr.level = MLX5E_TTC_FT_LEVEL; ft_attr.prio = MLX5E_NIC_PRIO; - ft_attr.underlay_qpn = underlay_qpn; ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr); if (IS_ERR(ft->t)) { @@ -1147,7 +1146,7 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv) priv->netdev->hw_features &= ~NETIF_F_NTUPLE; } - err = mlx5e_create_ttc_table(priv, 0); + err = mlx5e_create_ttc_table(priv); if (err) { netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a61b71b6fff3..41cd22a223dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2976,7 +2976,7 @@ static int mlx5e_setup_tc(struct net_device *netdev, u8 tc) new_channels.params = priv->channels.params; new_channels.params.num_tc = tc ? tc : 1; - if (test_bit(MLX5E_STATE_OPENED, &priv->state)) { + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 19e3d2fc2099..fcec7bedd3cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -40,28 +40,25 @@ #include "eswitch.h" int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft) + struct mlx5_flow_table *ft, u32 underlay_qpn) { u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {0}; u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0}; if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && - ft->underlay_qpn == 0) + underlay_qpn == 0) return 0; MLX5_SET(set_flow_table_root_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); MLX5_SET(set_flow_table_root_in, in, table_type, ft->type); MLX5_SET(set_flow_table_root_in, in, table_id, ft->id); + MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn); if (ft->vport) { MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport); MLX5_SET(set_flow_table_root_in, in, other_vport, 1); } - if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && - ft->underlay_qpn != 0) - MLX5_SET(set_flow_table_root_in, in, underlay_qpn, ft->underlay_qpn); - return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 8fad80688536..0f98a7cf4877 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -71,7 +71,8 @@ int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev, unsigned int index); int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft); + struct mlx5_flow_table *ft, + u32 underlay_qpn); int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u16 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u16 id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index b8a176503d38..0e487e8ca634 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -650,7 +650,7 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio if (ft->level >= min_level) return 0; - err = mlx5_cmd_update_root_ft(root->dev, ft); + err = mlx5_cmd_update_root_ft(root->dev, ft, root->underlay_qpn); if (err) mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", ft->id); @@ -818,8 +818,6 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa goto unlock_root; } - ft->underlay_qpn = ft_attr->underlay_qpn; - tree_init_node(&ft->node, 1, del_flow_table); log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); @@ -1489,7 +1487,8 @@ static int update_root_ft_destroy(struct mlx5_flow_table *ft) new_root_ft = find_next_ft(ft); if (new_root_ft) { - int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft); + int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, + root->underlay_qpn); if (err) { mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", @@ -2062,3 +2061,21 @@ err: mlx5_cleanup_fs(dev); return err; } + +int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) +{ + struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + + root->underlay_qpn = underlay_qpn; + return 0; +} +EXPORT_SYMBOL(mlx5_fs_add_rx_underlay_qpn); + +int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) +{ + struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + + root->underlay_qpn = 0; + return 0; +} +EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 81eafc7b9dd9..990acee6fb09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -118,7 +118,6 @@ struct mlx5_flow_table { /* FWD rules that point on this flow table */ struct list_head fwd_rules; u32 flags; - u32 underlay_qpn; }; struct mlx5_fc_cache { @@ -195,6 +194,7 @@ struct mlx5_flow_root_namespace { struct mlx5_flow_table *root_ft; /* Should be held when chaining flow tables */ struct mutex chain_lock; + u32 underlay_qpn; }; int mlx5_init_fc_stats(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c index 019c230da498..cc1858752e70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c @@ -66,6 +66,10 @@ static void mlx5i_init(struct mlx5_core_dev *mdev, mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev)); + /* Override RQ params as IPoIB supports only LINKED LIST RQ for now */ + mlx5e_set_rq_type_params(mdev, &priv->channels.params, MLX5_WQ_TYPE_LINKED_LIST); + priv->channels.params.lro_en = false; + mutex_init(&priv->state_lock); netdev->hw_features |= NETIF_F_SG; @@ -156,6 +160,8 @@ out: static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) { + mlx5_fs_remove_rx_underlay_qpn(mdev, qp->qpn); + mlx5_core_destroy_qp(mdev, qp); } @@ -170,6 +176,8 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv) return err; } + mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); + err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]); if (err) { mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); @@ -189,7 +197,6 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv) static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) { - struct mlx5i_priv *ipriv = priv->ppriv; int err; priv->fs.ns = mlx5_get_flow_namespace(priv->mdev, @@ -205,7 +212,7 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) priv->netdev->hw_features &= ~NETIF_F_NTUPLE; } - err = mlx5e_create_ttc_table(priv, ipriv->qp.qpn); + err = mlx5e_create_ttc_table(priv); if (err) { netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index ea56f6ade6b4..5f0a7bc692a4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -199,10 +199,11 @@ static int mlxsw_sp_erif_entry_get(struct mlxsw_sp *mlxsw_sp, entry->counter_valid = false; entry->counter = 0; + entry->index = mlxsw_sp_rif_index(rif); + if (!counters_enabled) return 0; - entry->index = mlxsw_sp_rif_index(rif); err = mlxsw_sp_rif_counter_value_get(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS, &cnt); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 33cec1cc1642..9f89c4137d21 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -206,6 +206,9 @@ void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp, { unsigned int *p_counter_index; + if (!mlxsw_sp_rif_counter_valid_get(rif, dir)) + return; + p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir); if (WARN_ON(!p_counter_index)) return; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 0d8411f1f954..f4bb0c0b7c1d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1497,8 +1497,7 @@ do_fdb_op: err = mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid, adding, true); if (err) { - if (net_ratelimit()) - netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n"); + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to set FDB entry\n"); return; } @@ -1558,8 +1557,7 @@ do_fdb_op: err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, fid, lag_vid, adding, true); if (err) { - if (net_ratelimit()) - netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n"); + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to set FDB entry\n"); return; } diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c index b8d5270359cd..e30676515529 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c @@ -247,7 +247,7 @@ nx_fw_cmd_set_mtu(struct netxen_adapter *adapter, int mtu) cmd.req.arg3 = 0; if (recv_ctx->state == NX_HOST_CTX_STATE_ACTIVE) - netxen_issue_cmd(adapter, &cmd); + rcode = netxen_issue_cmd(adapter, &cmd); if (rcode != NX_RCODE_SUCCESS) return -EIO; diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c index 67200c5498ab..0a8fde629991 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c @@ -983,7 +983,7 @@ void qed_set_rfs_mode_disable(struct qed_hwfn *p_hwfn, memset(&camline, 0, sizeof(union gft_cam_line_union)); qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id, camline.cam_line_mapped.camline); - memset(&ramline, 0, sizeof(union gft_cam_line_union)); + memset(&ramline, 0, sizeof(ramline)); for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++) { u32 hw_addr = PRS_REG_GFT_PROFILE_MASK_RAM; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 49bad00a0f8f..7245b1072518 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -37,8 +37,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 3 -#define _QLCNIC_LINUX_SUBVERSION 65 -#define QLCNIC_LINUX_VERSIONID "5.3.65" +#define _QLCNIC_LINUX_SUBVERSION 66 +#define QLCNIC_LINUX_VERSIONID "5.3.66" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 718bf58a7da6..4fb68797630e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -3168,6 +3168,40 @@ int qlcnic_83xx_flash_read32(struct qlcnic_adapter *adapter, u32 flash_addr, return 0; } +void qlcnic_83xx_get_port_type(struct qlcnic_adapter *adapter) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + struct qlcnic_cmd_args cmd; + u32 config; + int err; + + err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_GET_LINK_STATUS); + if (err) + return; + + err = qlcnic_issue_cmd(adapter, &cmd); + if (err) { + dev_info(&adapter->pdev->dev, + "Get Link Status Command failed: 0x%x\n", err); + goto out; + } else { + config = cmd.rsp.arg[3]; + + switch (QLC_83XX_SFP_MODULE_TYPE(config)) { + case QLC_83XX_MODULE_FIBRE_1000BASE_SX: + case QLC_83XX_MODULE_FIBRE_1000BASE_LX: + case QLC_83XX_MODULE_FIBRE_1000BASE_CX: + case QLC_83XX_MODULE_TP_1000BASE_T: + ahw->port_type = QLCNIC_GBE; + break; + default: + ahw->port_type = QLCNIC_XGBE; + } + } +out: + qlcnic_free_mbx_args(&cmd); +} + int qlcnic_83xx_test_link(struct qlcnic_adapter *adapter) { u8 pci_func; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index 3dfe8e27b51c..b75a81246856 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -637,6 +637,7 @@ void qlcnic_83xx_get_pauseparam(struct qlcnic_adapter *, int qlcnic_83xx_set_pauseparam(struct qlcnic_adapter *, struct ethtool_pauseparam *); int qlcnic_83xx_test_link(struct qlcnic_adapter *); +void qlcnic_83xx_get_port_type(struct qlcnic_adapter *adapter); int qlcnic_83xx_reg_test(struct qlcnic_adapter *); int qlcnic_83xx_get_regs_len(struct qlcnic_adapter *); int qlcnic_83xx_get_registers(struct qlcnic_adapter *, u32 *); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 9a869c15d8bf..7f7deeaf1cf0 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -486,6 +486,9 @@ static int qlcnic_set_link_ksettings(struct net_device *dev, u32 ret = 0; struct qlcnic_adapter *adapter = netdev_priv(dev); + if (qlcnic_83xx_check(adapter)) + qlcnic_83xx_get_port_type(adapter); + if (adapter->ahw->port_type != QLCNIC_GBE) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 513e6c74e199..24ca7df15d07 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -296,8 +296,9 @@ qcaspi_receive(struct qcaspi *qca) /* Allocate rx SKB if we don't have one available. */ if (!qca->rx_skb) { - qca->rx_skb = netdev_alloc_skb(net_dev, - net_dev->mtu + VLAN_ETH_HLEN); + qca->rx_skb = netdev_alloc_skb_ip_align(net_dev, + net_dev->mtu + + VLAN_ETH_HLEN); if (!qca->rx_skb) { netdev_dbg(net_dev, "out of RX resources\n"); qca->stats.out_of_mem++; @@ -377,7 +378,7 @@ qcaspi_receive(struct qcaspi *qca) qca->rx_skb, qca->rx_skb->dev); qca->rx_skb->ip_summed = CHECKSUM_UNNECESSARY; netif_rx_ni(qca->rx_skb); - qca->rx_skb = netdev_alloc_skb(net_dev, + qca->rx_skb = netdev_alloc_skb_ip_align(net_dev, net_dev->mtu + VLAN_ETH_HLEN); if (!qca->rx_skb) { netdev_dbg(net_dev, "out of RX resources\n"); @@ -759,7 +760,8 @@ qcaspi_netdev_init(struct net_device *dev) if (!qca->rx_buffer) return -ENOBUFS; - qca->rx_skb = netdev_alloc_skb(dev, qca->net_dev->mtu + VLAN_ETH_HLEN); + qca->rx_skb = netdev_alloc_skb_ip_align(dev, qca->net_dev->mtu + + VLAN_ETH_HLEN); if (!qca->rx_skb) { kfree(qca->rx_buffer); netdev_info(qca->net_dev, "Failed to allocate RX sk_buff.