Merge tag 'sched_urgent_for_v5.13_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fix from Borislav Petkov:
"A single fix to restore fairness between control groups with equal
priority"
* tag 'sched_urgent_for_v5.13_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/fair: Correctly insert cfs_rq's to list on unthrottle
diff --git a/Documentation/riscv/vm-layout.rst b/Documentation/riscv/vm-layout.rst
index 329d320..b7f9893 100644
--- a/Documentation/riscv/vm-layout.rst
+++ b/Documentation/riscv/vm-layout.rst
@@ -58,6 +58,6 @@
|
____________________________________________________________|____________________________________________________________
| | | |
- ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | modules
- ffffffff80000000 | -2 GB | ffffffffffffffff | 2 GB | kernel, BPF
+ ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | modules, BPF
+ ffffffff80000000 | -2 GB | ffffffffffffffff | 2 GB | kernel
__________________|____________|__________________|_________|____________________________________________________________
diff --git a/Documentation/vm/slub.rst b/Documentation/vm/slub.rst
index 03f294a..d302855 100644
--- a/Documentation/vm/slub.rst
+++ b/Documentation/vm/slub.rst
@@ -181,7 +181,7 @@
Here is a sample of slub debug output::
====================================================================
- BUG kmalloc-8: Redzone overwritten
+ BUG kmalloc-8: Right Redzone overwritten
--------------------------------------------------------------------
INFO: 0xc90f6d28-0xc90f6d2b. First byte 0x00 instead of 0xcc
@@ -189,10 +189,10 @@
INFO: Object 0xc90f6d20 @offset=3360 fp=0xc90f6d58
INFO: Allocated in get_modalias+0x61/0xf5 age=53 cpu=1 pid=554
- Bytes b4 0xc90f6d10: 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ
- Object 0xc90f6d20: 31 30 31 39 2e 30 30 35 1019.005
- Redzone 0xc90f6d28: 00 cc cc cc .
- Padding 0xc90f6d50: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ
+ Bytes b4 (0xc90f6d10): 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ
+ Object (0xc90f6d20): 31 30 31 39 2e 30 30 35 1019.005
+ Redzone (0xc90f6d28): 00 cc cc cc .
+ Padding (0xc90f6d50): 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ
[<c010523d>] dump_trace+0x63/0x1eb
[<c01053df>] show_trace_log_lvl+0x1a/0x2f
diff --git a/MAINTAINERS b/MAINTAINERS
index bc0ceef..8c5ee00 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16560,6 +16560,7 @@
SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
M: Karsten Graul <kgraul@linux.ibm.com>
+M: Guvenc Gulce <guvenc@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
diff --git a/Makefile b/Makefile
index ed669b2..2d7a8df 100644
--- a/Makefile
+++ b/Makefile
@@ -929,11 +929,14 @@
# Limit inlining across translation units to reduce binary size
KBUILD_LDFLAGS += -mllvm -import-instr-limit=5
-# Check for frame size exceeding threshold during prolog/epilog insertion.
+# Check for frame size exceeding threshold during prolog/epilog insertion
+# when using lld < 13.0.0.
ifneq ($(CONFIG_FRAME_WARN),0)
+ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 130000; echo $$?),0)
KBUILD_LDFLAGS += -plugin-opt=-warn-stack-size=$(CONFIG_FRAME_WARN)
endif
endif
+endif
ifdef CONFIG_LTO
KBUILD_CFLAGS += -fno-lto $(CC_FLAGS_LTO)
diff --git a/arch/arc/include/uapi/asm/sigcontext.h b/arch/arc/include/uapi/asm/sigcontext.h
index 95f8a438..7a5449d 100644
--- a/arch/arc/include/uapi/asm/sigcontext.h
+++ b/arch/arc/include/uapi/asm/sigcontext.h
@@ -18,6 +18,7 @@
*/
struct sigcontext {
struct user_regs_struct regs;
+ struct user_regs_arcv2 v2abi;
};
#endif /* _ASM_ARC_SIGCONTEXT_H */
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index b3ccb9e..cb2f885 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -61,6 +61,41 @@
unsigned int sigret_magic;
};
+static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs)
+{
+ int err = 0;
+#ifndef CONFIG_ISA_ARCOMPACT
+ struct user_regs_arcv2 v2abi;
+
+ v2abi.r30 = regs->r30;
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+ v2abi.r58 = regs->r58;
+ v2abi.r59 = regs->r59;
+#else
+ v2abi.r58 = v2abi.r59 = 0;
+#endif
+ err = __copy_to_user(&mctx->v2abi, &v2abi, sizeof(v2abi));
+#endif
+ return err;
+}
+
+static int restore_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs)
+{
+ int err = 0;
+#ifndef CONFIG_ISA_ARCOMPACT
+ struct user_regs_arcv2 v2abi;
+
+ err = __copy_from_user(&v2abi, &mctx->v2abi, sizeof(v2abi));
+
+ regs->r30 = v2abi.r30;
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+ regs->r58 = v2abi.r58;
+ regs->r59 = v2abi.r59;
+#endif
+#endif
+ return err;
+}
+
static int
stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs,
sigset_t *set)
@@ -94,6 +129,10 @@
err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), &uregs.scratch,
sizeof(sf->uc.uc_mcontext.regs.scratch));
+
+ if (is_isa_arcv2())
+ err |= save_arcv2_regs(&(sf->uc.uc_mcontext), regs);
+
err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
return err ? -EFAULT : 0;
@@ -109,6 +148,10 @@
err |= __copy_from_user(&uregs.scratch,
&(sf->uc.uc_mcontext.regs.scratch),
sizeof(sf->uc.uc_mcontext.regs.scratch));
+
+ if (is_isa_arcv2())
+ err |= restore_arcv2_regs(&(sf->uc.uc_mcontext), regs);
+
if (err)
return -EFAULT;
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 33ce59d..e2146a8 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -57,7 +57,6 @@
.init.ramfs : { INIT_RAM_FS }
. = ALIGN(PAGE_SIZE);
- _stext = .;
HEAD_TEXT_SECTION
INIT_TEXT_SECTION(L1_CACHE_BYTES)
@@ -83,6 +82,7 @@
.text : {
_text = .;
+ _stext = .;
TEXT_TEXT
SCHED_TEXT
CPUIDLE_TEXT
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 2d5c6be..93ce3ec 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -50,7 +50,7 @@
1098: nop; \
.pushsection __jump_table, "aw"; \
.long 1098b - ., LABEL - .; \
- FTR_ENTRY_LONG KEY; \
+ FTR_ENTRY_LONG KEY - .; \
.popsection
#endif
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index dca6648..f9e1f54 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -902,6 +902,10 @@
unsafe_copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set), badframe_block);
user_write_access_end();
+ /* Save the siginfo outside of the unsafe block. */
+ if (copy_siginfo_to_user(&frame->info, &ksig->info))
+ goto badframe;
+
/* Make sure signal handler doesn't get spurious FP exceptions */
tsk->thread.fp_state.fpscr = 0;
@@ -915,11 +919,6 @@
regs->nip = (unsigned long) &frame->tramp[0];
}
-
- /* Save the siginfo outside of the unsafe block. */
- if (copy_siginfo_to_user(&frame->info, &ksig->info))
- goto badframe;
-
/* Allocate a dummy caller frame for the signal handler. */
newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE;
err |= put_user(regs->gpr[1], (unsigned long __user *)newsp);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 043bbea..a6b36a4 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -20,6 +20,7 @@
#include <asm/machdep.h>
#include <asm/rtas.h>
#include <asm/kasan.h>
+#include <asm/sparsemem.h>
#include <asm/svm.h>
#include <mm/mmu_decl.h>
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 16d4d1b..5162241 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2254,7 +2254,7 @@
bool use_siar = regs_use_siar(regs);
unsigned long siar = mfspr(SPRN_SIAR);
- if (ppmu->flags & PPMU_P10_DD1) {
+ if (ppmu && (ppmu->flags & PPMU_P10_DD1)) {
if (siar)
return siar;
else
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index ed96376..30676eb 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -14,6 +14,7 @@
select CLK_SIFIVE
select CLK_SIFIVE_PRCI
select SIFIVE_PLIC
+ select RISCV_ERRATA_ALTERNATIVE
select ERRATA_SIFIVE
help
This enables support for SiFive SoC platform hardware.
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 4be0206..99ecd8b 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -16,7 +16,7 @@
CC_FLAGS_FTRACE := -fpatchable-function-entry=8
endif
-ifeq ($(CONFIG_64BIT)$(CONFIG_CMODEL_MEDLOW),yy)
+ifeq ($(CONFIG_CMODEL_MEDLOW),y)
KBUILD_CFLAGS_MODULE += -mcmodel=medany
endif
diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
index 8eef82e..abbb960 100644
--- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
+++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
@@ -273,7 +273,7 @@
cache-size = <2097152>;
cache-unified;
interrupt-parent = <&plic0>;
- interrupts = <19 20 21 22>;
+ interrupts = <19 21 22 20>;
reg = <0x0 0x2010000 0x0 0x1000>;
};
gpio: gpio@10060000 {
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 9469f46..380cd3a7 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -30,9 +30,8 @@
#define BPF_JIT_REGION_SIZE (SZ_128M)
#ifdef CONFIG_64BIT
-/* KASLR should leave at least 128MB for BPF after the kernel */
-#define BPF_JIT_REGION_START PFN_ALIGN((unsigned long)&_end)
-#define BPF_JIT_REGION_END (BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE)
+#define BPF_JIT_REGION_START (BPF_JIT_REGION_END - BPF_JIT_REGION_SIZE)
+#define BPF_JIT_REGION_END (MODULES_END)
#else
#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE)
#define BPF_JIT_REGION_END (VMALLOC_END)
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 9daacae..d7189c8 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -169,7 +169,7 @@
void __init kasan_init(void)
{
- phys_addr_t _start, _end;
+ phys_addr_t p_start, p_end;
u64 i;
/*
@@ -189,9 +189,9 @@
(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
/* Populate the linear mapping */
- for_each_mem_range(i, &_start, &_end) {
- void *start = (void *)__va(_start);
- void *end = (void *)__va(_end);
+ for_each_mem_range(i, &p_start, &p_end) {
+ void *start = (void *)__va(p_start);
+ void *end = (void *)__va(p_end);
if (start >= end)
break;
@@ -201,7 +201,7 @@
/* Populate kernel, BPF, modules mapping */
kasan_populate(kasan_mem_to_shadow((const void *)MODULES_VADDR),
- kasan_mem_to_shadow((const void *)BPF_JIT_REGION_END));
+ kasan_mem_to_shadow((const void *)MODULES_VADDR + SZ_2G));
for (i = 0; i < PTRS_PER_PTE; i++)
set_pte(&kasan_early_shadow_pte[i],
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 12de7a9..9cc71ca 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -651,9 +651,9 @@
.Lcleanup_sie_mcck:
larl %r13,.Lsie_entry
slgr %r9,%r13
- larl %r13,.Lsie_skip
+ lghi %r13,.Lsie_skip - .Lsie_entry
clgr %r9,%r13
- jh .Lcleanup_sie_int
+ jhe .Lcleanup_sie_int
oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST
.Lcleanup_sie_int:
BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index ceeba9f..fdee23e 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -578,10 +578,17 @@
* PKRU state is switched eagerly because it needs to be valid before we
* return to userland e.g. for a copy_to_user() operation.
*/
- if (current->mm) {
+ if (!(current->flags & PF_KTHREAD)) {
+ /*
+ * If the PKRU bit in xsave.header.xfeatures is not set,
+ * then the PKRU component was in init state, which means
+ * XRSTOR will set PKRU to 0. If the bit is not set then
+ * get_xsave_addr() will return NULL because the PKRU value
+ * in memory is not valid. This means pkru_val has to be
+ * set to 0 and not to init_pkru_value.
+ */
pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU);
- if (pk)
- pkru_val = pk->pkru;
+ pkru_val = pk ? pk->pkru : 0;
}
__write_pkru(pkru_val);
}
diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c
index 6ad165a..64511c4 100644
--- a/arch/x86/kernel/cpu/sgx/virt.c
+++ b/arch/x86/kernel/cpu/sgx/virt.c
@@ -212,6 +212,7 @@
list_splice_tail(&secs_pages, &zombie_secs_pages);
mutex_unlock(&zombie_secs_pages_lock);
+ xa_destroy(&vepc->page_array);
kfree(vepc);
return 0;
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index a4ec653..ec3ae30 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -307,13 +307,17 @@
return 0;
}
- if (!access_ok(buf, size))
- return -EACCES;
+ if (!access_ok(buf, size)) {
+ ret = -EACCES;
+ goto out;
+ }
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_set(current, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- NULL, buf) != 0;
+ if (!static_cpu_has(X86_FEATURE_FPU)) {
+ ret = fpregs_soft_set(current, NULL, 0,
+ sizeof(struct user_i387_ia32_struct),
+ NULL, buf);
+ goto out;
+ }
if (use_xsave()) {
struct _fpx_sw_bytes fx_sw_user;
@@ -369,6 +373,25 @@
fpregs_unlock();
return 0;
}
+
+ /*
+ * The above did an FPU restore operation, restricted to
+ * the user portion of the registers, and failed, but the
+ * microcode might have modified the FPU registers
+ * nevertheless.
+ *
+ * If the FPU registers do not belong to current, then
+ * invalidate the FPU register state otherwise the task might
+ * preempt current and return to user space with corrupted
+ * FPU registers.
+ *
+ * In case current owns the FPU registers then no further
+ * action is required. The fixup below will handle it
+ * correctly.
+ */
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ __cpu_invalidate_fpregs_state();
+
fpregs_unlock();
} else {
/*
@@ -377,7 +400,7 @@
*/
ret = __copy_from_user(&env, buf, sizeof(env));
if (ret)
- goto err_out;
+ goto out;
envp = &env;
}
@@ -405,16 +428,9 @@
if (use_xsave() && !fx_only) {
u64 init_bv = xfeatures_mask_user() & ~user_xfeatures;
- if (using_compacted_format()) {
- ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
- } else {
- ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
-
- if (!ret && state_size > offsetof(struct xregs_state, header))
- ret = validate_user_xstate_header(&fpu->state.xsave.header);
- }
+ ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
if (ret)
- goto err_out;
+ goto out;
sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures,
fx_only);
@@ -434,7 +450,7 @@
ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size);
if (ret) {
ret = -EFAULT;
- goto err_out;
+ goto out;
}
sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures,
@@ -452,7 +468,7 @@
} else {
ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size);
if (ret)
- goto err_out;
+ goto out;
fpregs_lock();
ret = copy_kernel_to_fregs_err(&fpu->state.fsave);
@@ -463,7 +479,7 @@
fpregs_deactivate(fpu);
fpregs_unlock();
-err_out:
+out:
if (ret)
fpu__clear_user_states(fpu);
return ret;
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 9a48f13..b4da665 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -655,6 +655,7 @@
if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP))
entry->ecx = F(RDPID);
++array->nent;
+ break;
default:
break;
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 6d72d8f..17fa4ab 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1410,6 +1410,9 @@
if (!apic_x2apic_mode(apic))
valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI);
+ if (alignment + len > 4)
+ return 1;
+
if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset)))
return 1;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 0144c40..8d5876d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4739,9 +4739,33 @@
context->inject_page_fault = kvm_inject_page_fault;
}
+static union kvm_mmu_role kvm_calc_nested_mmu_role(struct kvm_vcpu *vcpu)
+{
+ union kvm_mmu_role role = kvm_calc_shadow_root_page_role_common(vcpu, false);
+
+ /*
+ * Nested MMUs are used only for walking L2's gva->gpa, they never have
+ * shadow pages of their own and so "direct" has no meaning. Set it
+ * to "true" to try to detect bogus usage of the nested MMU.
+ */
+ role.base.direct = true;
+
+ if (!is_paging(vcpu))
+ role.base.level = 0;
+ else if (is_long_mode(vcpu))
+ role.base.level = is_la57_mode(vcpu) ? PT64_ROOT_5LEVEL :
+ PT64_ROOT_4LEVEL;
+ else if (is_pae(vcpu))
+ role.base.level = PT32E_ROOT_LEVEL;
+ else
+ role.base.level = PT32_ROOT_LEVEL;
+
+ return role;
+}
+
static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
{
- union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false);
+ union kvm_mmu_role new_role = kvm_calc_nested_mmu_role(vcpu);
struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;
if (new_role.as_u64 == g_context->mmu_role.as_u64)
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 0e62e6a..5e7e920 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -221,7 +221,7 @@
return &avic_physical_id_table[index];
}
-/**
+/*
* Note:
* AVIC hardware walks the nested page table to check permissions,
* but does not use the SPA address specified in the leaf page
@@ -764,7 +764,7 @@
return ret;
}
-/**
+/*
* Note:
* The HW cannot support posting multicast/broadcast
* interrupts to a vCPU. So, we still use legacy interrupt
@@ -1005,7 +1005,7 @@
WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
}
-/**
+/*
* This function is called during VCPU halt/unhalt.
*/
static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index e0ce5da..8d36f0c 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -199,9 +199,19 @@
sev->misc_cg = NULL;
}
-static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
+static void sev_decommission(unsigned int handle)
{
struct sev_data_decommission decommission;
+
+ if (!handle)
+ return;
+
+ decommission.handle = handle;
+ sev_guest_decommission(&decommission, NULL);
+}
+
+static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
+{
struct sev_data_deactivate deactivate;
if (!handle)
@@ -214,9 +224,7 @@
sev_guest_deactivate(&deactivate, NULL);
up_read(&sev_deactivate_lock);
- /* decommission handle */
- decommission.handle = handle;
- sev_guest_decommission(&decommission, NULL);
+ sev_decommission(handle);
}
static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
@@ -341,8 +349,10 @@
/* Bind ASID to this guest */
ret = sev_bind_asid(kvm, start.handle, error);
- if (ret)
+ if (ret) {
+ sev_decommission(start.handle);
goto e_free_session;
+ }
/* return handle to userspace */
params.handle = start.handle;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 50b42d7..c2a779b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6247,6 +6247,7 @@
switch (kvm_get_apic_mode(vcpu)) {
case LAPIC_MODE_INVALID:
WARN_ONCE(true, "Invalid local APIC state");
+ break;
case LAPIC_MODE_DISABLED:
break;
case LAPIC_MODE_XAPIC:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6d3955a..e0f4a46 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7106,7 +7106,10 @@
static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
{
- emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
+ struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+ vcpu->arch.hflags = emul_flags;
+ kvm_mmu_reset_context(vcpu);
}
static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
@@ -8258,6 +8261,7 @@
kvm_x86_ops.hardware_enable = NULL;
kvm_mmu_module_exit();
free_percpu(user_return_msrs);
+ kmem_cache_destroy(x86_emulator_cache);
kmem_cache_destroy(x86_fpu_cache);
#ifdef CONFIG_KVM_XEN
static_key_deferred_flush(&kvm_xen_enabled);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 12c686c..60ade7d 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -118,7 +118,9 @@
if (!IS_ENABLED(CONFIG_EFI))
return;
- if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA)
+ if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA ||
+ (efi_mem_type(addr) == EFI_BOOT_SERVICES_DATA &&
+ efi_mem_attributes(addr) & EFI_MEMORY_RUNTIME))
desc->flags |= IORES_MAP_ENCRYPTED;
}
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 5eb4dc2..e94da74 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -254,7 +254,13 @@
/* make sure all non-reserved blocks are inside the limits */
bi->start = max(bi->start, low);
- bi->end = min(bi->end, high);
+
+ /* preserve info for non-RAM areas above 'max_pfn': */
+ if (bi->end > high) {
+ numa_add_memblk_to(bi->nid, high, bi->end,
+ &numa_reserved_meminfo);
+ bi->end = high;
+ }
/* and there's no empty block */
if (bi->start >= bi->end)
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 02dc646..2edd866 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -779,4 +779,48 @@
DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar);
DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);
+#define RS690_LOWER_TOP_OF_DRAM2 0x30
+#define RS690_LOWER_TOP_OF_DRAM2_VALID 0x1
+#define RS690_UPPER_TOP_OF_DRAM2 0x31
+#define RS690_HTIU_NB_INDEX 0xA8
+#define RS690_HTIU_NB_INDEX_WR_ENABLE 0x100
+#define RS690_HTIU_NB_DATA 0xAC
+
+/*
+ * Some BIOS implementations support RAM above 4GB, but do not configure the
+ * PCI host to respond to bus master accesses for these addresses. These
+ * implementations set the TOP_OF_DRAM_SLOT1 register correctly, so PCI DMA
+ * works as expected for addresses below 4GB.
+ *
+ * Reference: "AMD RS690 ASIC Family Register Reference Guide" (pg. 2-57)
+ * https://www.amd.com/system/files/TechDocs/43372_rs690_rrg_3.00o.pdf
+ */
+static void rs690_fix_64bit_dma(struct pci_dev *pdev)
+{
+ u32 val = 0;
+ phys_addr_t top_of_dram = __pa(high_memory - 1) + 1;
+
+ if (top_of_dram <= (1ULL << 32))
+ return;
+
+ pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX,
+ RS690_LOWER_TOP_OF_DRAM2);
+ pci_read_config_dword(pdev, RS690_HTIU_NB_DATA, &val);
+
+ if (val)
+ return;
+
+ pci_info(pdev, "Adjusting top of DRAM to %pa for 64-bit DMA support\n", &top_of_dram);
+
+ pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX,
+ RS690_UPPER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE);
+ pci_write_config_dword(pdev, RS690_HTIU_NB_DATA, top_of_dram >> 32);
+
+ pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX,
+ RS690_LOWER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE);
+ pci_write_config_dword(pdev, RS690_HTIU_NB_DATA,
+ top_of_dram | RS690_LOWER_TOP_OF_DRAM2_VALID);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma);
+
#endif
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index a5c5f70..e65e0a4 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -19,16 +19,6 @@
If in doubt, say N.
-config ACPI_CPPC_CPUFREQ_FIE
- bool "Frequency Invariance support for CPPC cpufreq driver"
- depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY
- default y
- help
- This extends frequency invariance support in the CPPC cpufreq driver,
- by using CPPC delivered and reference performance counters.
-
- If in doubt, say N.
-
config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM
tristate "Allwinner nvmem based SUN50I CPUFreq driver"
depends on ARCH_SUNXI
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 3848b4c..2f769b1 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -10,18 +10,14 @@
#define pr_fmt(fmt) "CPPC Cpufreq:" fmt
-#include <linux/arch_topology.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/delay.h>
#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/dmi.h>
-#include <linux/irq_work.h>
-#include <linux/kthread.h>
#include <linux/time.h>
#include <linux/vmalloc.h>
-#include <uapi/linux/sched/types.h>
#include <asm/unaligned.h>
@@ -61,204 +57,6 @@
}
};
-#ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
-
-/* Frequency invariance support */
-struct cppc_freq_invariance {
- int cpu;
- struct irq_work irq_work;
- struct kthread_work work;
- struct cppc_perf_fb_ctrs prev_perf_fb_ctrs;
- struct cppc_cpudata *cpu_data;
-};
-
-static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
-static struct kthread_worker *kworker_fie;
-static bool fie_disabled;
-
-static struct cpufreq_driver cppc_cpufreq_driver;
-static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu);
-static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
- struct cppc_perf_fb_ctrs fb_ctrs_t0,
- struct cppc_perf_fb_ctrs fb_ctrs_t1);
-
-/**
- * cppc_scale_freq_workfn - CPPC arch_freq_scale updater for frequency invariance
- * @work: The work item.
- *
- * The CPPC driver register itself with the topology core to provide its own
- * implementation (cppc_scale_freq_tick()) of topology_scale_freq_tick() which
- * gets called by the scheduler on every tick.
- *
- * Note that the arch specific counters have higher priority than CPPC counters,
- * if available, though the CPPC driver doesn't need to have any special
- * handling for that.
- *
- * On an invocation of cppc_scale_freq_tick(), we schedule an irq work (since we
- * reach here from hard-irq context), which then schedules a normal work item
- * and cppc_scale_freq_workfn() updates the per_cpu arch_freq_scale variable
- * based on the counter updates since the last tick.
- */
-static void cppc_scale_freq_workfn(struct kthread_work *work)
-{
- struct cppc_freq_invariance *cppc_fi;
- struct cppc_perf_fb_ctrs fb_ctrs = {0};
- struct cppc_cpudata *cpu_data;
- unsigned long local_freq_scale;
- u64 perf;
-
- cppc_fi = container_of(work, struct cppc_freq_invariance, work);
- cpu_data = cppc_fi->cpu_data;
-
- if (cppc_get_perf_ctrs(cppc_fi->cpu, &fb_ctrs)) {
- pr_warn("%s: failed to read perf counters\n", __func__);
- return;
- }
-
- cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
- perf = cppc_perf_from_fbctrs(cpu_data, cppc_fi->prev_perf_fb_ctrs,
- fb_ctrs);
-
- perf <<= SCHED_CAPACITY_SHIFT;
- local_freq_scale = div64_u64(perf, cpu_data->perf_caps.highest_perf);
- if (WARN_ON(local_freq_scale > 1024))
- local_freq_scale = 1024;
-
- per_cpu(arch_freq_scale, cppc_fi->cpu) = local_freq_scale;
-}
-
-static void cppc_irq_work(struct irq_work *irq_work)
-{
- struct cppc_freq_invariance *cppc_fi;
-
- cppc_fi = container_of(irq_work, struct cppc_freq_invariance, irq_work);
- kthread_queue_work(kworker_fie, &cppc_fi->work);
-}
-
-static void cppc_scale_freq_tick(void)
-{
- struct cppc_freq_invariance *cppc_fi = &per_cpu(cppc_freq_inv, smp_processor_id());
-
- /*
- * cppc_get_perf_ctrs() can potentially sleep, call that from the right
- * context.
- */
- irq_work_queue(&cppc_fi->irq_work);
-}
-
-static struct scale_freq_data cppc_sftd = {
- .source = SCALE_FREQ_SOURCE_CPPC,
- .set_freq_scale = cppc_scale_freq_tick,
-};
-
-static void cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
- struct cppc_cpudata *cpu_data)
-{
- struct cppc_perf_fb_ctrs fb_ctrs = {0};
- struct cppc_freq_invariance *cppc_fi;
- int i, ret;
-
- if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
- return;
-
- if (fie_disabled)
- return;
-
- for_each_cpu(i, policy->cpus) {
- cppc_fi = &per_cpu(cppc_freq_inv, i);
- cppc_fi->cpu = i;
- cppc_fi->cpu_data = cpu_data;
- kthread_init_work(&cppc_fi->work, cppc_scale_freq_workfn);
- init_irq_work(&cppc_fi->irq_work, cppc_irq_work);
-
- ret = cppc_get_perf_ctrs(i, &fb_ctrs);
- if (ret) {
- pr_warn("%s: failed to read perf counters: %d\n",
- __func__, ret);
- fie_disabled = true;
- } else {
- cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
- }
- }
-}
-
-static void __init cppc_freq_invariance_init(void)
-{
- struct sched_attr attr = {
- .size = sizeof(struct sched_attr),
- .sched_policy = SCHED_DEADLINE,
- .sched_nice = 0,
- .sched_priority = 0,
- /*
- * Fake (unused) bandwidth; workaround to "fix"
- * priority inheritance.
- */
- .sched_runtime = 1000000,
- .sched_deadline = 10000000,
- .sched_period = 10000000,
- };
- int ret;
-
- if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
- return;
-
- if (fie_disabled)
- return;
-
- kworker_fie = kthread_create_worker(0, "cppc_fie");
- if (IS_ERR(kworker_fie))
- return;
-
- ret = sched_setattr_nocheck(kworker_fie->task, &attr);
- if (ret) {
- pr_warn("%s: failed to set SCHED_DEADLINE: %d\n", __func__,
- ret);
- kthread_destroy_worker(kworker_fie);
- return;
- }
-
- /* Register for freq-invariance */
- topology_set_scale_freq_source(&cppc_sftd, cpu_present_mask);
-}
-
-static void cppc_freq_invariance_exit(void)
-{
- struct cppc_freq_invariance *cppc_fi;
- int i;
-
- if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
- return;
-
- if (fie_disabled)
- return;
-
- topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_CPPC, cpu_present_mask);
-
- for_each_possible_cpu(i) {
- cppc_fi = &per_cpu(cppc_freq_inv, i);
- irq_work_sync(&cppc_fi->irq_work);
- }
-
- kthread_destroy_worker(kworker_fie);
- kworker_fie = NULL;
-}
-
-#else
-static inline void
-cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
- struct cppc_cpudata *cpu_data)
-{
-}
-
-static inline void cppc_freq_invariance_init(void)
-{
-}
-
-static inline void cppc_freq_invariance_exit(void)
-{
-}
-#endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */
-
/* Callback function used to retrieve the max frequency from DMI */
static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
{
@@ -547,12 +345,9 @@
cpu_data->perf_ctrls.desired_perf = caps->highest_perf;
ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
- if (ret) {
+ if (ret)
pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
caps->highest_perf, cpu, ret);
- } else {
- cppc_freq_invariance_policy_init(policy, cpu_data);
- }
return ret;
}
@@ -565,12 +360,12 @@
return (u32)t1 - (u32)t0;
}
-static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
- struct cppc_perf_fb_ctrs fb_ctrs_t0,
- struct cppc_perf_fb_ctrs fb_ctrs_t1)
+static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
+ struct cppc_perf_fb_ctrs fb_ctrs_t0,
+ struct cppc_perf_fb_ctrs fb_ctrs_t1)
{
u64 delta_reference, delta_delivered;
- u64 reference_perf;
+ u64 reference_perf, delivered_perf;
reference_perf = fb_ctrs_t0.reference_perf;
@@ -579,21 +374,12 @@
delta_delivered = get_delta(fb_ctrs_t1.delivered,
fb_ctrs_t0.delivered);
- /* Check to avoid divide-by zero and invalid delivered_perf */
- if (!delta_reference || !delta_delivered)
- return cpu_data->perf_ctrls.desired_perf;
-
- return (reference_perf * delta_delivered) / delta_reference;
-}
-
-static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
- struct cppc_perf_fb_ctrs fb_ctrs_t0,
- struct cppc_perf_fb_ctrs fb_ctrs_t1)
-{
- u64 delivered_perf;
-
- delivered_perf = cppc_perf_from_fbctrs(cpu_data, fb_ctrs_t0,
- fb_ctrs_t1);
+ /* Check to avoid divide-by zero */
+ if (delta_reference || delta_delivered)
+ delivered_perf = (reference_perf * delta_delivered) /
+ delta_reference;
+ else
+ delivered_perf = cpu_data->perf_ctrls.desired_perf;
return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
}
@@ -718,8 +504,6 @@
static int __init cppc_cpufreq_init(void)
{
- int ret;
-
if ((acpi_disabled) || !acpi_cpc_valid())
return -ENODEV;
@@ -727,11 +511,7 @@
cppc_check_hisi_workaround();
- ret = cpufreq_register_driver(&cppc_cpufreq_driver);
- if (!ret)
- cppc_freq_invariance_init();
-
- return ret;
+ return cpufreq_register_driver(&cppc_cpufreq_driver);
}
static inline void free_cpu_data(void)
@@ -748,7 +528,6 @@
static void __exit cppc_cpufreq_exit(void)
{
- cppc_freq_invariance_exit();
cpufreq_unregister_driver(&cppc_cpufreq_driver);
free_cpu_data();
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 6ab9d9a..39b5b46 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -59,6 +59,7 @@
#devices
config ALTERA_MSGDMA
tristate "Altera / Intel mSGDMA Engine"
+ depends on HAS_IOMEM
select DMA_ENGINE
help
Enable support for Altera / Intel mSGDMA controller.
