diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index 32a8893e5617..9edb2860a3e1 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -138,11 +138,10 @@ associated with the source address of the indirect branch. Specifically,
the BHB might be shared across privilege levels even in the presence of
Enhanced IBRS.
-Currently the only known real-world BHB attack vector is via
-unprivileged eBPF. Therefore, it's highly recommended to not enable
-unprivileged eBPF, especially when eIBRS is used (without retpolines).
-For a full mitigation against BHB attacks, it's recommended to use
-retpolines (or eIBRS combined with retpolines).
+Previously the only known real-world BHB attack vector was via unprivileged
+eBPF. Further research has found attacks that don't require unprivileged eBPF.
+For a full mitigation against BHB attacks it is recommended to set BHI_DIS_S or
+use the BHB clearing sequence.
Attack scenarios
----------------
@@ -430,6 +429,23 @@ The possible values in this file are:
'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB
=========================== =======================================================
+ - Branch History Injection (BHI) protection status:
+
+.. list-table::
+
+ * - BHI: Not affected
+ - System is not affected
+ * - BHI: Retpoline
+ - System is protected by retpoline
+ * - BHI: BHI_DIS_S
+ - System is protected by BHI_DIS_S
+ * - BHI: SW loop; KVM SW loop
+ - System is protected by software clearing sequence
+ * - BHI: Syscall hardening
+ - Syscalls are hardened against BHI
+ * - BHI: Syscall hardening; KVM: SW loop
+ - System is protected from userspace attacks by syscall hardening; KVM is protected by software clearing sequence
+
Full mitigation might require a microcode update from the CPU
vendor. When the necessary microcode is not available, the kernel will
report vulnerability.
@@ -484,7 +500,11 @@ Spectre variant 2
Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at
boot, by setting the IBRS bit, and they're automatically protected against
- Spectre v2 variant attacks.
+ some Spectre v2 variant attacks. The BHB can still influence the choice of
+ indirect branch predictor entry, and although branch predictor entries are
+ isolated between modes when eIBRS is enabled, the BHB itself is not isolated
+ between modes. Systems which support BHI_DIS_S will set it to protect against
+ BHI attacks.
On Intel's enhanced IBRS systems, this includes cross-thread branch target
injections on SMT systems (STIBP). In other words, Intel eIBRS enables
@@ -638,6 +658,22 @@ kernel command line.
spectre_v2=off. Spectre variant 1 mitigations
cannot be disabled.
+ spectre_bhi=
+
+ [X86] Control mitigation of Branch History Injection
+ (BHI) vulnerability. Syscalls are hardened against BHI
+ regardless of this setting. This setting affects the deployment
+ of the HW BHI control and the SW BHB clearing sequence.
+
+ on
+ unconditionally enable.
+ off
+ unconditionally disable.
+ auto
+ enable if hardware mitigation
+ control(BHI_DIS_S) is available, otherwise
+ enable alternate mitigation in KVM.
+
For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt
Mitigation selection guide
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d2150bd3acc5..95efaccca453 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6031,6 +6031,18 @@
sonypi.*= [HW] Sony Programmable I/O Control Device driver
See Documentation/admin-guide/laptops/sonypi.rst
+ spectre_bhi= [X86] Control mitigation of Branch History Injection
+ (BHI) vulnerability. Syscalls are hardened against BHI
+ reglardless of this setting. This setting affects the
+ deployment of the HW BHI control and the SW BHB
+ clearing sequence.
+
+ on - unconditionally enable.
+ off - unconditionally disable.
+ auto - (default) enable hardware mitigation
+ (BHI_DIS_S) if available, otherwise enable
+ alternate mitigation in KVM.
+
spectre_v2= [X86] Control mitigation of Spectre variant 2
(indirect branch speculation) vulnerability.
The default operation protects the kernel from
diff --git a/Makefile b/Makefile
index c436247d750c..f29a75b75861 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 6
PATCHLEVEL = 8
-SUBLEVEL = 4
+SUBLEVEL = 5
EXTRAVERSION =
NAME = Hurr durr I'ma ninja sloth
diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
index 46aaeba28604..ebe37678102f 100644
--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
@@ -943,6 +943,8 @@ bluetooth: bluetooth {
vddrf-supply = <&pp1300_l2c>;
vddch0-supply = <&pp3300_l10c>;
max-speed = <3200000>;
+
+ qcom,local-bd-address-broken;
};
};
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index e3bef38fc2e2..964d0446dae9 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -729,7 +729,6 @@ static void sve_init_header_from_task(struct user_sve_header *header,
{
unsigned int vq;
bool active;
- bool fpsimd_only;
enum vec_type task_type;
memset(header, 0, sizeof(*header));
@@ -745,12 +744,10 @@ static void sve_init_header_from_task(struct user_sve_header *header,
case ARM64_VEC_SVE:
if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
header->flags |= SVE_PT_VL_INHERIT;
- fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE);
break;
case ARM64_VEC_SME:
if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT))
header->flags |= SVE_PT_VL_INHERIT;
- fpsimd_only = false;
break;
default:
WARN_ON_ONCE(1);
@@ -758,7 +755,7 @@ static void sve_init_header_from_task(struct user_sve_header *header,
}
if (active) {
- if (fpsimd_only) {
+ if (target->thread.fp_type == FP_STATE_FPSIMD) {
header->flags |= SVE_PT_REGS_FPSIMD;
} else {
header->flags |= SVE_PT_REGS_SVE;
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index a60fb13e2192..2fc68da4036d 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -154,7 +154,8 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
/* Switch to requested VMID */
__tlb_switch_to_guest(mmu, &cxt, false);
- __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+ __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
+ TLBI_TTL_UNKNOWN);
dsb(ish);
__tlbi(vmalle1is);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index ab9d05fcf98b..ce5cef7d73c4 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -829,12 +829,15 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
* Perform the appropriate TLB invalidation based on the
* evicted pte value (if any).
*/
- if (kvm_pte_table(ctx->old, ctx->level))
- kvm_tlb_flush_vmid_range(mmu, ctx->addr,
- kvm_granule_size(ctx->level));
- else if (kvm_pte_valid(ctx->old))
+ if (kvm_pte_table(ctx->old, ctx->level)) {
+ u64 size = kvm_granule_size(ctx->level);
+ u64 addr = ALIGN_DOWN(ctx->addr, size);
+
+ kvm_tlb_flush_vmid_range(mmu, addr, size);
+ } else if (kvm_pte_valid(ctx->old)) {
kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
ctx->addr, ctx->level);
+ }
}
if (stage2_pte_is_counted(ctx->old))
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index b32e2940df7d..1a60b95381e8 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -171,7 +171,8 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
/* Switch to requested VMID */
__tlb_switch_to_guest(mmu, &cxt);
- __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+ __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
+ TLBI_TTL_UNKNOWN);
dsb(ish);
__tlbi(vmalle1is);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index d14504821b79..92270acfc00d 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1631,7 +1631,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
- if (esr_fsc_is_permission_fault(esr)) {
+ if (esr_fsc_is_translation_fault(esr)) {
/* Beyond sanitised PARange (which is the IPA limit) */
if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
kvm_inject_size_fault(vcpu);
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 8955da5c47cf..00217d8d034b 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -876,7 +876,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
emit(A64_UXTH(is64, dst, dst), ctx);
break;
case 32:
- emit(A64_REV32(is64, dst, dst), ctx);
+ emit(A64_REV32(0, dst, dst), ctx);
/* upper 32 bits already cleared */
break;
case 64:
@@ -1189,7 +1189,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
} else {
emit_a64_mov_i(1, tmp, off, ctx);
if (sign_extend)
- emit(A64_LDRSW(dst, src_adj, off_adj), ctx);
+ emit(A64_LDRSW(dst, src, tmp), ctx);
else
emit(A64_LDR32(dst, src, tmp), ctx);
}
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 3438ab72c346..d975fb5d7cbe 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -130,7 +130,7 @@ void set_pud_at(struct mm_struct *mm, unsigned long addr,
WARN_ON(pte_hw_valid(pud_pte(*pudp)));
assert_spin_locked(pud_lockptr(mm, pudp));
- WARN_ON(!(pud_large(pud)));
+ WARN_ON(!(pud_leaf(pud)));
#endif
trace_hugepage_set_pud(addr, pud_val(pud));
return set_pte_at(mm, addr, pudp_ptep(pudp), pud_pte(pud));
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index ec0cab9fbddd..72ec1d9bd3f3 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -319,7 +319,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
#define __get_kernel_nofault(dst, src, type, err_label) \
do { \
- long __kr_err; \
+ long __kr_err = 0; \
\
__get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \
if (unlikely(__kr_err)) \
@@ -328,7 +328,7 @@ do { \
#define __put_kernel_nofault(dst, src, type, err_label) \
do { \
- long __kr_err; \
+ long __kr_err = 0; \
\
__put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \
if (unlikely(__kr_err)) \
diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h
index 10aaa83db89e..95050ebe9ad0 100644
--- a/arch/riscv/include/uapi/asm/auxvec.h
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -34,7 +34,7 @@
#define AT_L3_CACHEGEOMETRY 47
/* entries in ARCH_DLINFO */
-#define AT_VECTOR_SIZE_ARCH 9
+#define AT_VECTOR_SIZE_ARCH 10
#define AT_MINSIGSTKSZ 51
#endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 37e87fdcf6a0..30e12b310cab 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -80,6 +80,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
*/
lockdep_assert_held(&text_mutex);
+ preempt_disable();
+
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
@@ -92,6 +94,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
+ preempt_enable();
+
return 0;
}
NOKPROBE_SYMBOL(__patch_insn_set);
@@ -122,6 +126,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
if (!riscv_patch_in_stop_machine)
lockdep_assert_held(&text_mutex);
+ preempt_disable();
+
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
@@ -134,6 +140,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
+ preempt_enable();
+
return ret;
}
NOKPROBE_SYMBOL(__patch_insn_write);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 92922dbd5b5c..e4bc61c4e58a 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -27,8 +27,6 @@
#include <asm/vector.h>
#include <asm/cpufeature.h>
-register unsigned long gp_in_global __asm__("gp");
-
#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __read_mostly;
@@ -37,7 +35,7 @@ EXPORT_SYMBOL(__stack_chk_guard);
extern asmlinkage void ret_from_fork(void);
-void arch_cpu_idle(void)
+void noinstr arch_cpu_idle(void)
{
cpu_do_idle();
}
@@ -207,7 +205,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
if (unlikely(args->fn)) {
/* Kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
- childregs->gp = gp_in_global;
/* Supervisor/Machine, irqs on: */
childregs->status = SR_PP | SR_PIE;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 501e66debf69..5a2edd7f027e 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -119,6 +119,13 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
struct __sc_riscv_v_state __user *state = sc_vec;
void __user *datap;
+ /*
+ * Mark the vstate as clean prior performing the actual copy,
+ * to avoid getting the vstate incorrectly clobbered by the
+ * discarded vector state.
+ */
+ riscv_v_vstate_set_restore(current, regs);
+
/* Copy everything of __sc_riscv_v_state except datap. */
err = __copy_from_user(¤t->thread.vstate, &state->v_state,
offsetof(struct __riscv_v_ext_state, datap));
@@ -133,13 +140,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
* Copy the whole vector content from user space datap. Use
* copy_from_user to prevent information leak.