\n"); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index f68c4db656ed..2d686ccf971b 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3220,7 +3220,8 @@ static int sh_eth_drv_probe(struct platform_device *pdev) /* MDIO bus init */ ret = sh_mdio_init(mdp, pd); if (ret) { - dev_err(&ndev->dev, "failed to initialise MDIO\n"); + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, "MDIO init failed: %d\n", ret); goto out_release; } diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index 7b916aa21bde..4d7fb8af880d 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -18,8 +18,12 @@ #include "mcdi.h" enum { - EFX_REV_SIENA_A0 = 0, - EFX_REV_HUNT_A0 = 1, + /* Revisions 0-2 were Falcon A0, A1 and B0 respectively. + * They are not supported by this driver but these revision numbers + * form part of the ethtool API for register dumping. + */ + EFX_REV_SIENA_A0 = 3, + EFX_REV_HUNT_A0 = 4, }; static inline int efx_nic_rev(struct efx_nic *efx) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index cd8c60132390..a74c481401c4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3725,7 +3725,7 @@ static void sysfs_display_ring(void *head, int size, int extend_desc, ep++; } else { seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n", - i, (unsigned int)virt_to_phys(ep), + i, (unsigned int)virt_to_phys(p), le32_to_cpu(p->des0), le32_to_cpu(p->des1), le32_to_cpu(p->des2), le32_to_cpu(p->des3)); p++; diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 5a90fed06260..5b56c24b6ed2 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -411,13 +411,14 @@ static int vsw_port_remove(struct vio_dev *vdev) if (port) { del_timer_sync(&port->vio.timer); + del_timer_sync(&port->clean_timer); napi_disable(&port->napi); + unregister_netdev(port->dev); list_del_rcu(&port->list); synchronize_rcu(); - del_timer_sync(&port->clean_timer); spin_lock_irqsave(&port->vp->lock, flags); sunvnet_port_rm_txq_common(port); spin_unlock_irqrestore(&port->vp->lock, flags); @@ -427,7 +428,6 @@ static int vsw_port_remove(struct vio_dev *vdev) dev_set_drvdata(&vdev->dev, NULL); - unregister_netdev(port->dev); free_netdev(port->dev); } diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 729a7da90b5b..e6222e535019 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1353,9 +1353,10 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe) tx_pipe->dma_channel = knav_dma_open_channel(dev, tx_pipe->dma_chan_name, &config); - if (IS_ERR_OR_NULL(tx_pipe->dma_channel)) { + if (IS_ERR(tx_pipe->dma_channel)) { dev_err(dev, "failed opening tx chan(%s)\n", tx_pipe->dma_chan_name); + ret = PTR_ERR(tx_pipe->dma_channel); goto err; } @@ -1673,9 +1674,10 @@ static int netcp_setup_navigator_resources(struct net_device *ndev) netcp->rx_channel = knav_dma_open_channel(netcp->netcp_device->device, netcp->dma_chan_name, &config); - if (IS_ERR_OR_NULL(netcp->rx_channel)) { + if (IS_ERR(netcp->rx_channel)) { dev_err(netcp->ndev_dev, "failed opening rx chan(%s\n", netcp->dma_chan_name); + ret = PTR_ERR(netcp->rx_channel); goto fail; } diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 897176fc5043..dd92950a4615 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2651,7 +2651,6 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr) case HWTSTAMP_FILTER_NONE: cpts_rx_enable(cpts, 0); break; - case HWTSTAMP_FILTER_ALL: case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c index 8716b8c07feb..6f3c805f7211 100644 --- a/drivers/net/irda/irda-usb.c +++ b/drivers/net/irda/irda-usb.c @@ -1077,7 +1077,7 @@ static int stir421x_patch_device(struct irda_usb_cb *self) * are "42101001.sb" or "42101002.sb" */ sprintf(stir421x_fw_name, "4210%4X.sb", - self->usbdev->descriptor.bcdDevice); + le16_to_cpu(self->usbdev->descriptor.bcdDevice)); ret = request_firmware(&fw, stir421x_fw_name, &self->usbdev->dev); if (ret < 0) return ret; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index b34eaaae03fd..346ad2ff3998 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -789,10 +789,12 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu) */ static struct lock_class_key macvlan_netdev_addr_lock_key; -#define ALWAYS_ON_FEATURES \ - (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX | \ +#define ALWAYS_ON_OFFLOADS \ + (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST) +#define ALWAYS_ON_FEATURES (ALWAYS_ON_OFFLOADS | NETIF_F_LLTX) + #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_LRO | \ @@ -827,6 +829,7 @@ static int macvlan_init(struct net_device *dev) dev->features |= ALWAYS_ON_FEATURES; dev->hw_features |= NETIF_F_LRO; dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; + dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->gso_max_size = lowerdev->gso_max_size; dev->gso_max_segs = lowerdev->gso_max_segs; dev->hard_header_len = lowerdev->hard_header_len; diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 963838d4fac1..599ce24c514f 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -122,10 +122,9 @@ int mdio_mux_init(struct device *dev, pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL); if (pb == NULL) { ret_val = -ENOMEM; - goto err_parent_bus; + goto err_pb_kz; } - pb->switch_data = data; pb->switch_fn = switch_fn; pb->current_child = -1; @@ -154,6 +153,7 @@ int mdio_mux_init(struct device *dev, cb->mii_bus = mdiobus_alloc(); if (!cb->mii_bus) { ret_val = -ENOMEM; + devm_kfree(dev, cb); of_node_put(child_bus_node); break; } @@ -170,7 +170,6 @@ int mdio_mux_init(struct device *dev, mdiobus_free(cb->mii_bus); devm_kfree(dev, cb); } else { - of_node_get(child_bus_node); cb->next = pb->children; pb->children = cb; } @@ -181,9 +180,11 @@ int mdio_mux_init(struct device *dev, return 0; } + devm_kfree(dev, pb); +err_pb_kz: /* balance the reference of_mdio_find_bus() took */ - put_device(&pb->mii_bus->dev); - + if (!mux_bus) + put_device(&parent_bus->dev); err_parent_bus: of_node_put(parent_bus_node); return ret_val; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index a898e5c4ef1b..8e73f5f36e71 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -364,9 +364,6 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) mutex_init(&bus->mdio_lock); - if (bus->reset) - bus->reset(bus); - /* de-assert bus level PHY GPIO resets */ if (bus->num_reset_gpios > 0) { bus->reset_gpiod = devm_kcalloc(&bus->dev, @@ -396,6 +393,9 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) } } + if (bus->reset) + bus->reset(bus); + for (i = 0; i < PHY_MAX_ADDR; i++) { if ((bus->phy_mask & (1 << i)) == 0) { struct phy_device *phydev; diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c index c4f1c363e24b..9df3c1ffff35 100644 --- a/drivers/net/usb/ch9200.c +++ b/drivers/net/usb/ch9200.c @@ -310,8 +310,8 @@ static int get_mac_address(struct usbnet *dev, unsigned char *data) int rd_mac_len = 0; netdev_dbg(dev->net, "get_mac_address:\n\tusbnet VID:%0x PID:%0x\n", - dev->udev->descriptor.idVendor, - dev->udev->descriptor.idProduct); + le16_to_cpu(dev->udev->descriptor.idVendor), + le16_to_cpu(dev->udev->descriptor.idProduct)); memset(mac_addr, 0, sizeof(mac_addr)); rd_mac_len = control_read(dev, REQUEST_READ, 0, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index d7165767ca9d..8f923a147fa9 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1196,6 +1196,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 25bc764ae7dc..d1c7029ded7c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2962,6 +2962,11 @@ vmxnet3_force_close(struct vmxnet3_adapter *adapter) /* we need to enable NAPI, otherwise dev_close will deadlock */ for (i = 0; i < adapter->num_rx_queues; i++) napi_enable(&adapter->rx_queue[i].napi); + /* + * Need to clear the quiesce bit to ensure that vmxnet3_close + * can quiesce the device properly + */ + clear_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state); dev_close(adapter->netdev); } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index ceda5861da78..db882493875c 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -989,6 +989,7 @@ static u32 vrf_fib_table(const struct net_device *dev) static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + kfree_skb(skb); return 0; } @@ -998,7 +999,7 @@ static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook, { struct net *net = dev_net(dev); - if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0) + if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1) skb = NULL; /* kfree_skb(skb) handled by nf code */ return skb; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 6ffc482550c1..7b61adb6270c 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1934,8 +1934,7 @@ abort_transaction_no_dev_fatal: xennet_disconnect_backend(info); xennet_destroy_queues(info); out: - unregister_netdev(info->netdev); - xennet_free_netdev(info->netdev); + device_unregister(&dev->dev); return err; } diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index e443b0d0b236..34b9ad6b3143 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -35,7 +35,7 @@ static struct bus_type ccwgroup_bus_type; static void __ccwgroup_remove_symlinks(struct ccwgroup_device *gdev) { int i; - char str[8]; + char str[16]; for (i = 0; i < gdev->count; i++) { sprintf(str, "cdev%d", i); @@ -238,7 +238,7 @@ static void ccwgroup_release(struct device *dev) static int __ccwgroup_create_symlinks(struct ccwgroup_device *gdev) { - char str[8]; + char str[16]; int i, rc; for (i = 0; i < gdev->count; i++) { diff --git a/drivers/s390/cio/qdio_debug.h b/drivers/s390/cio/qdio_debug.h index f33ce8577619..1d595d17bf11 100644 --- a/drivers/s390/cio/qdio_debug.h +++ b/drivers/s390/cio/qdio_debug.h @@ -11,7 +11,7 @@ #include "qdio.h" /* that gives us 15 characters in the text event views */ -#define QDIO_DBF_LEN 16 +#define QDIO_DBF_LEN 32 extern debug_info_t *qdio_dbf_setup; extern debug_info_t *qdio_dbf_error; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index f6aa21176d89..30bc6105aac3 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -701,6 +701,7 @@ enum qeth_discipline_id { }; struct qeth_discipline { + const struct device_type *devtype; void (*start_poll)(struct ccw_device *, int, unsigned long); qdio_handler_t *input_handler; qdio_handler_t *output_handler; @@ -875,6 +876,9 @@ extern struct qeth_discipline qeth_l2_discipline; extern struct qeth_discipline qeth_l3_discipline; extern const struct attribute_group *qeth_generic_attr_groups[]; extern const struct attribute_group *qeth_osn_attr_groups[]; +extern const struct attribute_group qeth_device_attr_group; +extern const struct attribute_group qeth_device_blkt_group; +extern const struct device_type qeth_generic_devtype; extern struct workqueue_struct *qeth_wq; int qeth_card_hw_is_reachable(struct qeth_card *); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 38114a8d56e0..fc6d85f2b38d 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5530,10 +5530,12 @@ void qeth_core_free_discipline(struct qeth_card *card) card->discipline = NULL; } -static const struct device_type qeth_generic_devtype = { +const struct device_type qeth_generic_devtype = { .name = "qeth_generic", .groups = qeth_generic_attr_groups, }; +EXPORT_SYMBOL_GPL(qeth_generic_devtype); + static const struct device_type qeth_osn_devtype = { .name = "qeth_osn", .groups = qeth_osn_attr_groups, @@ -5659,23 +5661,22 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) goto err_card; } - if (card->info.type == QETH_CARD_TYPE_OSN) - gdev->dev.type = &qeth_osn_devtype; - else - gdev->dev.type = &qeth_generic_devtype; - switch (card->info.type) { case QETH_CARD_TYPE_OSN: case QETH_CARD_TYPE_OSM: rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2); if (rc) goto err_card; + + gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN) + ? card->discipline->devtype + : &qeth_osn_devtype; rc = card->discipline->setup(card->gdev); if (rc) goto err_disc; - case QETH_CARD_TYPE_OSD: - case QETH_CARD_TYPE_OSX: + break; default: + gdev->dev.type = &qeth_generic_devtype; break; } @@ -5731,8 +5732,10 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev) if (rc) goto err; rc = card->discipline->setup(card->gdev); - if (rc) + if (rc) { + qeth_core_free_discipline(card); goto err; + } } rc = card->discipline->set_online(gdev); err: diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index 75b29fd2fcf4..db6a285d41e0 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -413,12 +413,16 @@ static ssize_t qeth_dev_layer2_store(struct device *dev, if (card->options.layer2 == newdis) goto out; - else { - card->info.mac_bits = 0; - if (card->discipline) { - card->discipline->remove(card->gdev); - qeth_core_free_discipline(card); - } + if (card->info.type == QETH_CARD_TYPE_OSM) { + /* fixed layer, can't switch */ + rc = -EOPNOTSUPP; + goto out; + } + + card->info.mac_bits = 0; + if (card->discipline) { + card->discipline->remove(card->gdev); + qeth_core_free_discipline(card); } rc = qeth_core_load_discipline(card, newdis); @@ -426,6 +430,8 @@ static ssize_t qeth_dev_layer2_store(struct device *dev, goto out; rc = card->discipline->setup(card->gdev); + if (rc) + qeth_core_free_discipline(card); out: mutex_unlock(&card->discipline_mutex); return rc ? rc : count; @@ -703,10 +709,11 @@ static struct attribute *qeth_blkt_device_attrs[] = { &dev_attr_inter_jumbo.attr, NULL, }; -static struct attribute_group qeth_device_blkt_group = { +const struct attribute_group qeth_device_blkt_group = { .name = "blkt", .attrs = qeth_blkt_device_attrs, }; +EXPORT_SYMBOL_GPL(qeth_device_blkt_group); static struct attribute *qeth_device_attrs[] = { &dev_attr_state.attr, @@ -726,9 +733,10 @@ static struct attribute *qeth_device_attrs[] = { &dev_attr_switch_attrs.attr, NULL, }; -static struct attribute_group qeth_device_attr_group = { +const struct attribute_group qeth_device_attr_group = { .attrs = qeth_device_attrs, }; +EXPORT_SYMBOL_GPL(qeth_device_attr_group); const struct attribute_group *qeth_generic_attr_groups[] = { &qeth_device_attr_group, diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h index 29d9fb3890ad..0d59f9a45ea9 100644 --- a/drivers/s390/net/qeth_l2.h +++ b/drivers/s390/net/qeth_l2.h @@ -8,6 +8,8 @@ #include "qeth_core.h" +extern const struct attribute_group *qeth_l2_attr_groups[]; + int qeth_l2_create_device_attributes(struct device *); void qeth_l2_remove_device_attributes(struct device *); void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 1b07f382d74c..bd2df62a5cdf 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -880,11 +880,21 @@ static int qeth_l2_stop(struct net_device *dev) return 0; } +static const struct device_type qeth_l2_devtype = { + .name = "qeth_layer2", + .groups = qeth_l2_attr_groups, +}; + static int qeth_l2_probe_device(struct ccwgroup_device *gdev) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); + int rc; - qeth_l2_create_device_attributes(&gdev->dev); + if (gdev->dev.type == &qeth_generic_devtype) { + rc = qeth_l2_create_device_attributes(&gdev->dev); + if (rc) + return rc; + } INIT_LIST_HEAD(&card->vid_list); hash_init(card->mac_htable); card->options.layer2 = 1; @@ -896,7 +906,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) { struct qeth_card *card = dev_get_drvdata(&cgdev->dev); - qeth_l2_remove_device_attributes(&cgdev->dev); + if (cgdev->dev.type == &qeth_generic_devtype) + qeth_l2_remove_device_attributes(&cgdev->dev); qeth_set_allowed_threads(card, 0, 1); wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0); @@ -954,7 +965,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) case QETH_CARD_TYPE_OSN: card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, ether_setup); - card->dev->flags |= IFF_NOARP; break; default: card->dev = alloc_etherdev(0); @@ -969,9 +979,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) card->dev->min_mtu = 64; card->dev->max_mtu = ETH_MAX_MTU; card->dev->netdev_ops = &qeth_l2_netdev_ops; - card->dev->ethtool_ops = - (card->info.type != QETH_CARD_TYPE_OSN) ? - &qeth_l2_ethtool_ops : &qeth_l2_osn_ops; + if (card->info.type == QETH_CARD_TYPE_OSN) { + card->dev->ethtool_ops = &qeth_l2_osn_ops; + card->dev->flags |= IFF_NOARP; + } else { + card->dev->ethtool_ops = &qeth_l2_ethtool_ops; + } card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { card->dev->hw_features = NETIF_F_SG; @@ -1269,6 +1282,7 @@ static int qeth_l2_control_event(struct qeth_card *card, } struct qeth_discipline qeth_l2_discipline = { + .devtype = &qeth_l2_devtype, .start_poll = qeth_qdio_start_poll, .