@@ -701,6 +702,7 @@
config XILINX_ZYNQMP_DPDMA
tristate "Xilinx DPDMA Engine"
+ depends on HAS_IOMEM && OF
select DMA_ENGINE
select DMA_VIRTUAL_CHANNELS
help
diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
index 4ec909e..4ae05792 100644
--- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
+++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
@@ -332,6 +332,7 @@
}
if (priv->dpdmai_attr.version.major > DPDMAI_VER_MAJOR) {
+ err = -EINVAL;
dev_err(dev, "DPDMAI major version mismatch\n"
"Found %u.%u, supported version is %u.%u\n",
priv->dpdmai_attr.version.major,
@@ -341,6 +342,7 @@
}
if (priv->dpdmai_attr.version.minor > DPDMAI_VER_MINOR) {
+ err = -EINVAL;
dev_err(dev, "DPDMAI minor version mismatch\n"
"Found %u.%u, supported version is %u.%u\n",
priv->dpdmai_attr.version.major,
@@ -475,6 +477,7 @@
ppriv->store =
dpaa2_io_store_create(DPAA2_QDMA_STORE_SIZE, dev);
if (!ppriv->store) {
+ err = -ENOMEM;
dev_err(dev, "dpaa2_io_store_create() failed\n");
goto err_store;
}
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 302cba5..d4419bf 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -110,6 +110,7 @@
pasid = iommu_sva_get_pasid(sva);
if (pasid == IOMMU_PASID_INVALID) {
iommu_sva_unbind_device(sva);
+ rc = -EINVAL;
goto failed;
}
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 776fd44..442d55c 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -168,6 +168,32 @@
return rc;
}
+static void idxd_cleanup_interrupts(struct idxd_device *idxd)
+{
+ struct pci_dev *pdev = idxd->pdev;
+ struct idxd_irq_entry *irq_entry;
+ int i, msixcnt;
+
+ msixcnt = pci_msix_vec_count(pdev);
+ if (msixcnt <= 0)
+ return;
+
+ irq_entry = &idxd->irq_entries[0];
+ free_irq(irq_entry->vector, irq_entry);
+
+ for (i = 1; i < msixcnt; i++) {
+
+ irq_entry = &idxd->irq_entries[i];
+ if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE))
+ idxd_device_release_int_handle(idxd, idxd->int_handles[i],
+ IDXD_IRQ_MSIX);
+ free_irq(irq_entry->vector, irq_entry);
+ }
+
+ idxd_mask_error_interrupts(idxd);
+ pci_free_irq_vectors(pdev);
+}
+
static int idxd_setup_wqs(struct idxd_device *idxd)
{
struct device *dev = &idxd->pdev->dev;
@@ -242,6 +268,7 @@
engine->idxd = idxd;
device_initialize(&engine->conf_dev);
engine->conf_dev.parent = &idxd->conf_dev;
+ engine->conf_dev.bus = &dsa_bus_type;
engine->conf_dev.type = &idxd_engine_device_type;
rc = dev_set_name(&engine->conf_dev, "engine%d.%d", idxd->id, engine->id);
if (rc < 0) {
@@ -303,6 +330,19 @@
return rc;
}
+static void idxd_cleanup_internals(struct idxd_device *idxd)
+{
+ int i;
+
+ for (i = 0; i < idxd->max_groups; i++)
+ put_device(&idxd->groups[i]->conf_dev);
+ for (i = 0; i < idxd->max_engines; i++)
+ put_device(&idxd->engines[i]->conf_dev);
+ for (i = 0; i < idxd->max_wqs; i++)
+ put_device(&idxd->wqs[i]->conf_dev);
+ destroy_workqueue(idxd->wq);
+}
+
static int idxd_setup_internals(struct idxd_device *idxd)
{
struct device *dev = &idxd->pdev->dev;
@@ -531,12 +571,12 @@
dev_dbg(dev, "Loading RO device config\n");
rc = idxd_device_load_config(idxd);
if (rc < 0)
- goto err;
+ goto err_config;
}
rc = idxd_setup_interrupts(idxd);
if (rc)
- goto err;
+ goto err_config;
dev_dbg(dev, "IDXD interrupt setup complete.\n");
@@ -549,6 +589,8 @@
dev_dbg(dev, "IDXD device %d probed successfully\n", idxd->id);
return 0;
+ err_config:
+ idxd_cleanup_internals(idxd);
err:
if (device_pasid_enabled(idxd))
idxd_disable_system_pasid(idxd);
@@ -556,6 +598,18 @@
return rc;
}
+static void idxd_cleanup(struct idxd_device *idxd)
+{
+ struct device *dev = &idxd->pdev->dev;
+
+ perfmon_pmu_remove(idxd);
+ idxd_cleanup_interrupts(idxd);
+ idxd_cleanup_internals(idxd);
+ if (device_pasid_enabled(idxd))
+ idxd_disable_system_pasid(idxd);
+ iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA);
+}
+
static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct device *dev = &pdev->dev;
@@ -608,7 +662,7 @@
rc = idxd_register_devices(idxd);
if (rc) {
dev_err(dev, "IDXD sysfs setup failed\n");
- goto err;
+ goto err_dev_register;
}
idxd->state = IDXD_DEV_CONF_READY;
@@ -618,6 +672,8 @@
return 0;
+ err_dev_register:
+ idxd_cleanup(idxd);
err:
pci_iounmap(pdev, idxd->reg_base);
err_iomap:
@@ -787,6 +843,7 @@
static void __exit idxd_exit_module(void)
{
+ idxd_unregister_driver();
pci_unregister_driver(&idxd_pci_driver);
idxd_cdev_remove();
idxd_unregister_bus_type();
diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c
index 0d5c42f..97d9a6f 100644
--- a/drivers/dma/ipu/ipu_irq.c
+++ b/drivers/dma/ipu/ipu_irq.c
@@ -230,7 +230,7 @@
}
/**
- * ipu_irq_map() - map an IPU interrupt source to an IRQ number
+ * ipu_irq_unmap() - unmap an IPU interrupt source
* @source: interrupt source bit position (see ipu_irq_map())
* @return: 0 or negative error code
*/
diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c
index 27c0735..375e7e6 100644
--- a/drivers/dma/mediatek/mtk-uart-apdma.c
+++ b/drivers/dma/mediatek/mtk-uart-apdma.c
@@ -131,10 +131,7 @@
static void mtk_uart_apdma_desc_free(struct virt_dma_desc *vd)
{
- struct dma_chan *chan = vd->tx.chan;
- struct mtk_chan *c = to_mtk_uart_apdma_chan(chan);
-
- kfree(c->desc);
+ kfree(container_of(vd, struct mtk_uart_apdma_desc, vd));
}
static void mtk_uart_apdma_start_tx(struct mtk_chan *c)
@@ -207,14 +204,9 @@
static void mtk_uart_apdma_tx_handler(struct mtk_chan *c)
{
- struct mtk_uart_apdma_desc *d = c->desc;
-
mtk_uart_apdma_write(c, VFF_INT_FLAG, VFF_TX_INT_CLR_B);
mtk_uart_apdma_write(c, VFF_INT_EN, VFF_INT_EN_CLR_B);
mtk_uart_apdma_write(c, VFF_EN, VFF_EN_CLR_B);
-
- list_del(&d->vd.node);
- vchan_cookie_complete(&d->vd);
}
static void mtk_uart_apdma_rx_handler(struct mtk_chan *c)
@@ -245,9 +237,17 @@
c->rx_status = d->avail_len - cnt;
mtk_uart_apdma_write(c, VFF_RPT, wg);
+}
- list_del(&d->vd.node);
- vchan_cookie_complete(&d->vd);
+static void mtk_uart_apdma_chan_complete_handler(struct mtk_chan *c)
+{
+ struct mtk_uart_apdma_desc *d = c->desc;
+
+ if (d) {
+ list_del(&d->vd.node);
+ vchan_cookie_complete(&d->vd);
+ c->desc = NULL;
+ }
}
static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id)
@@ -261,6 +261,7 @@
mtk_uart_apdma_rx_handler(c);
else if (c->dir == DMA_MEM_TO_DEV)
mtk_uart_apdma_tx_handler(c);
+ mtk_uart_apdma_chan_complete_handler(c);
spin_unlock_irqrestore(&c->vc.lock, flags);
return IRQ_HANDLED;
@@ -348,7 +349,7 @@
return NULL;
/* Now allocate and setup the descriptor */
- d = kzalloc(sizeof(*d), GFP_ATOMIC);
+ d = kzalloc(sizeof(*d), GFP_NOWAIT);
if (!d)
return NULL;
@@ -366,7 +367,7 @@
unsigned long flags;
spin_lock_irqsave(&c->vc.lock, flags);
- if (vchan_issue_pending(&c->vc)) {
+ if (vchan_issue_pending(&c->vc) && !c->desc) {
vd = vchan_next_desc(&c->vc);
c->desc = to_mtk_uart_apdma_desc(&vd->tx);
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index fd8d2bc..110de8a 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2694,13 +2694,15 @@
for (i = 0; i < len / period_len; i++) {
desc = pl330_get_desc(pch);
if (!desc) {
+ unsigned long iflags;
+
dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n",
__func__, __LINE__);
if (!first)
return NULL;
- spin_lock_irqsave(&pl330->pool_lock, flags);
+ spin_lock_irqsave(&pl330->pool_lock, iflags);
while (!list_empty(&first->node)) {
desc = list_entry(first->node.next,
@@ -2710,7 +2712,7 @@
list_move_tail(&first->node, &pl330->desc_pool);
- spin_unlock_irqrestore(&pl330->pool_lock, flags);
+ spin_unlock_irqrestore(&pl330->pool_lock, iflags);
return NULL;
}
diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig
index 365f94e..3f926a6 100644
--- a/drivers/dma/qcom/Kconfig
+++ b/drivers/dma/qcom/Kconfig
@@ -33,6 +33,7 @@
config QCOM_HIDMA_MGMT
tristate "Qualcomm Technologies HIDMA Management support"
+ depends on HAS_IOMEM
select DMA_ENGINE
help
Enable support for the Qualcomm Technologies HIDMA Management.
diff --git a/drivers/dma/sf-pdma/Kconfig b/drivers/dma/sf-pdma/Kconfig
index f8ffa02e..ba46a0a 100644
--- a/drivers/dma/sf-pdma/Kconfig
+++ b/drivers/dma/sf-pdma/Kconfig
@@ -1,5 +1,6 @@
config SF_PDMA
tristate "Sifive PDMA controller driver"
+ depends on HAS_IOMEM
select DMA_ENGINE
select DMA_VIRTUAL_CHANNELS
help
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index d530c1b..6885b3d 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1913,7 +1913,7 @@
/* Enable runtime PM and initialize the device. */
pm_runtime_enable(&pdev->dev);
- ret = pm_runtime_get_sync(&pdev->dev);
+ ret = pm_runtime_resume_and_get(&pdev->dev);
if (ret < 0) {
dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret);
return ret;
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 265d7c0..e182739 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -3675,6 +3675,9 @@
kfree(base->lcla_pool.base_unaligned);
+ if (base->lcpa_base)
+ iounmap(base->lcpa_base);
+
if (base->phy_lcpa)
release_mem_region(base->phy_lcpa,
base->lcpa_size);
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 36ba8b4..18cbd1e 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -1452,7 +1452,7 @@
return -ENOMEM;
}
- ret = pm_runtime_get_sync(dmadev->ddev.dev);
+ ret = pm_runtime_resume_and_get(dmadev->ddev.dev);
if (ret < 0)
return ret;
@@ -1718,7 +1718,7 @@
u32 ccr, id;
int ret;
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return ret;
diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index 70b29bd..6c70980 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -113,6 +113,7 @@
#define XILINX_DPDMA_CH_VDO 0x020
#define XILINX_DPDMA_CH_PYLD_SZ 0x024
#define XILINX_DPDMA_CH_DESC_ID 0x028
+#define XILINX_DPDMA_CH_DESC_ID_MASK GENMASK(15, 0)
/* DPDMA descriptor fields */
#define XILINX_DPDMA_DESC_CONTROL_PREEMBLE 0xa5
@@ -866,7 +867,8 @@
* will be used, but it should be enough.
*/
list_for_each_entry(sw_desc, &desc->descriptors, node)
- sw_desc->hw.desc_id = desc->vdesc.tx.cookie;
+ sw_desc->hw.desc_id = desc->vdesc.tx.cookie
+ & XILINX_DPDMA_CH_DESC_ID_MASK;
sw_desc = list_first_entry(&desc->descriptors,
struct xilinx_dpdma_sw_desc, node);
@@ -1086,7 +1088,8 @@
if (!chan->running || !pending)
goto out;
- desc_id = dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_ID);
+ desc_id = dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_ID)
+ & XILINX_DPDMA_CH_DESC_ID_MASK;
/* If the retrigger raced with vsync, retry at the next frame. */
sw_desc = list_first_entry(&pending->descriptors,
@@ -1459,7 +1462,7 @@
*/
static void xilinx_dpdma_disable_irq(struct xilinx_dpdma_device *xdev)
{
- dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ERR_ALL);
+ dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ALL);
dpdma_write(xdev->reg, XILINX_DPDMA_EIDS, XILINX_DPDMA_EINTR_ALL);
}
@@ -1596,6 +1599,26 @@
return dma_get_slave_channel(&xdev->chan[chan_id]->vchan.chan);
}
+static void dpdma_hw_init(struct xilinx_dpdma_device *xdev)
+{
+ unsigned int i;
+ void __iomem *reg;
+
+ /* Disable all interrupts */
+ xilinx_dpdma_disable_irq(xdev);
+
+ /* Stop all channels */
+ for (i = 0; i < ARRAY_SIZE(xdev->chan); i++) {
+ reg = xdev->reg + XILINX_DPDMA_CH_BASE
+ + XILINX_DPDMA_CH_OFFSET * i;
+ dpdma_clr(reg, XILINX_DPDMA_CH_CNTL, XILINX_DPDMA_CH_CNTL_ENABLE);
+ }
+
+ /* Clear the interrupt status registers */
+ dpdma_write(xdev->reg, XILINX_DPDMA_ISR, XILINX_DPDMA_INTR_ALL);
+ dpdma_write(xdev->reg, XILINX_DPDMA_EISR, XILINX_DPDMA_EINTR_ALL);
+}
+
static int xilinx_dpdma_probe(struct platform_device *pdev)
{
struct xilinx_dpdma_device *xdev;
@@ -1622,6 +1645,8 @@
if (IS_ERR(xdev->reg))
return PTR_ERR(xdev->reg);
+ dpdma_hw_init(xdev);
+
xdev->irq = platform_get_irq(pdev, 0);
if (xdev->irq < 0) {
dev_err(xdev->dev, "failed to get platform irq\n");
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index d841956..5fecf5a 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -468,7 +468,7 @@
struct zynqmp_dma_desc_sw *desc;
int i, ret;
- ret = pm_runtime_get_sync(chan->dev);
+ ret = pm_runtime_resume_and_get(chan->dev);
if (ret < 0)
return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 0597aeb..327b1f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -6871,8 +6871,12 @@
if (ring->use_doorbell) {
WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER,
(adev->doorbell_index.kiq * 2) << 2);
+ /* If GC has entered CGPG, ringing doorbell > first page doesn't
+ * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround
+ * this issue.
+ */
WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
- (adev->doorbell_index.userqueue_end * 2) << 2);
+ (adev->doorbell.size - 4));
}
WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 516467e..c09225d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3673,8 +3673,12 @@
if (ring->use_doorbell) {
WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER,
(adev->doorbell_index.kiq * 2) << 2);
+ /* If GC has entered CGPG, ringing doorbell > first page doesn't
+ * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround
+ * this issue.
+ */
WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
- (adev->doorbell_index.userqueue_end * 2) << 2);
+ (adev->doorbell.size - 4));
}
WREG32_SOC15_RLC(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL,
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 37a23aa..66d623f 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -642,11 +642,45 @@
nmi_exit();
}
+static u32 do_read_iar(struct pt_regs *regs)
+{
+ u32 iar;
+
+ if (gic_supports_nmi() && unlikely(!interrupts_enabled(regs))) {
+ u64 pmr;
+
+ /*
+ * We were in a context with IRQs disabled. However, the
+ * entry code has set PMR to a value that allows any
+ * interrupt to be acknowledged, and not just NMIs. This can
+ * lead to surprising effects if the NMI has been retired in
+ * the meantime, and that there is an IRQ pending. The IRQ
+ * would then be taken in NMI context, something that nobody
+ * wants to debug twice.
+ *
+ * Until we sort this, drop PMR again to a level that will
+ * actually only allow NMIs before reading IAR, and then
+ * restore it to what it was.
+ */
+ pmr = gic_read_pmr();
+ gic_pmr_mask_irqs();
+ isb();
+
+ iar = gic_read_iar();
+
+ gic_write_pmr(pmr);
+ } else {
+ iar = gic_read_iar();
+ }
+
+ return iar;
+}
+
static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
{
u32 irqnr;
- irqnr = gic_read_iar();
+ irqnr = do_read_iar(regs);
/* Check for special IDs first */
if ((irqnr >= 1020 && irqnr <= 1023))
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index d174823..4ffbfd5 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -350,6 +350,7 @@
rtnl_lock();
result = register_netdevice(dev);
if (result) {
+ tty_kref_put(tty);
rtnl_unlock();
free_netdev(dev);
return -ENODEV;
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index 029e77d..a45865b 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -82,6 +82,8 @@
bool can_ka_first_pass;
bool can_speed_check;
atomic_t free_ctx_cnt;
+ void *rxbuf[MCBA_MAX_RX_URBS];
+ dma_addr_t rxbuf_dma[MCBA_MAX_RX_URBS];
};
/* CAN frame */
@@ -633,6 +635,7 @@
for (i = 0; i < MCBA_MAX_RX_URBS; i++) {
struct urb *urb = NULL;
u8 *buf;
+ dma_addr_t buf_dma;
/* create a URB, and a buffer for it */
urb = usb_alloc_urb(0, GFP_KERNEL);
@@ -642,7 +645,7 @@
}
buf = usb_alloc_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE,
- GFP_KERNEL, &urb->transfer_dma);
+ GFP_KERNEL, &buf_dma);
if (!buf) {
netdev_err(netdev, "No memory left for USB buffer\n");
usb_free_urb(urb);
@@ -661,11 +664,14 @@
if (err) {
usb_unanchor_urb(urb);
usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE,
- buf, urb->transfer_dma);
+ buf, buf_dma);
usb_free_urb(urb);
break;
}
+ priv->rxbuf[i] = buf;
+ priv->rxbuf_dma[i] = buf_dma;
+
/* Drop reference, USB core will take care of freeing it */
usb_free_urb(urb);
}
@@ -708,7 +714,14 @@
static void mcba_urb_unlink(struct mcba_priv *priv)
{
+ int i;
+
usb_kill_anchored_urbs(&priv->rx_submitted);
+
+ for (i = 0; i < MCBA_MAX_RX_URBS; ++i)
+ usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE,
+ priv->rxbuf[i], priv->rxbuf_dma[i]);
+
usb_kill_anchored_urbs(&priv->tx_submitted);
}
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 881f887..5257148 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -236,36 +236,48 @@
static int ena_xdp_tx_map_frame(struct ena_ring *xdp_ring,
struct ena_tx_buffer *tx_info,
struct xdp_frame *xdpf,
- void **push_hdr,
- u32 *push_len)
+ struct ena_com_tx_ctx *ena_tx_ctx)
{
struct ena_adapter *adapter = xdp_ring->adapter;
struct ena_com_buf *ena_buf;
- dma_addr_t dma = 0;
+ int push_len = 0;
+ dma_addr_t dma;
+ void *data;
u32 size;
tx_info->xdpf = xdpf;
+ data = tx_info->xdpf->data;
size = tx_info->xdpf->len;
- ena_buf = tx_info->bufs;
- /* llq push buffer */
- *push_len = min_t(u32, size, xdp_ring->tx_max_header_size);
- *push_hdr = tx_info->xdpf->data;
+ if (xdp_ring->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) {
+ /* Designate part of the packet for LLQ */
+ push_len = min_t(u32, size, xdp_ring->tx_max_header_size);
- if (size - *push_len > 0) {
+ ena_tx_ctx->push_header = data;
+
+ size -= push_len;
+ data += push_len;
+ }
+
+ ena_tx_ctx->header_len = push_len;
+
+ if (size > 0) {
dma = dma_map_single(xdp_ring->dev,
- *push_hdr + *push_len,
- size - *push_len,
+ data,
+ size,
DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(xdp_ring->dev, dma)))
goto error_report_dma_error;
- tx_info->map_linear_data = 1;
- tx_info->num_of_bufs = 1;
- }
+ tx_info->map_linear_data = 0;
- ena_buf->paddr = dma;
- ena_buf->len = size;
+ ena_buf = tx_info->bufs;
+ ena_buf->paddr = dma;
+ ena_buf->len = size;
+
+ ena_tx_ctx->ena_bufs = ena_buf;
+ ena_tx_ctx->num_bufs = tx_info->num_of_bufs = 1;
+ }
return 0;
@@ -274,10 +286,6 @@
&xdp_ring->syncp);
netif_warn(adapter, tx_queued, adapter->netdev, "Failed to map xdp buff\n");
- xdp_return_frame_rx_napi(tx_info->xdpf);
- tx_info->xdpf = NULL;
- tx_info->num_of_bufs = 0;
-
return -EINVAL;
}
@@ -289,8 +297,6 @@
struct ena_com_tx_ctx ena_tx_ctx = {};
struct ena_tx_buffer *tx_info;
u16 next_to_use, req_id;
- void *push_hdr;
- u32 push_len;
int rc;
next_to_use = xdp_ring->next_to_use;
@@ -298,15 +304,11 @@
tx_info = &xdp_ring->tx_buffer_info[req_id];
tx_info->num_of_bufs = 0;
- rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &push_hdr, &push_len);
+ rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &ena_tx_ctx);
if (unlikely(rc))
return rc;
- ena_tx_ctx.ena_bufs = tx_info->bufs;
- ena_tx_ctx.push_header = push_hdr;
- ena_tx_ctx.num_bufs = tx_info->num_of_bufs;
ena_tx_ctx.req_id = req_id;
- ena_tx_ctx.header_len = push_len;
rc = ena_xmit_common(dev,
xdp_ring,
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index b3d74332..7748b27 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1849,6 +1849,7 @@
free_netdev(netdev);
out_pci_release:
pci_release_mem_regions(pdev);
+ pci_disable_pcie_error_reporting(pdev);
out_pci_disable:
pci_disable_device(pdev);
return err;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fcc729d..aef3fcc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7308,7 +7308,7 @@
entries_sp = ctx->vnic_max_vnic_entries + ctx->qp_max_l2_entries +
2 * (extra_qps + ctx->qp_min_qp1_entries) + min;
entries_sp = roundup(entries_sp, ctx->tqm_entries_multiple);
- entries = ctx->qp_max_l2_entries + extra_qps + ctx->qp_min_qp1_entries;
+ entries = ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries);
entries = roundup(entries, ctx->tqm_entries_multiple);
entries = clamp_t(u32, entries, min, ctx->tqm_max_entries_per_ring);
for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) {
@@ -11750,6 +11750,8 @@
bnxt_hwrm_coal_params_qcaps(bp);
}
+static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt);
+
static int bnxt_fw_init_one(struct bnxt *bp)
{
int rc;
@@ -11764,6 +11766,9 @@
netdev_err(bp->dev, "Firmware init phase 2 failed\n");
return rc;
}
+ rc = bnxt_probe_phy(bp, false);
+ if (rc)
+ return rc;
rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false);
if (rc)
return rc;
@@ -13155,6 +13160,7 @@
bnxt_hwrm_func_drv_unrgtr(bp);
bnxt_free_hwrm_short_cmd_req(bp);
bnxt_free_hwrm_resources(bp);
+ bnxt_ethtool_free(bp);
kfree(bp->fw_health);
bp->fw_health = NULL;
bnxt_cleanup_pci(bp);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 61ea3ec..83ed10ac 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -1337,13 +1337,27 @@
return ret;
}
- spin_lock_bh(&adap->win0_lock);
- ret = t4_load_phy_fw(adap, MEMWIN_NIC, NULL, data, size);
- spin_unlock_bh(&adap->win0_lock);
- if (ret)
- dev_err(adap->pdev_dev, "Failed to load PHY FW\n");
+ /* We have to RESET the chip/firmware because we need the
+ * chip in uninitialized state for loading new PHY image.
+ * Otherwise, the running firmware will only store the PHY
+ * image in local RAM which will be lost after next reset.
+ */
+ ret = t4_fw_reset(adap, adap->mbox, PIORSTMODE_F | PIORST_F);
+ if (ret < 0) {
+ dev_err(adap->pdev_dev,
+ "Set FW to RESET for flashing PHY FW failed. ret: %d\n",
+ ret);
+ return ret;
+ }
- return ret;
+ ret = t4_load_phy_fw(adap, MEMWIN_NIC, NULL, data, size);
+ if (ret < 0) {
+ dev_err(adap->pdev_dev, "Failed to load PHY FW. ret: %d\n",
+ ret);
+ return ret;
+ }
+
+ return 0;
}
static int cxgb4_ethtool_flash_fw(struct net_device *netdev,
@@ -1610,16 +1624,14 @@
u32 ftid)
{
struct tid_info *t = &adap->tids;
- struct filter_entry *f;
- if (ftid < t->nhpftids)
- f = &adap->tids.hpftid_tab[ftid];
- else if (ftid < t->nftids)
- f = &adap->tids.ftid_tab[ftid - t->nhpftids];
- else
- f = lookup_tid(&adap->tids, ftid);
+ if (ftid >= t->hpftid_base && ftid < t->hpftid_base + t->nhpftids)
+ return &t->hpftid_tab[ftid - t->hpftid_base];
- return f;
+ if (ftid >= t->ftid_base && ftid < t->ftid_base + t->nftids)
+ return &t->ftid_tab[ftid - t->ftid_base];
+
+ return lookup_tid(t, ftid);
}
static void cxgb4_fill_filter_rule(struct ethtool_rx_flow_spec *fs,
@@ -1826,6 +1838,11 @@
filter_id = filter_info->loc_array[cmd->fs.location];
f = cxgb4_get_filter_entry(adapter, filter_id);
+ if (f->fs.prio)
+ filter_id -= adapter->tids.hpftid_base;
+ else if (!f->fs.hash)
+ filter_id -= (adapter->tids.ftid_base - adapter->tids.nhpftids);
+
ret = cxgb4_flow_rule_destroy(dev, f->fs.tc_prio, &f->fs, filter_id);
if (ret)
goto err;
@@ -1885,6 +1902,11 @@
filter_info = &adapter->ethtool_filters->port[pi->port_id];
+ if (fs.prio)
+ tid += adapter->tids.hpftid_base;
+ else if (!fs.hash)
+ tid += (adapter->tids.ftid_base - adapter->tids.nhpftids);
+
filter_info->loc_array[cmd->fs.location] = tid;
set_bit(cmd->fs.location, filter_info->bmap);
filter_info->in_use++;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 22c9ac9..6260b3b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -198,7 +198,7 @@
WORD_MASK, f->fs.nat_lip[3] |
f->fs.nat_lip[2] << 8 |
f->fs.nat_lip[1] << 16 |
- (u64)f->fs.nat_lip[0] << 25, 1);
+ (u64)f->fs.nat_lip[0] << 24, 1);
}
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 1f601de..762113a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -4424,10 +4424,8 @@
/* Load PHY Firmware onto adapter.
*/
- spin_lock_bh(&adap->win0_lock);
ret = t4_load_phy_fw(adap, MEMWIN_NIC, phy_info->phy_fw_version,
(u8 *)phyf->data, phyf->size);
- spin_unlock_bh(&adap->win0_lock);
if (ret < 0)
dev_err(adap->pdev_dev, "PHY Firmware transfer error %d\n",
-ret);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 9428ef1..a0555f4d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3060,16 +3060,19 @@
* @addr: the start address to write
* @n: length of data to write in bytes
* @data: the data to write
+ * @byte_oriented: whether to store data as bytes or as words
*
* Writes up to a page of data (256 bytes) to the serial flash starting
* at the given address. All the data must be written to the same page.
+ * If @byte_oriented is set the write data is stored as byte stream
+ * (i.e. matches what on disk), otherwise in big-endian.
*/
static int t4_write_flash(struct adapter *adapter, unsigned int addr,
- unsigned int n, const u8 *data)
+ unsigned int n, const u8 *data, bool byte_oriented)
{
- int ret;
- u32 buf[64];
unsigned int i, c, left, val, offset = addr & 0xff;
+ u32 buf[64];
+ int ret;
if (addr >= adapter->params.sf_size || offset + n > SF_PAGE_SIZE)
return -EINVAL;
@@ -3080,10 +3083,14 @@
(ret = sf1_write(adapter, 4, 1, 1, val)) != 0)
goto unlock;
- for (left = n; left; left -= c) {
+ for (left = n; left; left -= c, data += c) {
c = min(left, 4U);
- for (val = 0, i = 0; i < c; ++i)
- val = (val << 8) + *data++;
+ for (val = 0, i = 0; i < c; ++i) {
+ if (byte_oriented)
+ val = (val << 8) + data[i];
+ else
+ val = (val << 8) + data[c - i - 1];
+ }
ret = sf1_write(adapter, c, c != left, 1, val);
if (ret)
@@ -3096,7 +3103,8 @@
t4_write_reg(adapter, SF_OP_A, 0); /* unlock SF */
/* Read the page to verify the write succeeded */
- ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, 1);
+ ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf,
+ byte_oriented);
if (ret)
return ret;
@@ -3692,7 +3700,7 @@
*/
memcpy(first_page, fw_data, SF_PAGE_SIZE);
((struct fw_hdr *)first_page)->fw_ver = cpu_to_be32(0xffffffff);
- ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page);
+ ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page, true);
if (ret)
goto out;
@@ -3700,14 +3708,14 @@
for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) {
addr += SF_PAGE_SIZE;
fw_data += SF_PAGE_SIZE;
- ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data);
+ ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data, true);
if (ret)
goto out;
}
- ret = t4_write_flash(adap,
- fw_start + offsetof(struct fw_hdr, fw_ver),
- sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver);
+ ret = t4_write_flash(adap, fw_start + offsetof(struct fw_hdr, fw_ver),
+ sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver,
+ true);
out:
if (ret)
dev_err(adap->pdev_dev, "firmware download failed, error %d\n",
@@ -3812,9 +3820,11 @@
/* Copy the supplied PHY Firmware image to the adapter memory location
* allocated by the adapter firmware.
*/
+ spin_lock_bh(&adap->win0_lock);
ret = t4_memory_rw(adap, win, mtype, maddr,
phy_fw_size, (__be32 *)phy_fw_data,
T4_MEMORY_WRITE);
+ spin_unlock_bh(&adap->win0_lock);
if (ret)
return ret;
@@ -10208,7 +10218,7 @@
n = size - i;
else
n = SF_PAGE_SIZE;
- ret = t4_write_flash(adap, addr, n, cfg_data);
+ ret = t4_write_flash(adap, addr, n, cfg_data, true);
if (ret)
goto out;
@@ -10677,13 +10687,14 @@
for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) {
addr += SF_PAGE_SIZE;
boot_data += SF_PAGE_SIZE;
- ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data);
+ ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data,
+ false);
if (ret)
goto out;
}
ret = t4_write_flash(adap, boot_sector, SF_PAGE_SIZE,
- (const u8 *)header);
+ (const u8 *)header, false);
out:
if (ret)
@@ -10758,7 +10769,7 @@
for (i = 0; i < size; i += SF_PAGE_SIZE) {
n = min_t(u32, size - i, SF_PAGE_SIZE);
- ret = t4_write_flash(adap, addr, n, cfg_data);
+ ret = t4_write_flash(adap, addr, n, cfg_data, false);
if (ret)
goto out;
@@ -10770,7 +10781,8 @@
for (i = 0; i < npad; i++) {
u8 data = 0;
- ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data);
+ ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data,
+ false);
if (ret)
goto out;
}
diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
index 46b0dba..7c99217 100644
--- a/drivers/net/ethernet/ec_bhf.c
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -576,10 +576,12 @@
struct ec_bhf_priv *priv = netdev_priv(net_dev);
unregister_netdev(net_dev);
- free_netdev(net_dev);
pci_iounmap(dev, priv->dma_io);
pci_iounmap(dev, priv->io);
+
+ free_netdev(net_dev);
+
pci_release_regions(dev);
pci_clear_master(dev);
pci_disable_device(dev);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index b6eba29..7968568 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5897,6 +5897,7 @@
unmap_bars:
be_unmap_pci_bars(adapter);
free_netdev:
+ pci_disable_pcie_error_reporting(pdev);
free_netdev(netdev);
rel_reg:
pci_release_regions(pdev);
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 1753807..d71eac7 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -215,15 +215,13 @@
{
struct fec_enet_private *fep =
container_of(cc, struct fec_enet_private, cc);
- const struct platform_device_id *id_entry =
- platform_get_device_id(fep->pdev);
u32 tempval;
tempval = readl(fep->hwp + FEC_ATIME_CTRL);
tempval |= FEC_T_CTRL_CAPTURE;
writel(tempval, fep->hwp + FEC_ATIME_CTRL);
- if (id_entry->driver_data & FEC_QUIRK_BUG_CAPTURE)
+ if (fep->quirks & FEC_QUIRK_BUG_CAPTURE)
udelay(1);
return readl(fep->hwp + FEC_ATIME);
@@ -604,6 +602,10 @@
fep->ptp_caps.enable = fec_ptp_enable;
fep->cycle_speed = clk_get_rate(fep->clk_ptp);
+ if (!fep->cycle_speed) {
+ fep->cycle_speed = NSEC_PER_SEC;
+ dev_err(&fep->pdev->dev, "clk_ptp clock rate is zero\n");
+ }
fep->ptp_inc = NSEC_PER_SEC / fep->cycle_speed;
spin_lock_init(&fep->tmreg_lock);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index d70ee57..27f9dac 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1717,12 +1717,13 @@
* ice_vsi_cfg_txqs - Configure the VSI for Tx
* @vsi: the VSI being configured
* @rings: Tx ring array to be configured
+ * @count: number of Tx ring array elements
*
* Return 0 on success and a negative value on error
* Configure the Tx VSI for operation.