*/
- err = copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
- if (unlikely(err))
- return err;
-
- riscv_v_vstate_set_restore(current, regs);
-
- return err;
+ return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
}
#else
#define save_v_state(task, regs) (0)
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index a1b9be3c4332..142f5f5168fb 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -121,7 +121,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
pr_cont("\n");
__show_regs(regs);
- dump_instr(KERN_EMERG, regs);
+ dump_instr(KERN_INFO, regs);
}
force_sig_fault(signo, code, (void __user *)addr);
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 9b517fe1b8a8..272c431ac5b9 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -37,6 +37,7 @@ endif
# Disable -pg to prevent insert call site
CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
+CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
# Disable profiling and instrumentation for VDSO code
GCOV_PROFILE := n
diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c
index 39e72aa016a4..b467ba5ed910 100644
--- a/arch/riscv/kvm/aia_aplic.c
+++ b/arch/riscv/kvm/aia_aplic.c
@@ -137,11 +137,21 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending)
raw_spin_lock_irqsave(&irqd->lock, flags);
sm = irqd->sourcecfg & APLIC_SOURCECFG_SM_MASK;
- if (!pending &&
- ((sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) ||
- (sm == APLIC_SOURCECFG_SM_LEVEL_LOW)))
+ if (sm == APLIC_SOURCECFG_SM_INACTIVE)
goto skip_write_pending;
+ if (sm == APLIC_SOURCECFG_SM_LEVEL_HIGH ||
+ sm == APLIC_SOURCECFG_SM_LEVEL_LOW) {
+ if (!pending)
+ goto skip_write_pending;
+ if ((irqd->state & APLIC_IRQ_STATE_INPUT) &&
+ sm == APLIC_SOURCECFG_SM_LEVEL_LOW)
+ goto skip_write_pending;
+ if (!(irqd->state & APLIC_IRQ_STATE_INPUT) &&
+ sm == APLIC_SOURCECFG_SM_LEVEL_HIGH)
+ goto skip_write_pending;
+ }
+
if (pending)
irqd->state |= APLIC_IRQ_STATE_PENDING;
else
@@ -187,16 +197,31 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled)
static bool aplic_read_input(struct aplic *aplic, u32 irq)
{
- bool ret;
- unsigned long flags;
+ u32 sourcecfg, sm, raw_input, irq_inverted;
struct aplic_irq *irqd;
+ unsigned long flags;
+ bool ret = false;
if (!irq || aplic->nr_irqs <= irq)
return false;
irqd = &aplic->irqs[irq];
raw_spin_lock_irqsave(&irqd->lock, flags);
- ret = (irqd->state & APLIC_IRQ_STATE_INPUT) ? true : false;
+
+ sourcecfg = irqd->sourcecfg;
+ if (sourcecfg & APLIC_SOURCECFG_D)
+ goto skip;
+
+ sm = sourcecfg & APLIC_SOURCECFG_SM_MASK;
+ if (sm == APLIC_SOURCECFG_SM_INACTIVE)
+ goto skip;
+
+ raw_input = (irqd->state & APLIC_IRQ_STATE_INPUT) ? 1 : 0;
+ irq_inverted = (sm == APLIC_SOURCECFG_SM_LEVEL_LOW ||
+ sm == APLIC_SOURCECFG_SM_EDGE_FALL) ? 1 : 0;
+ ret = !!(raw_input ^ irq_inverted);
+
+skip:
raw_spin_unlock_irqrestore(&irqd->lock, flags);
return ret;
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 893566e004b7..07d743f87b3f 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -99,7 +99,7 @@ static void __ipi_flush_tlb_range_asid(void *info)
local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
}
-static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
+static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid,
unsigned long start, unsigned long size,
unsigned long stride)
{
@@ -200,7 +200,7 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- __flush_tlb_range((struct cpumask *)cpu_online_mask, FLUSH_TLB_NO_ASID,
+ __flush_tlb_range(cpu_online_mask, FLUSH_TLB_NO_ASID,
start, end - start, PAGE_SIZE);
}
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index e3a4500a5a75..47e1f54c587a 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -366,7 +366,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e
}
pmd = boot_crst_alloc(_SEGMENT_ENTRY_EMPTY);
pud_populate(&init_mm, pud, pmd);
- } else if (pud_large(*pud)) {
+ } else if (pud_leaf(*pud)) {
continue;
}
pgtable_pmd_populate(pud, addr, next, mode);
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 1299b56e43f6..12a7b8678925 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -730,7 +730,7 @@ static inline int pud_bad(pud_t pud)
{
unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK;
- if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud))
+ if (type > _REGION_ENTRY_TYPE_R3 || pud_leaf(pud))
return 1;
if (type < _REGION_ENTRY_TYPE_R3)
return 0;
@@ -1398,7 +1398,7 @@ static inline unsigned long pud_deref(pud_t pud)
unsigned long origin_mask;
origin_mask = _REGION_ENTRY_ORIGIN;
- if (pud_large(pud))
+ if (pud_leaf(pud))
origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
return (unsigned long)__va(pud_val(pud) & origin_mask);
}
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 49a11f6dd7ae..26c08ee87740 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -653,6 +653,7 @@ SYM_DATA_START_LOCAL(daton_psw)
SYM_DATA_END(daton_psw)
.section .rodata, "a"
+ .balign 8
#define SYSCALL(esame,emu) .quad __s390x_ ## esame
SYM_DATA_START(sys_call_table)
#include "asm/syscall_table.h"
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 522a5ea0a9f4..335e3f5d71f7 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -90,7 +90,6 @@ static void paicrypt_event_destroy(struct perf_event *event)
event->cpu);
struct paicrypt_map *cpump = mp->mapptr;
- cpump->event = NULL;
static_branch_dec(&pai_key);
mutex_lock(&pai_reserve_mutex);
debug_sprintf_event(cfm_dbg, 5, "%s event %#llx cpu %d users %d"
@@ -348,10 +347,15 @@ static int paicrypt_add(struct perf_event *event, int flags)
static void paicrypt_stop(struct perf_event *event, int flags)
{
- if (!event->attr.sample_period) /* Counting */
+ struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
+ struct paicrypt_map *cpump = mp->mapptr;
+
+ if (!event->attr.sample_period) { /* Counting */
paicrypt_read(event);
- else /* Sampling */
+ } else { /* Sampling */
perf_sched_cb_dec(event->pmu);
+ cpump->event = NULL;
+ }
event->hw.state = PERF_HES_STOPPED;
}
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index 95d1a890640a..db37c38ddcee 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -121,7 +121,6 @@ static void paiext_event_destroy(struct perf_event *event)
struct paiext_map *cpump = mp->mapptr;
mutex_lock(&paiext_reserve_mutex);
- cpump->event = NULL;
if (refcount_dec_and_test(&cpump->refcnt)) /* Last reference gone */
paiext_free(mp);
paiext_root_free();
@@ -355,10 +354,15 @@ static int paiext_add(struct perf_event *event, int flags)
static void paiext_stop(struct perf_event *event, int flags)
{
- if (!event->attr.sample_period) /* Counting */
+ struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr);
+ struct paiext_map *cpump = mp->mapptr;
+
+ if (!event->attr.sample_period) { /* Counting */
paiext_read(event);
- else /* Sampling */
+ } else { /* Sampling */
perf_sched_cb_dec(event->pmu);
+ cpump->event = NULL;
+ }
event->hw.state = PERF_HES_STOPPED;
}
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 8da39deb56ca..08a7eca03daf 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -596,7 +596,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
pud = pud_offset(p4d, vmaddr);
VM_BUG_ON(pud_none(*pud));
/* large puds cannot yet be handled */
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
return -EFAULT;
pmd = pmd_offset(pud, vmaddr);
VM_BUG_ON(pmd_none(*pmd));
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 297a6d897d5a..5f64f3d0fafb 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -224,7 +224,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
if (p4d_present(*p4dp)) {
pudp = pud_offset(p4dp, addr);
if (pud_present(*pudp)) {
- if (pud_large(*pudp))
+ if (pud_leaf(*pudp))
return (pte_t *) pudp;
pmdp = pmd_offset(pudp, addr);
}
@@ -240,7 +240,7 @@ int pmd_huge(pmd_t pmd)
int pud_huge(pud_t pud)
{
- return pud_large(pud);
+ return pud_leaf(pud);
}
bool __init arch_hugetlb_valid_size(unsigned long size)
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 631e3a4ee2de..739185fc39ea 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -274,7 +274,7 @@ static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end,
if (pud_none(*pudp))
return -EINVAL;
next = pud_addr_end(addr, end);
- if (pud_large(*pudp)) {
+ if (pud_leaf(*pudp)) {
need_split = !!(flags & SET_MEMORY_4K);
need_split |= !!(addr & ~PUD_MASK);
need_split |= !!(addr + PUD_SIZE > next);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 99422926efe1..3ff07b6bcd65 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -470,7 +470,7 @@ static int pmd_lookup(struct mm_struct *mm, unsigned long addr, pmd_t **pmdp)
return -ENOENT;
/* Large PUDs are not supported yet. */
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
return -EFAULT;
*pmdp = pmd_offset(pud, addr);
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 186a020857cf..84e173c02ab9 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -323,7 +323,7 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end,
if (!add) {
if (pud_none(*pud))
continue;
- if (pud_large(*pud)) {
+ if (pud_leaf(*pud)) {
if (IS_ALIGNED(addr, PUD_SIZE) &&
IS_ALIGNED(next, PUD_SIZE)) {
pud_clear(pud);
@@ -344,7 +344,7 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end,
if (!pmd)
goto out;
pud_populate(&init_mm, pud, pmd);
- } else if (pud_large(*pud)) {
+ } else if (pud_leaf(*pud)) {
continue;
}
ret = modify_pmd_table(pud, addr, next, add, direct);
@@ -591,7 +591,7 @@ pte_t *vmem_get_alloc_pte(unsigned long addr, bool alloc)
if (!pmd)
goto out;
pud_populate(&init_mm, pud, pmd);
- } else if (WARN_ON_ONCE(pud_large(*pud))) {
+ } else if (WARN_ON_ONCE(pud_leaf(*pud))) {
goto out;
}
pmd = pmd_offset(pud, addr);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index b418333bb086..5af0402e94b8 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -516,11 +516,12 @@ static void bpf_skip(struct bpf_jit *jit, int size)
* PLT for hotpatchable calls. The calling convention is the same as for the
* ftrace hotpatch trampolines: %r0 is return address, %r1 is clobbered.
*/
-extern const char bpf_plt[];
-extern const char bpf_plt_ret[];
-extern const char bpf_plt_target[];
-extern const char bpf_plt_end[];
-#define BPF_PLT_SIZE 32
+struct bpf_plt {
+ char code[16];
+ void *ret;
+ void *target;
+} __packed;
+extern const struct bpf_plt bpf_plt;
asm(
".pushsection .rodata\n"
" .balign 8\n"
@@ -531,15 +532,14 @@ asm(
" .balign 8\n"
"bpf_plt_ret: .quad 0\n"
"bpf_plt_target: .quad 0\n"
- "bpf_plt_end:\n"
" .popsection\n"
);
-static void bpf_jit_plt(void *plt, void *ret, void *target)
+static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target)
{
- memcpy(plt, bpf_plt, BPF_PLT_SIZE);
- *(void **)((char *)plt + (bpf_plt_ret - bpf_plt)) = ret;
- *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target ?: ret;
+ memcpy(plt, &bpf_plt, sizeof(*plt));
+ plt->ret = ret;
+ plt->target = target;
}
/*
@@ -662,9 +662,9 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
jit->prg = ALIGN(jit->prg, 8);
jit->prologue_plt = jit->prg;
if (jit->prg_buf)
- bpf_jit_plt(jit->prg_buf + jit->prg,
+ bpf_jit_plt((struct bpf_plt *)(jit->prg_buf + jit->prg),
jit->prg_buf + jit->prologue_plt_ret, NULL);
- jit->prg += BPF_PLT_SIZE;
+ jit->prg += sizeof(struct bpf_plt);
}
static int get_probe_mem_regno(const u8 *insn)
@@ -2040,9 +2040,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
struct bpf_jit jit;
int pass;
- if (WARN_ON_ONCE(bpf_plt_end - bpf_plt != BPF_PLT_SIZE))
- return orig_fp;
-
if (!fp->jit_requested)
return orig_fp;
@@ -2148,14 +2145,11 @@ bool bpf_jit_supports_far_kfunc_call(void)
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *old_addr, void *new_addr)
{
+ struct bpf_plt expected_plt, current_plt, new_plt, *plt;
struct {
u16 opc;
s32 disp;
} __packed insn;
- char expected_plt[BPF_PLT_SIZE];
- char current_plt[BPF_PLT_SIZE];
- char new_plt[BPF_PLT_SIZE];
- char *plt;
char *ret;
int err;
@@ -2174,18 +2168,18 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
*/
} else {
/* Verify the PLT. */
- plt = (char *)ip + (insn.disp << 1);
- err = copy_from_kernel_nofault(current_plt, plt, BPF_PLT_SIZE);
+ plt = ip + (insn.disp << 1);
+ err = copy_from_kernel_nofault(¤t_plt, plt,
+ sizeof(current_plt));
if (err < 0)
return err;
ret = (char *)ip + 6;
- bpf_jit_plt(expected_plt, ret, old_addr);
- if (memcmp(current_plt, expected_plt, BPF_PLT_SIZE))
+ bpf_jit_plt(&expected_plt, ret, old_addr);
+ if (memcmp(¤t_plt, &expected_plt, sizeof(current_plt)))
return -EINVAL;
/* Adjust the call address. */
- bpf_jit_plt(new_plt, ret, new_addr);
- s390_kernel_write(plt + (bpf_plt_target - bpf_plt),
- new_plt + (bpf_plt_target - bpf_plt),
+ bpf_jit_plt(&new_plt, ret, new_addr);
+ s390_kernel_write(&plt->target, &new_plt.target,
sizeof(void *));
}
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index f83017992eaa..d7db4e737218 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1665,7 +1665,7 @@ bool kern_addr_valid(unsigned long addr)
if (pud_none(*pud))
return false;
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
return pfn_valid(pud_pfn(*pud));
pmd = pmd_offset(pud, addr);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 184730705650..890ba8e48bc3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2612,6 +2612,31 @@ config MITIGATION_RFDS
stored in floating point, vector and integer registers.