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 687972356d6b..9696baa49e2d 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -269,3 +269,11 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) } else qeth_bridgeport_an_set(card, 0); } + +const struct attribute_group *qeth_l2_attr_groups[] = { + &qeth_device_attr_group, + &qeth_device_blkt_group, + /* l2 specific, see l2_{create,remove}_device_attributes(): */ + &qeth_l2_bridgeport_attr_group, + NULL, +}; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 6e0354ef4b86..d8df1e635163 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3039,8 +3039,13 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) static int qeth_l3_probe_device(struct ccwgroup_device *gdev) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); + int rc; - qeth_l3_create_device_attributes(&gdev->dev); + rc = qeth_l3_create_device_attributes(&gdev->dev); + if (rc) + return rc; + hash_init(card->ip_htable); + hash_init(card->ip_mc_htable); card->options.layer2 = 0; card->info.hwtrap = 0; return 0; @@ -3306,6 +3311,7 @@ static int qeth_l3_control_event(struct qeth_card *card, } struct qeth_discipline qeth_l3_discipline = { + .devtype = &qeth_generic_devtype, .start_poll = qeth_qdio_start_poll, .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 2a76ea78a0bf..b18fe2014cf2 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -87,7 +87,7 @@ struct vq_info_block { } __packed; struct virtio_feature_desc { - __u32 features; + __le32 features; __u8 index; } __packed; diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c index ecebe2eecc3a..026182d3b27c 100644 --- a/drivers/soc/ti/knav_dma.c +++ b/drivers/soc/ti/knav_dma.c @@ -413,7 +413,7 @@ static int of_channel_match_helper(struct device_node *np, const char *name, * @name: slave channel name * @config: dma configuration parameters * - * Returns pointer to appropriate DMA channel on success or NULL. + * Returns pointer to appropriate DMA channel on success or error. */ void *knav_dma_open_channel(struct device *dev, const char *name, struct knav_dma_cfg *config) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 15bac390dff9..b98436f5c7c7 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1135,20 +1135,19 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, u32 acllen = 0; int rc = 0; struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); - struct cifs_tcon *tcon; + struct smb_version_operations *ops; cifs_dbg(NOISY, "converting ACL to mode for %s\n", path); if (IS_ERR(tlink)) return PTR_ERR(tlink); - tcon = tlink_tcon(tlink); - if (pfid && (tcon->ses->server->ops->get_acl_by_fid)) - pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid, - &acllen); - else if (tcon->ses->server->ops->get_acl) - pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path, - &acllen); + ops = tlink_tcon(tlink)->ses->server->ops; + + if (pfid && (ops->get_acl_by_fid)) + pntsd = ops->get_acl_by_fid(cifs_sb, pfid, &acllen); + else if (ops->get_acl) + pntsd = ops->get_acl(cifs_sb, inode, path, &acllen); else { cifs_put_tlink(tlink); return -EOPNOTSUPP; @@ -1181,23 +1180,23 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); - struct cifs_tcon *tcon; + struct smb_version_operations *ops; if (IS_ERR(tlink)) return PTR_ERR(tlink); - tcon = tlink_tcon(tlink); + + ops = tlink_tcon(tlink)->ses->server->ops; cifs_dbg(NOISY, "set ACL from mode for %s\n", path); /* Get the security descriptor */ - if (tcon->ses->server->ops->get_acl == NULL) { + if (ops->get_acl == NULL) { cifs_put_tlink(tlink); return -EOPNOTSUPP; } - pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path, - &secdesclen); + pntsd = ops->get_acl(cifs_sb, inode, path, &secdesclen); if (IS_ERR(pntsd)) { rc = PTR_ERR(pntsd); cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc); @@ -1224,13 +1223,12 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc); - if (tcon->ses->server->ops->set_acl == NULL) + if (ops->set_acl == NULL) rc = -EOPNOTSUPP; if (!rc) { /* Set the security descriptor */ - rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode, - path, aclflag); + rc = ops->set_acl(pnntsd, secdesclen, inode, path, aclflag); cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc); } cifs_put_tlink(tlink); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 8be55be70faf..bcc7d9acad64 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -418,7 +418,7 @@ struct smb_version_operations { int (*validate_negotiate)(const unsigned int, struct cifs_tcon *); ssize_t (*query_all_EAs)(const unsigned int, struct cifs_tcon *, const unsigned char *, const unsigned char *, char *, - size_t, const struct nls_table *, int); + size_t, struct cifs_sb_info *); int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *, const char *, const void *, const __u16, const struct nls_table *, int); diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index e49958c3f8bb..6eb3147132e3 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -480,8 +480,7 @@ extern int CIFSSMBCopy(unsigned int xid, extern ssize_t CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon, const unsigned char *searchName, const unsigned char *ea_name, char *EAData, - size_t bufsize, const struct nls_table *nls_codepage, - int remap_special_chars); + size_t bufsize, struct cifs_sb_info *cifs_sb); extern int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, const char *fileName, const char *ea_name, const void *ea_value, const __u16 ea_value_len, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 4c01b3f9abf0..fbb0d4cbda41 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -697,9 +697,7 @@ cifs_echo_callback(struct mid_q_entry *mid) { struct TCP_Server_Info *server = mid->callback_data; - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(server, 1, CIFS_ECHO_OP); } @@ -1599,9 +1597,7 @@ cifs_readv_callback(struct mid_q_entry *mid) } queue_work(cifsiod_wq, &rdata->work); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(server, 1, 0); } @@ -2058,7 +2054,6 @@ cifs_writev_callback(struct mid_q_entry *mid) { struct cifs_writedata *wdata = mid->callback_data; struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; unsigned int written; WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf; @@ -2095,9 +2090,7 @@ cifs_writev_callback(struct mid_q_entry *mid) } queue_work(cifsiod_wq, &wdata->work); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(tcon->ses->server, 1, 0); } @@ -6076,11 +6069,13 @@ ssize_t CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon, const unsigned char *searchName, const unsigned char *ea_name, char *EAData, size_t buf_size, - const struct nls_table *nls_codepage, int remap) + struct cifs_sb_info *cifs_sb) { /* BB assumes one setup word */ TRANSACTION2_QPI_REQ *pSMB = NULL; TRANSACTION2_QPI_RSP *pSMBr = NULL; + int remap = cifs_remap(cifs_sb); + struct nls_table *nls_codepage = cifs_sb->local_nls; int rc = 0; int bytes_returned; int list_len; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 6ef78ad838e6..0fd081bd2a2f 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -582,7 +582,7 @@ cifs_relock_file(struct cifsFileInfo *cfile) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); int rc = 0; - down_read(&cinode->lock_sem); + down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING); if (cinode->can_cache_brlcks) { /* can cache locks - no need to relock */ up_read(&cinode->lock_sem); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index c3b2fa0b2ec8..4d1fcd76d022 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -563,8 +563,7 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path, rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path, "SETFILEBITS", ea_value, 4 /* size of buf */, - cifs_sb->local_nls, - cifs_remap(cifs_sb)); + cifs_sb); cifs_put_tlink(tlink); if (rc < 0) return (int)rc; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 48ff7703b919..e4afdaae743f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1240,15 +1240,19 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, goto tcon_exit; } - if (rsp->ShareType & SMB2_SHARE_TYPE_DISK) + switch (rsp->ShareType) { + case SMB2_SHARE_TYPE_DISK: cifs_dbg(FYI, "connection to disk share\n"); - else if (rsp->ShareType & SMB2_SHARE_TYPE_PIPE) { + break; + case SMB2_SHARE_TYPE_PIPE: tcon->ipc = true; cifs_dbg(FYI, "connection to pipe share\n"); - } else if (rsp->ShareType & SMB2_SHARE_TYPE_PRINT) { - tcon->print = true; + break; + case SMB2_SHARE_TYPE_PRINT: + tcon->ipc = true; cifs_dbg(FYI, "connection to printer\n"); - } else { + break; + default: cifs_dbg(VFS, "unknown share type %d\n", rsp->ShareType); rc = -EOPNOTSUPP; goto tcon_error_exit; @@ -2173,9 +2177,7 @@ smb2_echo_callback(struct mid_q_entry *mid) if (mid->mid_state == MID_RESPONSE_RECEIVED) credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(server, credits_received, CIFS_ECHO_OP); } @@ -2433,9 +2435,7 @@ smb2_readv_callback(struct mid_q_entry *mid) cifs_stats_fail_inc(tcon, SMB2_READ_HE); queue_work(cifsiod_wq, &rdata->work); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(server, credits_received, 0); } @@ -2594,7 +2594,6 @@ smb2_writev_callback(struct mid_q_entry *mid) { struct cifs_writedata *wdata = mid->callback_data; struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; unsigned int written; struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf; unsigned int credits_received = 1; @@ -2634,9 +2633,7 @@ smb2_writev_callback(struct mid_q_entry *mid) cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); queue_work(cifsiod_wq, &wdata->work); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(tcon->ses->server, credits_received, 0); } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 4d64b5b8fc9c..47a125ece11e 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -94,7 +94,7 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) now = jiffies; /* commands taking longer than one second are indications that something is wrong, unless it is quite a slow link or server */ - if ((now - midEntry->when_alloc) > HZ) { + if (time_after(now, midEntry->when_alloc + HZ)) { if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) { pr_debug(" CIFS slow rsp: cmd %d mid %llu", midEntry->command, midEntry->mid); @@ -613,9 +613,7 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) } spin_unlock(&GlobalMid_Lock); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); return rc; } diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 20af5187ba63..3cb5c9e2d4e7 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -235,8 +235,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler, if (pTcon->ses->server->ops->query_all_EAs) rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon, - full_path, name, value, size, - cifs_sb->local_nls, cifs_remap(cifs_sb)); + full_path, name, value, size, cifs_sb); break; case XATTR_CIFS_ACL: { @@ -336,8 +335,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size) if (pTcon->ses->server->ops->query_all_EAs) rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon, - full_path, NULL, data, buf_size, - cifs_sb->local_nls, cifs_remap(cifs_sb)); + full_path, NULL, data, buf_size, cifs_sb); list_ea_exit: kfree(full_path); free_xid(xid); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5efb4db44e1e..d5093b52b485 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -40,6 +40,9 @@ struct bpf_reg_state { */ s64 min_value; u64 max_value; + u32 min_align; + u32 aux_off; + u32 aux_off_align; }; enum bpf_stack_slot_type { @@ -87,6 +90,7 @@ struct bpf_verifier_env { struct bpf_prog *prog; /* eBPF program being verified */ struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ + bool strict_alignment; /* perform strict pointer alignment checks */ struct bpf_verifier_state cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 1b166d2e19c5..b25e7baa273e 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -109,7 +109,6 @@ struct mlx5_flow_table_attr { int max_fte; u32 level; u32 flags; - u32 underlay_qpn; }; struct mlx5_flow_table * @@ -167,4 +166,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); +int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); +int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); + #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9c23bd2efb56..3f39d27decf4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3296,11 +3296,15 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, - int fd, u32 flags); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); + +typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp); +int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, + int fd, u32 flags); +bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op); + int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, diff --git a/include/net/x25.h b/include/net/x25.h index c383aa4edbf0..6d30a01d281d 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -298,10 +298,10 @@ void x25_check_rbuf(struct sock *); /* sysctl_net_x25.c */ #ifdef CONFIG_SYSCTL -void x25_register_sysctl(void); +int x25_register_sysctl(void); void x25_unregister_sysctl(void); #else -static inline void x25_register_sysctl(void) {}; +static inline int x25_register_sysctl(void) { return 0; }; static inline void x25_unregister_sysctl(void) {}; #endif /* CONFIG_SYSCTL */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 945a1f5f63c5..94dfa9def355 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -132,6 +132,13 @@ enum bpf_attach_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) +/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will