*/
static int
-ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings)
+ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, u16 count)
{
struct ice_aqc_add_tx_qgrp *qg_buf;
u16 q_idx = 0;
@@ -1734,7 +1735,7 @@
qg_buf->num_txqs = 1;
- for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) {
+ for (q_idx = 0; q_idx < count; q_idx++) {
err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf);
if (err)
goto err_cfg_txqs;
@@ -1754,7 +1755,7 @@
*/
int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi)
{
- return ice_vsi_cfg_txqs(vsi, vsi->tx_rings);
+ return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq);
}
/**
@@ -1769,7 +1770,7 @@
int ret;
int i;
- ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings);
+ ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq);
if (ret)
return ret;
@@ -2009,17 +2010,18 @@
* @rst_src: reset source
* @rel_vmvf_num: Relative ID of VF/VM
* @rings: Tx ring array to be stopped
+ * @count: number of Tx ring array elements
*/
static int
ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
- u16 rel_vmvf_num, struct ice_ring **rings)
+ u16 rel_vmvf_num, struct ice_ring **rings, u16 count)
{
u16 q_idx;
if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS)
return -EINVAL;
- for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) {
+ for (q_idx = 0; q_idx < count; q_idx++) {
struct ice_txq_meta txq_meta = { };
int status;
@@ -2047,7 +2049,7 @@
ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
u16 rel_vmvf_num)
{
- return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings);
+ return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings, vsi->num_txq);
}
/**
@@ -2056,7 +2058,7 @@
*/
int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi)
{
- return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings);
+ return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings, vsi->num_xdp_txq);
}
/**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 4ee85a2..0eb2307 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2556,6 +2556,20 @@
}
/**
+ * ice_xdp_safe_mode - XDP handler for safe mode
+ * @dev: netdevice
+ * @xdp: XDP command
+ */
+static int ice_xdp_safe_mode(struct net_device __always_unused *dev,
+ struct netdev_bpf *xdp)
+{
+ NL_SET_ERR_MSG_MOD(xdp->extack,
+ "Please provide working DDP firmware package in order to use XDP\n"
+ "Refer to Documentation/networking/device_drivers/ethernet/intel/ice.rst");
+ return -EOPNOTSUPP;
+}
+
+/**
* ice_xdp - implements XDP handler
* @dev: netdevice
* @xdp: XDP command
@@ -6937,6 +6951,7 @@
.ndo_change_mtu = ice_change_mtu,
.ndo_get_stats64 = ice_get_stats64,
.ndo_tx_timeout = ice_tx_timeout,
+ .ndo_bpf = ice_xdp_safe_mode,
};
static const struct net_device_ops ice_netdev_ops = {
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 36dc3e5..21ef2f1 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -154,6 +154,7 @@
static int xrx200_alloc_skb(struct xrx200_chan *ch)
{
+ struct sk_buff *skb = ch->skb[ch->dma.desc];
dma_addr_t mapping;
int ret = 0;
@@ -168,6 +169,7 @@
XRX200_DMA_DATA_LEN, DMA_FROM_DEVICE);
if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) {
dev_kfree_skb_any(ch->skb[ch->dma.desc]);
+ ch->skb[ch->dma.desc] = skb;
ret = -ENOMEM;
goto skip;
}
@@ -198,7 +200,6 @@
ch->dma.desc %= LTQ_DESC_NUM;
if (ret) {
- ch->skb[ch->dma.desc] = skb;
net_dev->stats.rx_dropped++;
netdev_err(net_dev, "failed to allocate new rx buffer\n");
return ret;
@@ -352,8 +353,8 @@
struct xrx200_chan *ch = ptr;
if (napi_schedule_prep(&ch->napi)) {
- __napi_schedule(&ch->napi);
ltq_dma_disable_irq(&ch->dma);
+ __napi_schedule(&ch->napi);
}
ltq_dma_ack_irq(&ch->dma);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index a9166cd..ceebfc20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -303,6 +303,7 @@
int ret = 0, i;
mutex_lock(&mlx5_intf_mutex);
+ priv->flags &= ~MLX5_PRIV_FLAGS_DETACH;
for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) {
if (!priv->adev[i]) {
bool is_supported = false;
@@ -320,6 +321,16 @@
}
} else {
adev = &priv->adev[i]->adev;
+
+ /* Pay attention that this is not PCI driver that
+ * mlx5_core_dev is connected, but auxiliary driver.
+ *
+ * Here we can race of module unload with devlink
+ * reload, but we don't need to take extra lock because
+ * we are holding global mlx5_intf_mutex.
+ */
+ if (!adev->dev.driver)
+ continue;
adrv = to_auxiliary_drv(adev->dev.driver);
if (adrv->resume)
@@ -350,6 +361,10 @@
continue;
adev = &priv->adev[i]->adev;
+ /* Auxiliary driver was unbind manually through sysfs */
+ if (!adev->dev.driver)
+ goto skip_suspend;
+
adrv = to_auxiliary_drv(adev->dev.driver);
if (adrv->suspend) {
@@ -357,9 +372,11 @@
continue;
}
+skip_suspend:
del_adev(&priv->adev[i]->adev);
priv->adev[i] = NULL;
}
+ priv->flags |= MLX5_PRIV_FLAGS_DETACH;
mutex_unlock(&mlx5_intf_mutex);
}
@@ -448,6 +465,8 @@
struct mlx5_priv *priv = &dev->priv;
lockdep_assert_held(&mlx5_intf_mutex);
+ if (priv->flags & MLX5_PRIV_FLAGS_DETACH)
+ return 0;
delete_drivers(dev);
if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
index 0dd7615..bc33eaa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
@@ -64,6 +64,8 @@
struct mlx5e_priv *priv = netdev_priv(dev);
struct devlink_port *port;
+ if (!netif_device_present(dev))
+ return NULL;
port = mlx5e_devlink_get_dl_port(priv);
if (port->registered)
return port;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index d907c1a..778e229 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -1,7 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
// Copyright (c) 2020 Mellanox Technologies
-#include <linux/ptp_classify.h>
#include "en/ptp.h"
#include "en/txrx.h"
#include "en/params.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index ab935cc..c96668b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -6,6 +6,7 @@
#include "en.h"
#include "en_stats.h"
+#include <linux/ptp_classify.h>
struct mlx5e_ptpsq {
struct mlx5e_txqsq txqsq;
@@ -43,6 +44,27 @@
DECLARE_BITMAP(state, MLX5E_PTP_STATE_NUM_STATES);
};
+static inline bool mlx5e_use_ptpsq(struct sk_buff *skb)
+{
+ struct flow_keys fk;
+
+ if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+ return false;
+
+ if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
+ return false;
+
+ if (fk.basic.n_proto == htons(ETH_P_1588))
+ return true;
+
+ if (fk.basic.n_proto != htons(ETH_P_IP) &&
+ fk.basic.n_proto != htons(ETH_P_IPV6))
+ return false;
+
+ return (fk.basic.ip_proto == IPPROTO_UDP &&
+ fk.ports.dst == htons(PTP_EV_PORT));
+}
+
int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
u8 lag_port, struct mlx5e_ptp **cp);
void mlx5e_ptp_close(struct mlx5e_ptp *c);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
index be0ee03..2e9bee4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
@@ -129,10 +129,9 @@
work);
struct mlx5e_neigh_hash_entry *nhe = update_work->nhe;
struct neighbour *n = update_work->n;
+ struct mlx5e_encap_entry *e = NULL;
bool neigh_connected, same_dev;
- struct mlx5e_encap_entry *e;
unsigned char ha[ETH_ALEN];
- struct mlx5e_priv *priv;
u8 nud_state, dead;
rtnl_lock();
@@ -156,14 +155,12 @@
if (!same_dev)
goto out;
- list_for_each_entry(e, &nhe->encap_list, encap_list) {
- if (!mlx5e_encap_take(e))
- continue;
+ /* mlx5e_get_next_init_encap() releases previous encap before returning
+ * the next one.
+ */
+ while ((e = mlx5e_get_next_init_encap(nhe, e)) != NULL)
+ mlx5e_rep_update_flows(netdev_priv(e->out_dev), e, neigh_connected, ha);
- priv = netdev_priv(e->out_dev);
- mlx5e_rep_update_flows(priv, e, neigh_connected, ha);
- mlx5e_encap_put(priv, e);
- }
out:
rtnl_unlock();
mlx5e_release_neigh_update_work(update_work);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index 3113822..85eaadc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -94,13 +94,9 @@
ASSERT_RTNL();
- /* wait for encap to be fully initialized */
- wait_for_completion(&e->res_ready);
-
mutex_lock(&esw->offloads.encap_tbl_lock);
encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID);
- if (e->compl_result < 0 || (encap_connected == neigh_connected &&
- ether_addr_equal(e->h_dest, ha)))
+ if (encap_connected == neigh_connected && ether_addr_equal(e->h_dest, ha))
goto unlock;
mlx5e_take_all_encap_flows(e, &flow_list);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index f1fb116..490131e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -251,9 +251,12 @@
mlx5e_take_tmp_flow(flow, flow_list, 0);
}
+typedef bool (match_cb)(struct mlx5e_encap_entry *);
+
static struct mlx5e_encap_entry *
-mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe,
- struct mlx5e_encap_entry *e)
+mlx5e_get_next_matching_encap(struct mlx5e_neigh_hash_entry *nhe,
+ struct mlx5e_encap_entry *e,
+ match_cb match)
{
struct mlx5e_encap_entry *next = NULL;
@@ -288,7 +291,7 @@
/* wait for encap to be fully initialized */
wait_for_completion(&next->res_ready);
/* continue searching if encap entry is not in valid state after completion */
- if (!(next->flags & MLX5_ENCAP_ENTRY_VALID)) {
+ if (!match(next)) {
e = next;
goto retry;
}
@@ -296,6 +299,30 @@
return next;
}
+static bool mlx5e_encap_valid(struct mlx5e_encap_entry *e)
+{
+ return e->flags & MLX5_ENCAP_ENTRY_VALID;
+}
+
+static struct mlx5e_encap_entry *
+mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe,
+ struct mlx5e_encap_entry *e)
+{
+ return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_valid);
+}
+
+static bool mlx5e_encap_initialized(struct mlx5e_encap_entry *e)
+{
+ return e->compl_result >= 0;
+}
+
+struct mlx5e_encap_entry *
+mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe,
+ struct mlx5e_encap_entry *e)
+{
+ return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_initialized);
+}
+
void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
{
struct mlx5e_neigh *m_neigh = &nhe->m_neigh;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 3d45341..26f7fab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -532,9 +532,6 @@
struct mlx5_core_dev *mdev = priv->mdev;
struct net_device *netdev = priv->netdev;
- if (!priv->ipsec)
- return;
-
if (!(mlx5_accel_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_ESP) ||
!MLX5_CAP_ETH(mdev, swp)) {
mlx5_core_dbg(mdev, "mlx5e: ESP and SWP offload not supported\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 5cd466e..25403af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -356,7 +356,7 @@
int mlx5e_arfs_create_tables(struct mlx5e_priv *priv)
{
- int err = 0;
+ int err = -ENOMEM;
int i;
if (!(priv->netdev->hw_features & NETIF_F_NTUPLE))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ec6bafe..d26b8ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2705,8 +2705,6 @@
nch = priv->channels.params.num_channels;
ntc = priv->channels.params.num_tc;
num_rxqs = nch * priv->profile->rq_groups;
- if (priv->channels.params.ptp_rx)
- num_rxqs++;
mlx5e_netdev_set_tcs(netdev, nch, ntc);
@@ -4824,22 +4822,15 @@
}
if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)) {
- netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM;
- netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM;
- netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
- netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+ netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL;
+ netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL;
}
if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) {
- netdev->hw_features |= NETIF_F_GSO_GRE |
- NETIF_F_GSO_GRE_CSUM;
- netdev->hw_enc_features |= NETIF_F_GSO_GRE |
- NETIF_F_GSO_GRE_CSUM;
- netdev->gso_partial_features |= NETIF_F_GSO_GRE |
- NETIF_F_GSO_GRE_CSUM;
+ netdev->hw_features |= NETIF_F_GSO_GRE;
+ netdev->hw_enc_features |= NETIF_F_GSO_GRE;
+ netdev->gso_partial_features |= NETIF_F_GSO_GRE;
}
if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_IPIP)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dd64878..d4b0f27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4765,7 +4765,7 @@
list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) {
wait_for_completion(&hpe->res_ready);
if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id)
- hpe->hp->pair->peer_gone = true;
+ mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair);
mlx5e_hairpin_put(priv, hpe);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 25c09179..1702753 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -178,6 +178,9 @@
void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list);
struct mlx5e_neigh_hash_entry;
+struct mlx5e_encap_entry *
+mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe,
+ struct mlx5e_encap_entry *e);
void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);
void mlx5e_tc_reoffload_flows_work(struct work_struct *work);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 8ba6267..320fe0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -32,7 +32,6 @@
#include <linux/tcp.h>
#include <linux/if_vlan.h>
-#include <linux/ptp_classify.h>
#include <net/geneve.h>
#include <net/dsfield.h>
#include "en.h"
@@ -67,24 +66,6 @@
}
#endif
-static bool mlx5e_use_ptpsq(struct sk_buff *skb)
-{
- struct flow_keys fk;
-
- if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
- return false;
-
- if (fk.basic.n_proto == htons(ETH_P_1588))
- return true;
-
- if (fk.basic.n_proto != htons(ETH_P_IP) &&
- fk.basic.n_proto != htons(ETH_P_IPV6))
- return false;
-
- return (fk.basic.ip_proto == IPPROTO_UDP &&
- fk.ports.dst == htons(PTP_EV_PORT));
-}
-
static u16 mlx5e_select_ptpsq(struct net_device *dev, struct sk_buff *skb)
{
struct mlx5e_priv *priv = netdev_priv(dev);
@@ -145,9 +126,9 @@
}
ptp_channel = READ_ONCE(priv->channels.ptp);
- if (unlikely(ptp_channel) &&
- test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) &&
- mlx5e_use_ptpsq(skb))
+ if (unlikely(ptp_channel &&
+ test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) &&
+ mlx5e_use_ptpsq(skb)))
return mlx5e_select_ptpsq(dev, skb);
txq_ix = netdev_pick_tx(dev, skb, NULL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 77c0ca6..9403334 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -136,7 +136,7 @@
eqe = next_eqe_sw(eq);
if (!eqe)
- return 0;
+ goto out;
do {
struct mlx5_core_cq *cq;
@@ -161,6 +161,8 @@
++eq->cons_index;
} while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq)));
+
+out:
eq_update_ci(eq, 1);
if (cqn != -1)
@@ -248,9 +250,9 @@
++eq->cons_index;
} while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq)));
- eq_update_ci(eq, 1);
out:
+ eq_update_ci(eq, 1);
mlx5_eq_async_int_unlock(eq_async, recovery, &flags);
return unlikely(recovery) ? num_eqes : 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index b88705a..97e6cb6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1054,6 +1054,12 @@
goto err_vhca_mapping;
}
+ /* External controller host PF has factory programmed MAC.
+ * Read it from the device.
+ */
+ if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF)
+ mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac);
+
esw_vport_change_handle_locked(vport);
esw->enabled_vports++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a1d67bd..0d0f63a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1161,7 +1161,7 @@
err = mlx5_core_set_hca_defaults(dev);
if (err) {
mlx5_core_err(dev, "Failed to set hca defaults\n");
- goto err_sriov;
+ goto err_set_hca;
}
mlx5_vhca_event_start(dev);
@@ -1194,6 +1194,7 @@
mlx5_sf_hw_table_destroy(dev);
err_vhca:
mlx5_vhca_event_stop(dev);
+err_set_hca:
mlx5_cleanup_fs(dev);
err_fs:
mlx5_accel_tls_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 50af84e..174f71e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -54,7 +54,7 @@
mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
mkey->iova = MLX5_GET64(mkc, mkc, start_addr);
mkey->size = MLX5_GET64(mkc, mkc, len);
- mkey->key |= mlx5_idx_to_mkey(mkey_index);
+ mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index);
mkey->pd = MLX5_GET(mkc, mkc, pd);
init_waitqueue_head(&mkey->wait);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index 441b545..540cf05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -156,6 +156,9 @@
{
int err;
+ if (!MLX5_CAP_GEN(dev, roce))
+ return;
+
err = mlx5_nic_vport_enable_roce(dev);
if (err) {
mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 6a0c6f9..fa0288a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -163,6 +163,7 @@
sf_index = event->function_id - base_id;
sf_dev = xa_load(&table->devices, sf_index);
switch (event->new_vhca_state) {
+ case MLX5_VHCA_STATE_INVALID:
case MLX5_VHCA_STATE_ALLOCATED:
if (sf_dev)
mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
index 054c2e2..7466f01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
@@ -694,7 +694,11 @@
if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM)
return -EINVAL;
- memcpy(padded_data, data, data_sz);
+ inline_data_sz =
+ MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data);
+
+ /* Add an alignment padding */
+ memcpy(padded_data + data_sz % inline_data_sz, data, data_sz);
/* Remove L2L3 outer headers */
MLX5_SET(ste_single_action_remove_header_v1, hw_action, action_id,
@@ -706,32 +710,34 @@
hw_action += DR_STE_ACTION_DOUBLE_SZ;
used_actions++; /* Remove and NOP are a single double action */
- inline_data_sz =
- MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data);
+ /* Point to the last dword of the header */
+ data_ptr += (data_sz / inline_data_sz) * inline_data_sz;
- /* Add the new header inline + 2 extra bytes */
+ /* Add the new header using inline action 4Byte at a time, the header
+ * is added in reversed order to the beginning of the packet to avoid
+ * incorrect parsing by the HW. Since header is 14B or 18B an extra
+ * two bytes are padded and later removed.
+ */
for (i = 0; i < data_sz / inline_data_sz + 1; i++) {
void *addr_inline;
MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, action_id,
DR_STE_V1_ACTION_ID_INSERT_INLINE);
/* The hardware expects here offset to words (2 bytes) */
- MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset,
- i * 2);
+ MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, 0);
/* Copy bytes one by one to avoid endianness problem */
addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v1,
hw_action, inline_data);
- memcpy(addr_inline, data_ptr, inline_data_sz);
+ memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz);
hw_action += DR_STE_ACTION_DOUBLE_SZ;
- data_ptr += inline_data_sz;
used_actions++;
}
- /* Remove 2 extra bytes */
+ /* Remove first 2 extra bytes */
MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, action_id,
DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
- MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, data_sz / 2);
+ MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, 0);
/* The hardware expects here size in words (2 bytes) */
MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, remove_size, 1);
used_actions++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
index 612b0ac..9737565 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
@@ -124,10 +124,11 @@
static inline bool
mlx5dr_is_supported(struct mlx5_core_dev *dev)
{
- return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) ||
- (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) &&
- (MLX5_CAP_GEN(dev, steering_format_version) <=
- MLX5_STEERING_FORMAT_CONNECTX_6DX));
+ return MLX5_CAP_GEN(dev, roce) &&
+ (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) ||
+ (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) &&
+ (MLX5_CAP_GEN(dev, steering_format_version) <=
+ MLX5_STEERING_FORMAT_CONNECTX_6DX)));
}
/* buddy functions & structure */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index 01cc00a..b6931bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -424,6 +424,15 @@
return err;
}
+static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp)
+{
+ int i;
+
+ for (i = 0; i < hp->num_channels; i++)
+ mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY,
+ MLX5_SQC_STATE_RST, 0, 0);
+}
+
static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp)
{
int i;
@@ -432,13 +441,9 @@
for (i = 0; i < hp->num_channels; i++)
mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY,
MLX5_RQC_STATE_RST, 0, 0);
-
/* unset peer SQs */
- if (hp->peer_gone)
- return;
- for (i = 0; i < hp->num_channels; i++)
- mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY,
- MLX5_SQC_STATE_RST, 0, 0);
+ if (!hp->peer_gone)
+ mlx5_hairpin_unpair_peer_sq(hp);
}
struct mlx5_hairpin *
@@ -485,3 +490,16 @@
mlx5_hairpin_destroy_queues(hp);
kfree(hp);
}
+
+void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp)
+{
+ int i;
+
+ mlx5_hairpin_unpair_peer_sq(hp);
+
+ /* destroy peer SQ */
+ for (i = 0; i < hp->num_channels; i++)
+ mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]);
+
+ hp->peer_gone = true;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 457ad42..4c1440a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -465,8 +465,6 @@
void *in;
int err;
- if (!vport)
- return -EINVAL;
if (!MLX5_CAP_GEN(mdev, vport_group_manager))
return -EACCES;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index dfea143..85f0ce2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -693,7 +693,8 @@
MLXSW_THERMAL_TRIP_MASK,
module_tz,
&mlxsw_thermal_module_ops,
- NULL, 0, 0);
+ NULL, 0,
+ module_tz->parent->polling_delay);
if (IS_ERR(module_tz->tzdev)) {
err = PTR_ERR(module_tz->tzdev);
return err;
@@ -815,7 +816,8 @@
MLXSW_THERMAL_TRIP_MASK,
gearbox_tz,
&mlxsw_thermal_gearbox_ops,
- NULL, 0, 0);
+ NULL, 0,
+ gearbox_tz->parent->polling_delay);
if (IS_ERR(gearbox_tz->tzdev))
return PTR_ERR(gearbox_tz->tzdev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 900b4bf..2bc5a90 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3907,7 +3907,7 @@
#define MLXSW_REG_QEEC_HIGHEST_SHAPER_BS 25
#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1 5
#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2 11
-#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 5
+#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 11
static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port,
enum mlxsw_reg_qeec_hr hr, u8 index,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index 04672eb..9958d50 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -1332,6 +1332,7 @@
u8 band, u32 child_handle)
{
struct mlxsw_sp_qdisc *old_qdisc;
+ u32 parent;
if (band < mlxsw_sp_qdisc->num_classes &&
mlxsw_sp_qdisc->qdiscs[band].handle == child_handle)
@@ -1352,7 +1353,9 @@
if (old_qdisc)
mlxsw_sp_qdisc_destroy(mlxsw_sp_port, old_qdisc);
- mlxsw_sp_qdisc = mlxsw_sp_qdisc->ops->find_class(mlxsw_sp_qdisc, band);
+ parent = TC_H_MAKE(mlxsw_sp_qdisc->handle, band + 1);
+ mlxsw_sp_qdisc = mlxsw_sp_qdisc->ops->find_class(mlxsw_sp_qdisc,
+ parent);
if (!WARN_ON(!mlxsw_sp_qdisc))
mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 0c42833..adfb978 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -379,6 +379,7 @@
int ocelot_port_flush(struct ocelot *ocelot, int port)
{
+ unsigned int pause_ena;
int err, val;
/* Disable dequeuing from the egress queues */
@@ -387,6 +388,7 @@
QSYS_PORT_MODE, port);
/* Disable flow control */
+ ocelot_fields_read(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, &pause_ena);
ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0);
/* Disable priority flow control */
@@ -422,6 +424,9 @@
/* Clear flushing again. */
ocelot_rmw_gix(ocelot, 0, REW_PORT_CFG_FLUSH_ENA, REW_PORT_CFG, port);
+ /* Re-enable flow control */
+ ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, pause_ena);
+
return err;
}
EXPORT_SYMBOL(ocelot_port_flush);
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 7e6bac8..344ea11 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -1602,6 +1602,8 @@
free_netdev(netdev);
err_out_free_res:
+ if (NX_IS_REVISION_P3(pdev->revision))
+ pci_disable_pcie_error_reporting(pdev);
pci_release_regions(pdev);
err_out_disable_pdev:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 17d5b64..e81dd34 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -1266,9 +1266,11 @@
p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_STATIC;
p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled;
+ BUILD_BUG_ON(sizeof(dcbx_info->operational.params) !=
+ sizeof(p_hwfn->p_dcbx_info->set.config.params));
memcpy(&p_hwfn->p_dcbx_info->set.config.params,
&dcbx_info->operational.params,
- sizeof(struct qed_dcbx_admin_params));
+ sizeof(p_hwfn->p_dcbx_info->set.config.params));
p_hwfn->p_dcbx_info->set.config.valid = true;
memcpy(params, &p_hwfn->p_dcbx_info->set, sizeof(struct qed_dcbx_set));
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 96b947f..3beafc6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -2690,6 +2690,7 @@
kfree(ahw);
err_out_free_res:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_regions(pdev);
err_out_disable_pdev:
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index 41fbd2c..ab1e0fc 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -126,24 +126,24 @@
struct rtnl_link_stats64 *s)
{
struct rmnet_priv *priv = netdev_priv(dev);
- struct rmnet_vnd_stats total_stats;
+ struct rmnet_vnd_stats total_stats = { };
struct rmnet_pcpu_stats *pcpu_ptr;
+ struct rmnet_vnd_stats snapshot;
unsigned int cpu, start;
- memset(&total_stats, 0, sizeof(struct rmnet_vnd_stats));
-
for_each_possible_cpu(cpu) {
pcpu_ptr = per_cpu_ptr(priv->pcpu_stats, cpu);
do {
start = u64_stats_fetch_begin_irq(&pcpu_ptr->syncp);
- total_stats.rx_pkts += pcpu_ptr->stats.rx_pkts;
- total_stats.rx_bytes += pcpu_ptr->stats.rx_bytes;
- total_stats.tx_pkts += pcpu_ptr->stats.tx_pkts;
- total_stats.tx_bytes += pcpu_ptr->stats.tx_bytes;
+ snapshot = pcpu_ptr->stats; /* struct assignment */
} while (u64_stats_fetch_retry_irq(&pcpu_ptr->syncp, start));
- total_stats.tx_drops += pcpu_ptr->stats.tx_drops;
+ total_stats.rx_pkts += snapshot.rx_pkts;
+ total_stats.rx_bytes += snapshot.rx_bytes;
+ total_stats.tx_pkts += snapshot.tx_pkts;
+ total_stats.tx_bytes += snapshot.tx_bytes;
+ total_stats.tx_drops += snapshot.tx_drops;
}
s->rx_packets = total_stats.rx_pkts;
@@ -354,4 +354,4 @@
}
return 0;
-}
\ No newline at end of file
+}
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 2c89cde..2ee72dc 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1671,7 +1671,7 @@
{
switch(stringset) {
case ETH_SS_STATS:
- memcpy(data, *rtl8169_gstrings, sizeof(rtl8169_gstrings));
+ memcpy(data, rtl8169_gstrings, sizeof(rtl8169_gstrings));
break;
}
}
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index c5b1548..713d362 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2287,7 +2287,7 @@
{
switch (stringset) {
case ETH_SS_STATS:
- memcpy(data, *sh_eth_gstrings_stats,
+ memcpy(data, sh_eth_gstrings_stats,
sizeof(sh_eth_gstrings_stats));
break;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index b70d44ac..3c73453 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -76,10 +76,10 @@
#define LPI_CTRL_STATUS_TLPIEN 0x00000001 /* Transmit LPI Entry */
/* GMAC HW ADDR regs */
-#define GMAC_ADDR_HIGH(reg) (((reg > 15) ? 0x00000800 : 0x00000040) + \
- (reg * 8))
-#define GMAC_ADDR_LOW(reg) (((reg > 15) ? 0x00000804 : 0x00000044) + \
- (reg * 8))
+#define GMAC_ADDR_HIGH(reg) ((reg > 15) ? 0x00000800 + (reg - 16) * 8 : \
+ 0x00000040 + (reg * 8))
+#define GMAC_ADDR_LOW(reg) ((reg > 15) ? 0x00000804 + (reg - 16) * 8 : \
+ 0x00000044 + (reg * 8))
#define GMAC_MAX_PERFECT_ADDRESSES 1
#define GMAC_PCS_BASE 0x000000c0 /* PCS register base */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 1e17a23..a696ada 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -622,6 +622,8 @@
void stmmac_remove_config_dt(struct platform_device *pdev,
struct plat_stmmacenet_data *plat)
{
+ clk_disable_unprepare(plat->stmmac_clk);
+ clk_disable_unprepare(plat->pclk);
of_node_put(plat->phy_node);
of_node_put(plat->mdio_node);
}
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index a1f5f07..9a13953 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -774,12 +774,15 @@
stat = be32_to_cpu(cur_p->app0);
while (stat & STS_CTRL_APP0_CMPLT) {
+ /* Make sure that the other fields are read after bd is
+ * released by dma
+ */
+ rmb();
dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys),
be32_to_cpu(cur_p->len), DMA_TO_DEVICE);
skb = (struct sk_buff *)ptr_from_txbd(cur_p);
if (skb)
dev_consume_skb_irq(skb);
- cur_p->app0 = 0;
cur_p->app1 = 0;
cur_p->app2 = 0;
cur_p->app3 = 0;
@@ -788,6 +791,12 @@
ndev->stats.tx_packets++;
ndev->stats.tx_bytes += be32_to_cpu(cur_p->len);
+ /* app0 must be visible last, as it is used to flag
+ * availability of the bd
+ */
+ smp_mb();
+ cur_p->app0 = 0;
+
lp->tx_bd_ci++;
if (lp->tx_bd_ci >= lp->tx_bd_num)
lp->tx_bd_ci = 0;
@@ -814,6 +823,9 @@
if (cur_p->app0)
return NETDEV_TX_BUSY;
+ /* Make sure to read next bd app0 after this one */
+ rmb();
+
tail++;
if (tail >= lp->tx_bd_num)
tail = 0;
@@ -849,7 +861,7 @@
smp_mb();
/* Space might have just been freed - check again */
- if (temac_check_tx_bd_space(lp, num_frag))
+ if (temac_check_tx_bd_space(lp, num_frag + 1))
return NETDEV_TX_BUSY;
netif_wake_queue(ndev);
@@ -876,7 +888,6 @@
return NETDEV_TX_OK;
}
cur_p->phys = cpu_to_be32(skb_dma_addr);
- ptr_to_txbd((void *)skb, cur_p);
for (ii = 0; ii < num_frag; ii++) {
if (++lp->tx_bd_tail >= lp->tx_bd_num)
@@ -915,6 +926,11 @@
}
cur_p->app0 |= cpu_to_be32(STS_CTRL_APP0_EOP);
+ /* Mark last fragment with skb address, so it can be consumed
+ * in temac_start_xmit_done()
+ */
+ ptr_to_txbd((void *)skb, cur_p);
+
tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
lp->tx_bd_tail++;
if (lp->tx_bd_tail >= lp->tx_bd_num)
@@ -926,6 +942,11 @@
wmb();
lp->dma_out(lp, TX_TAILDESC_PTR, tail_p); /* DMA start */
+ if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) {
+ netdev_info(ndev, "%s -> netif_stop_queue\n", __func__);
+ netif_stop_queue(ndev);
+ }
+
return NETDEV_TX_OK;
}
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 6515422..7685a17 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -799,6 +799,7 @@
ax->tty = NULL;
unregister_netdev(ax->dev);
+ free_netdev(ax->dev);
}
/* Perform I/O control on an active ax25 channel. */
diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c
index 0d8293a..b806f2f 100644
--- a/drivers/net/mhi/net.c
+++ b/drivers/net/mhi/net.c
@@ -49,7 +49,7 @@
return 0;
}
-static int mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev)
{
struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
const struct mhi_net_proto *proto = mhi_netdev->proto;
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 9bd9a5c..6bbc81a 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -826,16 +826,12 @@
{
int err;
- err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET);
+ err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART);
if (err < 0)
return err;
usleep_range(10, 20);
- /* After reset FORCE_LINK_GOOD bit is set. Although the
- * default value should be unset. Disable FORCE_LINK_GOOD
- * for the phy to work properly.
- */
return phy_modify(phydev, MII_DP83867_PHYCTRL,
DP83867_PHYCR_FORCE_LINK_GOOD, 0);
}
diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c
index 2e60bc1..359ea0d 100644
--- a/drivers/net/usb/cdc_eem.c
+++ b/drivers/net/usb/cdc_eem.c
@@ -123,10 +123,10 @@
}
skb2 = skb_copy_expand(skb, EEM_HEAD, ETH_FCS_LEN + padlen, flags);
+ dev_kfree_skb_any(skb);
if (!skb2)
return NULL;
- dev_kfree_skb_any(skb);
skb = skb2;
done:
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index b04055f..df0d183 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1880,7 +1880,7 @@
static const struct driver_info cdc_ncm_info = {
.description = "CDC NCM",
.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
- | FLAG_LINK_INTR,
+ | FLAG_LINK_INTR | FLAG_ETHER,
.bind = cdc_ncm_bind,
.unbind = cdc_ncm_unbind,
.manage_power = usbnet_manage_power,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6700f19..bc55ec7 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -575,7 +575,7 @@
if (info->flags & QMI_WWAN_FLAG_PASS_THROUGH) {
skb->protocol = htons(ETH_P_MAP);
- return (netif_rx(skb) == NET_RX_SUCCESS);
+ return 1;
}
switch (skb->data[0] & 0xf0) {
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index f6abb2f..e25bfb7 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -8678,7 +8678,7 @@
{
switch (stringset) {
case ETH_SS_STATS:
- memcpy(data, *rtl8152_gstrings, sizeof(rtl8152_gstrings));
+ memcpy(data, rtl8152_gstrings, sizeof(rtl8152_gstrings));
break;
}
}
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index b286993..13141db 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -1483,7 +1483,7 @@
ret = smsc75xx_wait_ready(dev, 0);
if (ret < 0) {
netdev_warn(dev->net, "device not ready in smsc75xx_bind\n");
- goto err;
+ goto free_pdata;
}
smsc75xx_init_mac_address(dev);
@@ -1492,7 +1492,7 @@
ret = smsc75xx_reset(dev);
if (ret < 0) {
netdev_warn(dev->net, "smsc75xx_reset error %d\n", ret);
- goto err;
+ goto cancel_work;
}
dev->net->netdev_ops = &smsc75xx_netdev_ops;
@@ -1503,8 +1503,11 @@
dev->net->max_mtu = MAX_SINGLE_PACKET_SIZE;
return 0;
-err:
+cancel_work:
+ cancel_work_sync(&pdata->set_multicast);
+free_pdata:
kfree(pdata);
+ dev->data[0] = 0;
return ret;
}
@@ -1515,7 +1518,6 @@
cancel_work_sync(&pdata->set_multicast);
netif_dbg(dev, ifdown, dev->net, "free pdata\n");
kfree(pdata);
- pdata = NULL;
dev->data[0] = 0;
}
}
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 503e2fd..28a6c4c 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1183,9 +1183,6 @@
dev->flags = IFF_MASTER | IFF_NOARP;
- /* MTU is irrelevant for VRF device; set to 64k similar to lo */
- dev->mtu = 64 * 1024;
-
/* similarly, oper state is irrelevant; set to up to avoid confusion */
dev->operstate = IF_OPER_UP;
netdev_lockdep_set_classes(dev);
@@ -1685,7 +1682,8 @@
* which breaks networking.