See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst>
+choice
+ prompt "Clear branch history"
+ depends on CPU_SUP_INTEL
+ default SPECTRE_BHI_ON
+ help
+ Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks
+ where the branch history buffer is poisoned to speculatively steer
+ indirect branches.
+ See <file:Documentation/admin-guide/hw-vuln/spectre.rst>
+
+config SPECTRE_BHI_ON
+ bool "on"
+ help
+ Equivalent to setting spectre_bhi=on command line parameter.
+config SPECTRE_BHI_OFF
+ bool "off"
+ help
+ Equivalent to setting spectre_bhi=off command line parameter.
+config SPECTRE_BHI_AUTO
+ bool "auto"
+ help
+ Equivalent to setting spectre_bhi=auto command line parameter.
+
+endchoice
+
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index f19c038409aa..e9522c6893be 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -84,7 +84,7 @@ LDFLAGS_vmlinux += -T
hostprogs := mkpiggy
HOST_EXTRACFLAGS += -I$(srctree)/tools/include
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
quiet_cmd_voffset = VOFFSET $@
cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index b99e08e6815b..ee0fac468e7f 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -330,6 +330,7 @@ static size_t parse_elf(void *output)
return ehdr.e_entry - LOAD_PHYSICAL_ADDR;
}
+const unsigned long kernel_text_size = VO___start_rodata - VO__text;
const unsigned long kernel_total_size = VO__end - VO__text;
static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4);
@@ -357,6 +358,19 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
return entry;
}
+/*
+ * Set the memory encryption xloadflag based on the mem_encrypt= command line
+ * parameter, if provided.
+ */
+static void parse_mem_encrypt(struct setup_header *hdr)
+{
+ int on = cmdline_find_option_bool("mem_encrypt=on");
+ int off = cmdline_find_option_bool("mem_encrypt=off");
+
+ if (on > off)
+ hdr->xloadflags |= XLF_MEM_ENCRYPTION;
+}
+
/*
* The compressed kernel image (ZO), has been moved so that its position
* is against the end of the buffer used to hold the uncompressed kernel
@@ -387,6 +401,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
/* Clear flags intended for solely in-kernel use. */
boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG;
+ parse_mem_encrypt(&boot_params_ptr->hdr);
+
sanitize_boot_params(boot_params_ptr);
if (boot_params_ptr->screen_info.orig_video_mode == 7) {
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 454acd7a2daf..4c9b75281417 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -116,6 +116,9 @@ static bool fault_in_kernel_space(unsigned long address)
#undef __init
#define __init
+#undef __head
+#define __head
+
#define __BOOT_COMPRESSED
/* Basic instruction decoding support needed */
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index d07be9d05cd0..ddd4efdc79d6 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -3,13 +3,17 @@
* Confidential Computing Platform Capability checks
*
* Copyright (C) 2021 Advanced Micro Devices, Inc.
+ * Copyright (C) 2024 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved.
*
* Author: Tom Lendacky <thomas.lendacky@xxxxxxx>
*/
#include <linux/export.h>
#include <linux/cc_platform.h>
+#include <linux/string.h>
+#include <linux/random.h>
+#include <asm/archrandom.h>
#include <asm/coco.h>
#include <asm/processor.h>
@@ -148,3 +152,40 @@ u64 cc_mkdec(u64 val)
}
}
EXPORT_SYMBOL_GPL(cc_mkdec);
+
+__init void cc_random_init(void)
+{
+ /*
+ * The seed is 32 bytes (in units of longs), which is 256 bits, which
+ * is the security level that the RNG is targeting.
+ */
+ unsigned long rng_seed[32 / sizeof(long)];
+ size_t i, longs;
+
+ if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+ return;
+
+ /*
+ * Since the CoCo threat model includes the host, the only reliable
+ * source of entropy that can be neither observed nor manipulated is
+ * RDRAND. Usually, RDRAND failure is considered tolerable, but since
+ * CoCo guests have no other unobservable source of entropy, it's
+ * important to at least ensure the RNG gets some initial random seeds.
+ */
+ for (i = 0; i < ARRAY_SIZE(rng_seed); i += longs) {
+ longs = arch_get_random_longs(&rng_seed[i], ARRAY_SIZE(rng_seed) - i);
+
+ /*
+ * A zero return value means that the guest doesn't have RDRAND
+ * or the CPU is physically broken, and in both cases that
+ * means most crypto inside of the CoCo instance will be
+ * broken, defeating the purpose of CoCo in the first place. So
+ * just panic here because it's absolutely unsafe to continue
+ * executing.
+ */
+ if (longs == 0)
+ panic("RDRAND is defective.");
+ }
+ add_device_randomness(rng_seed, sizeof(rng_seed));
+ memzero_explicit(rng_seed, sizeof(rng_seed));
+}
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 6356060caaf3..6de50b80702e 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -49,7 +49,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
if (likely(unr < NR_syscalls)) {
unr = array_index_nospec(unr, NR_syscalls);
- regs->ax = sys_call_table[unr](regs);
+ regs->ax = x64_sys_call(regs, unr);
return true;
}
return false;
@@ -66,7 +66,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
xnr = array_index_nospec(xnr, X32_NR_syscalls);
- regs->ax = x32_sys_call_table[xnr](regs);
+ regs->ax = x32_sys_call(regs, xnr);
return true;
}
return false;
@@ -162,7 +162,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
if (likely(unr < IA32_NR_syscalls)) {
unr = array_index_nospec(unr, IA32_NR_syscalls);
- regs->ax = ia32_sys_call_table[unr](regs);
+ regs->ax = ia32_sys_call(regs, unr);
} else if (nr != -1) {
regs->ax = __ia32_sys_ni_syscall(regs);
}
@@ -189,7 +189,7 @@ static __always_inline bool int80_is_external(void)
}
/**
- * int80_emulation - 32-bit legacy syscall entry
+ * do_int80_emulation - 32-bit legacy syscall C entry from asm
*
* This entry point can be used by 32-bit and 64-bit programs to perform
* 32-bit system calls. Instances of INT $0x80 can be found inline in
@@ -207,7 +207,7 @@ static __always_inline bool int80_is_external(void)
* eax: system call number
* ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6
*/
-DEFINE_IDTENTRY_RAW(int80_emulation)
+__visible noinstr void do_int80_emulation(struct pt_regs *regs)
{
int nr;
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 9bb485977629..e986331b14e1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
/* clobbers %rax, make sure it is after saving the syscall nr */
IBRS_ENTER
UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
call do_syscall_64 /* returns with IRQs disabled */
@@ -1494,3 +1495,63 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead)
call make_task_dead
SYM_CODE_END(rewind_stack_and_make_dead)
.popsection
+
+/*
+ * This sequence executes branches in order to remove user branch information
+ * from the branch history tracker in the Branch Predictor, therefore removing
+ * user influence on subsequent BTB lookups.
+ *
+ * It should be used on parts prior to Alder Lake. Newer parts should use the
+ * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being
+ * virtualized on newer hardware the VMM should protect against BHI attacks by
+ * setting BHI_DIS_S for the guests.
+ *
+ * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging
+ * and not clearing the branch history. The call tree looks like:
+ *
+ * call 1
+ * call 2
+ * call 2
+ * call 2
+ * call 2
+ * call 2
+ * ret
+ * ret
+ * ret
+ * ret
+ * ret
+ * ret
+ *
+ * This means that the stack is non-constant and ORC can't unwind it with %rsp
+ * alone. Therefore we unconditionally set up the frame pointer, which allows
+ * ORC to unwind properly.
+ *
+ * The alignment is for performance and not for safety, and may be safely
+ * refactored in the future if needed.
+ */
+SYM_FUNC_START(clear_bhb_loop)
+ push %rbp
+ mov %rsp, %rbp
+ movl $5, %ecx
+ ANNOTATE_INTRA_FUNCTION_CALL
+ call 1f
+ jmp 5f
+ .align 64, 0xcc
+ ANNOTATE_INTRA_FUNCTION_CALL
+1: call 2f
+ RET
+ .align 64, 0xcc
+2: movl $5, %eax
+3: jmp 4f
+ nop
+4: sub $1, %eax
+ jnz 3b
+ sub $1, %ecx
+ jnz 1b
+ RET
+5: lfence
+ pop %rbp
+ RET
+SYM_FUNC_END(clear_bhb_loop)
+EXPORT_SYMBOL_GPL(clear_bhb_loop)
+STACK_FRAME_NON_STANDARD(clear_bhb_loop)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index eabf48c4d4b4..c779046cc3fe 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -92,6 +92,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
IBRS_ENTER
UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
/*
* SYSENTER doesn't filter flags, so we need to clear NT and AC
@@ -206,6 +207,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
IBRS_ENTER
UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
movq %rsp, %rdi
call do_fast_syscall_32
@@ -276,3 +278,17 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
int3
SYM_CODE_END(entry_SYSCALL_compat)
+
+/*
+ * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries
+ * point to C routines, however since this is a system call interface the branch
+ * history needs to be scrubbed to protect against BHI attacks, and that
+ * scrubbing needs to take place in assembly code prior to entering any C
+ * routines.
+ */
+SYM_CODE_START(int80_emulation)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ CLEAR_BRANCH_HISTORY
+ jmp do_int80_emulation
+SYM_CODE_END(int80_emulation)
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 8cfc9bc73e7f..c2235bae17ef 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -18,8 +18,25 @@
#include <asm/syscalls_32.h>
#undef __SYSCALL
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
+#ifdef CONFIG_X86_32
#define __SYSCALL(nr, sym) __ia32_##sym,
-
-__visible const sys_call_ptr_t ia32_sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_32.h>
};
+#undef __SYSCALL
+#endif
+
+#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs);
+
+long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_32.h>
+ default: return __ia32_sys_ni_syscall(regs);
+ }
+};
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index be120eec1fc9..33b3f09e6f15 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -11,8 +11,23 @@
#include <asm/syscalls_64.h>
#undef __SYSCALL
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
#define __SYSCALL(nr, sym) __x64_##sym,
-
-asmlinkage const sys_call_ptr_t sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_64.h>
};
+#undef __SYSCALL
+
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+
+long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_64.h>
+ default: return __x64_sys_ni_syscall(regs);
+ }
+};
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index bdd0e03a1265..03de4a932131 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -11,8 +11,12 @@
#include <asm/syscalls_x32.h>
#undef __SYSCALL
-#define __SYSCALL(nr, sym) __x64_##sym,
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
-asmlinkage const sys_call_ptr_t x32_sys_call_table[] = {
-#include <asm/syscalls_x32.h>
+long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_x32.h>
+ default: return __x64_sys_ni_syscall(regs);
+ }
};
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index d49d661ec0a7..807de7b596ab 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1236,11 +1236,11 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
struct pmu *pmu = event->pmu;
/*
- * Make sure we get updated with the first PEBS
- * event. It will trigger also during removal, but
- * that does not hurt:
+ * Make sure we get updated with the first PEBS event.
+ * During removal, ->pebs_data_cfg is still valid for
+ * the last PEBS event. Don't clear it.