perform strict alignment checking as if the kernel + * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, + * and NET_IP_ALIGN defined to 2. + */ +#define BPF_F_STRICT_ALIGNMENT (1U << 0) + #define BPF_PSEUDO_MAP_FD 1 /* flags for BPF_MAP_UPDATE_ELEM command */ @@ -177,6 +184,7 @@ union bpf_attr { __u32 log_size; /* size of user buffer */ __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ + __u32 prog_flags; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8e56ac70e0d1..15ac20382aba 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -888,9 +888,18 @@ enum { /* XDP section */ #define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) -#define XDP_FLAGS_SKB_MODE (2U << 0) +#define XDP_FLAGS_SKB_MODE (1U << 1) +#define XDP_FLAGS_DRV_MODE (1U << 2) #define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ - XDP_FLAGS_SKB_MODE) + XDP_FLAGS_SKB_MODE | \ + XDP_FLAGS_DRV_MODE) + +/* These are stored into IFLA_XDP_ATTACHED on dump. */ +enum { + XDP_ATTACHED_NONE = 0, + XDP_ATTACHED_DRV, + XDP_ATTACHED_SKB, +}; enum { IFLA_XDP_UNSPEC, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index fd2411fd6914..265a0d854e33 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -783,7 +783,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD kern_version +#define BPF_PROG_LOAD_LAST_FIELD prog_flags static int bpf_prog_load(union bpf_attr *attr) { @@ -796,6 +796,9 @@ static int bpf_prog_load(union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; + if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT) + return -EINVAL; + /* copy eBPF program license from user space */ if (strncpy_from_user(license, u64_to_user_ptr(attr->license), sizeof(license) - 1) < 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c5b56c92f8e2..1eddb713b815 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -140,7 +140,7 @@ struct bpf_verifier_stack_elem { struct bpf_verifier_stack_elem *next; }; -#define BPF_COMPLEXITY_LIMIT_INSNS 65536 +#define BPF_COMPLEXITY_LIMIT_INSNS 98304 #define BPF_COMPLEXITY_LIMIT_STACK 1024 #define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA) @@ -241,6 +241,12 @@ static void print_verifier_state(struct bpf_verifier_state *state) if (reg->max_value != BPF_REGISTER_MAX_RANGE) verbose(",max_value=%llu", (unsigned long long)reg->max_value); + if (reg->min_align) + verbose(",min_align=%u", reg->min_align); + if (reg->aux_off) + verbose(",aux_off=%u", reg->aux_off); + if (reg->aux_off_align) + verbose(",aux_off_align=%u", reg->aux_off_align); } for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] == STACK_SPILL) @@ -466,6 +472,9 @@ static void init_reg_state(struct bpf_reg_state *regs) regs[i].imm = 0; regs[i].min_value = BPF_REGISTER_MIN_RANGE; regs[i].max_value = BPF_REGISTER_MAX_RANGE; + regs[i].min_align = 0; + regs[i].aux_off = 0; + regs[i].aux_off_align = 0; } /* frame pointer */ @@ -492,6 +501,7 @@ 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].min_align = 0; } static void mark_reg_unknown_value_and_range(struct bpf_reg_state *regs, @@ -779,17 +789,33 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) } static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, - int off, int size) + int off, int size, bool strict) { - if (reg->id && size != 1) { - verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n"); - return -EACCES; + int ip_align; + int reg_off; + + /* Byte size accesses are always allowed. */ + if (!strict || size == 1) + return 0; + + reg_off = reg->off; + if (reg->id) { + if (reg->aux_off_align % size) { + verbose("Packet access is only %u byte aligned, %d byte access not allowed\n", + reg->aux_off_align, size); + return -EACCES; + } + reg_off += reg->aux_off; } - /* skb->data is NET_IP_ALIGN-ed */ - if ((NET_IP_ALIGN + reg->off + off) % size != 0) { + /* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking + * we force this to 2 which is universally what architectures use + * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. + */ + ip_align = strict ? 2 : NET_IP_ALIGN; + if ((ip_align + reg_off + off) % size != 0) { verbose("misaligned packet access off %d+%d+%d size %d\n", - NET_IP_ALIGN, reg->off, off, size); + ip_align, reg_off, off, size); return -EACCES; } @@ -797,9 +823,9 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, } static int check_val_ptr_alignment(const struct bpf_reg_state *reg, - int size) + int size, bool strict) { - if (size != 1) { + if (strict && size != 1) { verbose("Unknown alignment. Only byte-sized access allowed in value access.\n"); return -EACCES; } @@ -807,16 +833,20 @@ static int check_val_ptr_alignment(const struct bpf_reg_state *reg, return 0; } -static int check_ptr_alignment(const struct bpf_reg_state *reg, +static int check_ptr_alignment(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int off, int size) { + bool strict = env->strict_alignment; + + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) + strict = true; + switch (reg->type) { case PTR_TO_PACKET: - return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 : - check_pkt_ptr_alignment(reg, off, size); + return check_pkt_ptr_alignment(reg, off, size, strict); case PTR_TO_MAP_VALUE_ADJ: - return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 : - check_val_ptr_alignment(reg, size); + return check_val_ptr_alignment(reg, size, strict); default: if (off % size != 0) { verbose("misaligned access off %d size %d\n", @@ -849,7 +879,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, if (size < 0) return size; - err = check_ptr_alignment(reg, off, size); + err = check_ptr_alignment(env, reg, off, size); if (err) return err; @@ -883,6 +913,8 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, value_regno); /* note that reg.[id|off|range] == 0 */ state->regs[value_regno].type = reg_type; + state->regs[value_regno].aux_off = 0; + state->regs[value_regno].aux_off_align = 0; } } else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) { @@ -1455,6 +1487,8 @@ add_imm: */ dst_reg->off += imm; } else { + bool had_id; + if (src_reg->type == PTR_TO_PACKET) { /* R6=pkt(id=0,off=0,r=62) R7=imm22; r7 += r6 */ tmp_reg = *dst_reg; /* save r7 state */ @@ -1488,14 +1522,23 @@ add_imm: src_reg->imm); return -EACCES; } + + had_id = (dst_reg->id != 0); + /* dst_reg stays as pkt_ptr type and since some positive * integer value was added to the pointer, increment its 'id' */ dst_reg->id = ++env->id_gen; - /* something was added to pkt_ptr, set range and off to zero */ + /* something was added to pkt_ptr, set range to zero */ + dst_reg->aux_off += dst_reg->off; dst_reg->off = 0; dst_reg->range = 0; + if (had_id) + dst_reg->aux_off_align = min(dst_reg->aux_off_align, + src_reg->min_align); + else + dst_reg->aux_off_align = src_reg->min_align; } return 0; } @@ -1669,6 +1712,13 @@ static void check_reg_overflow(struct bpf_reg_state *reg) reg->min_value = BPF_REGISTER_MIN_RANGE; } +static u32 calc_align(u32 imm) +{ + if (!imm) + return 1U << 31; + return imm - ((imm - 1) & imm); +} + static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { @@ -1676,8 +1726,10 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, s64 min_val = BPF_REGISTER_MIN_RANGE; u64 max_val = BPF_REGISTER_MAX_RANGE; u8 opcode = BPF_OP(insn->code); + u32 dst_align, src_align; dst_reg = ®s[insn->dst_reg]; + src_align = 0; if (BPF_SRC(insn->code) == BPF_X) { check_reg_overflow(®s[insn->src_reg]); min_val = regs[insn->src_reg].min_value; @@ -1693,12 +1745,18 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, regs[insn->src_reg].type != UNKNOWN_VALUE) { min_val = BPF_REGISTER_MIN_RANGE; max_val = BPF_REGISTER_MAX_RANGE; + src_align = 0; + } else { + src_align = regs[insn->src_reg].min_align; } } else if (insn->imm < BPF_REGISTER_MAX_RANGE && (s64)insn->imm > BPF_REGISTER_MIN_RANGE) { min_val = max_val = insn->imm; + src_align = calc_align(insn->imm); } + dst_align = dst_reg->min_align; + /* We don't know anything about what was done to this register, mark it * as unknown. */ @@ -1723,18 +1781,21 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, dst_reg->min_value += min_val; if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value += max_val; + dst_reg->min_align = min(src_align, dst_align); break; case BPF_SUB: if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) dst_reg->min_value -= min_val; if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value -= max_val; + dst_reg->min_align = min(src_align, dst_align); break; case BPF_MUL: if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) dst_reg->min_value *= min_val; if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value *= max_val; + dst_reg->min_align = max(src_align, dst_align); break; case BPF_AND: /* Disallow AND'ing of negative numbers, ain't nobody got time @@ -1746,17 +1807,23 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, else dst_reg->min_value = 0; dst_reg->max_value = max_val; + dst_reg->min_align = max(src_align, dst_align); break; case BPF_LSH: /* Gotta have special overflow logic here, if we're shifting * more than MAX_RANGE then just assume we have an invalid * range. */ - if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) + if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) { dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) - dst_reg->min_value <<= min_val; - + dst_reg->min_align = 1; + } else { + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value <<= min_val; + if (!dst_reg->min_align) + dst_reg->min_align = 1; + dst_reg->min_align <<= min_val; + } if (max_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->max_value = BPF_REGISTER_MAX_RANGE; else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) @@ -1766,11 +1833,19 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* RSH by a negative number is undefined, and the BPF_RSH is an * unsigned shift, so make the appropriate casts. */ - if (min_val < 0 || dst_reg->min_value < 0) + if (min_val < 0 || dst_reg->min_value < 0) { dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - else + } else { dst_reg->min_value = (u64)(dst_reg->min_value) >> min_val; + } + if (min_val < 0) { + dst_reg->min_align = 1; + } else { + dst_reg->min_align >>= (u64) min_val; + if (!dst_reg->min_align) + dst_reg->min_align = 1; + } if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value >>= max_val; break; @@ -1872,6 +1947,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) regs[insn->dst_reg].imm = insn->imm; 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); } } else if (opcode > BPF_END) { @@ -2564,6 +2640,7 @@ peek_stack: env->explored_states[t + 1] = STATE_LIST_MARK; } else { /* conditional jump with two edges */ + env->explored_states[t] = STATE_LIST_MARK; ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret == 1) goto peek_stack; @@ -2722,6 +2799,12 @@ static bool states_equal(struct bpf_verifier_env *env, rcur->type != NOT_INIT)) continue; + /* Don't care about the reg->id in this case. */ + if (rold->type == PTR_TO_MAP_VALUE_OR_NULL && + rcur->type == PTR_TO_MAP_VALUE_OR_NULL && + rold->map_ptr == rcur->map_ptr) + continue; + if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET && compare_ptrs_to_packet(rold, rcur)) continue; @@ -2856,8 +2939,15 @@ static int do_check(struct bpf_verifier_env *env) goto process_bpf_exit; } - if (log_level && do_print_state) { - verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx); + if (need_resched()) + cond_resched(); + + if (log_level > 1 || (log_level && do_print_state)) { + if (log_level > 1) + verbose("%d:", insn_idx); + else + verbose("\nfrom %d to %d:", + prev_insn_idx, insn_idx); print_verifier_state(&env->cur_state); do_print_state = false; } @@ -3494,6 +3584,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) } else { log_level = 0; } + if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT) + env->strict_alignment = true; + else + env->strict_alignment = false; ret = replace_map_fd_with_map_ptr(env); if (ret < 0) @@ -3599,6 +3693,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, mutex_lock(&bpf_verifier_lock); log_level = 0; + env->strict_alignment = false; env->explored_states = kcalloc(env->prog->len, sizeof(struct bpf_verifier_state_list *), diff --git a/kernel/fork.c b/kernel/fork.c index 06d759ab4c62..aa1076c5e4a9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1845,11 +1845,13 @@ static __latent_entropy struct task_struct *copy_process( */ recalc_sigpending(); if (signal_pending(current)) { - spin_unlock(¤t->sighand->siglock); - write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; goto bad_fork_cancel_cgroup; } + if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) { + retval = -ENOMEM; + goto bad_fork_cancel_cgroup; + } if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); @@ -1907,6 +1909,8 @@ static __latent_entropy struct task_struct *copy_process( return p; bad_fork_cancel_cgroup: + spin_unlock(¤t->sighand->siglock); + write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p); bad_fork_free_pid: cgroup_threadgroup_change_end(current); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index d1f3e9f558b8..74a5a7255b4d 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -277,7 +277,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) * if reparented. */ for (;;) { - set_current_state(TASK_UNINTERRUPTIBLE); + set_current_state(TASK_INTERRUPTIBLE); if (pid_ns->nr_hashed == init_pids) break; schedule(); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index c5ce7745b230..574f78824d8a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -835,6 +835,13 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return -EPROTONOSUPPORT; } } + + if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { + __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); + + if (defpvid >= VLAN_VID_MASK) + return -EINVAL; + } #endif return 0; diff --git a/net/core/dev.c b/net/core/dev.c index 96cf83da0d66..fca407b4a6ea 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6852,6 +6852,32 