*/
dev->min_mtu = IPV6_MIN_MTU;
- dev->max_mtu = ETH_MAX_MTU;
+ dev->max_mtu = IP6_MAX_MTU;
+ dev->mtu = dev->max_mtu;
}
static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 51ce767..7a6fd46 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1693,8 +1693,13 @@
static void mac80211_hwsim_stop(struct ieee80211_hw *hw)
{
struct mac80211_hwsim_data *data = hw->priv;
+
data->started = false;
hrtimer_cancel(&data->beacon_timer);
+
+ while (!skb_queue_empty(&data->pending))
+ ieee80211_free_txskb(hw, skb_dequeue(&data->pending));
+
wiphy_dbg(hw->wiphy, "%s\n", __func__);
}
diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile
index eca805c..9e6ce0d 100644
--- a/drivers/pci/controller/dwc/Makefile
+++ b/drivers/pci/controller/dwc/Makefile
@@ -18,6 +18,7 @@
obj-$(CONFIG_PCIE_KIRIN) += pcie-kirin.o
obj-$(CONFIG_PCIE_HISI_STB) += pcie-histb.o
obj-$(CONFIG_PCI_MESON) += pci-meson.o
+obj-$(CONFIG_PCIE_TEGRA194) += pcie-tegra194.o
obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o
obj-$(CONFIG_PCIE_UNIPHIER_EP) += pcie-uniphier-ep.o
@@ -38,6 +39,6 @@
ifdef CONFIG_PCI_QUIRKS
obj-$(CONFIG_ARM64) += pcie-al.o
obj-$(CONFIG_ARM64) += pcie-hisi.o
-obj-$(CONFIG_ARM64) += pcie-tegra194.o
+obj-$(CONFIG_ARM64) += pcie-tegra194-acpi.o
endif
endif
diff --git a/drivers/pci/controller/dwc/pcie-tegra194-acpi.c b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c
new file mode 100644
index 0000000..c2de6ed
--- /dev/null
+++ b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * ACPI quirks for Tegra194 PCIe host controller
+ *
+ * Copyright (C) 2021 NVIDIA Corporation.
+ *
+ * Author: Vidya Sagar <vidyas@nvidia.com>
+ */
+
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/pci-ecam.h>
+
+#include "pcie-designware.h"
+
+struct tegra194_pcie_ecam {
+ void __iomem *config_base;
+ void __iomem *iatu_base;
+ void __iomem *dbi_base;
+};
+
+static int tegra194_acpi_init(struct pci_config_window *cfg)
+{
+ struct device *dev = cfg->parent;
+ struct tegra194_pcie_ecam *pcie_ecam;
+
+ pcie_ecam = devm_kzalloc(dev, sizeof(*pcie_ecam), GFP_KERNEL);
+ if (!pcie_ecam)
+ return -ENOMEM;
+
+ pcie_ecam->config_base = cfg->win;
+ pcie_ecam->iatu_base = cfg->win + SZ_256K;
+ pcie_ecam->dbi_base = cfg->win + SZ_512K;
+ cfg->priv = pcie_ecam;
+
+ return 0;
+}
+
+static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index,
+ u32 val, u32 reg)
+{
+ u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
+
+ writel(val, pcie_ecam->iatu_base + offset + reg);
+}
+
+static void program_outbound_atu(struct tegra194_pcie_ecam *pcie_ecam,
+ int index, int type, u64 cpu_addr,
+ u64 pci_addr, u64 size)
+{
+ atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr),
+ PCIE_ATU_LOWER_BASE);
+ atu_reg_write(pcie_ecam, index, upper_32_bits(cpu_addr),
+ PCIE_ATU_UPPER_BASE);
+ atu_reg_write(pcie_ecam, index, lower_32_bits(pci_addr),
+ PCIE_ATU_LOWER_TARGET);
+ atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr + size - 1),
+ PCIE_ATU_LIMIT);
+ atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr),
+ PCIE_ATU_UPPER_TARGET);
+ atu_reg_write(pcie_ecam, index, type, PCIE_ATU_CR1);
+ atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
+}
+
+static void __iomem *tegra194_map_bus(struct pci_bus *bus,
+ unsigned int devfn, int where)
+{
+ struct pci_config_window *cfg = bus->sysdata;
+ struct tegra194_pcie_ecam *pcie_ecam = cfg->priv;
+ u32 busdev;
+ int type;
+
+ if (bus->number < cfg->busr.start || bus->number > cfg->busr.end)
+ return NULL;
+
+ if (bus->number == cfg->busr.start) {
+ if (PCI_SLOT(devfn) == 0)
+ return pcie_ecam->dbi_base + where;
+ else
+ return NULL;
+ }
+
+ busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
+ PCIE_ATU_FUNC(PCI_FUNC(devfn));
+
+ if (bus->parent->number == cfg->busr.start) {
+ if (PCI_SLOT(devfn) == 0)
+ type = PCIE_ATU_TYPE_CFG0;
+ else
+ return NULL;
+ } else {
+ type = PCIE_ATU_TYPE_CFG1;
+ }
+
+ program_outbound_atu(pcie_ecam, 0, type, cfg->res.start, busdev,
+ SZ_256K);
+
+ return pcie_ecam->config_base + where;
+}
+
+const struct pci_ecam_ops tegra194_pcie_ops = {
+ .init = tegra194_acpi_init,
+ .pci_ops = {
+ .map_bus = tegra194_map_bus,
+ .read = pci_generic_config_read,
+ .write = pci_generic_config_write,
+ }
+};
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index bafd2c6..504669e 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -22,8 +22,6 @@
#include <linux/of_irq.h>
#include <linux/of_pci.h>
#include <linux/pci.h>
-#include <linux/pci-acpi.h>
-#include <linux/pci-ecam.h>
#include <linux/phy/phy.h>
#include <linux/pinctrl/consumer.h>
#include <linux/platform_device.h>
@@ -247,24 +245,6 @@
GEN4_CORE_CLK_FREQ
};
-static const u32 event_cntr_ctrl_offset[] = {
- 0x1d8,
- 0x1a8,
- 0x1a8,
- 0x1a8,
- 0x1c4,
- 0x1d8
-};
-
-static const u32 event_cntr_data_offset[] = {
- 0x1dc,
- 0x1ac,
- 0x1ac,
- 0x1ac,
- 0x1c8,
- 0x1dc
-};
-
struct tegra_pcie_dw {
struct device *dev;
struct resource *appl_res;
@@ -313,104 +293,6 @@
enum dw_pcie_device_mode mode;
};
-#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
-struct tegra194_pcie_ecam {
- void __iomem *config_base;
- void __iomem *iatu_base;
- void __iomem *dbi_base;
-};
-
-static int tegra194_acpi_init(struct pci_config_window *cfg)
-{
- struct device *dev = cfg->parent;
- struct tegra194_pcie_ecam *pcie_ecam;
-
- pcie_ecam = devm_kzalloc(dev, sizeof(*pcie_ecam), GFP_KERNEL);
- if (!pcie_ecam)
- return -ENOMEM;
-
- pcie_ecam->config_base = cfg->win;
- pcie_ecam->iatu_base = cfg->win + SZ_256K;
- pcie_ecam->dbi_base = cfg->win + SZ_512K;
- cfg->priv = pcie_ecam;
-
- return 0;
-}
-
-static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index,
- u32 val, u32 reg)
-{
- u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
-
- writel(val, pcie_ecam->iatu_base + offset + reg);
-}
-
-static void program_outbound_atu(struct tegra194_pcie_ecam *pcie_ecam,
- int index, int type, u64 cpu_addr,
- u64 pci_addr, u64 size)
-{
- atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr),
- PCIE_ATU_LOWER_BASE);
- atu_reg_write(pcie_ecam, index, upper_32_bits(cpu_addr),
- PCIE_ATU_UPPER_BASE);
- atu_reg_write(pcie_ecam, index, lower_32_bits(pci_addr),
- PCIE_ATU_LOWER_TARGET);
- atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr + size - 1),
- PCIE_ATU_LIMIT);
- atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr),
- PCIE_ATU_UPPER_TARGET);
- atu_reg_write(pcie_ecam, index, type, PCIE_ATU_CR1);
- atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
-static void __iomem *tegra194_map_bus(struct pci_bus *bus,
- unsigned int devfn, int where)
-{
- struct pci_config_window *cfg = bus->sysdata;
- struct tegra194_pcie_ecam *pcie_ecam = cfg->priv;
- u32 busdev;
- int type;
-
- if (bus->number < cfg->busr.start || bus->number > cfg->busr.end)
- return NULL;
-
- if (bus->number == cfg->busr.start) {
- if (PCI_SLOT(devfn) == 0)
- return pcie_ecam->dbi_base + where;
- else
- return NULL;
- }
-
- busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
- PCIE_ATU_FUNC(PCI_FUNC(devfn));
-
- if (bus->parent->number == cfg->busr.start) {
- if (PCI_SLOT(devfn) == 0)
- type = PCIE_ATU_TYPE_CFG0;
- else
- return NULL;
- } else {
- type = PCIE_ATU_TYPE_CFG1;
- }
-
- program_outbound_atu(pcie_ecam, 0, type, cfg->res.start, busdev,
- SZ_256K);
-
- return pcie_ecam->config_base + where;
-}
-
-const struct pci_ecam_ops tegra194_pcie_ops = {
- .init = tegra194_acpi_init,
- .pci_ops = {
- .map_bus = tegra194_map_bus,
- .read = pci_generic_config_read,
- .write = pci_generic_config_write,
- }
-};
-#endif /* defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) */
-
-#ifdef CONFIG_PCIE_TEGRA194
-
static inline struct tegra_pcie_dw *to_tegra_pcie(struct dw_pcie *pci)
{
return container_of(pci, struct tegra_pcie_dw, pci);
@@ -694,6 +576,24 @@
};
#if defined(CONFIG_PCIEASPM)
+static const u32 event_cntr_ctrl_offset[] = {
+ 0x1d8,
+ 0x1a8,
+ 0x1a8,
+ 0x1a8,
+ 0x1c4,
+ 0x1d8
+};
+
+static const u32 event_cntr_data_offset[] = {
+ 0x1dc,
+ 0x1ac,
+ 0x1ac,
+ 0x1ac,
+ 0x1c8,
+ 0x1dc
+};
+
static void disable_aspm_l11(struct tegra_pcie_dw *pcie)
{
u32 val;
@@ -2411,5 +2311,3 @@
MODULE_AUTHOR("Vidya Sagar <vidyas@nvidia.com>");
MODULE_DESCRIPTION("NVIDIA PCIe host controller driver");
MODULE_LICENSE("GPL v2");
-
-#endif /* CONFIG_PCIE_TEGRA194 */
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 051b48b..e3f5e7a 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -514,7 +514,7 @@
udelay(PIO_RETRY_DELAY);
}
- dev_err(dev, "config read/write timed out\n");
+ dev_err(dev, "PIO read/write transfer time out\n");
return -ETIMEDOUT;
}
@@ -657,6 +657,35 @@
return true;
}
+static bool advk_pcie_pio_is_running(struct advk_pcie *pcie)
+{
+ struct device *dev = &pcie->pdev->dev;
+
+ /*
+ * Trying to start a new PIO transfer when previous has not completed
+ * cause External Abort on CPU which results in kernel panic:
+ *
+ * SError Interrupt on CPU0, code 0xbf000002 -- SError
+ * Kernel panic - not syncing: Asynchronous SError Interrupt
+ *
+ * Functions advk_pcie_rd_conf() and advk_pcie_wr_conf() are protected
+ * by raw_spin_lock_irqsave() at pci_lock_config() level to prevent
+ * concurrent calls at the same time. But because PIO transfer may take
+ * about 1.5s when link is down or card is disconnected, it means that
+ * advk_pcie_wait_pio() does not always have to wait for completion.
+ *
+ * Some versions of ARM Trusted Firmware handles this External Abort at
+ * EL3 level and mask it to prevent kernel panic. Relevant TF-A commit:
+ * https://git.trustedfirmware.org/TF-A/trusted-firmware-a.git/commit/?id=3c7dcdac5c50
+ */
+ if (advk_readl(pcie, PIO_START)) {
+ dev_err(dev, "Previous PIO read/write transfer is still running\n");
+ return true;
+ }
+
+ return false;
+}
+
static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
int where, int size, u32 *val)
{
@@ -673,9 +702,10 @@
return pci_bridge_emul_conf_read(&pcie->bridge, where,
size, val);
- /* Start PIO */
- advk_writel(pcie, 0, PIO_START);
- advk_writel(pcie, 1, PIO_ISR);
+ if (advk_pcie_pio_is_running(pcie)) {
+ *val = 0xffffffff;
+ return PCIBIOS_SET_FAILED;
+ }
/* Program the control register */
reg = advk_readl(pcie, PIO_CTRL);
@@ -694,7 +724,8 @@
/* Program the data strobe */
advk_writel(pcie, 0xf, PIO_WR_DATA_STRB);
- /* Start the transfer */
+ /* Clear PIO DONE ISR and start the transfer */
+ advk_writel(pcie, 1, PIO_ISR);
advk_writel(pcie, 1, PIO_START);
ret = advk_pcie_wait_pio(pcie);
@@ -734,9 +765,8 @@
if (where % size)
return PCIBIOS_SET_FAILED;
- /* Start PIO */
- advk_writel(pcie, 0, PIO_START);
- advk_writel(pcie, 1, PIO_ISR);
+ if (advk_pcie_pio_is_running(pcie))
+ return PCIBIOS_SET_FAILED;
/* Program the control register */
reg = advk_readl(pcie, PIO_CTRL);
@@ -763,7 +793,8 @@
/* Program the data strobe */
advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB);
- /* Start the transfer */
+ /* Clear PIO DONE ISR and start the transfer */
+ advk_writel(pcie, 1, PIO_ISR);
advk_writel(pcie, 1, PIO_START);
ret = advk_pcie_wait_pio(pcie);
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index 85dcb70..a143b02 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -353,6 +353,8 @@
dev_warn(dev, "More than one I/O resource converted for %pOF. CPU base address for old range lost!\n",
dev_node);
*io_base = range.cpu_addr;
+ } else if (resource_type(res) == IORESOURCE_MEM) {
+ res->flags &= ~IORESOURCE_MEM_64;
}
pci_add_resource_offset(resources, res, res->start - range.pci_addr);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index dcb229d..22b2bb1 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3547,6 +3547,18 @@
}
/*
+ * Some NVIDIA GPU devices do not work with bus reset, SBR needs to be
+ * prevented for those affected devices.
+ */
+static void quirk_nvidia_no_bus_reset(struct pci_dev *dev)
+{
+ if ((dev->device & 0xffc0) == 0x2340)
+ quirk_no_bus_reset(dev);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+ quirk_nvidia_no_bus_reset);
+
+/*
* Some Atheros AR9xxx and QCA988x chips do not behave after a bus reset.
* The device will throw a Link Down error on AER-capable systems and
* regardless of AER, config space of the device is never accessible again
@@ -3566,6 +3578,16 @@
*/
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CAVIUM, 0xa100, quirk_no_bus_reset);
+/*
+ * Some TI KeyStone C667X devices do not support bus/hot reset. The PCIESS
+ * automatically disables LTSSM when Secondary Bus Reset is received and
+ * the device stops working. Prevent bus reset for these devices. With
+ * this change, the device can be assigned to VMs with VFIO, but it will
+ * leak state between VMs. Reference
+ * https://e2e.ti.com/support/processors/f/791/t/954382
+ */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TI, 0xb005, quirk_no_bus_reset);
+
static void quirk_no_pm_reset(struct pci_dev *dev)
{
/*
@@ -3901,6 +3923,69 @@
return 0;
}
+#define PCI_DEVICE_ID_HINIC_VF 0x375E
+#define HINIC_VF_FLR_TYPE 0x1000
+#define HINIC_VF_FLR_CAP_BIT (1UL << 30)
+#define HINIC_VF_OP 0xE80
+#define HINIC_VF_FLR_PROC_BIT (1UL << 18)
+#define HINIC_OPERATION_TIMEOUT 15000 /* 15 seconds */
+
+/* Device-specific reset method for Huawei Intelligent NIC virtual functions */
+static int reset_hinic_vf_dev(struct pci_dev *pdev, int probe)
+{
+ unsigned long timeout;
+ void __iomem *bar;
+ u32 val;
+
+ if (probe)
+ return 0;
+
+ bar = pci_iomap(pdev, 0, 0);
+ if (!bar)
+ return -ENOTTY;
+
+ /* Get and check firmware capabilities */
+ val = ioread32be(bar + HINIC_VF_FLR_TYPE);
+ if (!(val & HINIC_VF_FLR_CAP_BIT)) {
+ pci_iounmap(pdev, bar);
+ return -ENOTTY;
+ }
+
+ /* Set HINIC_VF_FLR_PROC_BIT for the start of FLR */
+ val = ioread32be(bar + HINIC_VF_OP);
+ val = val | HINIC_VF_FLR_PROC_BIT;
+ iowrite32be(val, bar + HINIC_VF_OP);
+
+ pcie_flr(pdev);
+
+ /*
+ * The device must recapture its Bus and Device Numbers after FLR
+ * in order generate Completions. Issue a config write to let the
+ * device capture this information.
+ */
+ pci_write_config_word(pdev, PCI_VENDOR_ID, 0);
+
+ /* Firmware clears HINIC_VF_FLR_PROC_BIT when reset is complete */
+ timeout = jiffies + msecs_to_jiffies(HINIC_OPERATION_TIMEOUT);
+ do {
+ val = ioread32be(bar + HINIC_VF_OP);
+ if (!(val & HINIC_VF_FLR_PROC_BIT))
+ goto reset_complete;
+ msleep(20);
+ } while (time_before(jiffies, timeout));
+
+ val = ioread32be(bar + HINIC_VF_OP);
+ if (!(val & HINIC_VF_FLR_PROC_BIT))
+ goto reset_complete;
+
+ pci_warn(pdev, "Reset dev timeout, FLR ack reg: %#010x\n", val);
+
+reset_complete:
+ pci_iounmap(pdev, bar);
+
+ return 0;
+}
+
static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF,
reset_intel_82599_sfp_virtfn },
@@ -3913,6 +3998,8 @@
{ PCI_VENDOR_ID_INTEL, 0x0a54, delay_250ms_after_flr },
{ PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID,
reset_chelsio_generic_dev },
+ { PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HINIC_VF,
+ reset_hinic_vf_dev },
{ 0 }
};
@@ -4753,6 +4840,8 @@
{ PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs },
{ PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs },
{ PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs },
+ /* Broadcom multi-function device */
+ { PCI_VENDOR_ID_BROADCOM, 0x16D7, pci_quirk_mf_endpoint_acs },
{ PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs },
/* Amazon Annapurna Labs */
{ PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs },
@@ -5154,7 +5243,8 @@
static void quirk_amd_harvest_no_ats(struct pci_dev *pdev)
{
if ((pdev->device == 0x7312 && pdev->revision != 0x00) ||
- (pdev->device == 0x7340 && pdev->revision != 0xc5))
+ (pdev->device == 0x7340 && pdev->revision != 0xc5) ||
+ (pdev->device == 0x7341 && pdev->revision != 0x00))
return;
if (pdev->device == 0x15d8) {
@@ -5181,6 +5271,7 @@
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats);
/* AMD Navi14 dGPU */
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats);
/* AMD Raven platform iGPU */
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats);
#endif /* CONFIG_PCI_ATS */
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 03a246e..21c4c34 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -63,7 +63,7 @@
spin_unlock_irqrestore(&queue->lock, flags);
}
-s32 scaled_ppm_to_ppb(long ppm)
+long scaled_ppm_to_ppb(long ppm)
{
/*
* The 'freq' field in the 'struct timex' is in parts per
@@ -80,7 +80,7 @@
s64 ppb = 1 + ppm;
ppb *= 125;
ppb >>= 13;
- return (s32) ppb;
+ return (long) ppb;
}
EXPORT_SYMBOL(scaled_ppm_to_ppb);
@@ -138,7 +138,7 @@
delta = ktime_to_ns(kt);
err = ops->adjtime(ops, delta);
} else if (tx->modes & ADJ_FREQUENCY) {
- s32 ppb = scaled_ppm_to_ppb(tx->freq);
+ long ppb = scaled_ppm_to_ppb(tx->freq);
if (ppb > ops->max_adj || ppb < -ops->max_adj)
return -ERANGE;
if (ops->adjfine)
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index ecefc25..337353c 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -135,12 +135,13 @@
{
struct ap_queue_status status;
struct ap_message *ap_msg;
+ bool found = false;
status = ap_dqap(aq->qid, &aq->reply->psmid,
aq->reply->msg, aq->reply->len);
switch (status.response_code) {
case AP_RESPONSE_NORMAL:
- aq->queue_count--;
+ aq->queue_count = max_t(int, 0, aq->queue_count - 1);
if (aq->queue_count > 0)
mod_timer(&aq->timeout,
jiffies + aq->request_timeout);
@@ -150,8 +151,14 @@
list_del_init(&ap_msg->list);
aq->pendingq_count--;
ap_msg->receive(aq, ap_msg, aq->reply);
+ found = true;
break;
}
+ if (!found) {
+ AP_DBF_WARN("%s unassociated reply psmid=0x%016llx on 0x%02x.%04x\n",
+ __func__, aq->reply->psmid,
+ AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+ }
fallthrough;
case AP_RESPONSE_NO_PENDING_REPLY:
if (!status.queue_empty || aq->queue_count <= 0)
@@ -232,7 +239,7 @@
ap_msg->flags & AP_MSG_FLAG_SPECIAL);
switch (status.response_code) {
case AP_RESPONSE_NORMAL:
- aq->queue_count++;
+ aq->queue_count = max_t(int, 1, aq->queue_count + 1);
if (aq->queue_count == 1)
mod_timer(&aq->timeout, jiffies + aq->request_timeout);
list_move_tail(&ap_msg->list, &aq->pendingq);
diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c
index ffa1cf4..4378592 100644
--- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c
+++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c
@@ -2284,7 +2284,7 @@
mon_wdev->iftype = NL80211_IFTYPE_MONITOR;
mon_ndev->ieee80211_ptr = mon_wdev;
- ret = register_netdevice(mon_ndev);
+ ret = cfg80211_register_netdevice(mon_ndev);
if (ret) {
goto out;
}
@@ -2360,7 +2360,7 @@
adapter = rtw_netdev_priv(ndev);
pwdev_priv = adapter_wdev_data(adapter);
- unregister_netdevice(ndev);
+ cfg80211_unregister_netdevice(ndev);
if (ndev == pwdev_priv->pmon_ndev) {
pwdev_priv->pmon_ndev = NULL;
diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c
index 4545b23..bac0f54 100644
--- a/drivers/usb/chipidea/usbmisc_imx.c
+++ b/drivers/usb/chipidea/usbmisc_imx.c
@@ -686,6 +686,16 @@
int val;
unsigned long flags;
+ /* Clear VDATSRCENB0 to disable VDP_SRC and IDM_SNK required by BC 1.2 spec */
+ spin_lock_irqsave(&usbmisc->lock, flags);
+ val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
+ val &= ~MX7D_USB_OTG_PHY_CFG2_CHRG_VDATSRCENB0;
+ writel(val, usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
+ spin_unlock_irqrestore(&usbmisc->lock, flags);
+
+ /* TVDMSRC_DIS */
+ msleep(20);
+
/* VDM_SRC is connected to D- and IDP_SINK is connected to D+ */
spin_lock_irqsave(&usbmisc->lock, flags);
val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
@@ -695,7 +705,8 @@
usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
spin_unlock_irqrestore(&usbmisc->lock, flags);
- usleep_range(1000, 2000);
+ /* TVDMSRC_ON */
+ msleep(40);
/*
* Per BC 1.2, check voltage of D+:
@@ -798,7 +809,8 @@
usbmisc->base + MX7D_USB_OTG_PHY_CFG2);
spin_unlock_irqrestore(&usbmisc->lock, flags);
- usleep_range(1000, 2000);
+ /* TVDPSRC_ON */
+ msleep(40);
/* Check if D- is less than VDAT_REF to determine an SDP per BC 1.2 */
val = readl(usbmisc->base + MX7D_USB_OTG_PHY_STATUS);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index fc7d6cd..df8e69e 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -41,6 +41,8 @@
#define USB_VENDOR_GENESYS_LOGIC 0x05e3
#define USB_VENDOR_SMSC 0x0424
#define USB_PRODUCT_USB5534B 0x5534
+#define USB_VENDOR_CYPRESS 0x04b4
+#define USB_PRODUCT_CY7C65632 0x6570
#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01
#define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02
@@ -5698,6 +5700,11 @@
.bInterfaceClass = USB_CLASS_HUB,
.driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
{ .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+ | USB_DEVICE_ID_MATCH_PRODUCT,
+ .idVendor = USB_VENDOR_CYPRESS,
+ .idProduct = USB_PRODUCT_CY7C65632,
+ .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
+ { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
| USB_DEVICE_ID_MATCH_INT_CLASS,
.idVendor = USB_VENDOR_GENESYS_LOGIC,
.bInterfaceClass = USB_CLASS_HUB,
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 21129d3..4ac397e 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1671,8 +1671,8 @@
pm_runtime_get_sync(&pdev->dev);
- dwc3_debugfs_exit(dwc);
dwc3_core_exit_mode(dwc);
+ dwc3_debugfs_exit(dwc);
dwc3_core_exit(dwc);
dwc3_ulpi_exit(dwc);
diff --git a/fs/afs/main.c b/fs/afs/main.c
index b297525..179004b 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -203,8 +203,8 @@
goto error_fs;
afs_proc_symlink = proc_symlink("fs/afs", NULL, "../self/net/afs");
- if (IS_ERR(afs_proc_symlink)) {
- ret = PTR_ERR(afs_proc_symlink);
+ if (!afs_proc_symlink) {
+ ret = -ENOMEM;
goto error_proc;
}
diff --git a/fs/afs/write.c b/fs/afs/write.c
index a523bb8..e9ccaa3 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -837,6 +837,7 @@
struct inode *inode = file_inode(file);
struct afs_vnode *vnode = AFS_FS_I(inode);
unsigned long priv;
+ vm_fault_t ret = VM_FAULT_RETRY;
_enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index);
@@ -848,14 +849,14 @@
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page) &&
wait_on_page_fscache_killable(page) < 0)
- return VM_FAULT_RETRY;
+ goto out;
#endif
if (wait_on_page_writeback_killable(page))
- return VM_FAULT_RETRY;
+ goto out;
if (lock_page_killable(page) < 0)
- return VM_FAULT_RETRY;
+ goto out;
/* We mustn't change page->private until writeback is complete as that
* details the portion of the page we need to write back and we might
@@ -863,7 +864,7 @@
*/
if (wait_on_page_writeback_killable(page) < 0) {
unlock_page(page);
- return VM_FAULT_RETRY;
+ goto out;
}
priv = afs_page_dirty(page, 0, thp_size(page));
@@ -877,8 +878,10 @@
}
file_update_time(file);
+ ret = VM_FAULT_LOCKED;
+out:
sb_end_pagefault(inode->i_sb);
- return VM_FAULT_LOCKED;
+ return ret;
}
/*
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index aa57bdc..6d5c4e4 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -2442,16 +2442,16 @@
spin_lock(&sinfo->lock);
spin_lock(&cache->lock);
if (!--cache->ro) {
- num_bytes = cache->length - cache->reserved -
- cache->pinned - cache->bytes_super -
- cache->zone_unusable - cache->used;
- sinfo->bytes_readonly -= num_bytes;
if (btrfs_is_zoned(cache->fs_info)) {
/* Migrate zone_unusable bytes back */
cache->zone_unusable = cache->alloc_offset - cache->used;
sinfo->bytes_zone_unusable += cache->zone_unusable;
sinfo->bytes_readonly -= cache->zone_unusable;
}
+ num_bytes = cache->length - cache->reserved -
+ cache->pinned - cache->bytes_super -
+ cache->zone_unusable - cache->used;
+ sinfo->bytes_readonly -= num_bytes;
list_del_init(&cache->ro_list);
}
spin_unlock(&cache->lock);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 55efd3d..30dee68 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -735,6 +735,7 @@
__SetPageUptodate(page);
error = huge_add_to_page_cache(page, mapping, index);
if (unlikely(error)) {
+ restore_reserve_on_error(h, &pseudo_vma, addr, page);
put_page(page);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
goto out;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index be5b6d2..64864fb 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -471,7 +471,7 @@
info_type, fanotify_info_name(info),
info->name_len, buf, count);
if (ret < 0)
- return ret;
+ goto out_close_fd;
buf += ret;
count -= ret;
@@ -519,7 +519,7 @@
fanotify_event_object_fh(event),
info_type, dot, dot_len, buf, count);
if (ret < 0)
- return ret;
+ goto out_close_fd;
buf += ret;
count -= ret;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 7118ebe..9cbd915 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2676,7 +2676,9 @@
#ifdef CONFIG_SECURITY
static int proc_pid_attr_open(struct inode *inode, struct file *file)
{
- return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS);
+ file->private_data = NULL;
+ __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS);
+ return 0;
}
static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index f180240..11e555c 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -37,7 +37,6 @@
enum scale_freq_source {
SCALE_FREQ_SOURCE_CPUFREQ = 0,
SCALE_FREQ_SOURCE_ARCH,
- SCALE_FREQ_SOURCE_CPPC,
};
struct scale_freq_data {
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 9626fda..2a8ebe6 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -286,6 +286,7 @@
vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
extern struct page *huge_zero_page;
+extern unsigned long huge_zero_pfn;
static inline bool is_huge_zero_page(struct page *page)
{
@@ -294,7 +295,7 @@
static inline bool is_huge_zero_pmd(pmd_t pmd)
{
- return is_huge_zero_page(pmd_page(pmd));
+ return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd);
}
static inline bool is_huge_zero_pud(pud_t pud)
@@ -440,6 +441,11 @@
return false;
}
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+ return false;
+}
+
static inline bool is_huge_zero_pud(pud_t pud)
{
return false;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b92f25c..6504346 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -149,6 +149,7 @@
long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
long freed);
bool isolate_huge_page(struct page *page, struct list_head *list);
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
void putback_active_hugepage(struct page *page);
void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
void free_huge_page(struct page *page);
@@ -339,6 +340,11 @@
return false;
}
+static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+{
+ return 0;
+}
+
static inline void putback_active_hugepage(struct page *page)
{
}
@@ -604,6 +610,8 @@
unsigned long address);
int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
pgoff_t idx);
+void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
+ unsigned long address, struct page *page);
/* arch callback */
int __init __alloc_bootmem_huge_page(struct hstate *h);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 020a8f7..f8902bcd 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -542,6 +542,10 @@
enum {
MLX5_PRIV_FLAGS_DISABLE_IB_ADEV = 1 << 0,
MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV = 1 << 1,
+ /* Set during device detach to block any further devices
+ * creation/deletion on drivers rescan. Unset during device attach.
+ */
+ MLX5_PRIV_FLAGS_DETACH = 1 << 2,
};
struct mlx5_adev {
diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h
index 028f442..60ffeb6 100644
--- a/include/linux/mlx5/transobj.h
+++ b/include/linux/mlx5/transobj.h
@@ -85,4 +85,5 @@
struct mlx5_hairpin_params *params);
void mlx5_core_hairpin_destroy(struct mlx5_hairpin *pair);
+void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp);
#endif /* __TRANSOBJ_H__ */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c274f75..8ae3162 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1719,6 +1719,7 @@
struct address_space *check_mapping; /* Check page->mapping if set */
pgoff_t first_index; /* Lowest page->index to unmap */
pgoff_t last_index; /* Highest page->index to unmap */
+ struct page *single_page; /* Locked page to be unmapped */
};
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
@@ -1766,6 +1767,7 @@
extern int fixup_user_fault(struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked);
+void unmap_mapping_page(struct page *page);
void unmap_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t nr, bool even_cows);
void unmap_mapping_range(struct address_space *mapping,
@@ -1786,6 +1788,7 @@
BUG();
return -EFAULT;
}
+static inline void unmap_mapping_page(struct page *page) { }
static inline void unmap_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t nr, bool even_cows) { }
static inline void unmap_mapping_range(struct address_space *mapping,
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 0d47fd3..51d7f1b 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -235,7 +235,7 @@
* @ppm: Parts per million, but with a 16 bit binary fractional field
*/
-extern s32 scaled_ppm_to_ppb(long ppm);
+extern long scaled_ppm_to_ppb(long ppm);
/**
* ptp_find_pin() - obtain the pin index of a given auxiliary function
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index def5c62..8d04e7d 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -91,6 +91,7 @@
TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */
TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */
+ TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */
TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */
TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible
* and caller guarantees they will
diff --git a/include/linux/socket.h b/include/linux/socket.h
index b8fc5c5..0d8e3dc 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -438,6 +438,4 @@
int __user *usockvec);
extern int __sys_shutdown_sock(struct socket *sock, int how);
extern int __sys_shutdown(int fd, int how);
-
-extern struct ns_common *get_net_ns(struct ns_common *ns);
#endif /* _LINUX_SOCKET_H */
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index d9b7c91..6430a94c 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -23,6 +23,16 @@
#define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT)
#define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1)
+/* Clear all flags but only keep swp_entry_t related information */
+static inline pte_t pte_swp_clear_flags(pte_t pte)
+{
+ if (pte_swp_soft_dirty(pte))
+ pte = pte_swp_clear_soft_dirty(pte);
+ if (pte_swp_uffd_wp(pte))
+ pte = pte_swp_clear_uffd_wp(pte);
+ return pte;
+}
+
/*
* Store a type+offset into a swp_entry_t in an arch-independent format
*/
@@ -66,10 +76,7 @@
{
swp_entry_t arch_entry;
- if (pte_swp_soft_dirty(pte))
- pte = pte_swp_clear_soft_dirty(pte);
- if (pte_swp_uffd_wp(pte))
- pte = pte_swp_clear_uffd_wp(pte);
+ pte = pte_swp_clear_flags(pte);
arch_entry = __pte_to_swp_entry(pte);
return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
}
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 445b66c..e89530d 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5537,7 +5537,7 @@
*
* This function iterates over the interfaces associated with a given
* hardware that are currently active and calls the callback for them.