*/
- if (cpuc->n_pebs == 1)
+ if ((cpuc->n_pebs == 1) && add)
cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW;
if (needed_cb != pebs_needs_sched_cb(cpuc)) {
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index a38cc0afc90a..a3e0be0470a4 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -81,6 +81,7 @@
#ifndef __ASSEMBLY__
extern unsigned int output_len;
+extern const unsigned long kernel_text_size;
extern const unsigned long kernel_total_size;
unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index 18bbdda05322..3dd052bfefc5 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -21,6 +21,7 @@ static inline void cc_set_mask(u64 mask)
u64 cc_mkenc(u64 val);
u64 cc_mkdec(u64 val);
+void cc_random_init(void);
#else
#define cc_vendor (CC_VENDOR_NONE)
@@ -33,6 +34,7 @@ static inline u64 cc_mkdec(u64 val)
{
return val;
}
+static inline void cc_random_init(void) { }
#endif
#endif /* _ASM_X86_COCO_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index a1273698fc43..686e92d2663e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -33,6 +33,8 @@ enum cpuid_leafs
CPUID_7_EDX,
CPUID_8000_001F_EAX,
CPUID_8000_0021_EAX,
+ CPUID_LNX_5,
+ NR_CPUID_WORDS,
};
#define X86_CAP_FMT_NUM "%d:%d"
@@ -91,8 +93,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \
REQUIRED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 22))
#define DISABLED_MASK_BIT_SET(feature_bit) \
( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \
@@ -116,8 +119,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \
DISABLED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 22))
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 8511aad59581..76b3b00ff102 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 21 /* N 32-bit words worth of info */
+#define NCAPINTS 22 /* N 32-bit words worth of info */
#define NBUGINTS 2 /* N 32-bit bug flags */
/*
@@ -456,6 +456,17 @@
#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */
#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */
+/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0x80000022, etc and Linux defined features.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
+#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */
+#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */
+#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */
+
/*
* BUG word(s)
*/
@@ -504,4 +515,5 @@
#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */
#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 702d93fdd10e..88fcf08458d9 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -143,6 +143,7 @@
#define DISABLED_MASK18 (DISABLE_IBT)
#define DISABLED_MASK19 0
#define DISABLED_MASK20 0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define DISABLED_MASK21 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index b31eb9fd5954..f922b682b9b4 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -47,8 +47,8 @@ void __init sme_unmap_bootdata(char *real_mode_data);
void __init sme_early_init(void);
-void __init sme_encrypt_kernel(struct boot_params *bp);
-void __init sme_enable(struct boot_params *bp);
+void sme_encrypt_kernel(struct boot_params *bp);
+void sme_enable(struct boot_params *bp);
int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
@@ -81,8 +81,8 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
static inline void __init sme_early_init(void) { }
-static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
-static inline void __init sme_enable(struct boot_params *bp) { }
+static inline void sme_encrypt_kernel(struct boot_params *bp) { }
+static inline void sme_enable(struct boot_params *bp) { }
static inline void sev_es_init_vc_handling(void) { }
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index d1b5edaf6c34..d65f8ce6b7cf 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -50,10 +50,13 @@
#define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */
#define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */
#define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
+#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */
+#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT)
/* A mask for bits which the kernel toggles when controlling mitigations */
#define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \
- | SPEC_CTRL_RRSBA_DIS_S)
+ | SPEC_CTRL_RRSBA_DIS_S \
+ | SPEC_CTRL_BHI_DIS_S)
#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
#define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */
@@ -152,6 +155,10 @@
* are restricted to targets in
* kernel.
*/
+#define ARCH_CAP_BHI_NO BIT(20) /*
+ * CPU is not affected by Branch
+ * History Injection.
+ */
#define ARCH_CAP_PBRSB_NO BIT(24) /*
* Not susceptible to Post-Barrier
* Return Stack Buffer Predictions.
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 93c3e28dd8e0..3ff081a74ab2 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -335,6 +335,19 @@
ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF
.endm
+#ifdef CONFIG_X86_64
+.macro CLEAR_BRANCH_HISTORY
+ ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
+.endm
+
+.macro CLEAR_BRANCH_HISTORY_VMEXIT
+ ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT
+.endm
+#else
+#define CLEAR_BRANCH_HISTORY
+#define CLEAR_BRANCH_HISTORY_VMEXIT
+#endif
+
#else /* __ASSEMBLY__ */
#define ANNOTATE_RETPOLINE_SAFE \
@@ -377,6 +390,10 @@ extern void srso_alias_return_thunk(void);
extern void entry_untrain_ret(void);
extern void entry_ibpb(void);
+#ifdef CONFIG_X86_64
+extern void clear_bhb_loop(void);
+#endif
+
extern void (*x86_return_thunk)(void);
#ifdef CONFIG_CALL_DEPTH_TRACKING
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 7ba1726b71c7..e9187ddd3d1f 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -99,6 +99,7 @@
#define REQUIRED_MASK18 0
#define REQUIRED_MASK19 0
#define REQUIRED_MASK20 0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define REQUIRED_MASK21 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 36f905797075..75a5388d4068 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -199,15 +199,15 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)
struct snp_guest_request_ioctl;
void setup_ghcb(void);
-void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
- unsigned long npages);
-void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
- unsigned long npages);
+void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+ unsigned long npages);
+void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
+ unsigned long npages);
void snp_set_memory_shared(unsigned long vaddr, unsigned long npages);
void snp_set_memory_private(unsigned long vaddr, unsigned long npages);
void snp_set_wakeup_secondary_cpu(void);
bool snp_init(struct boot_params *bp);
-void __init __noreturn snp_abort(void);
+void __noreturn snp_abort(void);
void snp_dmi_setup(void);
int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index f44e2f9ab65d..2fc7bc3863ff 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,19 +16,17 @@
#include <asm/thread_info.h> /* for TS_COMPAT */
#include <asm/unistd.h>
+/* This is used purely for kernel/trace/trace_syscalls.c */
typedef long (*sys_call_ptr_t)(const struct pt_regs *);
extern const sys_call_ptr_t sys_call_table[];
-#if defined(CONFIG_X86_32)
-#define ia32_sys_call_table sys_call_table
-#else
/*
* These may not exist, but still put the prototypes in so we
* can use IS_ENABLED().
*/
-extern const sys_call_ptr_t ia32_sys_call_table[];
-extern const sys_call_ptr_t x32_sys_call_table[];
-#endif
+extern long ia32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x64_sys_call(const struct pt_regs *, unsigned int nr);
/*
* Only the low 32 bits of orig_ax are meaningful, so we return int.
@@ -127,6 +125,7 @@ static inline int syscall_get_arch(struct task_struct *task)
}
bool do_syscall_64(struct pt_regs *regs, int nr);
+void do_int80_emulation(struct pt_regs *regs);
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 01d19fc22346..eeea058cf602 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -38,6 +38,7 @@
#define XLF_EFI_KEXEC (1<<4)
#define XLF_5LEVEL (1<<5)
#define XLF_5LEVEL_ENABLED (1<<6)
+#define XLF_MEM_ENCRYPTION (1<<7)
#ifndef __ASSEMBLY__
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 01ac18f56147..0d7238d88b38 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1606,6 +1606,79 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_
dump_stack();
}
+/*
+ * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by
+ * branch history in userspace. Not needed if BHI_NO is set.
+ */
+static bool __init spec_ctrl_bhi_dis(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_BHI_CTRL))
+ return false;
+
+ x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S;
+ update_spec_ctrl(x86_spec_ctrl_base);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW);
+
+ return true;
+}
+
+enum bhi_mitigations {
+ BHI_MITIGATION_OFF,
+ BHI_MITIGATION_ON,
+ BHI_MITIGATION_AUTO,
+};
+
+static enum bhi_mitigations bhi_mitigation __ro_after_init =
+ IS_ENABLED(CONFIG_SPECTRE_BHI_ON) ? BHI_MITIGATION_ON :
+ IS_ENABLED(CONFIG_SPECTRE_BHI_OFF) ? BHI_MITIGATION_OFF :
+ BHI_MITIGATION_AUTO;
+
+static int __init spectre_bhi_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off"))
+ bhi_mitigation = BHI_MITIGATION_OFF;
+ else if (!strcmp(str, "on"))
+ bhi_mitigation = BHI_MITIGATION_ON;
+ else if (!strcmp(str, "auto"))
+ bhi_mitigation = BHI_MITIGATION_AUTO;
+ else
+ pr_err("Ignoring unknown spectre_bhi option (%s)", str);
+
+ return 0;
+}
+early_param("spectre_bhi", spectre_bhi_parse_cmdline);
+
+static void __init bhi_select_mitigation(void)
+{
+ if (bhi_mitigation == BHI_MITIGATION_OFF)
+ return;
+
+ /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */
+ if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
+ !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA))
+ return;
+
+ if (spec_ctrl_bhi_dis())
+ return;
+
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ /* Mitigate KVM by default */
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+ pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n");
+
+ if (bhi_mitigation == BHI_MITIGATION_AUTO)
+ return;
+
+ /* Mitigate syscalls when the mitigation is forced =on */
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
+ pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n");
+}
+
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -1717,6 +1790,9 @@ static void __init spectre_v2_select_mitigation(void)
mode == SPECTRE_V2_RETPOLINE)
spec_ctrl_disable_kernel_rrsba();
+ if (boot_cpu_has(X86_BUG_BHI))
+ bhi_select_mitigation();
+
spectre_v2_enabled = mode;
pr_info("%s\n", spectre_v2_strings[mode]);
@@ -2694,15 +2770,15 @@ static char *stibp_state(void)
switch (spectre_v2_user_stibp) {
case SPECTRE_V2_USER_NONE:
- return ", STIBP: disabled";
+ return "; STIBP: disabled";
case SPECTRE_V2_USER_STRICT:
- return ", STIBP: forced";
+ return "; STIBP: forced";
case SPECTRE_V2_USER_STRICT_PREFERRED:
- return ", STIBP: always-on";
+ return "; STIBP: always-on";
case SPECTRE_V2_USER_PRCTL:
case SPECTRE_V2_USER_SECCOMP:
if (static_key_enabled(&switch_to_cond_stibp))
- return ", STIBP: conditional";
+ return "; STIBP: conditional";
}
return "";
}
@@ -2711,10 +2787,10 @@ static char *ibpb_state(void)
{
if (boot_cpu_has(X86_FEATURE_IBPB)) {
if (static_key_enabled(&switch_mm_always_ibpb))
- return ", IBPB: always-on";
+ return "; IBPB: always-on";
if (static_key_enabled(&switch_mm_cond_ibpb))
- return ", IBPB: conditional";
- return ", IBPB: disabled";
+ return "; IBPB: conditional";
+ return "; IBPB: disabled";
}
return "";
}
@@ -2724,14 +2800,31 @@ static char *pbrsb_eibrs_state(void)
if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) ||
boot_cpu_has(X86_FEATURE_RSB_VMEXIT))
- return ", PBRSB-eIBRS: SW sequence";
+ return "; PBRSB-eIBRS: SW sequence";
else
- return ", PBRSB-eIBRS: Vulnerable";
+ return "; PBRSB-eIBRS: Vulnerable";
} else {
- return ", PBRSB-eIBRS: Not affected";
+ return "; PBRSB-eIBRS: Not affected";
}
}
+static const char * const spectre_bhi_state(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_BHI))
+ return "; BHI: Not affected";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW))
+ return "; BHI: BHI_DIS_S";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
+ return "; BHI: SW loop, KVM: SW loop";
+ else if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+ !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA))
+ return "; BHI: Retpoline";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
+ return "; BHI: Syscall hardening, KVM: SW loop";
+
+ return "; BHI: Vulnerable (Syscall hardening enabled)";
+}
+
static ssize_t spectre_v2_show_state(char *buf)
{
if (spectre_v2_enabled == SPECTRE_V2_LFENCE)
@@ -2744,13 +2837,15 @@ static ssize_t spectre_v2_show_state(char *buf)
spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n");
- return sysfs_emit(buf, "%s%s%s%s%s%s%s\n",
+ return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n",
spectre_v2_strings[spectre_v2_enabled],
ibpb_state(),
- boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+ boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "",
stibp_state(),
- boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "",
+ boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "",
pbrsb_eibrs_state(),
+ spectre_bhi_state(),
+ /* this should always be at the end */
spectre_v2_module_string());
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 40d8c110bb32..785fedddb5f0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1163,6 +1163,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#define NO_SPECTRE_V2 BIT(8)
#define NO_MMIO BIT(9)
#define NO_EIBRS_PBRSB BIT(10)
+#define NO_BHI BIT(11)
#define VULNWL(vendor, family, model, whitelist) \
X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
@@ -1225,18 +1226,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
/* AMD Family 0xf - 0x12 */
- VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+ VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+ VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+ VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
- VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
- VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
+ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI),
+ VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI),
/* Zhaoxin Family 7 */
- VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
- VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
+ VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI),
+ VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI),
{}
};
@@ -1473,6 +1474,13 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
if (vulnerable_to_rfds(ia32_cap))
setup_force_cpu_bug(X86_BUG_RFDS);
+ /* When virtualized, eIBRS could be hidden, assume vulnerable */
+ if (!(ia32_cap & ARCH_CAP_BHI_NO) &&
+ !cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
+ (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
+ boot_cpu_has(X86_FEATURE_HYPERVISOR)))
+ setup_force_cpu_bug(X86_BUG_BHI);
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index bc39252bc54f..c17f9403cf6c 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2474,12 +2474,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
return -EINVAL;
b = &per_cpu(mce_banks_array, s->id)[bank];
-
if (!b->init)
return -ENODEV;
b->ctl = new;
+
+ mutex_lock(&mce_sysfs_mutex);
mce_restart();
+ mutex_unlock(&mce_sysfs_mutex);
return size;
}
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 0dad49a09b7a..0ebca40dfd74 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -28,6 +28,7 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
{ X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 },
{ X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 },
+ { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 },
{ X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 },
{ X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 },
{ X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 },
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 15c700d35870..b223922248e9 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -196,12 +196,12 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
if (!smp_check_mpc(mpc, oem, str))
return 0;
- if (early) {
- /* Initialize the lapic mapping */
- if (!acpi_lapic)
- register_lapic_address(mpc->lapic);
+ /* Initialize the lapic mapping */
+ if (!acpi_lapic)
+ register_lapic_address(mpc->lapic);
+
+ if (early)
return 1;
- }
/* Now process the configuration blocks. */
while (count < mpc->length) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 97dd70285741..3998109195da 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -35,6 +35,7 @@
#include <asm/bios_ebda.h>
#include <asm/bugs.h>
#include <asm/cacheinfo.h>
+#include <asm/coco.h>
#include <asm/cpu.h>
#include <asm/efi.h>
#include <asm/gart.h>
@@ -993,6 +994,7 @@ void __init setup_arch(char **cmdline_p)
* memory size.