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) } EXPORT_SYMBOL(dev_change_proto_down); +bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op) +{ + struct netdev_xdp xdp; + + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_QUERY_PROG; + + /* Query must always succeed. */ + WARN_ON(xdp_op(dev, &xdp) < 0); + return xdp.prog_attached; +} + +static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op, + struct netlink_ext_ack *extack, + struct bpf_prog *prog) +{ + struct netdev_xdp xdp; + + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_SETUP_PROG; + xdp.extack = extack; + xdp.prog = prog; + + return xdp_op(dev, &xdp); +} + /** * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device @@ -6864,41 +6890,34 @@ EXPORT_SYMBOL(dev_change_proto_down); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags) { - int (*xdp_op)(struct net_device *dev, struct netdev_xdp *xdp); const struct net_device_ops *ops = dev->netdev_ops; struct bpf_prog *prog = NULL; - struct netdev_xdp xdp; + xdp_op_t xdp_op, xdp_chk; int err; ASSERT_RTNL(); - xdp_op = ops->ndo_xdp; + xdp_op = xdp_chk = ops->ndo_xdp; + if (!xdp_op && (flags & XDP_FLAGS_DRV_MODE)) + return -EOPNOTSUPP; if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE)) xdp_op = generic_xdp_install; + if (xdp_op == xdp_chk) + xdp_chk = generic_xdp_install; if (fd >= 0) { - if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) { - memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_QUERY_PROG; - - err = xdp_op(dev, &xdp); - if (err < 0) - return err; - if (xdp.prog_attached) - return -EBUSY; - } + if (xdp_chk && __dev_xdp_attached(dev, xdp_chk)) + return -EEXIST; + if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && + __dev_xdp_attached(dev, xdp_op)) + return -EBUSY; prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); if (IS_ERR(prog)) return PTR_ERR(prog); } - memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_SETUP_PROG; - xdp.extack = extack; - xdp.prog = prog; - - err = xdp_op(dev, &xdp); + err = dev_xdp_install(dev, xdp_op, extack, prog); if (err < 0 && prog) bpf_prog_put(prog); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 58b0bcc125b5..d274f81fcc2c 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1132,10 +1132,6 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, lladdr = neigh->ha; } - if (new & NUD_CONNECTED) - neigh->confirmed = jiffies; - neigh->updated = jiffies; - /* If entry was valid and address is not changed, do not change entry state, if new one is STALE. */ @@ -1157,6 +1153,16 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, } } + /* Update timestamps only once we know we will make a change to the + * neighbour entry. Otherwise we risk to move the locktime window with + * noop updates and ignore relevant ARP updates. + */ + if (new != old || lladdr != neigh->ha) { + if (new & NUD_CONNECTED) + neigh->confirmed = jiffies; + neigh->updated = jiffies; + } + if (new != old) { neigh_del_timer(neigh); if (new & NUD_PROBE) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bcb0f610ee42..49a279a7cc15 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -899,8 +899,7 @@ static size_t rtnl_port_size(const struct net_device *dev, static size_t rtnl_xdp_size(void) { size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */ - nla_total_size(1) + /* XDP_ATTACHED */ - nla_total_size(4); /* XDP_FLAGS */ + nla_total_size(1); /* XDP_ATTACHED */ return xdp_size; } @@ -1247,37 +1246,34 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) return 0; } +static u8 rtnl_xdp_attached_mode(struct net_device *dev) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + ASSERT_RTNL(); + + if (rcu_access_pointer(dev->xdp_prog)) + return XDP_ATTACHED_SKB; + if (ops->ndo_xdp && __dev_xdp_attached(dev, ops->ndo_xdp)) + return XDP_ATTACHED_DRV; + + return XDP_ATTACHED_NONE; +} + static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) { struct nlattr *xdp; - u32 xdp_flags = 0; - u8 val = 0; int err; xdp = nla_nest_start(skb, IFLA_XDP); if (!xdp) return -EMSGSIZE; - if (rcu_access_pointer(dev->xdp_prog)) { - xdp_flags = XDP_FLAGS_SKB_MODE; - val = 1; - } else if (dev->netdev_ops->ndo_xdp) { - struct netdev_xdp xdp_op = {}; - - xdp_op.command = XDP_QUERY_PROG; - err = dev->netdev_ops->ndo_xdp(dev, &xdp_op); - if (err) - goto err_cancel; - val = xdp_op.prog_attached; - } - err = nla_put_u8(skb, IFLA_XDP_ATTACHED, val); + + err = nla_put_u8(skb, IFLA_XDP_ATTACHED, + rtnl_xdp_attached_mode(dev)); if (err) goto err_cancel; - if (xdp_flags) { - err = nla_put_u32(skb, IFLA_XDP_FLAGS, xdp_flags); - if (err) - goto err_cancel; - } nla_nest_end(skb, xdp); return 0; @@ -1631,13 +1627,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, 0, flags, ext_filter_mask); - /* If we ran out of room on the first message, - * we're in trouble - */ - WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); - if (err < 0) - goto out; + if (err < 0) { + if (likely(skb->len)) + goto out; + + goto out_err; + } nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: @@ -1645,10 +1641,12 @@ cont: } } out: + err = skb->len; +out_err: cb->args[1] = idx; cb->args[0] = h; - return skb->len; + return err; } int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, @@ -2199,6 +2197,11 @@ static int do_setlink(const struct sk_buff *skb, err = -EINVAL; goto errout; } + if ((xdp_flags & XDP_FLAGS_SKB_MODE) && + (xdp_flags & XDP_FLAGS_DRV_MODE)) { + err = -EINVAL; + goto errout; + } } if (xdp[IFLA_XDP_FD]) { @@ -3452,8 +3455,12 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) err = br_dev->netdev_ops->ndo_bridge_getlink( skb, portid, seq, dev, filter_mask, NLM_F_MULTI); - if (err < 0 && err != -EOPNOTSUPP) - break; + if (err < 0 && err != -EOPNOTSUPP) { + if (likely(skb->len)) + break; + + goto out_err; + } } idx++; } @@ -3464,16 +3471,22 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) seq, dev, filter_mask, NLM_F_MULTI); - if (err < 0 && err != -EOPNOTSUPP) - break; + if (err < 0 && err != -EOPNOTSUPP) { + if (likely(skb->len)) + break; + + goto out_err; + } } idx++; } } + err = skb->len; +out_err: rcu_read_unlock(); cb->args[0] = idx; - return skb->len; + return err; } static inline size_t bridge_nlmsg_size(void) diff --git a/net/core/sock.c b/net/core/sock.c index 79c6aee6af9b..727f924b7f91 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,10 +139,7 @@ #include <trace/events/sock.h> -#ifdef CONFIG_INET #include <net/tcp.h> -#endif - #include <net/busy_poll.h> static DEFINE_MUTEX(proto_list_mutex); @@ -1803,28 +1800,24 @@ EXPORT_SYMBOL(skb_set_owner_w); * delay queue. We want to allow the owner socket to send more * packets, as if they were already TX completed by a typical driver. * But we also want to keep skb->sk set because some packet schedulers - * rely on it (sch_fq for example). So we set skb->truesize to a small - * amount (1) and decrease sk_wmem_alloc accordingly. + * rely on it (sch_fq for example). */ void skb_orphan_partial(struct sk_buff *skb) { - /* If this skb is a TCP pure ACK or already went here, - * we have nothing to do. 2 is already a very small truesize. - */ - if (skb->truesize <= 2) + if (skb_is_tcp_pure_ack(skb)) return; - /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, - * so we do not completely orphan skb, but transfert all - * accounted bytes but one, to avoid unexpected reorders. - */ if (skb->destructor == sock_wfree #ifdef CONFIG_INET || skb->destructor == tcp_wfree #endif ) { - atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); - skb->truesize = 1; + struct sock *sk = skb->sk; + + if (atomic_inc_not_zero(&sk->sk_refcnt)) { + atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + skb->destructor = sock_efree; + } } else { skb_orphan(skb); } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 840f14aaa016..992621172220 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -426,6 +426,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, newsk->sk_backlog_rcv = dccp_v4_do_rcv; newnp->pktoptions = NULL; newnp->opt = NULL; + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; @@ -490,6 +493,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 0937b34c27ca..d54345a06f72 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -653,6 +653,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) unsigned char *arp_ptr; struct rtable *rt; unsigned char *sha; + unsigned char *tha = NULL; __be32 sip, tip; u16 dev_type = dev->type; int addr_type; @@ -724,6 +725,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) break; #endif default: + tha = arp_ptr; arp_ptr += dev->addr_len; } memcpy(&tip, arp_ptr, 4); @@ -842,8 +844,18 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) It is possible, that this option should be enabled for some devices (strip is candidate) */ - is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip && - addr_type == RTN_UNICAST; + is_garp = tip == sip && addr_type == RTN_UNICAST; + + /* Unsolicited ARP _replies_ also require target hwaddr to be + * the same as source. + */ + if (is_garp && arp->ar_op == htons(ARPOP_REPLY)) + is_garp = + /* IPv4 over IEEE 1394 doesn't provide target + * hardware address field in its ARP payload. + */ + tha && + !memcmp(tha, sha, dev->addr_len); if (!n && ((arp->ar_op == htons(ARPOP_REPLY) && diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 39bd1edee676..83e3ed258467 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -763,7 +763,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; - int dumped = 0; + int dumped = 0, err; if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED) @@ -783,20 +783,27 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); - if (fib_table_dump(tb, skb, cb) < 0) - goto out; + err = fib_table_dump(tb, skb, cb); + if (err < 0) { + if (likely(skb->len)) + goto out; + + goto out_err; + } dumped = 1; next: e++; } } out: + err = skb->len; +out_err: rcu_read_unlock(); cb->args[1] = e; cb->args[0] = h; - return skb->len; + return err; } /* Prepare and feed intra-kernel routing request. diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 1201409ba1dc..51182ff2b441 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1983,6 +1983,8 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, /* rcu_read_lock is hold by caller */ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + int err; + if (i < s_i) { i++; continue; @@ -1993,17 +1995,14 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, continue; } - if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWROUTE, - tb->tb_id, - fa->fa_type, - xkey, - KEYLENGTH - fa->fa_slen, - fa->fa_tos, - fa->fa_info, NLM_F_MULTI) < 0) { + err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWROUTE, + tb->tb_id, fa->fa_type, + xkey, KEYLENGTH - fa->fa_slen, + fa->fa_tos, fa->fa_info, NLM_F_MULTI); + if (err < 0) { cb->args[4] = i; - return -1; + return err; } i++; } @@ -2025,10 +2024,13 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, t_key key = cb->args[3]; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) { + int err; + + err = fn_trie_dump_leaf(l, tb, skb, cb); + if (err < 0) { cb->args[3] = key; cb->args[2] = count; - return -1; + return err; } ++count; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3a02d52ed50e..551de4d023a8 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1980,6 +1980,20 @@ int ip_mr_input(struct sk_buff *skb) struct net *net = dev_net(skb->dev); int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; struct mr_table *mrt; + struct net_device *dev; + + /* skb->dev passed in is the loX master dev for vrfs. + * As there are no vifs associated with loopback devices, + * get the proper interface that does have a vif associated with it. + */ + dev = skb->dev; + if (netif_is_l3_master(skb->dev)) { + dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); + if (!dev) { + kfree_skb(skb); + return -ENODEV; + } + } /* Packet is looped back after forward, it should not be * forwarded second time, but still can be delivered locally. @@ -2017,7 +2031,7 @@ int ip_mr_input(struct sk_buff *skb) /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); if (!cache) { - int vif = ipmr_find_vif(mrt, skb->dev); + int vif = ipmr_find_vif(mrt, dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, @@ -2037,7 +2051,7 @@ int ip_mr_input(struct sk_buff *skb) } read_lock(&mrt_lock); - vif = ipmr_find_vif(mrt, skb->dev); + vif = ipmr_find_vif(mrt, dev); if (vif >= 0) { int err2 = ipmr_cache_unresolved(mrt, vif, skb); read_unlock(&mrt_lock); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5a3ad09e2786..174d4376baa5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1179,13 +1179,14 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, */ if (pkt_len > mss) { unsigned int new_len = (pkt_len / mss) * mss; - if (!in_sack && new_len < pkt_len) { + if (!in_sack && new_len < pkt_len) new_len += mss; - if (new_len >= skb->len) - return 0; - } pkt_len = new_len; } + + if (pkt_len >= skb->len && !in_sack) + return 0; + err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); if (err < 0) return err; @@ -3189,7 +3190,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, int delta; /* Non-retransmitted hole got filled? That's reordering */ - if (reord < prior_fackets) + if (reord < prior_fackets && reord <= tp->fackets_out) tcp_update_reordering(sk, tp->fackets_out - reord, 0); delta = tcp_is_fack(tp) ? pkts_acked : diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ea6e4cff9faf..1d6219bf2d6b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1612,7 +1612,7 @@ static void udp_v4_rehash(struct sock *sk) udp_lib_rehash(sk, new_hash); } -int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -1657,7 +1657,7 @@ EXPORT_SYMBOL(udp_encap_enable); * Note that in the success and error cases, the skb is assumed to * have either been requeued or freed. */ -int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index feb50a16398d..a8cf8c6fb60c 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -25,7 +25,6 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); -int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); void udp_destroy_sock(struct sock *sk); #ifdef CONFIG_PROC_FS diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8d297a79b568..6a4fb1e629fb 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1022,7 +1022,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = scope; ifa->prefix_len = pfxlen; - ifa->flags = flags | IFA_F_TENTATIVE; + ifa->flags = flags; + /* No need to add the TENTATIVE flag for addresses with NODAD */ + if (!