- * This version can only be used while holding the RTNL.
+ * This version can only be used while holding the wiphy mutex.
*
* @hw: the hardware struct of which the interfaces should be iterated over
* @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags
@@ -6392,7 +6392,12 @@
/**
* ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header
- * of injected frames
+ * of injected frames.
+ *
+ * To accurately parse and take into account rate and retransmission fields,
+ * you must initialize the chandef field in the ieee80211_tx_info structure
+ * of the skb before calling this function.
+ *
* @skb: packet injected by userspace
* @dev: the &struct device of this 802.11 device
*/
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index fa58871..bdc0459 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -184,6 +184,9 @@
void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid);
void net_ns_barrier(void);
+
+struct ns_common *get_net_ns(struct ns_common *ns);
+struct net *get_net_ns_by_fd(int fd);
#else /* CONFIG_NET_NS */
#include <linux/sched.h>
#include <linux/nsproxy.h>
@@ -203,13 +206,22 @@
}
static inline void net_ns_barrier(void) {}
+
+static inline struct ns_common *get_net_ns(struct ns_common *ns)
+{
+ return ERR_PTR(-EINVAL);
+}
+
+static inline struct net *get_net_ns_by_fd(int fd)
+{
+ return ERR_PTR(-EINVAL);
+}
#endif /* CONFIG_NET_NS */
extern struct list_head net_namespace_list;
struct net *get_net_ns_by_pid(pid_t pid);
-struct net *get_net_ns_by_fd(int fd);
#ifdef CONFIG_SYSCTL
void ipx_register_sysctl(void);
diff --git a/include/net/sock.h b/include/net/sock.h
index 0e962d8..7a7058f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1934,7 +1934,8 @@
static inline void sk_set_txhash(struct sock *sk)
{
- sk->sk_txhash = net_tx_rndhash();
+ /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */
+ WRITE_ONCE(sk->sk_txhash, net_tx_rndhash());
}
static inline bool sk_rethink_txhash(struct sock *sk)
@@ -2206,9 +2207,12 @@
static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
{
- if (sk->sk_txhash) {
+ /* This pairs with WRITE_ONCE() in sk_set_txhash() */
+ u32 txhash = READ_ONCE(sk->sk_txhash);
+
+ if (txhash) {
skb->l4_hash = 1;
- skb->hash = sk->sk_txhash;
+ skb->hash = txhash;
}
}
@@ -2266,8 +2270,13 @@
static inline int sock_error(struct sock *sk)
{
int err;
- if (likely(!sk->sk_err))
+
+ /* Avoid an atomic operation for the common case.
+ * This is racy since another cpu/thread can change sk_err under us.
+ */
+ if (likely(data_race(!sk->sk_err)))
return 0;
+
err = xchg(&sk->sk_err, 0);
return -err;
}
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 6de5a7f..d2a9420 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -863,8 +863,7 @@
__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
#define __NR_mount_setattr 442
__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
-#define __NR_quotactl_path 443
-__SYSCALL(__NR_quotactl_path, sys_quotactl_path)
+/* 443 is reserved for quotactl_path */
#define __NR_landlock_create_ruleset 444
__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 7d66876..d1b3270 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -289,6 +289,9 @@
/* Address indicating an error return. */
#define INADDR_NONE ((unsigned long int) 0xffffffff)
+/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */
+#define INADDR_DUMMY ((unsigned long int) 0xc0000008)
+
/* Network number for local host loopback. */
#define IN_LOOPBACKNET 127
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 94ba516..c6a2757 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6483,6 +6483,27 @@
bool mask_to_left;
};
+static struct bpf_verifier_state *
+sanitize_speculative_path(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn,
+ u32 next_idx, u32 curr_idx)
+{
+ struct bpf_verifier_state *branch;
+ struct bpf_reg_state *regs;
+
+ branch = push_stack(env, next_idx, curr_idx, true);
+ if (branch && insn) {
+ regs = branch->frame[branch->curframe]->regs;
+ if (BPF_SRC(insn->code) == BPF_K) {
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ } else if (BPF_SRC(insn->code) == BPF_X) {
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ mark_reg_unknown(env, regs, insn->src_reg);
+ }
+ }
+ return branch;
+}
+
static int sanitize_ptr_alu(struct bpf_verifier_env *env,
struct bpf_insn *insn,
const struct bpf_reg_state *ptr_reg,
@@ -6566,12 +6587,26 @@
tmp = *dst_reg;
*dst_reg = *ptr_reg;
}
- ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
+ ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1,
+ env->insn_idx);
if (!ptr_is_dst_reg && ret)
*dst_reg = tmp;
return !ret ? REASON_STACK : 0;
}
+static void sanitize_mark_insn_seen(struct bpf_verifier_env *env)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+
+ /* If we simulate paths under speculation, we don't update the
+ * insn as 'seen' such that when we verify unreachable paths in
+ * the non-speculative domain, sanitize_dead_code() can still
+ * rewrite/sanitize them.
+ */
+ if (!vstate->speculative)
+ env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
+}
+
static int sanitize_err(struct bpf_verifier_env *env,
const struct bpf_insn *insn, int reason,
const struct bpf_reg_state *off_reg,
@@ -8750,14 +8785,28 @@
if (err)
return err;
}
+
if (pred == 1) {
- /* only follow the goto, ignore fall-through */
+ /* Only follow the goto, ignore fall-through. If needed, push
+ * the fall-through branch for simulation under speculative
+ * execution.
+ */
+ if (!env->bypass_spec_v1 &&
+ !sanitize_speculative_path(env, insn, *insn_idx + 1,
+ *insn_idx))
+ return -EFAULT;
*insn_idx += insn->off;
return 0;
} else if (pred == 0) {
- /* only follow fall-through branch, since
- * that's where the program will go
+ /* Only follow the fall-through branch, since that's where the
+ * program will go. If needed, push the goto branch for
+ * simulation under speculative execution.
*/
+ if (!env->bypass_spec_v1 &&
+ !sanitize_speculative_path(env, insn,
+ *insn_idx + insn->off + 1,
+ *insn_idx))
+ return -EFAULT;
return 0;
}
@@ -10630,7 +10679,7 @@
}
regs = cur_regs(env);
- env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
+ sanitize_mark_insn_seen(env);
prev_insn_idx = env->insn_idx;
if (class == BPF_ALU || class == BPF_ALU64) {
@@ -10857,7 +10906,7 @@
return err;
env->insn_idx++;
- env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
+ sanitize_mark_insn_seen(env);
} else {
verbose(env, "invalid BPF_LD mode\n");
return -EINVAL;
@@ -11366,6 +11415,7 @@
{
struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
struct bpf_insn *insn = new_prog->insnsi;
+ u32 old_seen = old_data[off].seen;
u32 prog_len;
int i;
@@ -11386,7 +11436,8 @@
memcpy(new_data + off + cnt - 1, old_data + off,
sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
for (i = off; i < off + cnt - 1; i++) {
- new_data[i].seen = env->pass_cnt;
+ /* Expand insni[off]'s seen count to the patched range. */
+ new_data[i].seen = old_seen;
new_data[i].zext_dst = insn_has_def32(env, insn + i);
}
env->insn_aux_data = new_data;
@@ -12710,6 +12761,9 @@
* insn_aux_data was touched. These variables are compared to clear temporary
* data from failed pass. For testing and experiments do_check_common() can be
* run multiple times even when prior attempt to verify is unsuccessful.
+ *
+ * Note that special handling is needed on !env->bypass_spec_v1 if this is
+ * ever called outside of error path with subsequent program rejection.
*/
static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
{
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 825284b..684a606 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -464,6 +464,7 @@
VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
VMCOREINFO_STRUCT_SIZE(mem_section);
VMCOREINFO_OFFSET(mem_section, section_mem_map);
+ VMCOREINFO_NUMBER(SECTION_SIZE_BITS);
VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS);
#endif
VMCOREINFO_STRUCT_SIZE(page);
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index 7a14146..9423218 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -391,6 +391,7 @@
/* No obstacles. */
return vprintk_default(fmt, args);
}
+EXPORT_SYMBOL(vprintk);
void __init printk_safe_init(void)
{
@@ -411,4 +412,3 @@
/* Flush pending messages that did not have scheduled IRQ works. */
printk_safe_flush();
}
-EXPORT_SYMBOL(vprintk);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5226cc2..4ca80df 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6389,7 +6389,6 @@
{
return __sched_setscheduler(p, attr, false, true);
}
-EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
/**
* sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9299057..d23a09d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2198,9 +2198,6 @@
};
static struct saved_cmdlines_buffer *savedcmd;
-/* temporary disable recording */
-static atomic_t trace_record_taskinfo_disabled __read_mostly;
-
static inline char *get_saved_cmdlines(int idx)
{
return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
@@ -2486,8 +2483,6 @@
{
if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID))))
return true;
- if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on())
- return true;
if (!__this_cpu_read(trace_taskinfo_save))
return true;
return false;
@@ -3998,9 +3993,6 @@
return ERR_PTR(-EBUSY);
#endif
- if (!iter->snapshot)
- atomic_inc(&trace_record_taskinfo_disabled);
-
if (*pos != iter->pos) {
iter->ent = NULL;
iter->cpu = 0;
@@ -4043,9 +4035,6 @@
return;
#endif
- if (!iter->snapshot)
- atomic_dec(&trace_record_taskinfo_disabled);
-
trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
}
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index c1637f9..4702efb 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -115,9 +115,9 @@
prev_time = READ_ONCE(trace_clock_struct.prev_time);
now = sched_clock_cpu(this_cpu);
- /* Make sure that now is always greater than prev_time */
+ /* Make sure that now is always greater than or equal to prev_time */
if ((s64)(now - prev_time) < 0)
- now = prev_time + 1;
+ now = prev_time;
/*
* If in an NMI context then dont risk lockups and simply return
@@ -131,7 +131,7 @@
/* Reread prev_time in case it was already updated */
prev_time = READ_ONCE(trace_clock_struct.prev_time);
if ((s64)(now - prev_time) < 0)
- now = prev_time + 1;
+ now = prev_time;
trace_clock_struct.prev_time = now;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 63ed6b2..6d2a011 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -62,6 +62,7 @@
static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
+unsigned long huge_zero_pfn __read_mostly = ~0UL;
bool transparent_hugepage_enabled(struct vm_area_struct *vma)
{
@@ -98,6 +99,7 @@
__free_pages(zero_page, compound_order(zero_page));
goto retry;
}
+ WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));
/* We take additional reference here. It will be put back by shrinker */
atomic_set(&huge_zero_refcount, 2);
@@ -147,6 +149,7 @@
if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
struct page *zero_page = xchg(&huge_zero_page, NULL);
BUG_ON(zero_page == NULL);
+ WRITE_ONCE(huge_zero_pfn, ~0UL);
__free_pages(zero_page, compound_order(zero_page));
return HPAGE_PMD_NR;
}
@@ -2044,7 +2047,7 @@
count_vm_event(THP_SPLIT_PMD);
if (!vma_is_anonymous(vma)) {
- _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+ old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
/*
* We are going to unmap this huge page. So
* just go ahead and zap it
@@ -2053,16 +2056,25 @@
zap_deposited_table(mm, pmd);
if (vma_is_special_huge(vma))
return;
- page = pmd_page(_pmd);
- if (!PageDirty(page) && pmd_dirty(_pmd))
- set_page_dirty(page);
- if (!PageReferenced(page) && pmd_young(_pmd))
- SetPageReferenced(page);
- page_remove_rmap(page, true);
- put_page(page);
+ if (unlikely(is_pmd_migration_entry(old_pmd))) {
+ swp_entry_t entry;
+
+ entry = pmd_to_swp_entry(old_pmd);
+ page = migration_entry_to_page(entry);
+ } else {
+ page = pmd_page(old_pmd);
+ if (!PageDirty(page) && pmd_dirty(old_pmd))
+ set_page_dirty(page);
+ if (!PageReferenced(page) && pmd_young(old_pmd))
+ SetPageReferenced(page);
+ page_remove_rmap(page, true);
+ put_page(page);
+ }
add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
return;
- } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
+ }
+
+ if (is_huge_zero_pmd(*pmd)) {
/*
* FIXME: Do we want to invalidate secondary mmu by calling
* mmu_notifier_invalidate_range() see comments below inside
@@ -2338,17 +2350,17 @@
static void unmap_page(struct page *page)
{
- enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
+ enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC |
TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
- bool unmap_success;
VM_BUG_ON_PAGE(!PageHead(page), page);
if (PageAnon(page))
ttu_flags |= TTU_SPLIT_FREEZE;
- unmap_success = try_to_unmap(page, ttu_flags);
- VM_BUG_ON_PAGE(!unmap_success, page);
+ try_to_unmap(page, ttu_flags);
+
+ VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
}
static void remap_page(struct page *page, unsigned int nr)
@@ -2659,7 +2671,7 @@
struct deferred_split *ds_queue = get_deferred_split_queue(head);
struct anon_vma *anon_vma = NULL;
struct address_space *mapping = NULL;
- int count, mapcount, extra_pins, ret;
+ int extra_pins, ret;
pgoff_t end;
VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
@@ -2718,7 +2730,6 @@
}
unmap_page(head);
- VM_BUG_ON_PAGE(compound_mapcount(head), head);
/* block interrupt reentry in xa_lock and spinlock */
local_irq_disable();
@@ -2736,9 +2747,7 @@
/* Prevent deferred_split_scan() touching ->_refcount */
spin_lock(&ds_queue->split_queue_lock);
- count = page_count(head);
- mapcount = total_mapcount(head);
- if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
+ if (page_ref_freeze(head, 1 + extra_pins)) {
if (!list_empty(page_deferred_list(head))) {
ds_queue->split_queue_len--;
list_del(page_deferred_list(head));
@@ -2758,16 +2767,9 @@
__split_huge_page(page, list, end);
ret = 0;
} else {
- if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
- pr_alert("total_mapcount: %u, page_count(): %u\n",
- mapcount, count);
- if (PageTail(page))
- dump_page(head, NULL);
- dump_page(page, "total_mapcount(head) > 0");
- BUG();
- }
spin_unlock(&ds_queue->split_queue_lock);
-fail: if (mapping)
+fail:
+ if (mapping)
xa_unlock(&mapping->i_pages);
local_irq_enable();
remap_page(head, thp_nr_pages(head));
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5560b50..e0a5f9c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2121,12 +2121,18 @@
* be restored when a newly allocated huge page must be freed. It is
* to be called after calling vma_needs_reservation to determine if a
* reservation exists.
+ *
+ * vma_del_reservation is used in error paths where an entry in the reserve
+ * map was created during huge page allocation and must be removed. It is to
+ * be called after calling vma_needs_reservation to determine if a reservation
+ * exists.
*/
enum vma_resv_mode {
VMA_NEEDS_RESV,
VMA_COMMIT_RESV,
VMA_END_RESV,
VMA_ADD_RESV,
+ VMA_DEL_RESV,
};
static long __vma_reservation_common(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr,
@@ -2170,11 +2176,21 @@
ret = region_del(resv, idx, idx + 1);
}
break;
+ case VMA_DEL_RESV:
+ if (vma->vm_flags & VM_MAYSHARE) {
+ region_abort(resv, idx, idx + 1, 1);
+ ret = region_del(resv, idx, idx + 1);
+ } else {
+ ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
+ /* region_add calls of range 1 should never fail. */
+ VM_BUG_ON(ret < 0);
+ }
+ break;
default:
BUG();
}
- if (vma->vm_flags & VM_MAYSHARE)
+ if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV)
return ret;
/*
* We know private mapping must have HPAGE_RESV_OWNER set.
@@ -2222,25 +2238,39 @@
return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV);
}
-/*
- * This routine is called to restore a reservation on error paths. In the
- * specific error paths, a huge page was allocated (via alloc_huge_page)
- * and is about to be freed. If a reservation for the page existed,
- * alloc_huge_page would have consumed the reservation and set
- * HPageRestoreReserve in the newly allocated page. When the page is freed
- * via free_huge_page, the global reservation count will be incremented if
- * HPageRestoreReserve is set. However, free_huge_page can not adjust the
- * reserve map. Adjust the reserve map here to be consistent with global
- * reserve count adjustments to be made by free_huge_page.
- */
-static void restore_reserve_on_error(struct hstate *h,
- struct vm_area_struct *vma, unsigned long address,
- struct page *page)
+static long vma_del_reservation(struct hstate *h,
+ struct vm_area_struct *vma, unsigned long addr)
{
- if (unlikely(HPageRestoreReserve(page))) {
- long rc = vma_needs_reservation(h, vma, address);
+ return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV);
+}
- if (unlikely(rc < 0)) {
+/*
+ * This routine is called to restore reservation information on error paths.
+ * It should ONLY be called for pages allocated via alloc_huge_page(), and
+ * the hugetlb mutex should remain held when calling this routine.
+ *
+ * It handles two specific cases:
+ * 1) A reservation was in place and the page consumed the reservation.
+ * HPageRestoreReserve is set in the page.
+ * 2) No reservation was in place for the page, so HPageRestoreReserve is
+ * not set. However, alloc_huge_page always updates the reserve map.
+ *
+ * In case 1, free_huge_page later in the error path will increment the
+ * global reserve count. But, free_huge_page does not have enough context
+ * to adjust the reservation map. This case deals primarily with private
+ * mappings. Adjust the reserve map here to be consistent with global
+ * reserve count adjustments to be made by free_huge_page. Make sure the
+ * reserve map indicates there is a reservation present.
+ *
+ * In case 2, simply undo reserve map modifications done by alloc_huge_page.
+ */
+void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
+ unsigned long address, struct page *page)
+{
+ long rc = vma_needs_reservation(h, vma, address);
+
+ if (HPageRestoreReserve(page)) {
+ if (unlikely(rc < 0))
/*
* Rare out of memory condition in reserve map
* manipulation. Clear HPageRestoreReserve so that
@@ -2253,16 +2283,57 @@
* accounting of reserve counts.
*/
ClearHPageRestoreReserve(page);
- } else if (rc) {
- rc = vma_add_reservation(h, vma, address);
- if (unlikely(rc < 0))
- /*
- * See above comment about rare out of
- * memory condition.
- */
- ClearHPageRestoreReserve(page);
- } else
+ else if (rc)
+ (void)vma_add_reservation(h, vma, address);
+ else
vma_end_reservation(h, vma, address);
+ } else {
+ if (!rc) {
+ /*
+ * This indicates there is an entry in the reserve map
+ * added by alloc_huge_page. We know it was added
+ * before the alloc_huge_page call, otherwise
+ * HPageRestoreReserve would be set on the page.
+ * Remove the entry so that a subsequent allocation
+ * does not consume a reservation.
+ */
+ rc = vma_del_reservation(h, vma, address);
+ if (rc < 0)
+ /*
+ * VERY rare out of memory condition. Since
+ * we can not delete the entry, set
+ * HPageRestoreReserve so that the reserve
+ * count will be incremented when the page
+ * is freed. This reserve will be consumed
+ * on a subsequent allocation.
+ */
+ SetHPageRestoreReserve(page);
+ } else if (rc < 0) {
+ /*
+ * Rare out of memory condition from
+ * vma_needs_reservation call. Memory allocation is
+ * only attempted if a new entry is needed. Therefore,
+ * this implies there is not an entry in the
+ * reserve map.
+ *
+ * For shared mappings, no entry in the map indicates
+ * no reservation. We are done.
+ */
+ if (!(vma->vm_flags & VM_MAYSHARE))
+ /*
+ * For private mappings, no entry indicates
+ * a reservation is present. Since we can
+ * not add an entry, set SetHPageRestoreReserve
+ * on the page so reserve count will be
+ * incremented when freed. This reserve will
+ * be consumed on a subsequent allocation.
+ */
+ SetHPageRestoreReserve(page);
+ } else
+ /*
+ * No reservation present, do nothing
+ */
+ vma_end_reservation(h, vma, address);
}
}
@@ -4037,6 +4108,8 @@
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
entry = huge_ptep_get(src_pte);
if (!pte_same(src_pte_old, entry)) {
+ restore_reserve_on_error(h, vma, addr,
+ new);
put_page(new);
/* dst_entry won't change as in child */
goto again;
@@ -5006,6 +5079,7 @@
if (vm_shared || is_continue)
unlock_page(page);
out_release_nounlock:
+ restore_reserve_on_error(h, dst_vma, dst_addr, page);
put_page(page);
goto out;
}
@@ -5857,6 +5931,21 @@
return ret;
}
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+{
+ int ret = 0;
+
+ *hugetlb = false;
+ spin_lock_irq(&hugetlb_lock);
+ if (PageHeadHuge(page)) {
+ *hugetlb = true;
+ if (HPageFreed(page) || HPageMigratable(page))
+ ret = get_page_unless_zero(page);
+ }
+ spin_unlock_irq(&hugetlb_lock);
+ return ret;
+}
+
void putback_active_hugepage(struct page *page)
{
spin_lock_irq(&hugetlb_lock);
diff --git a/mm/internal.h b/mm/internal.h
index 2f11829..e8fdb53 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -384,27 +384,52 @@
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
/*
- * At what user virtual address is page expected in @vma?
+ * At what user virtual address is page expected in vma?
+ * Returns -EFAULT if all of the page is outside the range of vma.
+ * If page is a compound head, the entire compound page is considered.
*/
static inline unsigned long
-__vma_address(struct page *page, struct vm_area_struct *vma)
-{
- pgoff_t pgoff = page_to_pgoff(page);
- return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
-}
-
-static inline unsigned long
vma_address(struct page *page, struct vm_area_struct *vma)
{
- unsigned long start, end;
+ pgoff_t pgoff;
+ unsigned long address;
- start = __vma_address(page, vma);
- end = start + thp_size(page) - PAGE_SIZE;
+ VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
+ pgoff = page_to_pgoff(page);
+ if (pgoff >= vma->vm_pgoff) {
+ address = vma->vm_start +
+ ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+ /* Check for address beyond vma (or wrapped through 0?) */
+ if (address < vma->vm_start || address >= vma->vm_end)
+ address = -EFAULT;
+ } else if (PageHead(page) &&
+ pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) {
+ /* Test above avoids possibility of wrap to 0 on 32-bit */
+ address = vma->vm_start;
+ } else {
+ address = -EFAULT;
+ }
+ return address;
+}
- /* page should be within @vma mapping range */
- VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma);
+/*
+ * Then at what user virtual address will none of the page be found in vma?
+ * Assumes that vma_address() already returned a good starting address.
+ * If page is a compound head, the entire compound page is considered.
+ */
+static inline unsigned long
+vma_address_end(struct page *page, struct vm_area_struct *vma)
+{
+ pgoff_t pgoff;
+ unsigned long address;
- return max(start, vma->vm_start);
+ VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
+ pgoff = page_to_pgoff(page) + compound_nr(page);
+ address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+ /* Check for address beyond vma (or wrapped through 0?) */
+ if (address < vma->vm_start || address > vma->vm_end)
+ address = vma->vm_end;
+ return address;
}
static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 85ad98c..0143d32 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -949,6 +949,17 @@
return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;
}
+/*
+ * Return true if a page type of a given page is supported by hwpoison
+ * mechanism (while handling could fail), otherwise false. This function
+ * does not return true for hugetlb or device memory pages, so it's assumed
+ * to be called only in the context where we never have such pages.
+ */
+static inline bool HWPoisonHandlable(struct page *page)
+{
+ return PageLRU(page) || __PageMovable(page);
+}
+
/**
* __get_hwpoison_page() - Get refcount for memory error handling:
* @page: raw error page (hit by memory error)
@@ -959,8 +970,22 @@
static int __get_hwpoison_page(struct page *page)
{
struct page *head = compound_head(page);
+ int ret = 0;
+ bool hugetlb = false;
- if (!PageHuge(head) && PageTransHuge(head)) {
+ ret = get_hwpoison_huge_page(head, &hugetlb);
+ if (hugetlb)
+ return ret;
+
+ /*
+ * This check prevents from calling get_hwpoison_unless_zero()
+ * for any unsupported type of page in order to reduce the risk of
+ * unexpected races caused by taking a page refcount.
+ */
+ if (!HWPoisonHandlable(head))
+ return 0;
+
+ if (PageTransHuge(head)) {
/*
* Non anonymous thp exists only in allocation/free time. We
* can't handle such a case correctly, so let's give it up.
@@ -1017,7 +1042,7 @@
ret = -EIO;
}
} else {
- if (PageHuge(p) || PageLRU(p) || __PageMovable(p)) {
+ if (PageHuge(p) || HWPoisonHandlable(p)) {
ret = 1;
} else {
/*
@@ -1527,7 +1552,12 @@
return 0;
}
- if (!PageTransTail(p) && !PageLRU(p))
+ /*
+ * __munlock_pagevec may clear a writeback page's LRU flag without
+ * page_lock. We need wait writeback completion for this page or it
+ * may trigger vfs BUG while evict inode.
+ */
+ if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p))
goto identify_page_state;
/*
diff --git a/mm/memory.c b/mm/memory.c
index f3ffab9..486f4a2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1361,7 +1361,18 @@
else if (zap_huge_pmd(tlb, vma, pmd, addr))
goto next;
/* fall through */
+ } else if (details && details->single_page &&
+ PageTransCompound(details->single_page) &&
+ next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) {
+ spinlock_t *ptl = pmd_lock(tlb->mm, pmd);
+ /*
+ * Take and drop THP pmd lock so that we cannot return
+ * prematurely, while zap_huge_pmd() has cleared *pmd,
+ * but not yet decremented compound_mapcount().
+ */
+ spin_unlock(ptl);
}
+
/*
* Here there can be other concurrent MADV_DONTNEED or
* trans huge page faults running, and if the pmd is
@@ -3237,6 +3248,36 @@
}
/**
+ * unmap_mapping_page() - Unmap single page from processes.
+ * @page: The locked page to be unmapped.
+ *
+ * Unmap this page from any userspace process which still has it mmaped.
+ * Typically, for efficiency, the range of nearby pages has already been
+ * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once
+ * truncation or invalidation holds the lock on a page, it may find that
+ * the page has been remapped again: and then uses unmap_mapping_page()
+ * to unmap it finally.
+ */
+void unmap_mapping_page(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ struct zap_details details = { };
+
+ VM_BUG_ON(!PageLocked(page));
+ VM_BUG_ON(PageTail(page));
+
+ details.check_mapping = mapping;
+ details.first_index = page->index;
+ details.last_index = page->index + thp_nr_pages(page) - 1;
+ details.single_page = page;
+
+ i_mmap_lock_write(mapping);
+ if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
+ unmap_mapping_range_tree(&mapping->i_mmap, &details);
+ i_mmap_unlock_write(mapping);
+}
+
+/**
* unmap_mapping_pages() - Unmap pages from processes.
* @mapping: The address space containing pages to be unmapped.
* @start: Index of first page to be unmapped.
diff --git a/mm/migrate.c b/mm/migrate.c
index b234c3f..41ff2c9 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -295,6 +295,7 @@
goto out;
page = migration_entry_to_page(entry);
+ page = compound_head(page);
/*
* Once page cache replacement of page migration started, page_count
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 2cf01d9..e37bd43 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -212,23 +212,34 @@
pvmw->ptl = NULL;
}
} else if (!pmd_present(pmde)) {
+ /*
+ * If PVMW_SYNC, take and drop THP pmd lock so that we
+ * cannot return prematurely, while zap_huge_pmd() has
+ * cleared *pmd but not decremented compound_mapcount().
+ */
+ if ((pvmw->flags & PVMW_SYNC) &&
+ PageTransCompound(pvmw->page)) {
+ spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
+
+ spin_unlock(ptl);
+ }
return false;
}
if (!map_pte(pvmw))
goto next_pte;
while (1) {
+ unsigned long end;
+
if (check_pte(pvmw))
return true;
next_pte:
/* Seek to next pte only makes sense for THP */
if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
return not_found(pvmw);
+ end = vma_address_end(pvmw->page, pvmw->vma);
do {
pvmw->address += PAGE_SIZE;
- if (pvmw->address >= pvmw->vma->vm_end ||
- pvmw->address >=
- __vma_address(pvmw->page, pvmw->vma) +
- thp_size(pvmw->page))
+ if (pvmw->address >= end)
return not_found(pvmw);
/* Did we cross page table boundary? */
if (pvmw->address % PMD_SIZE == 0) {
@@ -266,14 +277,10 @@
.vma = vma,
.flags = PVMW_SYNC,
};
- unsigned long start, end;
- start = __vma_address(page, vma);
- end = start + thp_size(page) - PAGE_SIZE;
-
- if (unlikely(end < vma->vm_start || start >= vma->vm_end))
+ pvmw.address = vma_address(page, vma);
+ if (pvmw.address == -EFAULT)
return 0;
- pvmw.address = max(start, vma->vm_start);
if (!page_vma_mapped_walk(&pvmw))
return 0;
page_vma_mapped_walk_done(&pvmw);
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index c2210e1..4e640ba 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -135,9 +135,8 @@
{
pmd_t pmd;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
- VM_BUG_ON(!pmd_present(*pmdp));
- /* Below assumes pmd_present() is true */
- VM_BUG_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
+ VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
+ !pmd_devmap(*pmdp));
pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return pmd;
diff --git a/mm/rmap.c b/mm/rmap.c
index 693a610..e05c300 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -707,7 +707,6 @@
*/
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
- unsigned long address;
if (PageAnon(page)) {
struct anon_vma *page__anon_vma = page_anon_vma(page);
/*
@@ -717,15 +716,13 @@
if (!vma->anon_vma || !page__anon_vma ||
vma->anon_vma->root != page__anon_vma->root)
return -EFAULT;
- } else if (page->mapping) {
- if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping)
- return -EFAULT;
- } else
+ } else if (!vma->vm_file) {
return -EFAULT;
- address = __vma_address(page, vma);
- if (unlikely(address < vma->vm_start || address >= vma->vm_end))
+ } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) {
return -EFAULT;
- return address;
+ }
+
+ return vma_address(page, vma);
}
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
@@ -919,7 +916,7 @@
*/
mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
0, vma, vma->vm_mm, address,
- min(vma->vm_end, address + page_size(page)));
+ vma_address_end(page, vma));
mmu_notifier_invalidate_range_start(&range);
while (page_vma_mapped_walk(&pvmw)) {
@@ -1405,6 +1402,15 @@
struct mmu_notifier_range range;
enum ttu_flags flags = (enum ttu_flags)(long)arg;
+ /*
+ * When racing against e.g. zap_pte_range() on another cpu,
+ * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+ * try_to_unmap() may return false when it is about to become true,
+ * if page table locking is skipped: use TTU_SYNC to wait for that.
+ */
+ if (flags & TTU_SYNC)
+ pvmw.flags = PVMW_SYNC;
+
/* munlock has nothing to gain from examining un-locked vmas */
if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
return true;
@@ -1426,9 +1432,10 @@
* Note that the page can not be free in this function as call of
* try_to_unmap() must hold a reference on the page.
*/
+ range.end = PageKsm(page) ?
+ address + PAGE_SIZE : vma_address_end(page, vma);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
- address,
- min(vma->vm_end, address + page_size(page)));
+ address, range.end);
if (PageHuge(page)) {
/*
* If sharing is possible, start and end will be adjusted
@@ -1777,7 +1784,13 @@
else
rmap_walk(page, &rwc);
- return !page_mapcount(page) ? true : false;
+ /*
+ * When racing against e.g. zap_pte_range() on another cpu,
+ * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+ * try_to_unmap() may return false when it is about to become true,
+ * if page table locking is skipped: use TTU_SYNC to wait for that.
+ */
+ return !page_mapcount(page);
}
/**
@@ -1874,6 +1887,7 @@
struct vm_area_struct *vma = avc->vma;
unsigned long address = vma_address(page, vma);
+ VM_BUG_ON_VMA(address == -EFAULT, vma);
cond_resched();
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
@@ -1928,6 +1942,7 @@
pgoff_start, pgoff_end) {
unsigned long address = vma_address(page, vma);
+ VM_BUG_ON_VMA(address == -EFAULT, vma);
cond_resched();
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
diff --git a/mm/slab_common.c b/mm/slab_common.c
index a4a5714..7cab776 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -97,8 +97,7 @@
#ifdef CONFIG_DEBUG_VM
static int kmem_cache_sanity_check(const char *name, unsigned int size)
{
- if (!name || in_interrupt() || size < sizeof(void *) ||
- size > KMALLOC_MAX_SIZE) {
+ if (!name || in_interrupt() || size > KMALLOC_MAX_SIZE) {
pr_err("kmem_cache_create(%s) integrity check failed\n", name);
return -EINVAL;
}
diff --git a/mm/slub.c b/mm/slub.c
index 3f96e09..61bd40e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -15,6 +15,7 @@
#include <linux/module.h>
#include <linux/bit_spinlock.h>
#include <linux/interrupt.h>
+#include <linux/swab.h>
#include <linux/bitops.h>
#include <linux/slab.h>
#include "slab.h"
@@ -712,15 +713,15 @@
p, p - addr, get_freepointer(s, p));
if (s->flags & SLAB_RED_ZONE)
- print_section(KERN_ERR, "Redzone ", p - s->red_left_pad,
+ print_section(KERN_ERR, "Redzone ", p - s->red_left_pad,
s->red_left_pad);
else if (p > addr + 16)
print_section(KERN_ERR, "Bytes b4 ", p - 16, 16);
- print_section(KERN_ERR, "Object ", p,
+ print_section(KERN_ERR, "Object ", p,
min_t(unsigned int, s->object_size, PAGE_SIZE));
if (s->flags & SLAB_RED_ZONE)
- print_section(KERN_ERR, "Redzone ", p + s->object_size,
+ print_section(KERN_ERR, "Redzone ", p + s->object_size,
s->inuse - s->object_size);
off = get_info_end(s);
@@ -732,7 +733,7 @@
if (off != size_from_object(s))
/* Beginning of the filler is the free pointer */
- print_section(KERN_ERR, "Padding ", p + off,
+ print_section(KERN_ERR, "Padding ", p + off,
size_from_object(s) - off);
dump_stack();
@@ -909,11 +910,11 @@
u8 *endobject = object + s->object_size;
if (s->flags & SLAB_RED_ZONE) {
- if (!check_bytes_and_report(s, page, object, "Redzone",
+ if (!check_bytes_and_report(s, page, object, "Left Redzone",
object - s->red_left_pad, val, s->red_left_pad))
return 0;
- if (!check_bytes_and_report(s, page, object, "Redzone",
+ if (!check_bytes_and_report(s, page, object, "Right Redzone",
endobject, val, s->inuse - s->object_size))
return 0;
} else {
@@ -928,7 +929,7 @@
if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) &&
(!check_bytes_and_report(s, page, p, "Poison", p,
POISON_FREE, s->object_size - 1) ||
- !check_bytes_and_report(s, page, p, "Poison",
+ !check_bytes_and_report(s, page, p, "End Poison",
p + s->object_size - 1, POISON_END, 1)))
return 0;
/*
@@ -3689,7 +3690,6 @@
{
slab_flags_t flags = s->flags;
unsigned int size = s->object_size;
- unsigned int freepointer_area;
unsigned int order;
/*
@@ -3698,13 +3698,6 @@
* the possible location of the free pointer.