*/
mem_encrypt_setup_arch();
+ cc_random_init();
efi_fake_memmap();
efi_find_mirror();
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 0b04e3bfd72a..be2fa2fc02f3 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -89,7 +89,8 @@ static bool __init sev_es_check_cpu_features(void)
return true;
}
-static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason)
+static void __head __noreturn
+sev_es_terminate(unsigned int set, unsigned int reason)
{
u64 val = GHCB_MSR_TERM_REQ;
@@ -326,13 +327,7 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid
*/
static const struct snp_cpuid_table *snp_cpuid_get_table(void)
{
- void *ptr;
-
- asm ("lea cpuid_table_copy(%%rip), %0"
- : "=r" (ptr)
- : "p" (&cpuid_table_copy));
-
- return ptr;
+ return &RIP_REL_REF(cpuid_table_copy);
}
/*
@@ -391,7 +386,7 @@ static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted)
return xsave_size;
}
-static bool
+static bool __head
snp_cpuid_get_validated_func(struct cpuid_leaf *leaf)
{
const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -528,7 +523,8 @@ static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
* Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
* should be treated as fatal by caller.
*/
-static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
+static int __head
+snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
{
const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -570,7 +566,7 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le
* page yet, so it only supports the MSR based communication with the
* hypervisor and only the CPUID exit-code.
*/
-void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
+void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
{
unsigned int subfn = lower_bits(regs->cx, 32);
unsigned int fn = lower_bits(regs->ax, 32);
@@ -1016,7 +1012,8 @@ struct cc_setup_data {
* Search for a Confidential Computing blob passed in as a setup_data entry
* via the Linux Boot Protocol.
*/
-static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
+static __head
+struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
{
struct cc_setup_data *sd = NULL;
struct setup_data *hdr;
@@ -1043,7 +1040,7 @@ static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
* mapping needs to be updated in sync with all the changes to virtual memory
* layout and related mapping facilities throughout the boot process.
*/
-static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
+static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
{
const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table;
int i;
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 0f58242b54b8..eb2873b5eb1b 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -26,6 +26,7 @@
#include <linux/dmi.h>
#include <uapi/linux/sev-guest.h>
+#include <asm/init.h>
#include <asm/cpu_entry_area.h>
#include <asm/stacktrace.h>
#include <asm/sev.h>
@@ -683,8 +684,9 @@ static u64 __init get_jump_table_addr(void)
return ret;
}
-static void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
- unsigned long npages, enum psc_op op)
+static void __head
+early_set_pages_state(unsigned long vaddr, unsigned long paddr,
+ unsigned long npages, enum psc_op op)
{
unsigned long paddr_end;
u64 val;
@@ -740,7 +742,7 @@ static void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
}
-void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
unsigned long npages)
{
/*
@@ -2045,7 +2047,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
*
* Scan for the blob in that order.
*/
-static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
+static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
{
struct cc_blob_sev_info *cc_info;
@@ -2071,7 +2073,7 @@ static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
return cc_info;
}
-bool __init snp_init(struct boot_params *bp)
+bool __head snp_init(struct boot_params *bp)
{
struct cc_blob_sev_info *cc_info;
@@ -2093,7 +2095,7 @@ bool __init snp_init(struct boot_params *bp)
return true;
}
-void __init __noreturn snp_abort(void)
+void __head __noreturn snp_abort(void)
{
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
}
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 0544700ca50b..e2c3573f53e4 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3126,7 +3126,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
if (pud_none(pud) || !pud_present(pud))
goto out;
- if (pud_large(pud)) {
+ if (pud_leaf(pud)) {
level = PG_LEVEL_1G;
goto out;
}
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index aadefcaa9561..2f4e155080ba 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -52,7 +52,7 @@ enum kvm_only_cpuid_leafs {
#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1)
#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2)
#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3)
-#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
+#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5)
/* CPUID level 0x80000007 (EDX). */
@@ -102,10 +102,12 @@ static const struct cpuid_reg reverse_cpuid[] = {
*/
static __always_inline void reverse_cpuid_check(unsigned int x86_leaf)
{
+ BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_1);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_2);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_3);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_4);
+ BUILD_BUG_ON(x86_leaf == CPUID_LNX_5);
BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid));
BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0);
}
@@ -126,6 +128,7 @@ static __always_inline u32 __feature_translate(int x86_feature)
KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC);
KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
+ KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
default:
return x86_feature;
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index a8ce5226b3b5..86088d1250b3 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -84,9 +84,10 @@ struct enc_region {
};
/* Called with the sev_bitmap_lock held, or on shutdown */
-static int sev_flush_asids(int min_asid, int max_asid)
+static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
{
- int ret, asid, error = 0;
+ int ret, error = 0;
+ unsigned int asid;
/* Check if there are any ASIDs to reclaim before performing a flush */
asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
@@ -116,7 +117,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm)
}
/* Must be called with the sev_bitmap_lock held */
-static bool __sev_recycle_asids(int min_asid, int max_asid)
+static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid)
{
if (sev_flush_asids(min_asid, max_asid))
return false;
@@ -143,8 +144,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev)
static int sev_asid_new(struct kvm_sev_info *sev)
{
- int asid, min_asid, max_asid, ret;
+ /*
+ * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
+ * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
+ * Note: min ASID can end up larger than the max if basic SEV support is
+ * effectively disabled by disallowing use of ASIDs for SEV guests.
+ */
+ unsigned int min_asid = sev->es_active ? 1 : min_sev_asid;
+ unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
+ unsigned int asid;
bool retry = true;
+ int ret;
+
+ if (min_asid > max_asid)
+ return -ENOTTY;
WARN_ON(sev->misc_cg);
sev->misc_cg = get_current_misc_cg();
@@ -157,12 +170,6 @@ static int sev_asid_new(struct kvm_sev_info *sev)
mutex_lock(&sev_bitmap_lock);
- /*
- * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
- * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
- */
- min_asid = sev->es_active ? 1 : min_sev_asid;
- max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
again:
asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
if (asid > max_asid) {
@@ -187,7 +194,7 @@ static int sev_asid_new(struct kvm_sev_info *sev)
return ret;
}
-static int sev_get_asid(struct kvm *kvm)
+static unsigned int sev_get_asid(struct kvm *kvm)
{
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -284,8 +291,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
{
+ unsigned int asid = sev_get_asid(kvm);
struct sev_data_activate activate;
- int asid = sev_get_asid(kvm);
int ret;
/* activate ASID on the given handle */
@@ -2237,8 +2244,10 @@ void __init sev_hardware_setup(void)
goto out;
}
- sev_asid_count = max_sev_asid - min_sev_asid + 1;
- WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
+ if (min_sev_asid <= max_sev_asid) {
+ sev_asid_count = max_sev_asid - min_sev_asid + 1;
+ WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
+ }
sev_supported = true;
/* SEV-ES support requested? */
@@ -2269,7 +2278,9 @@ void __init sev_hardware_setup(void)
out:
if (boot_cpu_has(X86_FEATURE_SEV))
pr_info("SEV %s (ASIDs %u - %u)\n",
- sev_supported ? "enabled" : "disabled",
+ sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
+ "unusable" :
+ "disabled",
min_sev_asid, max_sev_asid);
if (boot_cpu_has(X86_FEATURE_SEV_ES))
pr_info("SEV-ES %s (ASIDs %u - %u)\n",
@@ -2317,7 +2328,7 @@ int sev_cpu_init(struct svm_cpu_data *sd)
*/
static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
{
- int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid;
+ unsigned int asid = sev_get_asid(vcpu->kvm);
/*
* Note! The address must be a kernel address, as regular page walk
@@ -2635,7 +2646,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
void pre_sev_run(struct vcpu_svm *svm, int cpu)
{
struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
- int asid = sev_get_asid(svm->vcpu.kvm);
+ unsigned int asid = sev_get_asid(svm->vcpu.kvm);
/* Assign the asid allocated with this SEV guest */
svm->asid = asid;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 83843379813e..b82e6ed4f024 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -732,13 +732,13 @@ TRACE_EVENT(kvm_nested_intr_vmexit,
* Tracepoint for nested #vmexit because of interrupt pending
*/
TRACE_EVENT(kvm_invlpga,
- TP_PROTO(__u64 rip, int asid, u64 address),
+ TP_PROTO(__u64 rip, unsigned int asid, u64 address),
TP_ARGS(rip, asid, address),
TP_STRUCT__entry(
- __field( __u64, rip )
- __field( int, asid )
- __field( __u64, address )
+ __field( __u64, rip )
+ __field( unsigned int, asid )
+ __field( __u64, address )
),
TP_fast_assign(
@@ -747,7 +747,7 @@ TRACE_EVENT(kvm_invlpga,
__entry->address = address;
),
- TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx",
+ TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx",
__entry->rip, __entry->asid, __entry->address)
);
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 2bfbf758d061..f6986dee6f8c 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -275,6 +275,8 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL)
call vmx_spec_ctrl_restore_host
+ CLEAR_BRANCH_HISTORY_VMEXIT
+
/* Put return value in AX */
mov %_ASM_BX, %_ASM_AX
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ffe580169c93..8e4e48840290 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1624,7 +1624,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr)
ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
- ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR)
+ ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
static u64 kvm_get_arch_capabilities(void)
{
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index ea3a28e7b613..f0dae4fb6d07 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -14,19 +14,6 @@ ifdef CONFIG_KCSAN
CFLAGS_REMOVE_delay.o = $(CC_FLAGS_FTRACE)
endif
-# Early boot use of cmdline; don't instrument it
-ifdef CONFIG_AMD_MEM_ENCRYPT
-KCOV_INSTRUMENT_cmdline.o := n
-KASAN_SANITIZE_cmdline.o := n
-KCSAN_SANITIZE_cmdline.o := n
-
-ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_cmdline.o = -pg
-endif
-
-CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables
-endif
-
inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
quiet_cmd_inat_tables = GEN $@
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 1e59367b4681..5b26a952e2fa 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -229,8 +229,12 @@ SYM_CODE_END(srso_return_thunk)
#define JMP_SRSO_UNTRAIN_RET "ud2"
/* Dummy for the alternative in CALL_UNTRAIN_RET. */
SYM_CODE_START(srso_alias_untrain_ret)
- RET
+ ANNOTATE_UNRET_SAFE
+ ANNOTATE_NOENDBR
+ ret
+ int3
SYM_FUNC_END(srso_alias_untrain_ret)
+__EXPORT_THUNK(srso_alias_untrain_ret)
#endif /* CONFIG_CPU_SRSO */
#ifdef CONFIG_CPU_UNRET_ENTRY
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index d6375b3c633b..b01df023de04 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -376,7 +376,7 @@ static void dump_pagetable(unsigned long address)
goto bad;
pr_cont("PUD %lx ", pud_val(*pud));
- if (!pud_present(*pud) || pud_large(*pud))
+ if (!pud_present(*pud) || pud_leaf(*pud))
goto out;
pmd = pmd_offset(pud, address);
@@ -1037,7 +1037,7 @@ spurious_kernel_fault(unsigned long error_code, unsigned long address)
if (!pud_present(*pud))
return 0;
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
return spurious_kernel_fault_check(error_code, (pte_t *) pud);
pmd = pmd_offset(pud, address);
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index f50cc210a981..968d7005f4a7 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
for (; addr < end; addr = next) {
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
- bool use_gbpage;
next = (addr & PUD_MASK) + PUD_SIZE;
if (next > end)
next = end;
- /* if this is already a gbpage, this portion is already mapped */
- if (pud_large(*pud))
- continue;
-
- /* Is using a gbpage allowed? */
- use_gbpage = info->direct_gbpages;
-
- /* Don't use gbpage if it maps more than the requested region. */
- /* at the begining: */
- use_gbpage &= ((addr & ~PUD_MASK) == 0);
- /* ... or at the end: */
- use_gbpage &= ((next & ~PUD_MASK) == 0);
-
- /* Never overwrite existing mappings */
- use_gbpage &= !pud_present(*pud);
-
- if (use_gbpage) {
+ if (info->direct_gbpages) {
pud_t pudval;
+ if (pud_present(*pud))
+ continue;
+
+ addr &= PUD_MASK;
pudval = __pud((addr - info->offset) | info->page_flag);
set_pud(pud, pudval);
continue;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a0dffaca6d2b..534436c9d399 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -617,7 +617,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
}
if (!pud_none(*pud)) {
- if (!pud_large(*pud)) {
+ if (!pud_leaf(*pud)) {
pmd = pmd_offset(pud, 0);
paddr_last = phys_pmd_init(pmd, paddr,
paddr_end,
@@ -1163,7 +1163,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
if (!pud_present(*pud))
continue;
- if (pud_large(*pud) &&
+ if (pud_leaf(*pud) &&
IS_ALIGNED(addr, PUD_SIZE) &&
IS_ALIGNED(next, PUD_SIZE)) {
spin_lock(&init_mm.page_table_lock);
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 0302491d799d..fcf508c52bdc 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -115,7 +115,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
- if (!pud_large(*pud))
+ if (!pud_leaf(*pud))
kasan_populate_pud(pud, addr, next, nid);
} while (pud++, addr = next, addr != end);
}
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 0166ab1780cc..cc47a818a640 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -41,9 +41,9 @@
#include <linux/mem_encrypt.h>
#include <linux/cc_platform.h>
+#include <asm/init.h>
#include <asm/setup.h>
#include <asm/sections.h>
-#include <asm/cmdline.h>
#include <asm/coco.h>
#include <asm/sev.h>
@@ -95,10 +95,7 @@ struct sme_populate_pgd_data {
*/
static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch");
-static char sme_cmdline_arg[] __initdata = "mem_encrypt";
-static char sme_cmdline_on[] __initdata = "on";
-
-static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
+static void __head sme_clear_pgd(struct sme_populate_pgd_data *ppd)
{
unsigned long pgd_start, pgd_end, pgd_size;
pgd_t *pgd_p;
@@ -113,7 +110,7 @@ static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
memset(pgd_p, 0, pgd_size);
}
-static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
+static pud_t __head *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
{
pgd_t *pgd;
p4d_t *p4d;
@@ -144,13 +141,13 @@ static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
set_pud(pud, __pud(PUD_FLAGS | __pa(pmd)));
}
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
return NULL;
return pud;
}
-static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
+static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
{
pud_t *pud;
pmd_t *pmd;
@@ -166,7 +163,7 @@ static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags));
}
-static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
+static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd)
{
pud_t *pud;
pmd_t *pmd;
@@ -192,7 +189,7 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
set_pte(pte, __pte(ppd->paddr | ppd->pte_flags));
}
-static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
+static void __head __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
{
while (ppd->vaddr < ppd->vaddr_end) {
sme_populate_pgd_large(ppd);
@@ -202,7 +199,7 @@ static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
}
}
-static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
+static void __head __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
{
while (ppd->vaddr < ppd->vaddr_end) {
sme_populate_pgd(ppd);
@@ -212,7 +209,7 @@ static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
}
}
-static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
+static void __head __sme_map_range(struct sme_populate_pgd_data *ppd,
pmdval_t pmd_flags, pteval_t pte_flags)
{
unsigned long vaddr_end;
@@ -236,22 +233,22 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
__sme_map_range_pte(ppd);
}
-static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
+static void __head sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
{
__sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
}
-static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
+static void __head sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
{
__sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
}
-static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
+static void __head sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
{
__sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
}
-static unsigned long __init sme_pgtable_calc(unsigned long len)
+static unsigned long __head sme_pgtable_calc(unsigned long len)
{
unsigned long entries = 0, tables = 0;
@@ -288,7 +285,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
return entries + tables;
}
-void __init sme_encrypt_kernel(struct boot_params *bp)
+void __head sme_encrypt_kernel(struct boot_params *bp)
{
unsigned long workarea_start, workarea_end, workarea_len;
unsigned long execute_start, execute_end, execute_len;
@@ -323,9 +320,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
* memory from being cached.
*/
- /* Physical addresses gives us the identity mapped virtual addresses */
- kernel_start = __pa_symbol(_text);
- kernel_end = ALIGN(__pa_symbol(_end), PMD_SIZE);
+ kernel_start = (unsigned long)RIP_REL_REF(_text);
+ kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE);
kernel_len = kernel_end - kernel_start;
initrd_start = 0;
@@ -342,14 +338,6 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
}
#endif
- /*
- * We're running identity mapped, so we must obtain the address to the
- * SME encryption workarea using rip-relative addressing.
- */
- asm ("lea sme_workarea(%%rip), %0"
- : "=r" (workarea_start)
- : "p" (sme_workarea));
-
/*
* Calculate required number of workarea bytes needed:
* executable encryption area size:
@@ -359,7 +347,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
* pagetable structures for the encryption of the kernel
* pagetable structures for workarea (in case not currently mapped)
*/
- execute_start = workarea_start;
+ execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea);
execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE;
execute_len = execute_end - execute_start;
@@ -502,13 +490,11 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
native_write_cr3(__native_read_cr3());
}
-void __init sme_enable(struct boot_params *bp)
+void __head sme_enable(struct boot_params *bp)
{
- const char *cmdline_ptr, *cmdline_arg, *cmdline_on;
unsigned int eax, ebx, ecx, edx;
unsigned long feature_mask;
unsigned long me_mask;
- char buffer[16];
bool snp;
u64 msr;
@@ -551,6 +537,9 @@ void __init sme_enable(struct boot_params *bp)
/* Check if memory encryption is enabled */
if (feature_mask == AMD_SME_BIT) {
+ if (!(bp->hdr.xloadflags & XLF_MEM_ENCRYPTION))
+ return;
+
/*
* No SME if Hypervisor bit is set. This check is here to
* prevent a guest from trying to enable SME. For running as a
@@ -570,31 +559,8 @@ void __init sme_enable(struct boot_params *bp)
msr = __rdmsr(MSR_AMD64_SYSCFG);
if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
return;
- } else {
- /* SEV state cannot be controlled by a command line option */
- goto out;
}
- /*
- * Fixups have not been applied to phys_base yet and we're running
- * identity mapped, so we must obtain the address to the SME command
- * line argument data using rip-relative addressing.
- */
- asm ("lea sme_cmdline_arg(%%rip), %0"
- : "=r" (cmdline_arg)
- : "p" (sme_cmdline_arg));
- asm ("lea sme_cmdline_on(%%rip), %0"
- : "=r" (cmdline_on)
- : "p" (sme_cmdline_on));
-
- cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
- ((u64)bp->ext_cmd_line_ptr << 32));
-
- if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0 ||
- strncmp(buffer, cmdline_on, sizeof(buffer)))
- return;
-
-out:
RIP_REL_REF(sme_me_mask) = me_mask;
physical_mask &= ~me_mask;
cc_vendor = CC_VENDOR_AMD;
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 0904d7e8e126..37d51cfd77cb 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -950,6 +950,38 @@ static void free_pfn_range(u64 paddr, unsigned long size)
memtype_free(paddr, paddr + size);
}
+static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
+ pgprot_t *pgprot)
+{
+ unsigned long prot;
+
+ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
+
+ /*
+ * We need the starting PFN and cachemode used for track_pfn_remap()
+ * that covered the whole VMA. For most mappings, we can obtain that
+ * information from the page tables. For COW mappings, we might now
+ * suddenly have anon folios mapped and follow_phys() will fail.
+ *
+ * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
+ * detect the PFN. If we need the cachemode as well, we're out of luck
+ * for now and have to fail fork().
+ */
+ if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) {
+ if (pgprot)
+ *pgprot = __pgprot(prot);
+ return 0;
+ }
+ if (is_cow_mapping(vma->vm_flags)) {
+ if (pgprot)
+ return -EINVAL;
+ *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+ return 0;
+ }
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+}
+
/*
* track_pfn_copy is called when vma that is covering the pfnmap gets
* copied through copy_page_range().
@@ -960,20 +992,13 @@ static void free_pfn_range(u64 paddr, unsigned long size)
int track_pfn_copy(struct vm_area_struct *vma)
{
resource_size_t paddr;
- unsigned long prot;
unsigned long vma_size = vma->vm_end - vma->vm_start;
pgprot_t pgprot;
if (vma->vm_flags & VM_PAT) {
- /*
- * reserve the whole chunk covered by vma. We need the
- * starting address and protection from pte.