(flags & IFA_F_NODAD)) + ifa->flags |= IFA_F_TENTATIVE; ifa->valid_lft = valid_lft; ifa->prefered_lft = prefered_lft; ifa->cstamp = ifa->tstamp = jiffies; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 93e58a5e1837..280268f1dd7b 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -63,7 +63,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, const struct net_offload *ops; int proto; struct frag_hdr *fptr; - unsigned int unfrag_ip6hlen; unsigned int payload_len; u8 *prevhdr; int offset = 0; @@ -116,8 +115,10 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, skb->network_header = (u8 *)ipv6h - skb->head; if (udpfrag) { - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); + int err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + return ERR_PTR(err); + fptr = (struct frag_hdr *)((u8 *)ipv6h + err); fptr->frag_off = htons(offset); if (skb->next) fptr->frag_off |= htons(IP6_MF); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 58f6288e9ba5..d4a31becbd25 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -597,7 +597,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int ptr, offset = 0, err = 0; u8 *prevhdr, nexthdr = 0; - hlen = ip6_find_1stfragopt(skb, &prevhdr); + err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + goto fail; + hlen = err; nexthdr = *prevhdr; mtu = ip6_skb_dst_mtu(skb); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index cd4252346a32..e9065b8d3af8 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -79,14 +79,13 @@ EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; - while (offset + 1 <= packet_len) { + while (offset <= packet_len) { + struct ipv6_opt_hdr *exthdr; switch (**nexthdr) { @@ -107,13 +106,16 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) return offset; } - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; + if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) + return -EINVAL; + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; } - return offset; + return -EINVAL; } EXPORT_SYMBOL(ip6_find_1stfragopt); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7a8237acd210..4f4310a36a04 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1062,6 +1062,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif + newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; @@ -1131,6 +1132,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * First: no IPv4 options. */ newinet->inet_opt = NULL; + newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 04862abfe4ec..06ec39b79609 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -526,7 +526,7 @@ out: return; } -int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -569,7 +569,7 @@ void udpv6_encap_enable(void) } EXPORT_SYMBOL(udpv6_encap_enable); -int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index e78bdc76dcc3..f180b3d85e31 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -26,7 +26,6 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); -int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); void udpv6_destroy_sock(struct sock *sk); #ifdef CONFIG_PROC_FS diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ac858c480f2f..a2267f80febb 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -29,6 +29,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u8 frag_hdr_sz = sizeof(struct frag_hdr); __wsum csum; int tnl_hlen; + int err; mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) @@ -90,7 +91,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Find the unfragmentable header and shift it left by frag_hdr_sz * bytes to insert fragment header. */ - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + return ERR_PTR(err); + unfrag_ip6hlen = err; nexthdr = *prevhdr; *prevhdr = NEXTHDR_FRAGMENT; unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f4001763134d..e3eeed19cc7a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2658,13 +2658,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); } - sockc.tsflags = po->sk.sk_tsflags; - if (msg->msg_controllen) { - err = sock_cmsg_send(&po->sk, msg, &sockc); - if (unlikely(err)) - goto out; - } - err = -ENXIO; if (unlikely(dev == NULL)) goto out; @@ -2672,6 +2665,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(!(dev->flags & IFF_UP))) goto out_put; + sockc.tsflags = po->sk.sk_tsflags; + if (msg->msg_controllen) { + err = sock_cmsg_send(&po->sk, msg, &sockc); + if (unlikely(err)) + goto out_put; + } + if (po->sk.sk_socket->type == SOCK_RAW) reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index bbe57d57b67f..e88342fde1bc 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1831,6 +1831,12 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, if (!qdisc_dev(root)) return 0; + if (tcm->tcm_parent) { + q = qdisc_match_from_root(root, TC_H_MAJ(tcm->tcm_parent)); + if (q && tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) + return -1; + return 0; + } hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 961ee59f696a..f5b45b8b8b16 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -240,12 +240,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct sctp_bind_addr *bp; struct ipv6_pinfo *np = inet6_sk(sk); struct sctp_sockaddr_entry *laddr; - union sctp_addr *baddr = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; struct in6_addr *final_p, final; __u8 matchlen = 0; - __u8 bmatchlen; sctp_scope_t scope; memset(fl6, 0, sizeof(struct flowi6)); @@ -312,23 +310,37 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { - if (!laddr->valid) + struct dst_entry *bdst; + __u8 bmatchlen; + + if (!laddr->valid || + laddr->state != SCTP_ADDR_SRC || + laddr->a.sa.sa_family != AF_INET6 || + scope > sctp_scope(&laddr->a)) continue; - if ((laddr->state == SCTP_ADDR_SRC) && - (laddr->a.sa.sa_family == AF_INET6) && - (scope <= sctp_scope(&laddr->a))) { - bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); - if (!baddr || (matchlen < bmatchlen)) { - baddr = &laddr->a; - matchlen = bmatchlen; - } - } - } - if (baddr) { - fl6->saddr = baddr->v6.sin6_addr; - fl6->fl6_sport = baddr->v6.sin6_port; + + fl6->saddr = laddr->a.v6.sin6_addr; + fl6->fl6_sport = laddr->a.v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + bdst = ip6_dst_lookup_flow(sk, fl6, final_p); + + if (!IS_ERR(bdst) && + ipv6_chk_addr(dev_net(bdst->dev), + &laddr->a.v6.sin6_addr, bdst->dev, 1)) { + if (!IS_ERR_OR_NULL(dst)) + dst_release(dst); + dst = bdst; + break; + } + + bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); + if (matchlen > bmatchlen) + continue; + + if (!IS_ERR_OR_NULL(dst)) + dst_release(dst); + dst = bdst; + matchlen = bmatchlen; } rcu_read_unlock(); @@ -665,6 +677,9 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; rcu_read_lock(); opt = rcu_dereference(np->opt); diff --git a/net/smc/Kconfig b/net/smc/Kconfig index c717ef0896aa..33954852f3f8 100644 --- a/net/smc/Kconfig +++ b/net/smc/Kconfig @@ -8,6 +8,10 @@ config SMC The Linux implementation of the SMC-R solution is designed as a separate socket family SMC. + Warning: SMC will expose all memory for remote reads and writes + once a connection is established. Don't enable this option except + for tightly controlled lab environment. + Select this option if you want to run SMC socket applications config SMC_DIAG diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index e41f594a1e1d..03ec058d18df 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -204,7 +204,7 @@ int smc_clc_send_confirm(struct smc_sock *smc) memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN); hton24(cclc.qpn, link->roce_qp->qp_num); cclc.rmb_rkey = - htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); + htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]); cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */ cclc.rmbe_alert_token = htonl(conn->alert_token_local); cclc.qp_mtu = min(link->path_mtu, link->peer_mtu); @@ -256,7 +256,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact) memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN); hton24(aclc.qpn, link->roce_qp->qp_num); aclc.rmb_rkey = - htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); + htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]); aclc.conn_idx = 1; /* as long as 1 RMB = 1 RMBE */ aclc.rmbe_alert_token = htonl(conn->alert_token_local); aclc.qp_mtu = link->path_mtu; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 65020e93ff21..3ac09a629ea1 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -613,19 +613,8 @@ int smc_rmb_create(struct smc_sock *smc) rmb_desc = NULL; continue; /* if mapping failed, try smaller one */ } - rc = smc_ib_get_memory_region(lgr->lnk[SMC_SINGLE_LINK].roce_pd, - IB_ACCESS_REMOTE_WRITE | - IB_ACCESS_LOCAL_WRITE, - &rmb_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) { - smc_ib_buf_unmap(lgr->lnk[SMC_SINGLE_LINK].smcibdev, - tmp_bufsize, rmb_desc, - DMA_FROM_DEVICE); - kfree(rmb_desc->cpu_addr); - kfree(rmb_desc); - rmb_desc = NULL; - continue; - } + rmb_desc->rkey[SMC_SINGLE_LINK] = + lgr->lnk[SMC_SINGLE_LINK].roce_pd->unsafe_global_rkey; rmb_desc->used = 1; write_lock_bh(&lgr->rmbs_lock); list_add(&rmb_desc->list, @@ -668,6 +657,7 @@ int smc_rmb_rtoken_handling(struct smc_connection *conn, for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if ((lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey) && + (lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr == dma_addr) && test_bit(i, lgr->rtokens_used_mask)) { conn->rtoken_idx = i; return 0; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 27eb38056a27..b013cb43a327 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -93,7 +93,7 @@ struct smc_buf_desc { u64 dma_addr[SMC_LINKS_PER_LGR_MAX]; /* mapped address of buffer */ void *cpu_addr; /* virtual address of buffer */ - struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX]; + u32 rkey[SMC_LINKS_PER_LGR_MAX]; /* for rmb only: * rkey provided to peer */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index cb69ab977cd7..b31715505a35 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -37,24 +37,6 @@ u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET; /* unique system * identifier */ -int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags, - struct ib_mr **mr) -{ - int rc; - - if (*mr) - return 0; /* already done */ - - /* obtain unique key - - * next invocation of get_dma_mr returns a different key! - */ - *mr = pd->device->get_dma_mr(pd, access_flags); - rc = PTR_ERR_OR_ZERO(*mr); - if (IS_ERR(*mr)) - *mr = NULL; - return rc; -} - static int smc_ib_modify_qp_init(struct smc_link *lnk) { struct ib_qp_attr qp_attr; @@ -210,7 +192,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) { int rc; - lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0); + lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, + IB_PD_UNSAFE_GLOBAL_RKEY); rc = PTR_ERR_OR_ZERO(lnk->roce_pd); if (IS_ERR(lnk->roce_pd)) lnk->roce_pd = NULL; diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 7e1f0e24d177..b567152a526d 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -61,8 +61,6 @@ void smc_ib_dealloc_protection_domain(struct smc_link *lnk); int smc_ib_create_protection_domain(struct smc_link *lnk); void smc_ib_destroy_queue_pair(struct smc_link *lnk); int smc_ib_create_queue_pair(struct smc_link *lnk); -int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags, - struct ib_mr **mr); int smc_ib_ready_link(struct smc_link *lnk); int smc_ib_modify_qp_rts(struct smc_link *lnk); int smc_ib_modify_qp_reset(struct smc_link *lnk); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 0d4f2f455a7c..1b92b72e812f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -362,25 +362,25 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) return 0; } -#define tipc_wait_for_cond(sock_, timeout_, condition_) \ -({ \ - int rc_ = 0; \ - int done_ = 0; \ - \ - while (!(condition_) && !done_) { \ - struct sock *sk_ = sock->sk; \ - DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ - \ - rc_ = tipc_sk_sock_err(sock_, timeout_); \ - if (rc_) \ - break; \ - prepare_to_wait(sk_sleep(sk_), &wait_, \ - TASK_INTERRUPTIBLE); \ - done_ = sk_wait_event(sk_, timeout_, \ - (condition_), &wait_); \ - remove_wait_queue(sk_sleep(sk_), &wait_); \ - } \ - rc_; \ +#define tipc_wait_for_cond(sock_, timeo_, condition_) \ +({ \ + struct sock *sk_; \ + int rc_; \ + \ + while ((rc_ = !