*/
size = ALIGN(size, sizeof(void *));
- /*
- * This is the area of the object where a freepointer can be
- * safely written. If redzoning adds more to the inuse size, we
- * can't use that portion for writing the freepointer, so
- * s->offset must be limited within this for the general case.
- */
- freepointer_area = size;
#ifdef CONFIG_SLUB_DEBUG
/*
@@ -3730,19 +3723,21 @@
/*
* With that we have determined the number of bytes in actual use
- * by the object. This is the potential offset to the free pointer.
+ * by the object and redzoning.
*/
s->inuse = size;
- if (((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) ||
- s->ctor)) {
+ if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) ||
+ ((flags & SLAB_RED_ZONE) && s->object_size < sizeof(void *)) ||
+ s->ctor) {
/*
* Relocate free pointer after the object if it is not
* permitted to overwrite the first word of the object on
* kmem_cache_free.
*
* This is the case if we do RCU, have a constructor or
- * destructor or are poisoning the objects.
+ * destructor, are poisoning the objects, or are
+ * redzoning an object smaller than sizeof(void *).
*
* The assumption that s->offset >= s->inuse means free
* pointer is outside of the object is used in the
@@ -3751,13 +3746,13 @@
*/
s->offset = size;
size += sizeof(void *);
- } else if (freepointer_area > sizeof(void *)) {
+ } else {
/*
* Store freelist pointer near middle of object to keep
* it away from the edges of the object to avoid small
* sized over/underflows from neighboring allocations.
*/
- s->offset = ALIGN(freepointer_area / 2, sizeof(void *));
+ s->offset = ALIGN_DOWN(s->object_size / 2, sizeof(void *));
}
#ifdef CONFIG_SLUB_DEBUG
diff --git a/mm/sparse.c b/mm/sparse.c
index b2ada9d..55c18aff 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -344,6 +344,15 @@
return sizeof(struct mem_section_usage) + usemap_size();
}
+static inline phys_addr_t pgdat_to_phys(struct pglist_data *pgdat)
+{
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+ return __pa_symbol(pgdat);
+#else
+ return __pa(pgdat);
+#endif
+}
+
#ifdef CONFIG_MEMORY_HOTREMOVE
static struct mem_section_usage * __init
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
@@ -362,7 +371,7 @@
* from the same section as the pgdat where possible to avoid
* this problem.
*/
- goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
+ goal = pgdat_to_phys(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
limit = goal + (1UL << PA_SECTION_SHIFT);
nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
again:
@@ -390,7 +399,7 @@
}
usemap_snr = pfn_to_section_nr(__pa(usage) >> PAGE_SHIFT);
- pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
+ pgdat_snr = pfn_to_section_nr(pgdat_to_phys(pgdat) >> PAGE_SHIFT);
if (usemap_snr == pgdat_snr)
return;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 149e774..996afa8 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1900,7 +1900,7 @@
static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte)
{
- return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte);
+ return pte_same(pte_swp_clear_flags(pte), swp_pte);
}
/*
diff --git a/mm/truncate.c b/mm/truncate.c
index 95af244..234ddd8 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -167,13 +167,10 @@
* its lock, b) when a concurrent invalidate_mapping_pages got there first and
* c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
*/
-static void
-truncate_cleanup_page(struct address_space *mapping, struct page *page)
+static void truncate_cleanup_page(struct page *page)
{
- if (page_mapped(page)) {
- unsigned int nr = thp_nr_pages(page);
- unmap_mapping_pages(mapping, page->index, nr, false);
- }
+ if (page_mapped(page))
+ unmap_mapping_page(page);
if (page_has_private(page))
do_invalidatepage(page, 0, thp_size(page));
@@ -218,7 +215,7 @@
if (page->mapping != mapping)
return -EIO;
- truncate_cleanup_page(mapping, page);
+ truncate_cleanup_page(page);
delete_from_page_cache(page);
return 0;
}
@@ -325,7 +322,7 @@
index = indices[pagevec_count(&pvec) - 1] + 1;
truncate_exceptional_pvec_entries(mapping, &pvec, indices);
for (i = 0; i < pagevec_count(&pvec); i++)
- truncate_cleanup_page(mapping, pvec.pages[i]);
+ truncate_cleanup_page(pvec.pages[i]);
delete_from_page_cache_batch(mapping, &pvec);
for (i = 0; i < pagevec_count(&pvec); i++)
unlock_page(pvec.pages[i]);
@@ -639,6 +636,16 @@
continue;
}
+ if (!did_range_unmap && page_mapped(page)) {
+ /*
+ * If page is mapped, before taking its lock,
+ * zap the rest of the file in one hit.
+ */
+ unmap_mapping_pages(mapping, index,
+ (1 + end - index), false);
+ did_range_unmap = 1;
+ }
+
lock_page(page);
WARN_ON(page_to_index(page) != index);
if (page->mapping != mapping) {
@@ -646,23 +653,11 @@
continue;
}
wait_on_page_writeback(page);
- if (page_mapped(page)) {
- if (!did_range_unmap) {
- /*
- * Zap the rest of the file in one hit.
- */
- unmap_mapping_pages(mapping, index,
- (1 + end - index), false);
- did_range_unmap = 1;
- } else {
- /*
- * Just zap this page
- */
- unmap_mapping_pages(mapping, index,
- 1, false);
- }
- }
+
+ if (page_mapped(page))
+ unmap_mapping_page(page);
BUG_ON(page_mapped(page));
+
ret2 = do_launder_page(mapping, page);
if (ret2 == 0) {
if (!invalidate_complete_page2(mapping, page))
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index be18af4..c7236da 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -768,7 +768,7 @@
if (a && a->status & ATIF_PROBE) {
a->status |= ATIF_PROBE_FAIL;
/*
- * we do not respond to probe or request packets for
+ * we do not respond to probe or request packets of
* this address while we are probing this address
*/
goto unlock;
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 789f257..fc8be49 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -409,8 +409,10 @@
if (WARN_ON(!forw_packet->if_outgoing))
return;
- if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface))
+ if (forw_packet->if_outgoing->soft_iface != soft_iface) {
+ pr_warn("%s: soft interface switch for queued OGM\n", __func__);
return;
+ }
if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE)
return;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 372e3b2..7dd51da 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -3229,7 +3229,7 @@
{
struct l2cap_chan *chan;
- bt_dev_dbg(pchan->conn->hcon->hdev, "pchan %p", pchan);
+ BT_DBG("pchan %p", pchan);
chan = l2cap_chan_create();
if (!chan)
@@ -3250,7 +3250,7 @@
*/
atomic_set(&chan->nesting, L2CAP_NESTING_SMP);
- bt_dev_dbg(pchan->conn->hcon->hdev, "created chan %p", chan);
+ BT_DBG("created chan %p", chan);
return chan;
}
@@ -3354,7 +3354,7 @@
{
struct smp_dev *smp;
- bt_dev_dbg(chan->conn->hcon->hdev, "chan %p", chan);
+ BT_DBG("chan %p", chan);
smp = chan->data;
if (smp) {
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 7ce8a77..e013d33 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -90,8 +90,8 @@
#endif
struct br_tunnel_info {
- __be64 tunnel_id;
- struct metadata_dst *tunnel_dst;
+ __be64 tunnel_id;
+ struct metadata_dst __rcu *tunnel_dst;
};
/* private vlan flags */
diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c
index 0d3a8c0..0101744 100644
--- a/net/bridge/br_vlan_tunnel.c
+++ b/net/bridge/br_vlan_tunnel.c
@@ -41,26 +41,33 @@
br_vlan_tunnel_rht_params);
}
+static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan)
+{
+ struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst);
+
+ WRITE_ONCE(vlan->tinfo.tunnel_id, 0);
+ RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL);
+ dst_release(&tdst->dst);
+}
+
void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg,
struct net_bridge_vlan *vlan)
{
- if (!vlan->tinfo.tunnel_dst)
+ if (!rcu_access_pointer(vlan->tinfo.tunnel_dst))
return;
rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode,
br_vlan_tunnel_rht_params);
- vlan->tinfo.tunnel_id = 0;
- dst_release(&vlan->tinfo.tunnel_dst->dst);
- vlan->tinfo.tunnel_dst = NULL;
+ vlan_tunnel_info_release(vlan);
}
static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg,
struct net_bridge_vlan *vlan, u32 tun_id)
{
- struct metadata_dst *metadata = NULL;
+ struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst);
__be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id));
int err;
- if (vlan->tinfo.tunnel_dst)
+ if (metadata)
return -EEXIST;
metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY,
@@ -69,8 +76,8 @@
return -EINVAL;
metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE;
- vlan->tinfo.tunnel_dst = metadata;
- vlan->tinfo.tunnel_id = key;
+ rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata);
+ WRITE_ONCE(vlan->tinfo.tunnel_id, key);
err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode,
br_vlan_tunnel_rht_params);
@@ -79,9 +86,7 @@
return 0;
out:
- dst_release(&vlan->tinfo.tunnel_dst->dst);
- vlan->tinfo.tunnel_dst = NULL;
- vlan->tinfo.tunnel_id = 0;
+ vlan_tunnel_info_release(vlan);
return err;
}
@@ -182,12 +187,15 @@
int br_handle_egress_vlan_tunnel(struct sk_buff *skb,
struct net_bridge_vlan *vlan)
{
+ struct metadata_dst *tunnel_dst;
+ __be64 tunnel_id;
int err;
- if (!vlan || !vlan->tinfo.tunnel_id)
+ if (!vlan)
return 0;
- if (unlikely(!skb_vlan_tag_present(skb)))
+ tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id);
+ if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb)))
return 0;
skb_dst_drop(skb);
@@ -195,7 +203,9 @@
if (err)
return err;
- skb_dst_set(skb, dst_clone(&vlan->tinfo.tunnel_dst->dst));
+ tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst);
+ if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst))
+ skb_dst_set(skb, &tunnel_dst->dst);
return 0;
}
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 909b9e6..f3e4d95 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -125,7 +125,7 @@
struct sock sk;
int bound;
int ifindex;
- struct notifier_block notifier;
+ struct list_head notifier;
struct list_head rx_ops;
struct list_head tx_ops;
unsigned long dropped_usr_msgs;
@@ -133,6 +133,10 @@
char procname [32]; /* inode number in decimal with \0 */
};
+static LIST_HEAD(bcm_notifier_list);
+static DEFINE_SPINLOCK(bcm_notifier_lock);
+static struct bcm_sock *bcm_busy_notifier;
+
static inline struct bcm_sock *bcm_sk(const struct sock *sk)
{
return (struct bcm_sock *)sk;
@@ -402,6 +406,7 @@
if (!op->count && (op->flags & TX_COUNTEVT)) {
/* create notification to user */
+ memset(&msg_head, 0, sizeof(msg_head));
msg_head.opcode = TX_EXPIRED;
msg_head.flags = op->flags;
msg_head.count = op->count;
@@ -439,6 +444,7 @@
/* this element is not throttled anymore */
data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV);
+ memset(&head, 0, sizeof(head));
head.opcode = RX_CHANGED;
head.flags = op->flags;
head.count = op->count;
@@ -560,6 +566,7 @@
}
/* create notification to user */
+ memset(&msg_head, 0, sizeof(msg_head));
msg_head.opcode = RX_TIMEOUT;
msg_head.flags = op->flags;
msg_head.count = op->count;
@@ -1378,20 +1385,15 @@
/*
* notification handler for netdevice status changes
*/
-static int bcm_notifier(struct notifier_block *nb, unsigned long msg,
- void *ptr)
+static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
+ struct net_device *dev)
{
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier);
struct sock *sk = &bo->sk;
struct bcm_op *op;
int notify_enodev = 0;
if (!net_eq(dev_net(dev), sock_net(sk)))
- return NOTIFY_DONE;
-
- if (dev->type != ARPHRD_CAN)
- return NOTIFY_DONE;
+ return;
switch (msg) {
@@ -1426,7 +1428,28 @@
sk->sk_error_report(sk);
}
}
+}
+static int bcm_notifier(struct notifier_block *nb, unsigned long msg,
+ void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+ if (dev->type != ARPHRD_CAN)
+ return NOTIFY_DONE;
+ if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
+ return NOTIFY_DONE;
+ if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */
+ return NOTIFY_DONE;
+
+ spin_lock(&bcm_notifier_lock);
+ list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) {
+ spin_unlock(&bcm_notifier_lock);
+ bcm_notify(bcm_busy_notifier, msg, dev);
+ spin_lock(&bcm_notifier_lock);
+ }
+ bcm_busy_notifier = NULL;
+ spin_unlock(&bcm_notifier_lock);
return NOTIFY_DONE;
}
@@ -1446,9 +1469,9 @@
INIT_LIST_HEAD(&bo->rx_ops);
/* set notifier */
- bo->notifier.notifier_call = bcm_notifier;
-
- register_netdevice_notifier(&bo->notifier);
+ spin_lock(&bcm_notifier_lock);
+ list_add_tail(&bo->notifier, &bcm_notifier_list);
+ spin_unlock(&bcm_notifier_lock);
return 0;
}
@@ -1471,7 +1494,14 @@
/* remove bcm_ops, timer, rx_unregister(), etc. */
- unregister_netdevice_notifier(&bo->notifier);
+ spin_lock(&bcm_notifier_lock);
+ while (bcm_busy_notifier == bo) {
+ spin_unlock(&bcm_notifier_lock);
+ schedule_timeout_uninterruptible(1);
+ spin_lock(&bcm_notifier_lock);
+ }
+ list_del(&bo->notifier);
+ spin_unlock(&bcm_notifier_lock);
lock_sock(sk);
@@ -1692,6 +1722,10 @@
.exit = canbcm_pernet_exit,
};
+static struct notifier_block canbcm_notifier = {
+ .notifier_call = bcm_notifier
+};
+
static int __init bcm_module_init(void)
{
int err;
@@ -1705,12 +1739,14 @@
}
register_pernet_subsys(&canbcm_pernet_ops);
+ register_netdevice_notifier(&canbcm_notifier);
return 0;
}
static void __exit bcm_module_exit(void)
{
can_proto_unregister(&bcm_can_proto);
+ unregister_netdevice_notifier(&canbcm_notifier);
unregister_pernet_subsys(&canbcm_pernet_ops);
}
diff --git a/net/can/isotp.c b/net/can/isotp.c
index 253b244..be6183f 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -143,10 +143,14 @@
u32 force_tx_stmin;
u32 force_rx_stmin;
struct tpcon rx, tx;
- struct notifier_block notifier;
+ struct list_head notifier;
wait_queue_head_t wait;
};
+static LIST_HEAD(isotp_notifier_list);
+static DEFINE_SPINLOCK(isotp_notifier_lock);
+static struct isotp_sock *isotp_busy_notifier;
+
static inline struct isotp_sock *isotp_sk(const struct sock *sk)
{
return (struct isotp_sock *)sk;
@@ -1013,7 +1017,14 @@
/* wait for complete transmission of current pdu */
wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
- unregister_netdevice_notifier(&so->notifier);
+ spin_lock(&isotp_notifier_lock);
+ while (isotp_busy_notifier == so) {
+ spin_unlock(&isotp_notifier_lock);
+ schedule_timeout_uninterruptible(1);
+ spin_lock(&isotp_notifier_lock);
+ }
+ list_del(&so->notifier);
+ spin_unlock(&isotp_notifier_lock);
lock_sock(sk);
@@ -1317,21 +1328,16 @@
return 0;
}
-static int isotp_notifier(struct notifier_block *nb, unsigned long msg,
- void *ptr)
+static void isotp_notify(struct isotp_sock *so, unsigned long msg,
+ struct net_device *dev)
{
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- struct isotp_sock *so = container_of(nb, struct isotp_sock, notifier);
struct sock *sk = &so->sk;
if (!net_eq(dev_net(dev), sock_net(sk)))
- return NOTIFY_DONE;
-
- if (dev->type != ARPHRD_CAN)
- return NOTIFY_DONE;
+ return;
if (so->ifindex != dev->ifindex)
- return NOTIFY_DONE;
+ return;
switch (msg) {
case NETDEV_UNREGISTER:
@@ -1357,7 +1363,28 @@
sk->sk_error_report(sk);
break;
}
+}
+static int isotp_notifier(struct notifier_block *nb, unsigned long msg,
+ void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+ if (dev->type != ARPHRD_CAN)
+ return NOTIFY_DONE;
+ if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
+ return NOTIFY_DONE;
+ if (unlikely(isotp_busy_notifier)) /* Check for reentrant bug. */
+ return NOTIFY_DONE;
+
+ spin_lock(&isotp_notifier_lock);
+ list_for_each_entry(isotp_busy_notifier, &isotp_notifier_list, notifier) {
+ spin_unlock(&isotp_notifier_lock);
+ isotp_notify(isotp_busy_notifier, msg, dev);
+ spin_lock(&isotp_notifier_lock);
+ }
+ isotp_busy_notifier = NULL;
+ spin_unlock(&isotp_notifier_lock);
return NOTIFY_DONE;
}
@@ -1394,8 +1421,9 @@
init_waitqueue_head(&so->wait);
- so->notifier.notifier_call = isotp_notifier;
- register_netdevice_notifier(&so->notifier);
+ spin_lock(&isotp_notifier_lock);
+ list_add_tail(&so->notifier, &isotp_notifier_list);
+ spin_unlock(&isotp_notifier_lock);
return 0;
}
@@ -1442,6 +1470,10 @@
.prot = &isotp_proto,
};
+static struct notifier_block canisotp_notifier = {
+ .notifier_call = isotp_notifier
+};
+
static __init int isotp_module_init(void)
{
int err;
@@ -1451,6 +1483,8 @@
err = can_proto_register(&isotp_can_proto);
if (err < 0)
pr_err("can: registration of isotp protocol failed\n");
+ else
+ register_netdevice_notifier(&canisotp_notifier);
return err;
}
@@ -1458,6 +1492,7 @@
static __exit void isotp_module_exit(void)
{
can_proto_unregister(&isotp_can_proto);
+ unregister_netdevice_notifier(&canisotp_notifier);
}
module_init(isotp_module_init);
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index e09d087..c3946c3 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -330,6 +330,9 @@
if ((do_skcb->offset + do_skb->len) < offset_start) {
__skb_unlink(do_skb, &session->skb_queue);
+ /* drop ref taken in j1939_session_skb_queue() */
+ skb_unref(do_skb);
+
kfree_skb(do_skb);
}
spin_unlock_irqrestore(&session->skb_queue.lock, flags);
@@ -349,12 +352,13 @@
skcb->flags |= J1939_ECU_LOCAL_SRC;
+ skb_get(skb);
skb_queue_tail(&session->skb_queue, skb);
}
static struct
-sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session,
- unsigned int offset_start)
+sk_buff *j1939_session_skb_get_by_offset(struct j1939_session *session,
+ unsigned int offset_start)
{
struct j1939_priv *priv = session->priv;
struct j1939_sk_buff_cb *do_skcb;
@@ -371,6 +375,10 @@
skb = do_skb;
}
}
+
+ if (skb)
+ skb_get(skb);
+
spin_unlock_irqrestore(&session->skb_queue.lock, flags);
if (!skb)
@@ -381,12 +389,12 @@
return skb;
}
-static struct sk_buff *j1939_session_skb_find(struct j1939_session *session)
+static struct sk_buff *j1939_session_skb_get(struct j1939_session *session)
{
unsigned int offset_start;
offset_start = session->pkt.dpo * 7;
- return j1939_session_skb_find_by_offset(session, offset_start);
+ return j1939_session_skb_get_by_offset(session, offset_start);
}
/* see if we are receiver
@@ -776,7 +784,7 @@
int ret = 0;
u8 dat[8];
- se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7);
+ se_skb = j1939_session_skb_get_by_offset(session, session->pkt.tx * 7);
if (!se_skb)
return -ENOBUFS;
@@ -801,7 +809,8 @@
netdev_err_once(priv->ndev,
"%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n",
__func__, session, skcb->offset, se_skb->len , session->pkt.tx);
- return -EOVERFLOW;
+ ret = -EOVERFLOW;
+ goto out_free;
}
if (!len) {
@@ -835,6 +844,12 @@
if (pkt_done)
j1939_tp_set_rxtimeout(session, 250);
+ out_free:
+ if (ret)
+ kfree_skb(se_skb);
+ else
+ consume_skb(se_skb);
+
return ret;
}
@@ -1007,7 +1022,7 @@
static int j1939_simple_txnext(struct j1939_session *session)
{
struct j1939_priv *priv = session->priv;
- struct sk_buff *se_skb = j1939_session_skb_find(session);
+ struct sk_buff *se_skb = j1939_session_skb_get(session);
struct sk_buff *skb;
int ret;
@@ -1015,8 +1030,10 @@
return 0;
skb = skb_clone(se_skb, GFP_ATOMIC);
- if (!skb)
- return -ENOMEM;
+ if (!skb) {
+ ret = -ENOMEM;
+ goto out_free;
+ }
can_skb_set_owner(skb, se_skb->sk);
@@ -1024,12 +1041,18 @@
ret = j1939_send_one(priv, skb);
if (ret)
- return ret;
+ goto out_free;
j1939_sk_errqueue(session, J1939_ERRQUEUE_SCHED);
j1939_sk_queue_activate_next(session);
- return 0;
+ out_free:
+ if (ret)
+ kfree_skb(se_skb);
+ else
+ consume_skb(se_skb);
+
+ return ret;
}
static bool j1939_session_deactivate_locked(struct j1939_session *session)
@@ -1170,9 +1193,10 @@
struct sk_buff *skb;
if (!session->transmission) {
- skb = j1939_session_skb_find(session);
+ skb = j1939_session_skb_get(session);
/* distribute among j1939 receivers */
j1939_sk_recv(session->priv, skb);
+ consume_skb(skb);
}
j1939_session_deactivate_activate_next(session);
@@ -1744,7 +1768,7 @@
{
struct j1939_priv *priv = session->priv;
struct j1939_sk_buff_cb *skcb;
- struct sk_buff *se_skb;
+ struct sk_buff *se_skb = NULL;
const u8 *dat;
u8 *tpdat;
int offset;
@@ -1786,7 +1810,7 @@
goto out_session_cancel;
}
- se_skb = j1939_session_skb_find_by_offset(session, packet * 7);
+ se_skb = j1939_session_skb_get_by_offset(session, packet * 7);
if (!se_skb) {
netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__,
session);
@@ -1848,11 +1872,13 @@
j1939_tp_set_rxtimeout(session, 250);
}
session->last_cmd = 0xff;
+ consume_skb(se_skb);
j1939_session_put(session);
return;
out_session_cancel:
+ kfree_skb(se_skb);
j1939_session_timers_cancel(session);
j1939_session_cancel(session, J1939_XTP_ABORT_FAULT);
j1939_session_put(session);
diff --git a/net/can/raw.c b/net/can/raw.c
index 139d947..ac96fc2 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -83,7 +83,7 @@
struct sock sk;
int bound;
int ifindex;
- struct notifier_block notifier;
+ struct list_head notifier;
int loopback;
int recv_own_msgs;
int fd_frames;
@@ -95,6 +95,10 @@
struct uniqframe __percpu *uniq;
};
+static LIST_HEAD(raw_notifier_list);
+static DEFINE_SPINLOCK(raw_notifier_lock);
+static struct raw_sock *raw_busy_notifier;
+
/* Return pointer to store the extra msg flags for raw_recvmsg().
* We use the space of one unsigned int beyond the 'struct sockaddr_can'
* in skb->cb.
@@ -263,21 +267,16 @@
return err;
}
-static int raw_notifier(struct notifier_block *nb,
- unsigned long msg, void *ptr)
+static void raw_notify(struct raw_sock *ro, unsigned long msg,
+ struct net_device *dev)
{
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- struct raw_sock *ro = container_of(nb, struct raw_sock, notifier);
struct sock *sk = &ro->sk;
if (!net_eq(dev_net(dev), sock_net(sk)))
- return NOTIFY_DONE;
-
- if (dev->type != ARPHRD_CAN)
- return NOTIFY_DONE;
+ return;
if (ro->ifindex != dev->ifindex)
- return NOTIFY_DONE;
+ return;
switch (msg) {
case NETDEV_UNREGISTER:
@@ -305,7 +304,28 @@
sk->sk_error_report(sk);
break;
}
+}
+static int raw_notifier(struct notifier_block *nb, unsigned long msg,
+ void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+ if (dev->type != ARPHRD_CAN)
+ return NOTIFY_DONE;
+ if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
+ return NOTIFY_DONE;
+ if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */
+ return NOTIFY_DONE;
+
+ spin_lock(&raw_notifier_lock);
+ list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) {
+ spin_unlock(&raw_notifier_lock);
+ raw_notify(raw_busy_notifier, msg, dev);
+ spin_lock(&raw_notifier_lock);
+ }
+ raw_busy_notifier = NULL;
+ spin_unlock(&raw_notifier_lock);
return NOTIFY_DONE;
}
@@ -334,9 +354,9 @@
return -ENOMEM;
/* set notifier */
- ro->notifier.notifier_call = raw_notifier;
-
- register_netdevice_notifier(&ro->notifier);
+ spin_lock(&raw_notifier_lock);
+ list_add_tail(&ro->notifier, &raw_notifier_list);
+ spin_unlock(&raw_notifier_lock);
return 0;
}
@@ -351,7 +371,14 @@
ro = raw_sk(sk);
- unregister_netdevice_notifier(&ro->notifier);
+ spin_lock(&raw_notifier_lock);
+ while (raw_busy_notifier == ro) {
+ spin_unlock(&raw_notifier_lock);
+ schedule_timeout_uninterruptible(1);
+ spin_lock(&raw_notifier_lock);
+ }
+ list_del(&ro->notifier);
+ spin_unlock(&raw_notifier_lock);
lock_sock(sk);
@@ -889,6 +916,10 @@
.prot = &raw_proto,
};
+static struct notifier_block canraw_notifier = {
+ .notifier_call = raw_notifier
+};
+
static __init int raw_module_init(void)
{
int err;
@@ -898,6 +929,8 @@
err = can_proto_register(&raw_can_proto);
if (err < 0)
pr_err("can: registration of raw protocol failed\n");
+ else
+ register_netdevice_notifier(&canraw_notifier);
return err;
}
@@ -905,6 +938,7 @@
static __exit void raw_module_exit(void)
{
can_proto_unregister(&raw_can_proto);
+ unregister_netdevice_notifier(&canraw_notifier);
}
module_init(raw_module_init);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 98f20efb..bf77457 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -238,6 +238,7 @@
write_lock(&n->lock);
if ((n->nud_state == NUD_FAILED) ||
+ (n->nud_state == NUD_NOARP) ||
(tbl->is_multicast &&
tbl->is_multicast(n->primary_key)) ||
time_after(tref, n->updated))
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 43b6ac4..9b5a767 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -641,6 +641,18 @@
}
EXPORT_SYMBOL_GPL(__put_net);
+/**
+ * get_net_ns - increment the refcount of the network namespace
+ * @ns: common namespace (net)
+ *
+ * Returns the net's common namespace.
+ */
+struct ns_common *get_net_ns(struct ns_common *ns)
+{
+ return &get_net(container_of(ns, struct net, ns))->ns;
+}
+EXPORT_SYMBOL_GPL(get_net_ns);
+
struct net *get_net_ns_by_fd(int fd)
{
struct file *file;
@@ -660,14 +672,8 @@
fput(file);
return net;
}
-
-#else
-struct net *get_net_ns_by_fd(int fd)
-{
- return ERR_PTR(-EINVAL);
-}
-#endif
EXPORT_SYMBOL_GPL(get_net_ns_by_fd);
+#endif
struct net *get_net_ns_by_pid(pid_t pid)
{
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 3e84279..ec931b0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4842,10 +4842,12 @@
if (err < 0)
goto errout;
- if (!skb->len) {
- err = -EINVAL;
+ /* Notification info is only filled for bridge ports, not the bridge
+ * device itself. Therefore, a zero notification length is valid and
+ * should not result in an error.