- */
- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
- WARN_ON_ONCE(1);
+ if (get_pat_info(vma, &paddr, &pgprot))
return -EINVAL;
- }
- pgprot = __pgprot(prot);
+ /* reserve the whole chunk covered by vma. */
return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
}
@@ -1048,7 +1073,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size, bool mm_wr_locked)
{
resource_size_t paddr;
- unsigned long prot;
if (vma && !(vma->vm_flags & VM_PAT))
return;
@@ -1056,11 +1080,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
/* free the chunk starting from pfn or the whole chunk */
paddr = (resource_size_t)pfn << PAGE_SHIFT;
if (!paddr && !size) {
- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
- WARN_ON_ONCE(1);
+ if (get_pat_info(vma, &paddr, NULL))
return;
- }
-
size = vma->vm_end - vma->vm_start;
}
free_pfn_range(paddr, size);
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 102880404046..135bb594df8b 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -684,7 +684,7 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
return NULL;
*level = PG_LEVEL_1G;
- if (pud_large(*pud) || !pud_present(*pud))
+ if (pud_leaf(*pud) || !pud_present(*pud))
return (pte_t *)pud;
pmd = pmd_offset(pud, address);
@@ -743,7 +743,7 @@ pmd_t *lookup_pmd_address(unsigned long address)
return NULL;
pud = pud_offset(p4d, address);
- if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud))
+ if (pud_none(*pud) || pud_leaf(*pud) || !pud_present(*pud))
return NULL;
return pmd_offset(pud, address);
@@ -1278,7 +1278,7 @@ static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end)
*/
while (end - start >= PUD_SIZE) {
- if (pud_large(*pud))
+ if (pud_leaf(*pud))
pud_clear(pud);
else
unmap_pmd_range(pud, start, start + PUD_SIZE);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 0cbc1b8e8e3d..a67bb8f982bd 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -777,7 +777,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
*/
int pud_clear_huge(pud_t *pud)
{
- if (pud_large(*pud)) {
+ if (pud_leaf(*pud)) {
pud_clear(pud);
return 1;
}
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 669ba1c345b3..912b1da7ed80 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -217,7 +217,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
pud = pud_offset(p4d, address);
/* The user page tables do not use large mappings: */
- if (pud_large(*pud)) {
+ if (pud_leaf(*pud)) {
WARN_ON(1);
return NULL;
}
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 919f647c740f..df484885ccd4 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -466,7 +466,7 @@ static int emit_call(u8 **pprog, void *func, void *ip)
static int emit_rsb_call(u8 **pprog, void *func, void *ip)
{
OPTIMIZER_HIDE_VAR(func);
- x86_call_depth_emit_accounting(pprog, func);
+ ip += x86_call_depth_emit_accounting(pprog, func);
return emit_patch(pprog, func, ip, 0xE8);
}
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
index 6f955eb1e163..d8af46e67750 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -170,7 +170,7 @@ int relocate_restore_code(void)
goto out;
}
pud = pud_offset(p4d, relocated_restore_code);
- if (pud_large(*pud)) {
+ if (pud_leaf(*pud)) {
set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
goto out;
}
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 72af496a160c..994aef4473a6 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1082,7 +1082,7 @@ static void __init xen_cleanmfnmap_pud(pud_t *pud, bool unpin)
pmd_t *pmd_tbl;
int i;
- if (pud_large(*pud)) {
+ if (pud_leaf(*pud)) {
pa = pud_val(*pud) & PHYSICAL_PAGE_MASK;
xen_free_ro_pages(pa, PUD_SIZE);
return;
@@ -1863,7 +1863,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
if (!pud_present(pud))
return 0;
pa = pud_val(pud) & PTE_PFN_MASK;
- if (pud_large(pud))
+ if (pud_leaf(pud))
return pa + (vaddr & ~PUD_MASK);
pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) *
diff --git a/block/bdev.c b/block/bdev.c
index e9f1b12bd75c..678807bcd003 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -738,17 +738,17 @@ void blkdev_put_no_open(struct block_device *bdev)
static bool bdev_writes_blocked(struct block_device *bdev)
{
- return bdev->bd_writers == -1;
+ return bdev->bd_writers < 0;
}
static void bdev_block_writes(struct block_device *bdev)
{
- bdev->bd_writers = -1;
+ bdev->bd_writers--;
}
static void bdev_unblock_writes(struct block_device *bdev)
{
- bdev->bd_writers = 0;
+ bdev->bd_writers++;
}
static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode)
diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c
index b91155ea9c34..c9131259f717 100644
--- a/drivers/acpi/acpica/dbnames.c
+++ b/drivers/acpi/acpica/dbnames.c
@@ -550,8 +550,12 @@ acpi_db_walk_for_fields(acpi_handle obj_handle,
ACPI_FREE(buffer.pointer);
buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER;
- acpi_evaluate_object(obj_handle, NULL, NULL, &buffer);
-
+ status = acpi_evaluate_object(obj_handle, NULL, NULL, &buffer);
+ if (ACPI_FAILURE(status)) {
+ acpi_os_printf("Could Not evaluate object %p\n",
+ obj_handle);
+ return (AE_OK);
+ }
/*
* Since this is a field unit, surround the output in braces
*/
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index e82786c63fbd..9bec0aee92e0 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -787,37 +787,6 @@ static const struct ata_port_info mv_port_info[] = {
},
};
-static const struct pci_device_id mv_pci_tbl[] = {
- { PCI_VDEVICE(MARVELL, 0x5040), chip_504x },
- { PCI_VDEVICE(MARVELL, 0x5041), chip_504x },
- { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 },
- { PCI_VDEVICE(MARVELL, 0x5081), chip_508x },
- /* RocketRAID 1720/174x have different identifiers */
- { PCI_VDEVICE(TTI, 0x1720), chip_6042 },
- { PCI_VDEVICE(TTI, 0x1740), chip_6042 },
- { PCI_VDEVICE(TTI, 0x1742), chip_6042 },
-
- { PCI_VDEVICE(MARVELL, 0x6040), chip_604x },
- { PCI_VDEVICE(MARVELL, 0x6041), chip_604x },
- { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 },
- { PCI_VDEVICE(MARVELL, 0x6080), chip_608x },
- { PCI_VDEVICE(MARVELL, 0x6081), chip_608x },
-
- { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x },
-
- /* Adaptec 1430SA */
- { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 },
-
- /* Marvell 7042 support */
- { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 },
-
- /* Highpoint RocketRAID PCIe series */
- { PCI_VDEVICE(TTI, 0x2300), chip_7042 },
- { PCI_VDEVICE(TTI, 0x2310), chip_7042 },
-
- { } /* terminate list */
-};
-
static const struct mv_hw_ops mv5xxx_ops = {
.phy_errata = mv5_phy_errata,
.enable_leds = mv5_enable_leds,
@@ -4303,6 +4272,36 @@ static int mv_pci_init_one(struct pci_dev *pdev,
static int mv_pci_device_resume(struct pci_dev *pdev);
#endif
+static const struct pci_device_id mv_pci_tbl[] = {
+ { PCI_VDEVICE(MARVELL, 0x5040), chip_504x },
+ { PCI_VDEVICE(MARVELL, 0x5041), chip_504x },
+ { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 },
+ { PCI_VDEVICE(MARVELL, 0x5081), chip_508x },
+ /* RocketRAID 1720/174x have different identifiers */
+ { PCI_VDEVICE(TTI, 0x1720), chip_6042 },
+ { PCI_VDEVICE(TTI, 0x1740), chip_6042 },
+ { PCI_VDEVICE(TTI, 0x1742), chip_6042 },
+
+ { PCI_VDEVICE(MARVELL, 0x6040), chip_604x },
+ { PCI_VDEVICE(MARVELL, 0x6041), chip_604x },
+ { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 },
+ { PCI_VDEVICE(MARVELL, 0x6080), chip_608x },
+ { PCI_VDEVICE(MARVELL, 0x6081), chip_608x },
+
+ { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x },
+
+ /* Adaptec 1430SA */
+ { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 },
+
+ /* Marvell 7042 support */
+ { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 },
+
+ /* Highpoint RocketRAID PCIe series */
+ { PCI_VDEVICE(TTI, 0x2300), chip_7042 },
+ { PCI_VDEVICE(TTI, 0x2310), chip_7042 },
+
+ { } /* terminate list */
+};
static struct pci_driver mv_pci_driver = {
.name = DRV_NAME,
@@ -4315,6 +4314,7 @@ static struct pci_driver mv_pci_driver = {
#endif
};
+MODULE_DEVICE_TABLE(pci, mv_pci_tbl);
/**
* mv_print_info - Dump key info to kernel log for perusal.
@@ -4487,7 +4487,6 @@ static void __exit mv_exit(void)
MODULE_AUTHOR("Brett Russ");
MODULE_DESCRIPTION("SCSI low-level driver for Marvell SATA controllers");
MODULE_LICENSE("GPL v2");
-MODULE_DEVICE_TABLE(pci, mv_pci_tbl);
MODULE_VERSION(DRV_VERSION);
MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index b51d7a9d0d90..a482741eb181 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -957,8 +957,7 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource,
offset -= (idx * window_size);
idx++;
- dist = ((long) (window_size - (offset + size))) >= 0 ? size :
- (long) (window_size - offset);
+ dist = min(size, window_size - offset);
memcpy_fromio(psource, dimm_mmio + offset / 4, dist);
psource += dist;
@@ -1005,8 +1004,7 @@ static void pdc20621_put_to_dimm(struct ata_host *host, void *psource,
readl(mmio + PDC_DIMM_WINDOW_CTLR);
offset -= (idx * window_size);
idx++;
- dist = ((long)(s32)(window_size - (offset + size))) >= 0 ? size :
- (long) (window_size - offset);
+ dist = min(size, window_size - offset);
memcpy_toio(dimm_mmio + offset / 4, psource, dist);
writel(0x01, mmio + PDC_GENERAL_CTLR);
readl(mmio + PDC_GENERAL_CTLR);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 9828da9b933c..7f39c813ce52 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -44,6 +44,7 @@ static bool fw_devlink_is_permissive(void);
static void __fw_devlink_link_to_consumers(struct device *dev);
static bool fw_devlink_drv_reg_done;
static bool fw_devlink_best_effort;
+static struct workqueue_struct *device_link_wq;
/**
* __fwnode_link_add - Create a link between two fwnode_handles.
@@ -532,12 +533,26 @@ static void devlink_dev_release(struct device *dev)
/*
* It may take a while to complete this work because of the SRCU
* synchronization in device_link_release_fn() and if the consumer or
- * supplier devices get deleted when it runs, so put it into the "long"
- * workqueue.
+ * supplier devices get deleted when it runs, so put it into the
+ * dedicated workqueue.
*/
- queue_work(system_long_wq, &link->rm_work);
+ queue_work(device_link_wq, &link->rm_work);
}
+/**
+ * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate
+ */
+void device_link_wait_removal(void)
+{
+ /*
+ * devlink removal jobs are queued in the dedicated work queue.
+ * To be sure that all removal jobs are terminated, ensure that any
+ * scheduled work has run to completion.
+ */
+ flush_workqueue(device_link_wq);
+}
+EXPORT_SYMBOL_GPL(device_link_wait_removal);
+
static struct class devlink_class = {
.name = "devlink",
.dev_groups = devlink_groups,
@@ -4098,9 +4113,14 @@ int __init devices_init(void)
sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj);
if (!sysfs_dev_char_kobj)
goto char_kobj_err;
+ device_link_wq = alloc_workqueue("device_link_wq", 0, 0);
+ if (!device_link_wq)
+ goto wq_err;
return 0;
+ wq_err:
+ kobject_put(sysfs_dev_char_kobj);
char_kobj_err:
kobject_put(sysfs_dev_block_kobj);
block_kobj_err:
diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c
index 41edd6a430eb..55999a50ccc0 100644
--- a/drivers/base/regmap/regcache-maple.c
+++ b/drivers/base/regmap/regcache-maple.c
@@ -112,7 +112,7 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min,
unsigned long *entry, *lower, *upper;
unsigned long lower_index, lower_last;
unsigned long upper_index, upper_last;
- int ret;
+ int ret = 0;
lower = NULL;
upper = NULL;
@@ -145,7 +145,7 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min,
upper_index = max + 1;
upper_last = mas.last;
- upper = kmemdup(&entry[max + 1],
+ upper = kmemdup(&entry[max - mas.index + 1],
((mas.last - max) *
sizeof(unsigned long)),
map->alloc_flags);
@@ -244,7 +244,7 @@ static int regcache_maple_sync(struct regmap *map, unsigned int min,
unsigned long lmin = min;
unsigned long lmax = max;
unsigned int r, v, sync_start;
- int ret;
+ int ret = 0;
bool sync_needed = false;
map->cache_bypass = true;
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index b40b32fa7f1c..19cfc342fc7b 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -826,11 +826,15 @@ EXPORT_SYMBOL_GPL(qca_uart_setup);
int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
{
+ bdaddr_t bdaddr_swapped;
struct sk_buff *skb;
int err;
- skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6, bdaddr,
- HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
+ baswap(&bdaddr_swapped, bdaddr);
+
+ skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6,
+ &bdaddr_swapped, HCI_EV_VENDOR,
+ HCI_INIT_TIMEOUT);
if (IS_ERR(skb)) {
err = PTR_ERR(skb);
bt_dev_err(hdev, "QCA Change address cmd failed (%d)", err);
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 8a60ad7acd70..ecbc52eaf101 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -7,7 +7,6 @@
*
* Copyright (C) 2007 Texas Instruments, Inc.
* Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved.
- * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
*
* Acknowledgements:
* This file is based on hci_ll.c, which was...
@@ -226,6 +225,7 @@ struct qca_serdev {
struct qca_power *bt_power;
u32 init_speed;
u32 oper_speed;
+ bool bdaddr_property_broken;
const char *firmware_name;
};
@@ -1843,6 +1843,7 @@ static int qca_setup(struct hci_uart *hu)
const char *firmware_name = qca_get_firmware_name(hu);
int ret;
struct qca_btsoc_version ver;
+ struct qca_serdev *qcadev;
const char *soc_name;
ret = qca_check_speeds(hu);
@@ -1904,16 +1905,11 @@ static int qca_setup(struct hci_uart *hu)
case QCA_WCN6750:
case QCA_WCN6855:
case QCA_WCN7850:
+ set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
- /* Set BDA quirk bit for reading BDA value from fwnode property
- * only if that property exist in DT.