(condition_))) { \ + DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ + sk_ = (sock_)->sk; \ + rc_ = tipc_sk_sock_err((sock_), timeo_); \ + if (rc_) \ + break; \ + prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \ + release_sock(sk_); \ + *(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \ + sched_annotate_sleep(); \ + lock_sock(sk_); \ + remove_wait_queue(sk_sleep(sk_), &wait_); \ + } \ + rc_; \ }) /** diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 8b911c29860e..5a1a98df3499 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1791,32 +1791,40 @@ void x25_kill_by_neigh(struct x25_neigh *nb) static int __init x25_init(void) { - int rc = proto_register(&x25_proto, 0); + int rc; - if (rc != 0) + rc = proto_register(&x25_proto, 0); + if (rc) goto out; rc = sock_register(&x25_family_ops); - if (rc != 0) + if (rc) goto out_proto; dev_add_pack(&x25_packet_type); rc = register_netdevice_notifier(&x25_dev_notifier); - if (rc != 0) + if (rc) goto out_sock; - pr_info("Linux Version 0.2\n"); + rc = x25_register_sysctl(); + if (rc) + goto out_dev; - x25_register_sysctl(); rc = x25_proc_init(); - if (rc != 0) - goto out_dev; + if (rc) + goto out_sysctl; + + pr_info("Linux Version 0.2\n"); + out: return rc; +out_sysctl: + x25_unregister_sysctl(); out_dev: unregister_netdevice_notifier(&x25_dev_notifier); out_sock: + dev_remove_pack(&x25_packet_type); sock_unregister(AF_X25); out_proto: proto_unregister(&x25_proto); diff --git a/net/x25/sysctl_net_x25.c b/net/x25/sysctl_net_x25.c index a06dfe143c67..ba078c85f0a1 100644 --- a/net/x25/sysctl_net_x25.c +++ b/net/x25/sysctl_net_x25.c @@ -73,9 +73,12 @@ static struct ctl_table x25_table[] = { { }, }; -void __init x25_register_sysctl(void) +int __init x25_register_sysctl(void) { x25_table_header = register_net_sysctl(&init_net, "net/x25", x25_table); + if (!x25_table_header) + return -ENOMEM; + return 0; } void x25_unregister_sysctl(void) diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c index b08ab4e88929..9d751e209f31 100644 --- a/samples/bpf/cookie_uid_helper_example.c +++ b/samples/bpf/cookie_uid_helper_example.c @@ -306,7 +306,9 @@ int main(int argc, char *argv[]) prog_attach_iptables(argv[2]); if (cfg_test_traffic) { if (signal(SIGINT, finish) == SIG_ERR) - error(1, errno, "register handler failed"); + error(1, errno, "register SIGINT handler failed"); + if (signal(SIGTERM, finish) == SIG_ERR) + error(1, errno, "register SIGTERM handler failed"); while (!test_finish) { print_table(); printf("\n"); diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index 9cce2a66bd66..512f87a5fd20 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -100,6 +100,7 @@ int main(int argc, char **argv) setrlimit(RLIMIT_MEMLOCK, &r); signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c index be59d7dcbdde..4ed690b907ff 100644 --- a/samples/bpf/sampleip_user.c +++ b/samples/bpf/sampleip_user.c @@ -180,6 +180,7 @@ int main(int argc, char **argv) return 1; } signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); /* do sampling */ printf("Sampling at %d Hertz for %d seconds. Ctrl-C also ends.\n", diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 0c5561d193a4..fa4336423da5 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -192,6 +192,7 @@ int main(int argc, char **argv) setrlimit(RLIMIT_MEMLOCK, &r); signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c index 7fee0f1ba9a3..7321a3f253c9 100644 --- a/samples/bpf/tracex2_user.c +++ b/samples/bpf/tracex2_user.c @@ -127,6 +127,7 @@ int main(int ac, char **argv) } signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); /* start 'ping' in the background to have some kfree_skb events */ f = popen("ping -c5 localhost", "r"); diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index 378850c70eb8..2431c0321b71 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -62,13 +62,14 @@ static void usage(const char *prog) fprintf(stderr, "usage: %s [OPTS] IFINDEX\n\n" "OPTS:\n" - " -S use skb-mode\n", + " -S use skb-mode\n" + " -N enforce native mode\n", prog); } int main(int argc, char **argv) { - const char *optstr = "S"; + const char *optstr = "SN"; char filename[256]; int opt; @@ -77,6 +78,9 @@ int main(int argc, char **argv) case 'S': xdp_flags |= XDP_FLAGS_SKB_MODE; break; + case 'N': + xdp_flags |= XDP_FLAGS_DRV_MODE; + break; default: usage(basename(argv[0])); return 1; @@ -102,6 +106,7 @@ int main(int argc, char **argv) } signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { printf("link set xdp fd failed\n"); diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index 92b8bde9337c..715cd12eaca5 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -79,6 +79,8 @@ static void usage(const char *cmd) printf(" -m <dest-MAC> Used in sending the IP Tunneled pkt\n"); printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n"); printf(" -P <IP-Protocol> Default is TCP\n"); + printf(" -S use skb-mode\n"); + printf(" -N enforce native mode\n"); printf(" -h Display this help\n"); } @@ -138,7 +140,7 @@ int main(int argc, char **argv) { unsigned char opt_flags[256] = {}; unsigned int kill_after_s = 0; - const char *optstr = "i:a:p:s:d:m:T:P:Sh"; + const char *optstr = "i:a:p:s:d:m:T:P:SNh"; int min_port = 0, max_port = 0; struct iptnl_info tnl = {}; struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; @@ -206,6 +208,9 @@ int main(int argc, char **argv) case 'S': xdp_flags |= XDP_FLAGS_SKB_MODE; break; + case 'N': + xdp_flags |= XDP_FLAGS_DRV_MODE; + break; default: usage(argv[0]); return 1; @@ -239,6 +244,7 @@ int main(int argc, char **argv) } signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); while (min_port <= max_port) { vip.dport = htons(min_port++); diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst index 6ba97a1f9c5a..ce753a408c56 100644 --- a/scripts/Makefile.headersinst +++ b/scripts/Makefile.headersinst @@ -8,6 +8,29 @@ # # ========================================================================== +PHONY := __headers +__headers: + +include scripts/Kbuild.include + +srcdir := $(srctree)/$(obj) +subdirs := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.)) +# caller may set destination dir (when installing to asm/) +_dst := $(if $(dst),$(dst),$(obj)) + +# Recursion +__headers: $(subdirs) + +.PHONY: $(subdirs) +$(subdirs): + $(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(_dst)/$@ + +# Skip header install/check for include/uapi and arch/$(hdr-arch)/include/uapi. +# We have only sub-directories there. +skip-inst := $(if $(filter %/uapi,$(obj)),1) + +ifeq ($(skip-inst),) + # generated header directory gen := $(if $(gen),$(gen),$(subst include/,include/generated/,$(obj))) @@ -15,21 +38,14 @@ gen := $(if $(gen),$(gen),$(subst include/,include/generated/,$(obj))) kbuild-file := $(srctree)/$(obj)/Kbuild -include $(kbuild-file) -# called may set destination dir (when installing to asm/) -_dst := $(if $(dst),$(dst),$(obj)) - old-kbuild-file := $(srctree)/$(subst uapi/,,$(obj))/Kbuild ifneq ($(wildcard $(old-kbuild-file)),) include $(old-kbuild-file) endif -include scripts/Kbuild.include - installdir := $(INSTALL_HDR_PATH)/$(subst uapi/,,$(_dst)) -srcdir := $(srctree)/$(obj) gendir := $(objtree)/$(gen) -subdirs := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.)) header-files := $(notdir $(wildcard $(srcdir)/*.h)) header-files += $(notdir $(wildcard $(srcdir)/*.agh)) header-files := $(filter-out $(no-export-headers), $(header-files)) @@ -88,11 +104,9 @@ quiet_cmd_check = CHECK $(printdir) ($(words $(all-files)) files) $(PERL) $< $(INSTALL_HDR_PATH)/include $(SRCARCH); \ touch $@ -PHONY += __headersinst __headerscheck - ifndef HDRCHECK # Rules for installing headers -__headersinst: $(subdirs) $(install-file) +__headers: $(install-file) @: targets += $(install-file) @@ -104,7 +118,7 @@ $(install-file): scripts/headers_install.sh \ $(call if_changed,install) else -__headerscheck: $(subdirs) $(check-file) +__headers: $(check-file) @: targets += $(check-file) @@ -113,11 +127,6 @@ $(check-file): scripts/headers_check.pl $(output-files) FORCE endif -# Recursion -.PHONY: $(subdirs) -$(subdirs): - $(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(_dst)/$@ - targets := $(wildcard $(sort $(targets))) cmd_files := $(wildcard \ $(foreach f,$(targets),$(dir $(f)).$(notdir $(f)).cmd)) @@ -126,6 +135,8 @@ ifneq ($(cmd_files),) include $(cmd_files) endif +endif # skip-inst + .PHONY: $(PHONY) PHONY += FORCE FORCE: ; diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c index ebc6dceddb58..7598361ef1f1 100644 --- a/tools/build/feature/test-bpf.c +++ b/tools/build/feature/test-bpf.c @@ -29,6 +29,7 @@ int main(void) attr.log_size = 0; attr.log_level = 0; attr.kern_version = 0; + attr.prog_flags = 0; /* * Test existence of __NR_bpf and BPF_PROG_LOAD. diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e553529929f6..94dfa9def355 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -132,6 +132,13 @@ enum bpf_attach_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) +/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will perform strict alignment checking as if the kernel + * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, + * and NET_IP_ALIGN defined to 2. + */ +#define BPF_F_STRICT_ALIGNMENT (1U << 0) + #define BPF_PSEUDO_MAP_FD 1 /* flags for BPF_MAP_UPDATE_ELEM command */ @@ -177,6 +184,7 @@ union bpf_attr { __u32 log_size; /* size of user buffer */ __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ + __u32 prog_flags; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -481,8 +489,7 @@ union bpf_attr { * u32 bpf_get_socket_uid(skb) * Get the owner uid of the socket stored inside sk_buff. * @skb: pointer to skb - * Return: uid of the socket owner on success or 0 if the socket pointer - * inside sk_buff is NULL + * Return: uid of the socket owner on success or overflowuid if failed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 4fe444b8092e..6e178987af8e 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -117,6 +117,28 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } +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) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.prog_type = type; + attr.insn_cnt = (__u32)insns_cnt; + attr.insns = ptr_to_u64(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; + log_buf[0] = 0; + attr.kern_version = kern_version; + attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0; + + return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); +} + int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags) { diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index edb4daeff7a5..972bd8333eb7 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -35,6 +35,10 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, size_t log_buf_sz); +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); int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 91edd0566237..f389b02d43a0 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -11,7 +11,8 @@ endif CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include LDLIBS += -lcap -lelf -TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs +TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ + test_align TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o @@ -34,6 +35,7 @@ $(BPFOBJ): force CLANG ?= clang %.o: %.c - $(CLANG) -I. -I../../../include/uapi -I../../../../samples/bpf/ \ + $(CLANG) -I. -I./include/uapi -I../../../include/uapi \ + -I../../../../samples/bpf/ \ -Wno-compare-distinct-pointer-types \ -O2 -target bpf -c $< -o $@ diff --git a/tools/testing/selftests/bpf/include/uapi/linux/types.h b/tools/testing/selftests/bpf/include/uapi/linux/types.h new file mode 100644 index 000000000000..51841848fbfe --- /dev/null +++ b/tools/testing/selftests/bpf/include/uapi/linux/types.h @@ -0,0 +1,22 @@ +#ifndef _UAPI_LINUX_TYPES_H +#define _UAPI_LINUX_TYPES_H + +#include <asm-generic/int-ll64.h> + +/* copied from linux:include/uapi/linux/types.h */ +#define __bitwise +typedef __u16 __bitwise __le16; +typedef __u16 __bitwise __be16; +typedef __u32 __bitwise __le32; +typedef __u32 __bitwise __be32; +typedef __u64 __bitwise __le64; +typedef __u64 __bitwise __be64; + +typedef __u16 __bitwise __sum16; +typedef __u32 __bitwise __wsum; + +#define __aligned_u64 __u64 __attribute__((aligned(8))) +#define __aligned_be64 __be64 __attribute__((aligned(8))) +#define __aligned_le64 __le64 __attribute__((aligned(8))) + +#endif /* _UAPI_LINUX_TYPES_H */ diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c new file mode 100644 index 000000000000..9644d4e069de --- /dev/null +++ b/tools/testing/selftests/bpf/test_align.c @@ -0,0 +1,453 @@ +#include <asm/types.h> +#include <linux/types.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <stddef.h> +#include <stdbool.h> + +#include <linux/unistd.h> +#include <linux/filter.h> +#include <linux/bpf_perf_event.h> +#include <linux/bpf.h> + +#include <bpf/bpf.h> + +#include "../../../include/linux/filter.h" + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +#define MAX_INSNS 512 +#define MAX_MATCHES 16 + +struct bpf_align_test { + const char *descr; + struct bpf_insn insns[MAX_INSNS]; + enum { + UNDEF, + ACCEPT, + REJECT + } result; + enum bpf_prog_type prog_type; + const char *matches[MAX_MATCHES]; +}; + +static struct bpf_align_test tests[] = { + { + .descr = "mov", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_3, 8), + BPF_MOV64_IMM(BPF_REG_3, 16), + BPF_MOV64_IMM(BPF_REG_3, 32), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "1: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp", + "2: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", + "3: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp", + "4: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp", + "5: R1=ctx R3=imm32,min_value=32,max_value=32,min_align=32 R10=fp", + }, + }, + { + .descr = "shift", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_4, 32), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "1: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp", + "2: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp", + "3: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", + "4: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp", + "5: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp", + "6: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp", + "7: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm32,min_value=32,max_value=32,min_align=32 R10=fp", + "8: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm16,min_value=16,max_value=16,min_align=16 R10=fp", + "9: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp", + "10: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm4,min_value=4,max_value=4,min_align=4 R10=fp", + "11: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm2,min_value=2,max_value=2,min_align=2 R10=fp", + }, + }, + { + .descr = "addsub", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "1: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", + "2: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=4 