+ */
+ if (!skb->len)
goto errout;
- }
rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
return 0;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3ad2287..bbc3b4b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1253,6 +1253,7 @@
struct sock *sk = skb->sk;
struct sk_buff_head *q;
unsigned long flags;
+ bool is_zerocopy;
u32 lo, hi;
u16 len;
@@ -1267,6 +1268,7 @@
len = uarg->len;
lo = uarg->id;
hi = uarg->id + len - 1;
+ is_zerocopy = uarg->zerocopy;
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
@@ -1274,7 +1276,7 @@
serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY;
serr->ee.ee_data = hi;
serr->ee.ee_info = lo;
- if (!uarg->zerocopy)
+ if (!is_zerocopy)
serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED;
q = &sk->sk_error_queue;
diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c
index 2a6733a..5d38e90 100644
--- a/net/ethtool/eeprom.c
+++ b/net/ethtool/eeprom.c
@@ -95,7 +95,7 @@
if (dev->sfp_bus)
return sfp_get_module_eeprom_by_page(dev->sfp_bus, page_data, extack);
- if (ops->get_module_info)
+ if (ops->get_module_eeprom_by_page)
return ops->get_module_eeprom_by_page(dev, page_data, extack);
return -EOPNOTSUPP;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 3fa7a39..baa5d10 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1421,7 +1421,7 @@
if (eeprom.offset + eeprom.len > total_len)
return -EINVAL;
- data = kmalloc(PAGE_SIZE, GFP_USER);
+ data = kzalloc(PAGE_SIZE, GFP_USER);
if (!data)
return -ENOMEM;
@@ -1486,7 +1486,7 @@
if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev))
return -EINVAL;
- data = kmalloc(PAGE_SIZE, GFP_USER);
+ data = kzalloc(PAGE_SIZE, GFP_USER);
if (!data)
return -ENOMEM;
@@ -1765,7 +1765,7 @@
return -EFAULT;
test.len = test_len;
- data = kmalloc_array(test_len, sizeof(u64), GFP_USER);
+ data = kcalloc(test_len, sizeof(u64), GFP_USER);
if (!data)
return -ENOMEM;
@@ -2293,7 +2293,7 @@
ret = ethtool_tunable_valid(&tuna);
if (ret)
return ret;
- data = kmalloc(tuna.len, GFP_USER);
+ data = kzalloc(tuna.len, GFP_USER);
if (!data)
return -ENOMEM;
ret = ops->get_tunable(dev, &tuna, data);
@@ -2485,7 +2485,7 @@
ret = ethtool_phy_tunable_valid(&tuna);
if (ret)
return ret;
- data = kmalloc(tuna.len, GFP_USER);
+ data = kzalloc(tuna.len, GFP_USER);
if (!data)
return -ENOMEM;
if (phy_drv_tunable) {
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index b3029ff..2d51b7a 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -353,6 +353,8 @@
int len = 0;
int ret;
+ len += nla_total_size(0); /* ETHTOOL_A_STRSET_STRINGSETS */
+
for (i = 0; i < ETH_SS_COUNT; i++) {
const struct strset_info *set_info = &data->sets[i];
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f17870e..2f94d22 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -575,7 +575,7 @@
return err;
}
- if (!inet_sk(sk)->inet_num && inet_autobind(sk))
+ if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk))
return -EAGAIN;
return sk->sk_prot->connect(sk, uaddr, addr_len);
}
@@ -803,7 +803,7 @@
sock_rps_record_flow(sk);
/* We may need to bind the socket. */
- if (!inet_sk(sk)->inet_num && !sk->sk_prot->no_autobind &&
+ if (data_race(!inet_sk(sk)->inet_num) && !sk->sk_prot->no_autobind &&
inet_autobind(sk))
return -EAGAIN;
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index bfaf327..e0480c6 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -472,6 +472,7 @@
kfree(doi_def->map.std->lvl.local);
kfree(doi_def->map.std->cat.cipso);
kfree(doi_def->map.std->cat.local);
+ kfree(doi_def->map.std);
break;
}
kfree(doi_def);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 2e35f68da..1c6429c 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1989,7 +1989,7 @@
return -EAFNOSUPPORT;
if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0)
- BUG();
+ return -EINVAL;
if (tb[IFLA_INET_CONF]) {
nla_for_each_nested(a, tb[IFLA_INET_CONF], rem)
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 7b6931a..752e392 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -759,6 +759,13 @@
icmp_param.data_len = room;
icmp_param.head_len = sizeof(struct icmphdr);
+ /* if we don't have a source address at this point, fall back to the
+ * dummy address instead of sending out a packet with a source address
+ * of 0.0.0.0
+ */
+ if (!fl4.saddr)
+ fl4.saddr = htonl(INADDR_DUMMY);
+
icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);
ende:
ip_rt_put(rt);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 7b272bb..6b3c558 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1801,6 +1801,7 @@
while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) {
in_dev->mc_list = i->next_rcu;
in_dev->mc_count--;
+ ip_mc_clear_src(i);
ip_ma_put(i);
}
}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 1c9f71a..95a7183 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -954,6 +954,7 @@
struct sock *sk;
struct net *net = dev_net(skb->dev);
struct icmphdr *icmph = icmp_hdr(skb);
+ bool rc = false;
/* We assume the packet has already been checked by icmp_rcv */
@@ -968,14 +969,15 @@
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
pr_debug("rcv on socket %p\n", sk);
- if (skb2)
- ping_queue_rcv_skb(sk, skb2);
+ if (skb2 && !ping_queue_rcv_skb(sk, skb2))
+ rc = true;
sock_put(sk);
- return true;
}
- pr_debug("no socket, dropping\n");
- return false;
+ if (!rc)
+ pr_debug("no socket, dropping\n");
+
+ return rc;
}
EXPORT_SYMBOL_GPL(ping_rcv);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f6787c5..6a36ac9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2056,6 +2056,19 @@
return err;
}
+/* get device for dst_alloc with local routes */
+static struct net_device *ip_rt_get_dev(struct net *net,
+ const struct fib_result *res)
+{
+ struct fib_nh_common *nhc = res->fi ? res->nhc : NULL;
+ struct net_device *dev = NULL;
+
+ if (nhc)
+ dev = l3mdev_master_dev_rcu(nhc->nhc_dev);
+
+ return dev ? : net->loopback_dev;
+}
+
/*
* NOTE. We drop all the packets that has local source
* addresses, because every properly looped back packet
@@ -2212,7 +2225,7 @@
}
}
- rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev,
+ rth = rt_dst_alloc(ip_rt_get_dev(net, res),
flags | RTCF_LOCAL, res->type,
IN_DEV_ORCONF(in_dev, NOPOLICY), false);
if (!rth)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 15f5504..1307ad0 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2607,6 +2607,9 @@
{
struct udp_sock *up = udp_sk(sk);
bool slow = lock_sock_fast(sk);
+
+ /* protects from races with udp_abort() */
+ sock_set_flag(sk, SOCK_DEAD);
udp_flush_pending_frames(sk);
unlock_sock_fast(sk, slow);
if (static_branch_unlikely(&udp_encap_needed_key)) {
@@ -2857,10 +2860,17 @@
{
lock_sock(sk);
+ /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing
+ * with close()
+ */
+ if (sock_flag(sk, SOCK_DEAD))
+ goto out;
+
sk->sk_err = err;
sk->sk_error_report(sk);
__udp_disconnect(sk, 0);
+out:
release_sock(sk);
return 0;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b0ef65e..701eb82 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5827,7 +5827,7 @@
return -EAFNOSUPPORT;
if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0)
- BUG();
+ return -EINVAL;
if (tb[IFLA_INET6_TOKEN]) {
err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]),
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index e204163..92f3235 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -135,6 +135,17 @@
}
EXPORT_SYMBOL_GPL(nft_fib6_eval_type);
+static bool nft_fib_v6_skip_icmpv6(const struct sk_buff *skb, u8 next, const struct ipv6hdr *iph)
+{
+ if (likely(next != IPPROTO_ICMPV6))
+ return false;
+
+ if (ipv6_addr_type(&iph->saddr) != IPV6_ADDR_ANY)
+ return false;
+
+ return ipv6_addr_type(&iph->daddr) & IPV6_ADDR_LINKLOCAL;
+}
+
void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
const struct nft_pktinfo *pkt)
{
@@ -163,10 +174,13 @@
lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph);
- if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
- nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
- nft_fib_store_result(dest, priv, nft_in(pkt));
- return;
+ if (nft_hook(pkt) == NF_INET_PRE_ROUTING ||
+ nft_hook(pkt) == NF_INET_INGRESS) {
+ if (nft_fib_is_loopback(pkt->skb, nft_in(pkt)) ||
+ nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) {
+ nft_fib_store_result(dest, priv, nft_in(pkt));
+ return;
+ }
}
*dest = 0;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 199b080..3fcd86f4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1598,6 +1598,9 @@
{
struct udp_sock *up = udp_sk(sk);
lock_sock(sk);
+
+ /* protects from races with udp_abort() */
+ sock_set_flag(sk, SOCK_DEAD);
udp_v6_flush_pending_frames(sk);
release_sock(sk);
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 1c572c8..6201965 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1066,11 +1066,6 @@
goto partial_message;
}
- if (skb_has_frag_list(head)) {
- kfree_skb_list(skb_shinfo(head)->frag_list);
- skb_shinfo(head)->frag_list = NULL;
- }
-
if (head != kcm->seq_skb)
kfree_skb(head);
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 9245c04..fc34ae2 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -4,7 +4,7 @@
*
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2019, 2021 Intel Corporation
*/
#include <linux/debugfs.h>
@@ -387,10 +387,17 @@
size_t count, loff_t *ppos)
{
struct ieee80211_local *local = file->private_data;
+ int ret;
rtnl_lock();
+ wiphy_lock(local->hw.wiphy);
__ieee80211_suspend(&local->hw, NULL);
- __ieee80211_resume(&local->hw);
+ ret = __ieee80211_resume(&local->hw);
+ wiphy_unlock(local->hw.wiphy);
+
+ if (ret)
+ cfg80211_shutdown_all_interfaces(local->hw.wiphy);
+
rtnl_unlock();
return count;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 214404a..648696b 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1442,7 +1442,7 @@
rcu_read_lock();
chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
- if (WARN_ON_ONCE(!chanctx_conf)) {
+ if (!chanctx_conf) {
rcu_read_unlock();
return NULL;
}
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 2e2f73a4..137fa4c 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -476,14 +476,7 @@
GFP_KERNEL);
}
- /* APs need special treatment */
if (sdata->vif.type == NL80211_IFTYPE_AP) {
- struct ieee80211_sub_if_data *vlan, *tmpsdata;
-
- /* down all dependent devices, that is VLANs */
- list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans,
- u.vlan.list)
- dev_close(vlan->dev);
WARN_ON(!list_empty(&sdata->u.ap.vlans));
} else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
/* remove all packets in parent bc_buf pointing to this dev */
@@ -641,6 +634,15 @@
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+ /* close all dependent VLAN interfaces before locking wiphy */
+ if (sdata->vif.type == NL80211_IFTYPE_AP) {
+ struct ieee80211_sub_if_data *vlan, *tmpsdata;
+
+ list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans,
+ u.vlan.list)
+ dev_close(vlan->dev);
+ }
+
wiphy_lock(sdata->local->hw.wiphy);
ieee80211_do_stop(sdata, true);
wiphy_unlock(sdata->local->hw.wiphy);
@@ -1591,6 +1593,9 @@
switch (sdata->vif.type) {
case NL80211_IFTYPE_AP:
+ if (!list_empty(&sdata->u.ap.vlans))
+ return -EBUSY;
+ break;
case NL80211_IFTYPE_STATION:
case NL80211_IFTYPE_ADHOC:
case NL80211_IFTYPE_OCB:
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 62145e5..f33a3ac 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -252,6 +252,7 @@
struct ieee80211_local *local =
container_of(work, struct ieee80211_local, restart_work);
struct ieee80211_sub_if_data *sdata;
+ int ret;
/* wait for scan work complete */
flush_workqueue(local->workqueue);
@@ -301,8 +302,12 @@
/* wait for all packet processing to be done */
synchronize_net();
- ieee80211_reconfig(local);
+ ret = ieee80211_reconfig(local);
wiphy_unlock(local->hw.wiphy);
+
+ if (ret)
+ cfg80211_shutdown_all_interfaces(local->hw.wiphy);
+
rtnl_unlock();
}
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 2480bd0..3f2aad2 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4062,10 +4062,14 @@
if (elems.mbssid_config_ie)
bss_conf->profile_periodicity =
elems.mbssid_config_ie->profile_periodicity;
+ else
+ bss_conf->profile_periodicity = 0;
if (elems.ext_capab_len >= 11 &&
(elems.ext_capab[10] & WLAN_EXT_CAPA11_EMA_SUPPORT))
bss_conf->ema_ap = true;
+ else
+ bss_conf->ema_ap = false;
/* continue assoc process */
ifmgd->assoc_data->timeout = jiffies;
@@ -5802,12 +5806,16 @@
beacon_ies->data, beacon_ies->len);
if (elem && elem->datalen >= 3)
sdata->vif.bss_conf.profile_periodicity = elem->data[2];
+ else
+ sdata->vif.bss_conf.profile_periodicity = 0;
elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY,
beacon_ies->data, beacon_ies->len);
if (elem && elem->datalen >= 11 &&
(elem->data[10] & WLAN_EXT_CAPA11_EMA_SUPPORT))
sdata->vif.bss_conf.ema_ap = true;
+ else
+ sdata->vif.bss_conf.ema_ap = false;
} else {
assoc_data->timeout = jiffies;
assoc_data->timeout_started = true;
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 6487b05..a6f3fb4 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -1514,7 +1514,7 @@
(info->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO))
return;
- if (time_is_before_jiffies(mi->sample_time))
+ if (time_is_after_jiffies(mi->sample_time))
return;
mi->sample_time = jiffies + MINSTREL_SAMPLE_INTERVAL;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 1bb43ed..af0ef45 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2240,17 +2240,15 @@
sc = le16_to_cpu(hdr->seq_ctrl);
frag = sc & IEEE80211_SCTL_FRAG;
- if (is_multicast_ether_addr(hdr->addr1)) {
- I802_DEBUG_INC(rx->local->dot11MulticastReceivedFrameCount);
- goto out_no_led;
- }
-
if (rx->sta)
cache = &rx->sta->frags;
if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
goto out;
+ if (is_multicast_ether_addr(hdr->addr1))
+ return RX_DROP_MONITOR;
+
I802_DEBUG_INC(rx->local->rx_handlers_fragments);
if (skb_linearize(rx->skb))
@@ -2376,7 +2374,6 @@
out:
ieee80211_led_rx(rx->local);
- out_no_led:
if (rx->sta)
rx->sta->rx_stats.packets++;
return RX_CONTINUE;
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index d4cc9ac..6b50cb5 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -251,13 +251,24 @@
struct ieee80211_mgmt *mgmt = (void *)skb->data;
struct ieee80211_bss *bss;
struct ieee80211_channel *channel;
+ size_t min_hdr_len = offsetof(struct ieee80211_mgmt,
+ u.probe_resp.variable);
+
+ if (!ieee80211_is_probe_resp(mgmt->frame_control) &&
+ !ieee80211_is_beacon(mgmt->frame_control) &&
+ !ieee80211_is_s1g_beacon(mgmt->frame_control))
+ return;
if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
- if (skb->len < 15)
- return;
- } else if (skb->len < 24 ||
- (!ieee80211_is_probe_resp(mgmt->frame_control) &&
- !ieee80211_is_beacon(mgmt->frame_control)))
+ if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+ min_hdr_len = offsetof(struct ieee80211_ext,
+ u.s1g_short_beacon.variable);
+ else
+ min_hdr_len = offsetof(struct ieee80211_ext,
+ u.s1g_beacon);
+ }
+
+ if (skb->len < min_hdr_len)
return;
sdata1 = rcu_dereference(local->scan_sdata);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 0b719f3..2651498 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2014,27 +2014,10 @@
ieee80211_tx(sdata, sta, skb, false);
}
-bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
- struct net_device *dev)
+static bool ieee80211_validate_radiotap_len(struct sk_buff *skb)
{
- struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
- struct ieee80211_radiotap_iterator iterator;
struct ieee80211_radiotap_header *rthdr =
- (struct ieee80211_radiotap_header *) skb->data;
- struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
- struct ieee80211_supported_band *sband =
- local->hw.wiphy->bands[info->band];
- int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len,
- NULL);
- u16 txflags;
- u16 rate = 0;
- bool rate_found = false;
- u8 rate_retries = 0;
- u16 rate_flags = 0;
- u8 mcs_known, mcs_flags, mcs_bw;
- u16 vht_known;
- u8 vht_mcs = 0, vht_nss = 0;
- int i;
+ (struct ieee80211_radiotap_header *)skb->data;
/* check for not even having the fixed radiotap header part */
if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header)))
@@ -2048,6 +2031,32 @@
if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data)))
return false; /* skb too short for claimed rt header extent */
+ return true;
+}
+
+bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
+ struct ieee80211_radiotap_iterator iterator;
+ struct ieee80211_radiotap_header *rthdr =
+ (struct ieee80211_radiotap_header *) skb->data;
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len,
+ NULL);
+ u16 txflags;
+ u16 rate = 0;
+ bool rate_found = false;
+ u8 rate_retries = 0;
+ u16 rate_flags = 0;
+ u8 mcs_known, mcs_flags, mcs_bw;
+ u16 vht_known;
+ u8 vht_mcs = 0, vht_nss = 0;
+ int i;
+
+ if (!ieee80211_validate_radiotap_len(skb))
+ return false;
+
info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT |
IEEE80211_TX_CTL_DONTFRAG;
@@ -2186,6 +2195,9 @@
return false;
if (rate_found) {
+ struct ieee80211_supported_band *sband =
+ local->hw.wiphy->bands[info->band];
+
info->control.flags |= IEEE80211_TX_CTRL_RATE_INJECT;
for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) {
@@ -2199,7 +2211,7 @@
} else if (rate_flags & IEEE80211_TX_RC_VHT_MCS) {
ieee80211_rate_set_vht(info->control.rates, vht_mcs,
vht_nss);
- } else {
+ } else if (sband) {
for (i = 0; i < sband->n_bitrates; i++) {
if (rate * 5 != sband->bitrates[i].bitrate)
continue;
@@ -2236,8 +2248,8 @@
info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS |
IEEE80211_TX_CTL_INJECTED;
- /* Sanity-check and process the injection radiotap header */
- if (!ieee80211_parse_tx_radiotap(skb, dev))
+ /* Sanity-check the length of the radiotap header */
+ if (!ieee80211_validate_radiotap_len(skb))
goto fail;
/* we now know there is a radiotap header with a length we can use */
@@ -2351,6 +2363,14 @@
ieee80211_select_queue_80211(sdata, skb, hdr);
skb_set_queue_mapping(skb, ieee80211_ac_from_tid(skb->priority));
+ /*
+ * Process the radiotap header. This will now take into account the
+ * selected chandef above to accurately set injection rates and
+ * retransmissions.
+ */
+ if (!ieee80211_parse_tx_radiotap(skb, dev))
+ goto fail_rcu;
+
/* remove the injection radiotap header */
skb_pull(skb, len_rthdr);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 0a0481f..060059e 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -947,7 +947,7 @@
switch (elem->data[0]) {
case WLAN_EID_EXT_HE_MU_EDCA:
- if (len == sizeof(*elems->mu_edca_param_set)) {
+ if (len >= sizeof(*elems->mu_edca_param_set)) {
elems->mu_edca_param_set = data;
if (crc)
*crc = crc32_be(*crc, (void *)elem,
@@ -968,7 +968,7 @@
}
break;
case WLAN_EID_EXT_UORA:
- if (len == 1)
+ if (len >= 1)
elems->uora_element = data;
break;
case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME:
@@ -976,7 +976,7 @@
elems->max_channel_switch_time = data;
break;
case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION:
- if (len == sizeof(*elems->mbssid_config_ie))
+ if (len >= sizeof(*elems->mbssid_config_ie))
elems->mbssid_config_ie = data;
break;
case WLAN_EID_EXT_HE_SPR:
@@ -985,7 +985,7 @@
elems->he_spr = data;
break;
case WLAN_EID_EXT_HE_6GHZ_CAPA:
- if (len == sizeof(*elems->he_6ghz_capa))
+ if (len >= sizeof(*elems->he_6ghz_capa))
elems->he_6ghz_capa = data;
break;
}
@@ -1074,14 +1074,14 @@
switch (id) {
case WLAN_EID_LINK_ID:
- if (elen + 2 != sizeof(struct ieee80211_tdls_lnkie)) {
+ if (elen + 2 < sizeof(struct ieee80211_tdls_lnkie)) {
elem_parse_failed = true;
break;
}
elems->lnk_id = (void *)(pos - 2);
break;
case WLAN_EID_CHAN_SWITCH_TIMING:
- if (elen != sizeof(struct ieee80211_ch_switch_timing)) {
+ if (elen < sizeof(struct ieee80211_ch_switch_timing)) {
elem_parse_failed = true;
break;
}
@@ -1244,7 +1244,7 @@
elems->sec_chan_offs = (void *)pos;
break;
case WLAN_EID_CHAN_SWITCH_PARAM:
- if (elen !=
+ if (elen <
sizeof(*elems->mesh_chansw_params_ie)) {
elem_parse_failed = true;
break;
@@ -1253,7 +1253,7 @@
break;
case WLAN_EID_WIDE_BW_CHANNEL_SWITCH:
if (!action ||
- elen != sizeof(*elems->wide_bw_chansw_ie)) {
+ elen < sizeof(*elems->wide_bw_chansw_ie)) {
elem_parse_failed = true;
break;
}
@@ -1272,7 +1272,7 @@
ie = cfg80211_find_ie(WLAN_EID_WIDE_BW_CHANNEL_SWITCH,
pos, elen);
if (ie) {
- if (ie[1] == sizeof(*elems->wide_bw_chansw_ie))
+ if (ie[1] >= sizeof(*elems->wide_bw_chansw_ie))
elems->wide_bw_chansw_ie =
(void *)(ie + 2);
else
@@ -1316,7 +1316,7 @@
elems->cisco_dtpc_elem = pos;
break;
case WLAN_EID_ADDBA_EXT:
- if (elen != sizeof(struct ieee80211_addba_ext_ie)) {
+ if (elen < sizeof(struct ieee80211_addba_ext_ie)) {
elem_parse_failed = true;
break;
}
@@ -1342,7 +1342,7 @@
elem, elems);
break;
case WLAN_EID_S1G_CAPABILITIES:
- if (elen == sizeof(*elems->s1g_capab))
+ if (elen >= sizeof(*elems->s1g_capab))
elems->s1g_capab = (void *)pos;
else
elem_parse_failed = true;
@@ -2178,8 +2178,6 @@
list_for_each_entry(ctx, &local->chanctx_list, list)
ctx->driver_present = false;
mutex_unlock(&local->chanctx_mtx);
-
- cfg80211_shutdown_all_interfaces(local->hw.wiphy);
}
static void ieee80211_assign_chanctx(struct ieee80211_local *local,
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 6b825fb..9b263f2 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -356,6 +356,8 @@
length--;
continue;
default:
+ if (length < 2)
+ return;
opsize = *ptr++;
if (opsize < 2) /* "silly options" */
return;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5edc686..6323500 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -280,11 +280,13 @@
/* try to fetch required memory from subflow */
if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
- if (ssk->sk_forward_alloc < skb->truesize)
+ int amount = sk_mem_pages(skb->truesize) << SK_MEM_QUANTUM_SHIFT;
+
+ if (ssk->sk_forward_alloc < amount)
goto drop;
- __sk_mem_reclaim(ssk, skb->truesize);
- if (!sk_rmem_schedule(sk, skb, skb->truesize))
- goto drop;
+
+ ssk->sk_forward_alloc -= amount;
+ sk->sk_forward_alloc += amount;
}
/* the skb map_seq accounts for the skb offset:
@@ -668,18 +670,22 @@
/* In most cases we will be able to lock the mptcp socket. If its already
* owned, we need to defer to the work queue to avoid ABBA deadlock.
*/
-static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
+static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
{
struct sock *sk = (struct sock *)msk;
unsigned int moved = 0;
if (inet_sk_state_load(sk) == TCP_CLOSE)
- return;
-
- mptcp_data_lock(sk);
+ return false;
__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
__mptcp_ofo_queue(msk);
+ if (unlikely(ssk->sk_err)) {
+ if (!sock_owned_by_user(sk))
+ __mptcp_error_report(sk);
+ else
+ set_bit(MPTCP_ERROR_REPORT, &msk->flags);
+ }
/* If the moves have caught up with the DATA_FIN sequence number
* it's time to ack the DATA_FIN and change socket state, but
@@ -688,7 +694,7 @@
*/
if (mptcp_pending_data_fin(sk, NULL))
mptcp_schedule_work(sk);
- mptcp_data_unlock(sk);
+ return moved > 0;
}
void mptcp_data_ready(struct sock *sk, struct sock *ssk)
@@ -696,7 +702,6 @@
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(sk);
int sk_rbuf, ssk_rbuf;
- bool wake;
/* The peer can send data while we are shutting down this
* subflow at msk destruction time, but we must avoid enqueuing
@@ -705,28 +710,22 @@
if (unlikely(subflow->disposable))
return;
- /* move_skbs_to_msk below can legitly clear the data_avail flag,
- * but we will need later to properly woke the reader, cache its
- * value
- */
- wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL;
- if (wake)
- set_bit(MPTCP_DATA_READY, &msk->flags);
-
ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
if (unlikely(ssk_rbuf > sk_rbuf))
sk_rbuf = ssk_rbuf;
- /* over limit? can't append more skbs to msk */
+ /* over limit? can't append more skbs to msk, Also, no need to wake-up*/
if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
- goto wake;
+ return;
- move_skbs_to_msk(msk, ssk);
-
-wake:
- if (wake)
+ /* Wake-up the reader only for in-sequence data */
+ mptcp_data_lock(sk);
+ if (move_skbs_to_msk(msk, ssk)) {
+ set_bit(MPTCP_DATA_READY, &msk->flags);
sk->sk_data_ready(sk);
+ }
+ mptcp_data_unlock(sk);
}
static bool mptcp_do_flush_join_list(struct mptcp_sock *msk)
@@ -858,7 +857,7 @@
sock_owned_by_me(sk);
mptcp_for_each_subflow(msk, subflow) {
- if (subflow->data_avail)
+ if (READ_ONCE(subflow->data_avail))
return mptcp_subflow_tcp_sock(subflow);
}
@@ -1955,6 +1954,9 @@
done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
mptcp_data_unlock(sk);
tcp_cleanup_rbuf(ssk, moved);
+
+ if (unlikely(ssk->sk_err))
+ __mptcp_error_report(sk);
unlock_sock_fast(ssk, slowpath);
} while (!done);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 0c6f99c..385796f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -362,7 +362,6 @@
enum mptcp_data_avail {
MPTCP_SUBFLOW_NODATA,
MPTCP_SUBFLOW_DATA_AVAIL,
- MPTCP_SUBFLOW_OOO_DATA
};
struct mptcp_delegated_action {
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ef3d037..be1de40 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -784,10 +784,10 @@
return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32));
}
-static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
+static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
{
- WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
- ssn, subflow->map_subflow_seq, subflow->map_data_len);
+ pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
+ ssn, subflow->map_subflow_seq, subflow->map_data_len);
}
static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb)
@@ -812,13 +812,13 @@
/* Mapping covers data later in the subflow stream,
* currently unsupported.
*/
- warn_bad_map(subflow, ssn);
+ dbg_bad_map(subflow, ssn);
return false;
}
if (unlikely(!before(ssn, subflow->map_subflow_seq +
subflow->map_data_len))) {
/* Mapping does covers past subflow data, invalid */
- warn_bad_map(subflow, ssn + skb->len);
+ dbg_bad_map(subflow, ssn);
return false;
}
return true;
@@ -1000,7 +1000,7 @@
struct sk_buff *skb;
if (!skb_peek(&ssk->sk_receive_queue))
- subflow->data_avail = 0;
+ WRITE_ONCE(subflow->data_avail, 0);
if (subflow->data_avail)
return true;
@@ -1039,18 +1039,13 @@
ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
ack_seq);
- if (ack_seq == old_ack) {
- subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
- break;
- } else if (after64(ack_seq, old_ack)) {
- subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA;
- break;
+ if (unlikely(before64(ack_seq, old_ack))) {
+ mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
+ continue;
}
- /* only accept in-sequence mapping. Old values are spurious
- * retransmission
- */
- mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
+ break;
}
return true;
@@ -1065,12 +1060,11 @@
* subflow_error_report() will introduce the appropriate barriers
*/
ssk->sk_err = EBADMSG;
- ssk->sk_error_report(ssk);
tcp_set_state(ssk, TCP_CLOSE);
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMPTCP;
tcp_send_active_reset(ssk, GFP_ATOMIC);
- subflow->data_avail = 0;
+ WRITE_ONCE(subflow->data_avail, 0);
return false;
}
@@ -1080,7 +1074,7 @@
subflow->map_seq = READ_ONCE(msk->ack_seq);
subflow->map_data_len = skb->len;
subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
- subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
return true;
}
@@ -1092,7 +1086,7 @@
if (subflow->map_valid &&
mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) {
subflow->map_valid = 0;
- subflow->data_avail = 0;
+ WRITE_ONCE(subflow->data_avail, 0);
pr_debug("Done with mapping: seq=%u data_len=%u",
subflow->map_subflow_seq,
@@ -1120,41 +1114,6 @@
*full_space = tcp_full_space(sk);
}
-static void subflow_data_ready(struct sock *sk)
-{
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- u16 state = 1 << inet_sk_state_load(sk);
- struct sock *parent = subflow->conn;
- struct mptcp_sock *msk;
-
- msk = mptcp_sk(parent);
- if (state & TCPF_LISTEN) {
- /* MPJ subflow are removed from accept queue before reaching here,
- * avoid stray wakeups
- */
- if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue))
- return;
-
- set_bit(MPTCP_DATA_READY, &msk->flags);
- parent->sk_data_ready(parent);
- return;
- }
-
- WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable &&
- !subflow->mp_join && !(state & TCPF_CLOSE));
-
- if (mptcp_subflow_data_available(sk))
- mptcp_data_ready(parent, sk);
-}
-
-static void subflow_write_space(struct sock *ssk)
-{
- struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
-
- mptcp_propagate_sndbuf(sk, ssk);
- mptcp_write_space(sk);
-}
-
void __mptcp_error_report(struct sock *sk)
{
struct mptcp_subflow_context *subflow;
@@ -1195,6 +1154,43 @@
mptcp_data_unlock(sk);
}
+static void subflow_data_ready(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ u16 state = 1 << inet_sk_state_load(sk);
+ struct sock *parent = subflow->conn;
+ struct mptcp_sock *msk;
+
+ msk = mptcp_sk(parent);
+ if (state & TCPF_LISTEN) {
+ /* MPJ subflow are removed from accept queue before reaching here,
+ * avoid stray wakeups
+ */
+ if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue))
+ return;
+
+ set_bit(MPTCP_DATA_READY, &msk->flags);
+ parent->sk_data_ready(parent);
+ return;
+ }
+
+ WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable &&
+ !subflow->mp_join && !(state & TCPF_CLOSE));
+
+ if (mptcp_subflow_data_available(sk))
+ mptcp_data_ready(parent, sk);
+ else if (unlikely(sk->sk_err))
+ subflow_error_report(sk);
+}
+
+static void subflow_write_space(struct sock *ssk)
+{
+ struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
+
+ mptcp_propagate_sndbuf(sk, ssk);
+ mptcp_write_space(sk);
+}
+
static struct inet_connection_sock_af_ops *
subflow_default_af_ops(struct sock *sk)
{
@@ -1505,6 +1501,8 @@
*/
if (mptcp_subflow_data_available(sk))
mptcp_data_ready(parent, sk);
+ else if (unlikely(sk->sk_err))
+ subflow_error_report(sk);
subflow_sched_work_if_closed(mptcp_sk(parent), sk);
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index b100c04..3d6d494 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -31,6 +31,9 @@
int length = (th->doff * 4) - sizeof(*th);
u8 buf[40], *ptr;
+ if (unlikely(length < 0))
+ return false;
+
ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf);
if (ptr == NULL)
return false;
@@ -47,6 +50,8 @@
length--;
continue;
default:
+ if (length < 2)
+ return true;
opsize = *ptr++;
if (opsize < 2)
return true;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 72bc759..bf4d6ec 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4364,44 +4364,7 @@
err = nf_tables_set_alloc_name(&ctx, set, name);
kfree(name);
if (err < 0)
- goto err_set_alloc_name;
-
- if (nla[NFTA_SET_EXPR]) {
- expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]);
- if (IS_ERR(expr)) {
- err = PTR_ERR(expr);
- goto err_set_alloc_name;
- }
- set->exprs[0] = expr;
- set->num_exprs++;
- } else if (nla[NFTA_SET_EXPRESSIONS]) {
- struct nft_expr *expr;
- struct nlattr *tmp;
- int left;
-
- if (!(flags & NFT_SET_EXPR)) {
- err = -EINVAL;
- goto err_set_alloc_name;
- }
- i = 0;
- nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
- if (i == NFT_SET_EXPR_MAX) {
- err = -E2BIG;
- goto err_set_init;
- }
- if (nla_type(tmp) != NFTA_LIST_ELEM) {
- err = -EINVAL;
- goto err_set_init;
- }
- expr = nft_set_elem_expr_alloc(&ctx, set, tmp);
- if (IS_ERR(expr)) {
- err = PTR_ERR(expr);
- goto err_set_init;
- }
- set->exprs[i++] = expr;
- set->num_exprs++;
- }
- }
+ goto err_set_name;
udata = NULL;
if (udlen) {
@@ -4413,20 +4376,19 @@
INIT_LIST_HEAD(&set->catchall_list);
set->table = table;
write_pnet(&set->net, net);
- set->ops = ops;
+ set->ops = ops;
set->ktype = ktype;
- set->klen = desc.klen;
+ set->klen = desc.klen;
set->dtype = dtype;
set->objtype = objtype;
- set->dlen = desc.dlen;
+ set->dlen = desc.dlen;
set->flags = flags;
- set->size = desc.size;
+ set->size = desc.size;
set->policy = policy;
- set->udlen = udlen;
- set->udata = udata;
+ set->udlen = udlen;
+ set->udata = udata;
set->timeout = timeout;
set->gc_int = gc_int;
- set->handle = nf_tables_alloc_handle(table);
set->field_count = desc.field_count;
for (i = 0; i < desc.field_count; i++)
@@ -4436,20 +4398,59 @@
if (err < 0)
goto err_set_init;
+ if (nla[NFTA_SET_EXPR]) {
+ expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]);
+ if (IS_ERR(expr)) {
+ err = PTR_ERR(expr);
+ goto err_set_expr_alloc;
+ }
+ set->exprs[0] = expr;
+ set->num_exprs++;
+ } else if (nla[NFTA_SET_EXPRESSIONS]) {
+ struct nft_expr *expr;
+ struct nlattr *tmp;
+ int left;
+
+ if (!(flags & NFT_SET_EXPR)) {
+ err = -EINVAL;
+ goto err_set_expr_alloc;
+ }
+ i = 0;
+ nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
+ if (i == NFT_SET_EXPR_MAX) {
+ err = -E2BIG;
+ goto err_set_expr_alloc;
+ }
+ if (nla_type(tmp) != NFTA_LIST_ELEM) {
+ err = -EINVAL;
+ goto err_set_expr_alloc;
+ }
+ expr = nft_set_elem_expr_alloc(&ctx, set, tmp);
+ if (IS_ERR(expr)) {
+ err = PTR_ERR(expr);
+ goto err_set_expr_alloc;
+ }
+ set->exprs[i++] = expr;
+ set->num_exprs++;
+ }
+ }
+
+ set->handle = nf_tables_alloc_handle(table);
+
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
if (err < 0)
- goto err_set_trans;
+ goto err_set_expr_alloc;
list_add_tail_rcu(&set->list, &table->sets);
table->use++;
return 0;
-err_set_trans:
- ops->destroy(set);
-err_set_init:
+err_set_expr_alloc:
for (i = 0; i < set->num_exprs; i++)
nft_expr_destroy(&ctx, set->exprs[i]);
-err_set_alloc_name:
+
+ ops->destroy(set);
+err_set_init:
kfree(set->name);
err_set_name:
kvfree(set);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ae906eb..330ba68 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2683,7 +2683,7 @@
}
if (likely(saddr == NULL)) {
dev = packet_cached_dev_get(po);
- proto = po->num;
+ proto = READ_ONCE(po->num);
} else {
err = -EINVAL;
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2896,7 +2896,7 @@
if (likely(saddr == NULL)) {
dev = packet_cached_dev_get(po);
- proto = po->num;
+ proto = READ_ONCE(po->num);
} else {
err = -EINVAL;
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -3034,10 +3034,13 @@
struct sock *sk = sock->sk;
struct packet_sock *po = pkt_sk(sk);
- if (po->tx_ring.pg_vec)
+ /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy.
+ * tpacket_snd() will redo the check safely.
+ */
+ if (data_race(po->tx_ring.pg_vec))
return tpacket_snd(po, msg);
- else
- return packet_snd(sock, msg, len);
+
+ return packet_snd(sock, msg, len);
}
/*
@@ -3168,7 +3171,7 @@
/* prevents packet_notifier() from calling
* register_prot_hook()
*/
- po->num = 0;
+ WRITE_ONCE(po->num, 0);
__unregister_prot_hook(sk, true);
rcu_read_lock();
dev_curr = po->prot_hook.dev;
@@ -3178,17 +3181,17 @@
}
BUG_ON(po->running);
- po->num = proto;
+ WRITE_ONCE(po->num, proto);
po->prot_hook.type = proto;
if (unlikely(unlisted)) {
dev_put(dev);
po->prot_hook.dev = NULL;
- po->ifindex = -1;
+ WRITE_ONCE(po->ifindex, -1);
packet_cached_dev_reset(po);
} else {
po->prot_hook.dev = dev;
- po->ifindex = dev ? dev->ifindex : 0;
+ WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0);
packet_cached_dev_assign(po, dev);
}
}
@@ -3502,7 +3505,7 @@
uaddr->sa_family = AF_PACKET;
memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data));
rcu_read_lock();
- dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex);
+ dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex));
if (dev)
strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data));
rcu_read_unlock();
@@ -3517,16 +3520,18 @@
struct sock *sk = sock->sk;
struct packet_sock *po = pkt_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr);
+ int ifindex;
if (peer)
return -EOPNOTSUPP;
+ ifindex = READ_ONCE(po->ifindex);
sll->sll_family = AF_PACKET;
- sll->sll_ifindex = po->ifindex;
- sll->sll_protocol = po->num;
+ sll->sll_ifindex = ifindex;
+ sll->sll_protocol = READ_ONCE(po->num);
sll->sll_pkttype = 0;
rcu_read_lock();
- dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex);
+ dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
if (dev) {
sll->sll_hatype = dev->type;
sll->sll_halen = dev->addr_len;
@@ -4105,7 +4110,7 @@
}
if (msg == NETDEV_UNREGISTER) {
packet_cached_dev_reset(po);
- po->ifindex = -1;
+ WRITE_ONCE(po->ifindex, -1);
if (po->prot_hook.dev)
dev_put(po->prot_hook.dev);
po->prot_hook.dev = NULL;
@@ -4411,7 +4416,7 @@
was_running = po->running;
num = po->num;
if (was_running) {
- po->num = 0;
+ WRITE_ONCE(po->num, 0);
__unregister_prot_hook(sk, false);
}
spin_unlock(&po->bind_lock);
@@ -4446,7 +4451,7 @@
spin_lock(&po->bind_lock);
if (was_running) {
- po->num = num;
+ WRITE_ONCE(po->num, num);
register_prot_hook(sk);
}
spin_unlock(&po->bind_lock);
@@ -4616,8 +4621,8 @@
s,
refcount_read(&s->sk_refcnt),
s->sk_type,
- ntohs(po->num),
- po->ifindex,
+ ntohs(READ_ONCE(po->num)),
+ READ_ONCE(po->ifindex),
po->running,
atomic_read(&s->sk_rmem_alloc),
from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)),
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index c0477bec..f2efaa4 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -436,7 +436,7 @@
struct qrtr_sock *ipc;
struct sk_buff *skb;
struct qrtr_cb *cb;
- unsigned int size;
+ size_t size;
unsigned int ver;
size_t hdrlen;
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 4db109f..5b426dc 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -714,7 +714,7 @@
if (rds_cmsg_recv(inc, msg, rs)) {
ret = -EFAULT;
- goto out;
+ break;
}
rds_recvmsg_zcookie(rs, msg);
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 18edd9a..a656baa 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -904,14 +904,19 @@
}
err = ct_nat_execute(skb, ct, ctinfo, range, maniptype);
- if (err == NF_ACCEPT &&
- ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) {
- if (maniptype == NF_NAT_MANIP_SRC)
- maniptype = NF_NAT_MANIP_DST;
- else
- maniptype = NF_NAT_MANIP_SRC;
+ if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
+ if (ct->status & IPS_SRC_NAT) {
+ if (maniptype == NF_NAT_MANIP_SRC)
+ maniptype = NF_NAT_MANIP_DST;
+ else
+ maniptype = NF_NAT_MANIP_SRC;
- err = ct_nat_execute(skb, ct, ctinfo, range, maniptype);
+ err = ct_nat_execute(skb, ct, ctinfo, range,
+ maniptype);
+ } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
+ err = ct_nat_execute(skb, ct, ctinfo, NULL,
+ NF_NAT_MANIP_SRC);
+ }
}
return err;
#else
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 7d37638..9515428 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -943,7 +943,7 @@
}
tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
- if (!tcph)
+ if (!tcph || tcph->doff < 5)
return NULL;
return skb_header_pointer(skb, offset,
@@ -967,6 +967,8 @@
length--;
continue;
}
+ if (length < 2)
+ break;
opsize = *ptr++;
if (opsize < 2 || opsize > length)
break;
@@ -1104,6 +1106,8 @@
length--;
continue;
}
+ if (length < 2)
+ break;
opsize = *ptr++;
if (opsize < 2 || opsize > length)
break;
@@ -2338,7 +2342,7 @@
/* List of known Diffserv codepoints:
*
- * Least Effort (CS1)
+ * Least Effort (CS1, LE)
* Best Effort (CS0)
* Max Reliability & LLT "Lo" (TOS1)
* Max Throughput (TOS2)
@@ -2360,7 +2364,7 @@
* Total 25 codepoints.
*/
-/* List of traffic classes in RFC 4594:
+/* List of traffic classes in RFC 4594, updated by RFC 8622:
* (roughly descending order of contended priority)
* (roughly ascending order of uncontended throughput)
*
@@ -2375,7 +2379,7 @@
* Ops, Admin, Management (CS2,TOS1) - eg. ssh
* Standard Service (CS0 & unrecognised codepoints)
* High Throughput Data (AF1x,TOS2) - eg. web traffic
- * Low Priority Data (CS1) - eg. BitTorrent
+ * Low Priority Data (CS1,LE) - eg. BitTorrent
* Total 12 traffic classes.
*/
@@ -2391,7 +2395,7 @@
* Video Streaming (AF4x, AF3x, CS3)
* Bog Standard (CS0 etc.)
* High Throughput (AF1x, TOS2)
- * Background Traffic (CS1)
+ * Background Traffic (CS1, LE)
*
* Total 8 traffic classes.
*/
@@ -2435,7 +2439,7 @@
* Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4)
* Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2, TOS1)
* Best Effort (CS0, AF1x, TOS2, and those not specified)
- * Background Traffic (CS1)
+ * Background Traffic (CS1, LE)
*
* Total 4 traffic classes.
*/
@@ -2473,7 +2477,7 @@
static int cake_config_diffserv3(struct Qdisc *sch)
{
/* Simplified Diffserv structure with 3 tins.
- * Low Priority (CS1)
+ * Low Priority (CS1, LE)
* Best Effort
* Latency Sensitive (TOS4, VA, EF, CS6, CS7)
*/
diff --git a/net/socket.c b/net/socket.c
index 27e3e7d..4f2c6d2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1072,19 +1072,6 @@
* what to do with it - that's up to the protocol still.
*/
-/**
- * get_net_ns - increment the refcount of the network namespace
- * @ns: common namespace (net)
- *
- * Returns the net's common namespace.
- */
-
-struct ns_common *get_net_ns(struct ns_common *ns)
-{
- return &get_net(container_of(ns, struct net, ns))->ns;
-}
-EXPORT_SYMBOL_GPL(get_net_ns);
-
static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
struct socket *sock;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5a31307ce..5d1192c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -535,12 +535,14 @@
u->path.mnt = NULL;
state = sk->sk_state;
sk->sk_state = TCP_CLOSE;
+
+ skpair = unix_peer(sk);
+ unix_peer(sk) = NULL;
+
unix_state_unlock(sk);
wake_up_interruptible_all(&u->peer_wait);
- skpair = unix_peer(sk);
-
if (skpair != NULL) {
if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
unix_state_lock(skpair);
@@ -555,7 +557,6 @@
unix_dgram_peer_wake_disconnect(sk, skpair);
sock_put(skpair); /* It may now die */
- unix_peer(sk) = NULL;
}
/* Try to flush out this socket. Throw out buffers at least */
diff --git a/net/wireless/Makefile b/net/wireless/Makefile
index 2eee939..af590ae 100644
--- a/net/wireless/Makefile
+++ b/net/wireless/Makefile
@@ -28,7 +28,7 @@
@$(kecho) " GEN $@"
@(echo '#include "reg.h"'; \
echo 'const u8 shipped_regdb_certs[] = {'; \
- cat $^ ; \
+ echo | cat - $^ ; \
echo '};'; \
echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \
) > $@
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 6fbf7537..8d0883e8 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1340,6 +1340,11 @@
rdev->devlist_generation++;
wdev->registered = true;
+ if (wdev->netdev &&
+ sysfs_create_link(&wdev->netdev->dev.kobj, &rdev->wiphy.dev.kobj,
+ "phy80211"))
+ pr_err("failed to add phy80211 symlink to netdev!\n");
+
nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE);
}
@@ -1365,14 +1370,6 @@
if (ret)
goto out;
- if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj,
- "phy80211")) {
- pr_err("failed to add phy80211 symlink to netdev!\n");
- unregister_netdevice(dev);
- ret = -EINVAL;
- goto out;
- }
-
cfg80211_register_wdev(rdev, wdev);
ret = 0;
out:
diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
index 6bdd964..d245968 100644
--- a/net/wireless/pmsr.c
+++ b/net/wireless/pmsr.c
@@ -334,6 +334,7 @@
gfp_t gfp)
{
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+ struct cfg80211_pmsr_request *tmp, *prev, *to_free = NULL;
struct sk_buff *msg;
void *hdr;
@@ -364,9 +365,20 @@
nlmsg_free(msg);
free_request:
spin_lock_bh(&wdev->pmsr_lock);
- list_del(&req->list);
+ /*
+ * cfg80211_pmsr_process_abort() may have already moved this request
+ * to the free list, and will free it later. In this case, don't free
+ * it here.
+ */
+ list_for_each_entry_safe(tmp, prev, &wdev->pmsr_list, list) {
+ if (tmp == req) {
+ list_del(&req->list);
+ to_free = req;
+ break;
+ }
+ }
spin_unlock_bh(&wdev->pmsr_lock);
- kfree(req);
+ kfree(to_free);
}
EXPORT_SYMBOL_GPL(cfg80211_pmsr_complete);
diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c
index 9b959e3..0c3f05c 100644
--- a/net/wireless/sysfs.c
+++ b/net/wireless/sysfs.c
@@ -133,6 +133,10 @@
if (rdev->wiphy.registered && rdev->ops->resume)
ret = rdev_resume(rdev);
wiphy_unlock(&rdev->wiphy);
+
+ if (ret)
+ cfg80211_shutdown_all_interfaces(&rdev->wiphy);
+
rtnl_unlock();
return ret;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 7ec021a..18dba3d 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1059,6 +1059,9 @@
case NL80211_IFTYPE_MESH_POINT:
/* mesh should be handled? */
break;
+ case NL80211_IFTYPE_OCB:
+ cfg80211_leave_ocb(rdev, dev);
+ break;
default:
break;
}
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index f9b1952..1e9baa5 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -192,15 +192,20 @@
Elf32_Word const *symtab_shndx)
{
unsigned long offset;
+ unsigned short shndx = w2(sym->st_shndx);
int index;
- if (sym->st_shndx != SHN_XINDEX)
- return w2(sym->st_shndx);
+ if (shndx > SHN_UNDEF && shndx < SHN_LORESERVE)
+ return shndx;
- offset = (unsigned long)sym - (unsigned long)symtab;
- index = offset / sizeof(*sym);
+ if (shndx == SHN_XINDEX) {
+ offset = (unsigned long)sym - (unsigned long)symtab;
+ index = offset / sizeof(*sym);
- return w(symtab_shndx[index]);
+ return w(symtab_shndx[index]);
+ }
+
+ return 0;
}
static unsigned int get_shnum(Elf_Ehdr const *ehdr, Elf_Shdr const *shdr0)
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 6de5a7f..d2a9420 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -863,8 +863,7 @@
__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
#define __NR_mount_setattr 442
__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
-#define __NR_quotactl_path 443
-__SYSCALL(__NR_quotactl_path, sys_quotactl_path)
+/* 443 is reserved for quotactl_path */
#define __NR_landlock_create_ruleset 444
__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 7d66876..d1b3270 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -289,6 +289,9 @@
/* Address indicating an error return. */
#define INADDR_NONE ((unsigned long int) 0xffffffff)
+/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */
+#define INADDR_DUMMY ((unsigned long int) 0xc0000008)
+
/* Network number for local host loopback. */
#define IN_LOOPBACKNET 127
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 6061431..e9b619a 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -1094,7 +1094,7 @@
goto out_put_ctx;
}
if (xsk->fd == umem->fd)
- umem->rx_ring_setup_done = true;
+ umem->tx_ring_setup_done = true;
}
err = xsk_get_mmap_offsets(xsk->fd, &off);
diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index 22eb31e..2f9948b 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -11,9 +11,9 @@
second_num=$2
# upper bound is first_num * 110%
- upper=$(( $first_num + $first_num / 10 ))
+ upper=$(expr $first_num + $first_num / 10 )
# lower bound is first_num * 90%
- lower=$(( $first_num - $first_num / 10 ))
+ lower=$(expr $first_num - $first_num / 10 )
if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then
echo "The difference between $first_num and $second_num are greater than 10%."
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index b8fc5c5..0d8e3dc 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -438,6 +438,4 @@
int __user *usockvec);
extern int __sys_shutdown_sock(struct socket *sock, int how);
extern int __sys_shutdown(int fd, int how);
-
-extern struct ns_common *get_net_ns(struct ns_common *ns);
#endif /* _LINUX_SOCKET_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 3ff4936..da19be7 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -776,10 +776,10 @@
if (dso) {
dso->kernel = DSO_SPACE__KERNEL;
map = map__new2(0, dso);
+ dso__put(dso);
}
if (!dso || !map) {
- dso__put(dso);
return -ENOMEM;
}
@@ -792,6 +792,7 @@
map->start = event->ksymbol.addr;
map->end = map->start + event->ksymbol.len;
maps__insert(&machine->kmaps, map);
+ map__put(map);
dso__set_loaded(dso);
if (is_bpf_image(event->ksymbol.name)) {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 8336dd8..d3cf2de 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -162,10 +162,10 @@
return false;
}
-static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2)
+static bool evsel_same_pmu_or_none(struct evsel *ev1, struct evsel *ev2)
{
if (!ev1->pmu_name || !ev2->pmu_name)
- return false;
+ return true;
return !strcmp(ev1->pmu_name, ev2->pmu_name);
}
@@ -288,7 +288,7 @@
*/
if (!has_constraint &&
ev->leader != metric_events[i]->leader &&
- evsel_same_pmu(ev->leader, metric_events[i]->leader))
+ evsel_same_pmu_or_none(ev->leader, metric_events[i]->leader))
break;
if (!strcmp(metric_events[i]->name, ev->name)) {
set_bit(ev->idx, evlist_used);
@@ -1073,16 +1073,18 @@
ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids);
if (ret)
- return ret;
+ goto out;
ret = resolve_metric(d->metric_no_group,
d->metric_list, NULL, d->ids);
if (ret)
- return ret;
+ goto out;
*(d->has_match) = true;
- return *d->ret;
+out:
+ *(d->ret) = ret;
+ return ret;
}
static int metricgroup__add_metric(const char *metric, bool metric_no_group,
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 1512092..3a9e332 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1147,7 +1147,7 @@
}
}
- if (test->insn_processed) {
+ if (!unpriv && test->insn_processed) {
uint32_t insn_processed;
char *proc;
diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c
index ca8fdb1..7d7ebee 100644
--- a/tools/testing/selftests/bpf/verifier/and.c
+++ b/tools/testing/selftests/bpf/verifier/and.c
@@ -61,6 +61,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R1 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 0
},
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index 8a1caf4..e061e879 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -508,6 +508,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT
},
{
@@ -528,6 +530,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT
},
{
@@ -569,6 +573,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
@@ -589,6 +595,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
@@ -609,6 +617,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
@@ -674,6 +684,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
@@ -695,6 +707,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 min value is outside of the allowed memory range",
+ .result_unpriv = REJECT,
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index 17fe33a7..2c8935b 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -8,6 +8,8 @@
BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 10, -4),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 7,
},
diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index bd5cae4..1c857b2 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -87,6 +87,8 @@
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -150,6 +152,8 @@
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -213,6 +217,8 @@
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -280,6 +286,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -348,6 +356,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -416,6 +426,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -484,6 +496,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -552,6 +566,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -620,6 +636,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -688,6 +706,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
@@ -756,6 +776,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
},
diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c
index 8dcd4e0..11fc68d 100644
--- a/tools/testing/selftests/bpf/verifier/jset.c
+++ b/tools/testing/selftests/bpf/verifier/jset.c
@@ -82,8 +82,8 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .retval_unpriv = 1,
- .result_unpriv = ACCEPT,
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.retval = 1,
.result = ACCEPT,
},
@@ -141,7 +141,8 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .result_unpriv = ACCEPT,
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -162,6 +163,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .result_unpriv = ACCEPT,
+ .errstr_unpriv = "R9 !read_ok",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index bd436df..111801a 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -420,6 +420,8 @@
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R7 invalid mem access 'inv'",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 0,
},
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index 7ae2859..a3e593d 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -120,7 +120,7 @@
.fixup_map_array_48b = { 1 },
.result = ACCEPT,
.result_unpriv = REJECT,
- .errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
+ .errstr_unpriv = "R2 pointer comparison prohibited",
.retval = 0,
},
{
@@ -159,7 +159,8 @@
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
// fake-dead code; targeted from branch A to
- // prevent dead code sanitization
+ // prevent dead code sanitization, rejected
+ // via branch B however
BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
@@ -167,7 +168,7 @@
.fixup_map_array_48b = { 1 },
.result = ACCEPT,
.result_unpriv = REJECT,
- .errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
.retval = 0,
},
{
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 5c70596..a2b732c 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -82,7 +82,7 @@
kvm_fd = open_kvm_dev_path_or_exit();
ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
- TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
+ TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n"
" rc: %i errno: %i", ret, errno);
close(kvm_fd);
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 6ad6c82..af1031f 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -166,75 +166,75 @@
return 0;
}
+#define ANON_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS)
+#define ANON_HUGE_FLAGS (ANON_FLAGS | MAP_HUGETLB)
+
const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i)
{
- static const int anon_flags = MAP_PRIVATE | MAP_ANONYMOUS;
- static const int anon_huge_flags = anon_flags | MAP_HUGETLB;
-
static const struct vm_mem_backing_src_alias aliases[] = {
[VM_MEM_SRC_ANONYMOUS] = {
.name = "anonymous",
- .flag = anon_flags,
+ .flag = ANON_FLAGS,
},
[VM_MEM_SRC_ANONYMOUS_THP] = {
.name = "anonymous_thp",
- .flag = anon_flags,
+ .flag = ANON_FLAGS,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB] = {
.name = "anonymous_hugetlb",
- .flag = anon_huge_flags,
+ .flag = ANON_HUGE_FLAGS,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = {
.name = "anonymous_hugetlb_16kb",
- .flag = anon_huge_flags | MAP_HUGE_16KB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_16KB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = {
.name = "anonymous_hugetlb_64kb",
- .flag = anon_huge_flags | MAP_HUGE_64KB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_64KB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = {
.name = "anonymous_hugetlb_512kb",
- .flag = anon_huge_flags | MAP_HUGE_512KB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_512KB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = {
.name = "anonymous_hugetlb_1mb",
- .flag = anon_huge_flags | MAP_HUGE_1MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_1MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = {
.name = "anonymous_hugetlb_2mb",
- .flag = anon_huge_flags | MAP_HUGE_2MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_2MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = {
.name = "anonymous_hugetlb_8mb",
- .flag = anon_huge_flags | MAP_HUGE_8MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_8MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = {
.name = "anonymous_hugetlb_16mb",
- .flag = anon_huge_flags | MAP_HUGE_16MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_16MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = {
.name = "anonymous_hugetlb_32mb",
- .flag = anon_huge_flags | MAP_HUGE_32MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_32MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = {
.name = "anonymous_hugetlb_256mb",
- .flag = anon_huge_flags | MAP_HUGE_256MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_256MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = {
.name = "anonymous_hugetlb_512mb",
- .flag = anon_huge_flags | MAP_HUGE_512MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_512MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = {
.name = "anonymous_hugetlb_1gb",
- .flag = anon_huge_flags | MAP_HUGE_1GB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_1GB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = {
.name = "anonymous_hugetlb_2gb",
- .flag = anon_huge_flags | MAP_HUGE_2GB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_2GB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = {
.name = "anonymous_hugetlb_16gb",
- .flag = anon_huge_flags | MAP_HUGE_16GB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_16GB,
},
[VM_MEM_SRC_SHMEM] = {
.name = "shmem",
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 76d9487f..5abe92d 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -1384,12 +1384,37 @@
ipv4_rt_replace_mpath
}
+# checks that cached input route on VRF port is deleted
+# when VRF is deleted
+ipv4_local_rt_cache()
+{
+ run_cmd "ip addr add 10.0.0.1/32 dev lo"
+ run_cmd "ip netns add test-ns"
+ run_cmd "ip link add veth-outside type veth peer name veth-inside"
+ run_cmd "ip link add vrf-100 type vrf table 1100"
+ run_cmd "ip link set veth-outside master vrf-100"
+ run_cmd "ip link set veth-inside netns test-ns"
+ run_cmd "ip link set veth-outside up"
+ run_cmd "ip link set vrf-100 up"
+ run_cmd "ip route add 10.1.1.1/32 dev veth-outside table 1100"
+ run_cmd "ip netns exec test-ns ip link set veth-inside up"
+ run_cmd "ip netns exec test-ns ip addr add 10.1.1.1/32 dev veth-inside"
+ run_cmd "ip netns exec test-ns ip route add 10.0.0.1/32 dev veth-inside"
+ run_cmd "ip netns exec test-ns ip route add default via 10.0.0.1"
+ run_cmd "ip netns exec test-ns ping 10.0.0.1 -c 1 -i 1"
+ run_cmd "ip link delete vrf-100"
+
+ # if we do not hang test is a success
+ log_test $? 0 "Cached route removed from VRF port device"
+}
+
ipv4_route_test()
{
route_setup
ipv4_rt_add
ipv4_rt_replace
+ ipv4_local_rt_cache
route_cleanup
}
diff --git a/tools/testing/selftests/net/icmp.sh b/tools/testing/selftests/net/icmp.sh
new file mode 100755
index 0000000..e4b04cd
--- /dev/null
+++ b/tools/testing/selftests/net/icmp.sh
@@ -0,0 +1,74 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for checking ICMP response with dummy address instead of 0.0.0.0.
+# Sets up two namespaces like:
+# +----------------------+ +--------------------+
+# | ns1 | v4-via-v6 routes: | ns2 |
+# | | ' | |
+# | +--------+ -> 172.16.1.0/24 -> +--------+ |
+# | | veth0 +--------------------------+ veth0 | |
+# | +--------+ <- 172.16.0.0/24 <- +--------+ |
+# | 172.16.0.1 | | 2001:db8:1::2/64 |
+# | 2001:db8:1::2/64 | | |
+# +----------------------+ +--------------------+
+#
+# And then tries to ping 172.16.1.1 from ns1. This results in a "net
+# unreachable" message being sent from ns2, but there is no IPv4 address set in
+# that address space, so the kernel should substitute the dummy address
+# 192.0.0.8 defined in RFC7600.
+
+NS1=ns1
+NS2=ns2
+H1_IP=172.16.0.1/32
+H1_IP6=2001:db8:1::1
+RT1=172.16.1.0/24
+PINGADDR=172.16.1.1
+RT2=172.16.0.0/24
+H2_IP6=2001:db8:1::2
+
+TMPFILE=$(mktemp)
+
+cleanup()
+{
+ rm -f "$TMPFILE"
+ ip netns del $NS1
+ ip netns del $NS2
+}
+
+trap cleanup EXIT
+
+# Namespaces
+ip netns add $NS1
+ip netns add $NS2
+
+# Connectivity
+ip -netns $NS1 link add veth0 type veth peer name veth0 netns $NS2
+ip -netns $NS1 link set dev veth0 up
+ip -netns $NS2 link set dev veth0 up
+ip -netns $NS1 addr add $H1_IP dev veth0
+ip -netns $NS1 addr add $H1_IP6/64 dev veth0 nodad
+ip -netns $NS2 addr add $H2_IP6/64 dev veth0 nodad
+ip -netns $NS1 route add $RT1 via inet6 $H2_IP6
+ip -netns $NS2 route add $RT2 via inet6 $H1_IP6
+
+# Make sure ns2 will respond with ICMP unreachable
+ip netns exec $NS2 sysctl -qw net.ipv4.icmp_ratelimit=0 net.ipv4.ip_forward=1
+
+# Run the test - a ping runs in the background, and we capture ICMP responses
+# with tcpdump; -c 1 means it should exit on the first ping, but add a timeout
+# in case something goes wrong
+ip netns exec $NS1 ping -w 3 -i 0.5 $PINGADDR >/dev/null &
+ip netns exec $NS1 timeout 10 tcpdump -tpni veth0 -c 1 'icmp and icmp[icmptype] != icmp-echo' > $TMPFILE 2>/dev/null
+
+# Parse response and check for dummy address
+# tcpdump output looks like:
+# IP 192.0.0.8 > 172.16.0.1: ICMP net 172.16.1.1 unreachable, length 92
+RESP_IP=$(awk '{print $2}' < $TMPFILE)
+if [[ "$RESP_IP" != "192.0.0.8" ]]; then
+ echo "FAIL - got ICMP response from $RESP_IP, should be 192.0.0.8"
+ exit 1
+else
+ echo "OK"
+ exit 0
+fi
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 9ca5f1b..2b495dc 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -197,9 +197,6 @@
ip -net "$ns4" route add default via 10.0.3.2
ip -net "$ns4" route add default via dead:beef:3::2
-# use TCP syn cookies, even if no flooding was detected.
-ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2
-
set_ethtool_flags() {
local ns="$1"
local dev="$2"
@@ -737,6 +734,14 @@
exit $ret
fi
+ # ns1<->ns2 is not subject to reordering/tc delays. Use it to test
+ # mptcp syncookie support.
+ if [ $sender = $ns1 ]; then
+ ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2
+ else
+ ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=1
+ fi
+
run_tests "$ns2" $sender 10.0.1.2
run_tests "$ns2" $sender dead:beef:1::2
run_tests "$ns2" $sender 10.0.2.1
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index a8fa641..7f26591 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
readonly BASE="ns-$(mktemp -u XXXXXX)"
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 2fedc07..11d7cdb 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -18,7 +18,8 @@
cleanup() {
local ns
- local -r jobs="$(jobs -p)"
+ local jobs
+ readonly jobs="$(jobs -p)"
[ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
rm -f $STATS
@@ -108,7 +109,7 @@
if [ ! -f ../bpf/xdp_dummy.o ]; then
echo "Missing xdp_dummy helper. Build bpf selftest first"
- exit -1
+ exit 1
fi
create_ns
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 3171069..cd6430b 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
# Makefile for netfilter selftests
-TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
+TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh
new file mode 100755
index 0000000..6caf6ac
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_fib.sh
@@ -0,0 +1,221 @@
+#!/bin/bash
+#
+# This tests the fib expression.
+#
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+nsrouter="nsrouter-$sfx"
+timeout=4
+
+log_netns=$(sysctl -n net.netfilter.nf_log_all_netns)
+
+cleanup()
+{
+ ip netns del ${ns1}
+ ip netns del ${ns2}
+ ip netns del ${nsrouter}
+
+ [ $log_netns -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns=$log_netns
+}
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without nft tool"
+ exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+ip netns add ${nsrouter}
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not create net namespace"
+ exit $ksft_skip
+fi
+
+trap cleanup EXIT
+
+dmesg | grep -q ' nft_rpfilter: '
+if [ $? -eq 0 ]; then
+ dmesg -c | grep ' nft_rpfilter: '
+ echo "WARN: a previous test run has failed" 1>&2
+fi
+
+sysctl -q net.netfilter.nf_log_all_netns=1
+ip netns add ${ns1}
+ip netns add ${ns2}
+
+load_ruleset() {
+ local netns=$1
+
+ip netns exec ${netns} nft -f /dev/stdin <<EOF
+table inet filter {
+ chain prerouting {
+ type filter hook prerouting priority 0; policy accept;
+ fib saddr . iif oif missing counter log prefix "$netns nft_rpfilter: " drop
+ }
+}
+EOF
+}
+
+load_ruleset_count() {
+ local netns=$1
+
+ip netns exec ${netns} nft -f /dev/stdin <<EOF
+table inet filter {
+ chain prerouting {
+ type filter hook prerouting priority 0; policy accept;
+ ip daddr 1.1.1.1 fib saddr . iif oif missing counter drop
+ ip6 daddr 1c3::c01d fib saddr . iif oif missing counter drop
+ }
+}
+EOF
+}
+
+check_drops() {
+ dmesg | grep -q ' nft_rpfilter: '
+ if [ $? -eq 0 ]; then
+ dmesg | grep ' nft_rpfilter: '
+ echo "FAIL: rpfilter did drop packets"
+ return 1
+ fi
+
+ return 0
+}
+
+check_fib_counter() {
+ local want=$1
+ local ns=$2
+ local address=$3
+
+ line=$(ip netns exec ${ns} nft list table inet filter | grep 'fib saddr . iif' | grep $address | grep "packets $want" )
+ ret=$?
+
+ if [ $ret -ne 0 ];then
+ echo "Netns $ns fib counter doesn't match expected packet count of $want for $address" 1>&2
+ ip netns exec ${ns} nft list table inet filter
+ return 1
+ fi
+
+ if [ $want -gt 0 ]; then
+ echo "PASS: fib expression did drop packets for $address"
+ fi
+
+ return 0
+}
+
+load_ruleset ${nsrouter}
+load_ruleset ${ns1}
+load_ruleset ${ns2}
+
+ip link add veth0 netns ${nsrouter} type veth peer name eth0 netns ${ns1} > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: No virtual ethernet pair device support in kernel"
+ exit $ksft_skip
+fi
+ip link add veth1 netns ${nsrouter} type veth peer name eth0 netns ${ns2}
+
+ip -net ${nsrouter} link set lo up
+ip -net ${nsrouter} link set veth0 up
+ip -net ${nsrouter} addr add 10.0.1.1/24 dev veth0
+ip -net ${nsrouter} addr add dead:1::1/64 dev veth0
+
+ip -net ${nsrouter} link set veth1 up
+ip -net ${nsrouter} addr add 10.0.2.1/24 dev veth1
+ip -net ${nsrouter} addr add dead:2::1/64 dev veth1
+
+ip -net ${ns1} link set lo up
+ip -net ${ns1} link set eth0 up
+
+ip -net ${ns2} link set lo up
+ip -net ${ns2} link set eth0 up
+
+ip -net ${ns1} addr add 10.0.1.99/24 dev eth0
+ip -net ${ns1} addr add dead:1::99/64 dev eth0
+ip -net ${ns1} route add default via 10.0.1.1
+ip -net ${ns1} route add default via dead:1::1
+
+ip -net ${ns2} addr add 10.0.2.99/24 dev eth0
+ip -net ${ns2} addr add dead:2::99/64 dev eth0
+ip -net ${ns2} route add default via 10.0.2.1
+ip -net ${ns2} route add default via dead:2::1
+
+test_ping() {
+ local daddr4=$1
+ local daddr6=$2
+
+ ip netns exec ${ns1} ping -c 1 -q $daddr4 > /dev/null
+ ret=$?
+ if [ $ret -ne 0 ];then
+ check_drops
+ echo "FAIL: ${ns1} cannot reach $daddr4, ret $ret" 1>&2
+ return 1
+ fi
+
+ ip netns exec ${ns1} ping -c 3 -q $daddr6 > /dev/null
+ ret=$?
+ if [ $ret -ne 0 ];then
+ check_drops
+ echo "FAIL: ${ns1} cannot reach $daddr6, ret $ret" 1>&2
+ return 1
+ fi
+
+ return 0
+}
+
+ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+sleep 3
+
+test_ping 10.0.2.1 dead:2::1 || exit 1
+check_drops || exit 1
+
+test_ping 10.0.2.99 dead:2::99 || exit 1
+check_drops || exit 1
+
+echo "PASS: fib expression did not cause unwanted packet drops"
+
+ip netns exec ${nsrouter} nft flush table inet filter
+
+ip -net ${ns1} route del default
+ip -net ${ns1} -6 route del default
+
+ip -net ${ns1} addr del 10.0.1.99/24 dev eth0
+ip -net ${ns1} addr del dead:1::99/64 dev eth0
+
+ip -net ${ns1} addr add 10.0.2.99/24 dev eth0
+ip -net ${ns1} addr add dead:2::99/64 dev eth0
+
+ip -net ${ns1} route add default via 10.0.2.1
+ip -net ${ns1} -6 route add default via dead:2::1
+
+ip -net ${nsrouter} addr add dead:2::1/64 dev veth0
+
+# switch to ruleset that doesn't log, this time
+# its expected that this does drop the packets.
+load_ruleset_count ${nsrouter}
+
+# ns1 has a default route, but nsrouter does not.
+# must not check return value, ping to 1.1.1.1 will
+# fail.
+check_fib_counter 0 ${nsrouter} 1.1.1.1 || exit 1
+check_fib_counter 0 ${nsrouter} 1c3::c01d || exit 1
+
+ip netns exec ${ns1} ping -c 1 -W 1 -q 1.1.1.1 > /dev/null
+check_fib_counter 1 ${nsrouter} 1.1.1.1 || exit 1
+
+sleep 2
+ip netns exec ${ns1} ping -c 3 -q 1c3::c01d > /dev/null
+check_fib_counter 3 ${nsrouter} 1c3::c01d || exit 1
+
+exit 0