R10=fp", + "3: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R10=fp", + "4: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp", + "5: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm12,min_value=12,max_value=12,min_align=4 R10=fp", + "6: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm14,min_value=14,max_value=14,min_align=2 R10=fp", + }, + }, + { + .descr = "mul", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 7), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 2), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "1: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp", + "2: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp", + "3: R1=ctx R3=imm14,min_value=14,max_value=14,min_align=2 R10=fp", + "4: R1=ctx R3=imm56,min_value=56,max_value=56,min_align=4 R10=fp", + }, + }, + +#define PREP_PKT_POINTERS \ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, \ + offsetof(struct __sk_buff, data)), \ + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, \ + offsetof(struct __sk_buff, data_end)) + +#define LOAD_UNKNOWN(DST_REG) \ + PREP_PKT_POINTERS, \ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), \ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), \ + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 1), \ + BPF_EXIT_INSN(), \ + BPF_LDX_MEM(BPF_B, DST_REG, BPF_REG_2, 0) + + { + .descr = "unknown shift", + .insns = { + LOAD_UNKNOWN(BPF_REG_3), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + LOAD_UNKNOWN(BPF_REG_4), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 5), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp", + "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv55,min_align=2 R10=fp", + "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv54,min_align=4 R10=fp", + "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv53,min_align=8 R10=fp", + "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv52,min_align=16 R10=fp", + "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv56 R10=fp", + "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv51,min_align=32 R10=fp", + "20: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv52,min_align=16 R10=fp", + "21: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv53,min_align=8 R10=fp", + "22: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv54,min_align=4 R10=fp", + "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv55,min_align=2 R10=fp", + }, + }, + { + .descr = "unknown mul", + .insns = { + LOAD_UNKNOWN(BPF_REG_3), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_3), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 1), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_3), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_3), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 4), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_3), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 8), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp", + "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", + "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv55,min_align=1 R10=fp", + "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", + "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv54,min_align=2 R10=fp", + "12: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", + "13: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv53,min_align=4 R10=fp", + "14: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", + "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv52,min_align=8 R10=fp", + "16: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv50,min_align=8 R10=fp" + }, + }, + { + .descr = "packet const offset", + .insns = { + PREP_PKT_POINTERS, + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + + BPF_MOV64_IMM(BPF_REG_0, 0), + + /* Skip over ethernet header. */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 0), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 2), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 3), + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 0), + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "4: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=0,r=0) R10=fp", + "5: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=14,r=0) R10=fp", + "6: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R4=pkt(id=0,off=14,r=0) R5=pkt(id=0,off=14,r=0) R10=fp", + "10: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv56 R5=pkt(id=0,off=14,r=18) R10=fp", + "14: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp", + "15: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp", + }, + }, + { + .descr = "packet variable offset", + .insns = { + LOAD_UNKNOWN(BPF_REG_6), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + + /* First, add a constant to the R5 packet pointer, + * then a variable with a known alignment. + */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0), + + /* Now, test in the other direction. Adding first + * the variable offset to R5, then the constant. + */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0), + + /* Test multiple accumulations of unknown values + * into a packet pointer. + */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + /* Calculated offset in R6 has unknown value, but known + * alignment of 4. + */ + "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R6=inv54,min_align=4 R10=fp", + + /* Offset is added to packet pointer R5, resulting in known + * auxiliary alignment and offset. + */ + "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R5=pkt(id=1,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + /* At the time the word size load is performed from R5, + * it's total offset is NET_IP_ALIGN + reg->off (0) + + * reg->aux_off (14) which is 16. Then the variable + * offset is considered using reg->aux_off_align which + * is 4 and meets the load's requirements. + */ + "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=1,off=4,r=4),aux_off=14,aux_off_align=4 R5=pkt(id=1,off=0,r=4),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + + /* Variable offset is added to R5 packet pointer, + * resulting in auxiliary alignment of 4. + */ + "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=0,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + /* Constant offset is added to R5, resulting in + * reg->off of 14. + */ + "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=14,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + /* At the time the word size load is performed from R5, + * it's total offset is NET_IP_ALIGN + reg->off (14) which + * is 16. Then the variable offset is considered using + * reg->aux_off_align which is 4 and meets the load's + * requirements. + */ + "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=2,off=18,r=18),aux_off_align=4 R5=pkt(id=2,off=14,r=18),aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + /* Constant offset is added to R5 packet pointer, + * resulting in reg->off value of 14. + */ + "26: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=0,off=14,r=8) R6=inv54,min_align=4 R10=fp", + /* Variable offset is added to R5, resulting in an + * auxiliary offset of 14, and an auxiliary alignment of 4. + */ + "27: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + /* Constant is added to R5 again, setting reg->off to 4. */ + "28: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=4,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + /* And once more we add a variable, which causes an accumulation + * of reg->off into reg->aux_off_align, with resulting value of + * 18. The auxiliary alignment stays at 4. + */ + "29: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=4,off=0,r=0),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + /* At the time the word size load is performed from R5, + * it's total offset is NET_IP_ALIGN + reg->off (0) + + * reg->aux_off (18) which is 20. Then the variable offset + * is considered using reg->aux_off_align which is 4 and meets + * the load's requirements. + */ + "33: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=4,off=4,r=4),aux_off=18,aux_off_align=4 R5=pkt(id=4,off=0,r=4),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + }, + }, +}; + +static int probe_filter_length(const struct bpf_insn *fp) +{ + int len; + + for (len = MAX_INSNS - 1; len > 0; --len) + if (fp[len].code != 0 || fp[len].imm != 0) + break; + return len + 1; +} + +static char bpf_vlog[32768]; + +static int do_test_single(struct bpf_align_test *test) +{ + struct bpf_insn *prog = test->insns; + int prog_type = test->prog_type; + int prog_len, i; + int fd_prog; + int ret; + + 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)); + if (fd_prog < 0) { + printf("Failed to load program.\n"); + printf("%s", bpf_vlog); + ret = 1; + } else { + ret = 0; + for (i = 0; i < MAX_MATCHES; i++) { + const char *t, *m = test->matches[i]; + + if (!m) + break; + t = strstr(bpf_vlog, m); + if (!t) { + printf("Failed to find match: %s\n", m); + ret = 1; + printf("%s", bpf_vlog); + break; + } + } + close(fd_prog); + } + return ret; +} + +static int do_test(unsigned int from, unsigned int to) +{ + int all_pass = 0; + int all_fail = 0; + unsigned int i; + + for (i = from; i < to; i++) { + struct bpf_align_test *test = &tests[i]; + int fail; + + printf("Test %3d: %s ... ", + i, test->descr); + fail = do_test_single(test); + if (fail) { + all_fail++; + printf("FAIL\n"); + } else { + all_pass++; + printf("PASS\n"); + } + } + printf("Results: %d pass %d fail\n", + all_pass, all_fail); + return 0; +} + +int main(int argc, char **argv) +{ + unsigned int from = 0, to = ARRAY_SIZE(tests); + + if (argc == 3) { + unsigned int l = atoi(argv[argc - 2]); + unsigned int u = atoi(argv[argc - 1]); + + if (l < to && u < to) { + from = l; + to = u + 1; + } + } else if (argc == 2) { + unsigned int t = atoi(argv[argc - 1]); + + if (t < to) { + from = t; + to = t + 1; + } + } + return do_test(from, to); +} diff --git a/tools/testing/selftests/bpf/test_pkt_access.c b/tools/testing/selftests/bpf/test_pkt_access.c index 39387bb7e08c..6e11ba11709e 100644 --- a/tools/testing/selftests/bpf/test_pkt_access.c +++ b/tools/testing/selftests/bpf/test_pkt_access.c @@ -5,6 +5,7 @@ * License as published by the Free Software Foundation. */ #include <stddef.h> +#include <string.h> #include <linux/bpf.h> #include <linux/if_ether.h> #include <linux/if_packet.h> diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore index 427621792229..2f1f7b013293 100644 --- a/tools/testing/selftests/powerpc/tm/.gitignore +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -11,3 +11,4 @@ tm-signal-context-chk-fpu tm-signal-context-chk-gpr tm-signal-context-chk-vmx tm-signal-context-chk-vsx +tm-vmx-unavail diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 5576ee6a51f2..958c11c14acd 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -2,7 +2,8 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu tm-signal-context-chk-vmx tm-signal-context-chk-vsx TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \ - tm-vmxcopy tm-fork tm-tar tm-tmspr $(SIGNAL_CONTEXT_CHK_TESTS) + tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail \ + $(SIGNAL_CONTEXT_CHK_TESTS) include ../../lib.mk @@ -13,6 +14,7 @@ CFLAGS += -mhtm $(OUTPUT)/tm-syscall: tm-syscall-asm.S $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include $(OUTPUT)/tm-tmspr: CFLAGS += -pthread +$(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS)) $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S diff --git a/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c new file mode 100644 index 000000000000..137185ba4937 --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c @@ -0,0 +1,118 @@ +/* + * Copyright 2017, Michael Neuling, IBM Corp. + * Licensed under GPLv2. + * Original: Breno Leitao <brenohl@br.ibm.com> & + * Gustavo Bueno Romero <gromero@br.ibm.com> + * Edited: Michael Neuling + * + * Force VMX unavailable during a transaction and see if it corrupts + * the checkpointed VMX register state after the abort. + */ + +#include <inttypes.h> +#include <htmintrin.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <pthread.h> +#include <sys/mman.h> +#include <unistd.h> +#include <pthread.h> + +#include "tm.h" +#include "utils.h" + +int passed; + +void *worker(void *unused) +{ + __int128 vmx0; + uint64_t texasr; + + asm goto ( + "li 3, 1;" /* Stick non-zero value in VMX0 */ + "std 3, 0(%[vmx0_ptr]);" + "lvx 0, 0, %[vmx0_ptr];" + + /* Wait here a bit so we get scheduled out 255 times */ + "lis 3, 0x3fff;" + "1: ;" + "addi 3, 3, -1;" + "cmpdi 3, 0;" + "bne 1b;" + + /* Kernel will hopefully turn VMX off now */ + + "tbegin. ;" + "beq failure;" + + /* Cause VMX unavail. Any VMX instruction */ + "vaddcuw 0,0,0;" + + "tend. ;" + "b %l[success];" + + /* Check VMX0 sanity after abort */ + "failure: ;" + "lvx 1, 0, %[vmx0_ptr];" + "vcmpequb. 2, 0, 1;" + "bc 4, 24, %l[value_mismatch];" + "b %l[value_match];" + : + : [vmx0_ptr] "r"(&vmx0) + : "r3" + : success, value_match, value_mismatch + ); + + /* HTM aborted and VMX0 is corrupted */ +value_mismatch: + texasr = __builtin_get_texasr(); + + printf("\n\n==============\n\n"); + printf("Failure with error: %lx\n", _TEXASR_FAILURE_CODE(texasr)); + printf("Summary error : %lx\n", _TEXASR_FAILURE_SUMMARY(texasr)); + printf("TFIAR exact : %lx\n\n", _TEXASR_TFIAR_EXACT(texasr)); + + passed = 0; + return NULL; + + /* HTM aborted but VMX0 is correct */ +value_match: +// printf("!"); + return NULL; + +success: +// printf("."); + return NULL; +} + +int tm_vmx_unavail_test() +{ + int threads; + pthread_t *thread; + + SKIP_IF(!have_htm()); + + passed = 1; + + threads = sysconf(_SC_NPROCESSORS_ONLN) * 4; + thread = malloc(sizeof(pthread_t)*threads); + if (!thread) + return EXIT_FAILURE; + + for (uint64_t i = 0; i < threads; i++) + pthread_create(&thread[i], NULL, &worker, NULL); + + for (uint64_t i = 0; i < threads; i++) + pthread_join(thread[i], NULL); + + free(thread); + + return passed ? EXIT_SUCCESS : EXIT_FAILURE; +} + + +int main(int argc, char **argv) +{ + return test_harness(tm_vmx_unavail_test, "tm_vmx_unavail_test"); +} |