- */
- if (fwnode_property_present(dev_fwnode(hdev->dev.parent), "local-bd-address")) {
- set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
- bt_dev_info(hdev, "setting quirk bit to read BDA from fwnode later");
- } else {
- bt_dev_dbg(hdev, "local-bd-address` is not present in the devicetree so not setting quirk bit for BDA");
- }
+ qcadev = serdev_device_get_drvdata(hu->serdev);
+ if (qcadev->bdaddr_property_broken)
+ set_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks);
hci_set_aosp_capable(hdev);
@@ -2295,6 +2291,9 @@ static int qca_serdev_probe(struct serdev_device *serdev)
if (!qcadev->oper_speed)
BT_DBG("UART will pick default operating speed");
+ qcadev->bdaddr_property_broken = device_property_read_bool(&serdev->dev,
+ "qcom,local-bd-address-broken");
+
if (data)
qcadev->btsoc_type = data->soc_type;
else
diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c
index 9c2a0c082a76..ed4b323886e4 100644
--- a/drivers/dma-buf/st-dma-fence-chain.c
+++ b/drivers/dma-buf/st-dma-fence-chain.c
@@ -84,11 +84,11 @@ static int sanitycheck(void *arg)
return -ENOMEM;
chain = mock_chain(NULL, f, 1);
- if (!chain)
+ if (chain)
+ dma_fence_enable_sw_signaling(chain);
+ else
err = -ENOMEM;
- dma_fence_enable_sw_signaling(chain);
-
dma_fence_signal(f);
dma_fence_put(f);
diff --git a/drivers/dpll/Kconfig b/drivers/dpll/Kconfig
index a4cae73f20d3..20607ed54243 100644
--- a/drivers/dpll/Kconfig
+++ b/drivers/dpll/Kconfig
@@ -4,4 +4,4 @@
#
config DPLL
- bool
+ bool
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index bfa30625f5d0..3dc2f9aaf08d 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -24,6 +24,8 @@ static bool efi_noinitrd;
static bool efi_nosoftreserve;
static bool efi_disable_pci_dma = IS_ENABLED(CONFIG_EFI_DISABLE_PCI_DMA);
+int efi_mem_encrypt;
+
bool __pure __efi_soft_reserve_enabled(void)
{
return !efi_nosoftreserve;
@@ -75,6 +77,12 @@ efi_status_t efi_parse_options(char const *cmdline)
efi_noinitrd = true;
} else if (IS_ENABLED(CONFIG_X86_64) && !strcmp(param, "no5lvl")) {
efi_no5lvl = true;
+ } else if (IS_ENABLED(CONFIG_ARCH_HAS_MEM_ENCRYPT) &&
+ !strcmp(param, "mem_encrypt") && val) {
+ if (parse_option_str(val, "on"))
+ efi_mem_encrypt = 1;
+ else if (parse_option_str(val, "off"))
+ efi_mem_encrypt = -1;
} else if (!strcmp(param, "efi") && val) {
efi_nochunk = parse_option_str(val, "nochunk");
efi_novamap |= parse_option_str(val, "novamap");
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index c04b82ea40f2..fc18fd649ed7 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -37,8 +37,8 @@ extern bool efi_no5lvl;
extern bool efi_nochunk;
extern bool efi_nokaslr;
extern int efi_loglevel;
+extern int efi_mem_encrypt;
extern bool efi_novamap;
-
extern const efi_system_table_t *efi_system_table;
typedef union efi_dxe_services_table efi_dxe_services_table_t;
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index dd80082aac1a..19b51dc34f67 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -238,6 +238,15 @@ efi_status_t efi_adjust_memory_range_protection(unsigned long start,
rounded_end = roundup(start + size, EFI_PAGE_SIZE);
if (memattr != NULL) {
+ status = efi_call_proto(memattr, set_memory_attributes,
+ rounded_start,
+ rounded_end - rounded_start,
+ EFI_MEMORY_RO);
+ if (status != EFI_SUCCESS) {
+ efi_warn("Failed to set EFI_MEMORY_RO attribute\n");
+ return status;
+ }
+
status = efi_call_proto(memattr, clear_memory_attributes,
rounded_start,
rounded_end - rounded_start,
@@ -818,7 +827,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
*kernel_entry = addr + entry;
- return efi_adjust_memory_range_protection(addr, kernel_total_size);
+ return efi_adjust_memory_range_protection(addr, kernel_text_size);
}
static void __noreturn enter_kernel(unsigned long kernel_addr,
@@ -890,6 +899,9 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
}
}
+ if (efi_mem_encrypt > 0)
+ hdr->xloadflags |= XLF_MEM_ENCRYPTION;
+
status = efi_decompress_kernel(&kernel_entry);
if (status != EFI_SUCCESS) {
efi_err("Failed to decompress kernel\n");
diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c
index 2a88736629ef..1438fdca0b74 100644
--- a/drivers/gpio/gpiolib-cdev.c
+++ b/drivers/gpio/gpiolib-cdev.c
@@ -734,6 +734,25 @@ static u32 line_event_id(int level)
GPIO_V2_LINE_EVENT_FALLING_EDGE;
}
+static inline char *make_irq_label(const char *orig)
+{
+ char *new;
+
+ if (!orig)
+ return NULL;
+
+ new = kstrdup_and_replace(orig, '/', ':', GFP_KERNEL);
+ if (!new)
+ return ERR_PTR(-ENOMEM);
+
+ return new;
+}
+
+static inline void free_irq_label(const char *label)
+{
+ kfree(label);
+}
+
#ifdef CONFIG_HTE
static enum hte_return process_hw_ts_thread(void *p)
@@ -1021,6 +1040,7 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us)
{
unsigned long irqflags;
int ret, level, irq;
+ char *label;
/* try hardware */
ret = gpiod_set_debounce(line->desc, debounce_period_us);
@@ -1043,11 +1063,17 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us)
if (irq < 0)
return -ENXIO;
+ label = make_irq_label(line->req->label);
+ if (IS_ERR(label))
+ return -ENOMEM;
+
irqflags = IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING;
ret = request_irq(irq, debounce_irq_handler, irqflags,
- line->req->label, line);
- if (ret)
+ label, line);
+ if (ret) {
+ free_irq_label(label);
return ret;
+ }
line->irq = irq;
} else {
ret = hte_edge_setup(line, GPIO_V2_LINE_FLAG_EDGE_BOTH);
@@ -1092,7 +1118,7 @@ static u32 gpio_v2_line_config_debounce_period(struct gpio_v2_line_config *lc,
static void edge_detector_stop(struct line *line)
{
if (line->irq) {
- free_irq(line->irq, line);
+ free_irq_label(free_irq(line->irq, line));
line->irq = 0;
}
@@ -1116,6 +1142,7 @@ static int edge_detector_setup(struct line *line,
unsigned long irqflags = 0;
u64 eflags;
int irq, ret;
+ char *label;
eflags = edflags & GPIO_V2_LINE_EDGE_FLAGS;
if (eflags && !kfifo_initialized(&line->req->events)) {
@@ -1152,11 +1179,17 @@ static int edge_detector_setup(struct line *line,
IRQF_TRIGGER_RISING : IRQF_TRIGGER_FALLING;
irqflags |= IRQF_ONESHOT;
+ label = make_irq_label(line->req->label);
+ if (IS_ERR(label))
+ return PTR_ERR(label);
+
/* Request a thread to read the events */
ret = request_threaded_irq(irq, edge_irq_handler, edge_irq_thread,
- irqflags, line->req->label, line);
- if (ret)
+ irqflags, label, line);
+ if (ret) {
+ free_irq_label(label);
return ret;
+ }
line->irq = irq;
return 0;
@@ -1979,7 +2012,7 @@ static void lineevent_free(struct lineevent_state *le)
blocking_notifier_chain_unregister(&le->gdev->device_notifier,
&le->device_unregistered_nb);
if (le->irq)
- free_irq(le->irq, le);
+ free_irq_label(free_irq(le->irq, le));
if (le->desc)
gpiod_free(le->desc);
kfree(le->label);
@@ -2120,6 +2153,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
int fd;
int ret;
int irq, irqflags = 0;
+ char *label;
if (copy_from_user(&eventreq, ip, sizeof(eventreq)))
return -EFAULT;
@@ -2204,15 +2238,23 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
if (ret)
goto out_free_le;
+ label = make_irq_label(le->label);
+ if (IS_ERR(label)) {
+ ret = PTR_ERR(label);
+ goto out_free_le;
+ }
+
/* Request a thread to read the events */
ret = request_threaded_irq(irq,
lineevent_irq_handler,
lineevent_irq_thread,
irqflags,
- le->label,
+ label,
le);
- if (ret)
+ if (ret) {
+ free_irq_label(label);
goto out_free_le;
+ }
le->irq = irq;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 3ad09d219333..d9da0331e834 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2402,6 +2402,11 @@ char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset)
}
EXPORT_SYMBOL_GPL(gpiochip_dup_line_label);
+static inline const char *function_name_or_default(const char *con_id)
+{
+ return con_id ?: "(default)";
+}
+
/**
* gpiochip_request_own_desc - Allow GPIO chip to request its own descriptor
* @gc: GPIO chip
@@ -2430,10 +2435,11 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc,
enum gpiod_flags dflags)
{
struct gpio_desc *desc = gpiochip_get_desc(gc, hwnum);
+ const char *name = function_name_or_default(label);
int ret;
if (IS_ERR(desc)) {
- chip_err(gc, "failed to get GPIO descriptor\n");
+ chip_err(gc, "failed to get GPIO %s descriptor\n", name);
return desc;
}
@@ -2443,8 +2449,8 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc,
ret = gpiod_configure_flags(desc, label, lflags, dflags);
if (ret) {
- chip_err(gc, "setup of own GPIO %s failed\n", label);
gpiod_free_commit(desc);
+ chip_err(gc, "setup of own GPIO %s failed\n", name);
return ERR_PTR(ret);
}
@@ -4119,19 +4125,17 @@ static struct gpio_desc *gpiod_find_by_fwnode(struct fwnode_handle *fwnode,
enum gpiod_flags *flags,
unsigned long *lookupflags)
{
+ const char *name = function_name_or_default(con_id);
struct gpio_desc *desc = ERR_PTR(-ENOENT);
if (is_of_node(fwnode)) {
- dev_dbg(consumer, "using DT '%pfw' for '%s' GPIO lookup\n",
- fwnode, con_id);
+ dev_dbg(consumer, "using DT '%pfw' for '%s' GPIO lookup\n", fwnode, name);
desc = of_find_gpio(to_of_node(fwnode), con_id, idx, lookupflags);
} else if (is_acpi_node(fwnode)) {
- dev_dbg(consumer, "using ACPI '%pfw' for '%s' GPIO lookup\n",
- fwnode, con_id);
+ dev_dbg(consumer, "using ACPI '%pfw' for '%s' GPIO lookup\n", fwnode, name);
desc = acpi_find_gpio(fwnode, con_id, idx, flags, lookupflags);
} else if (is_software_node(fwnode)) {
- dev_dbg(consumer, "using swnode '%pfw' for '%s' GPIO lookup\n",
- fwnode, con_id);
+ dev_dbg(consumer, "using swnode '%pfw' for '%s' GPIO lookup\n", fwnode, name);
desc = swnode_find_gpio(fwnode, con_id, idx, lookupflags);
}
@@ -4147,6 +4151,7 @@ struct gpio_desc *gpiod_find_and_request(struct device *consumer,
bool platform_lookup_allowed)
{
unsigned long lookupflags = GPIO_LOOKUP_FLAGS_DEFAULT;
+ const char *name = function_name_or_default(con_id);
struct gpio_desc *desc;
int ret;
@@ -4162,7 +4167,7 @@ struct gpio_desc *gpiod_find_and_request(struct device *consumer,
}
if (IS_ERR(desc)) {
- dev_dbg(consumer, "No GPIO consumer %s found\n", con_id);
+ dev_dbg(consumer, "No GPIO consumer %s found\n", name);
return desc;
}
@@ -4183,15 +4188,14 @@ struct gpio_desc *gpiod_find_and_request(struct device *consumer,
*
* FIXME: Make this more sane and safe.
*/
- dev_info(consumer,
- "nonexclusive access to GPIO for %s\n", con_id);
+ dev_info(consumer, "nonexclusive access to GPIO for %s\n", name);
return desc;
}
ret = gpiod_configure_flags(desc, con_id, lookupflags, flags);
if (ret < 0) {
- dev_dbg(consumer, "setup of GPIO %s failed\n", con_id);
gpiod_put(desc);
+ dev_dbg(consumer, "setup of GPIO %s failed\n", name);
return ERR_PTR(ret);
}
@@ -4307,6 +4311,7 @@ EXPORT_SYMBOL_GPL(gpiod_get_optional);
int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
unsigned long lflags, enum gpiod_flags dflags)
{
+ const char *name = function_name_or_default(con_id);
int ret;
if (lflags & GPIO_ACTIVE_LOW)
@@ -4350,7 +4355,7 @@ int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
/* No particular flag request, return here... */
if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) {
- gpiod_dbg(desc, "no flags found for %s\n", con_id);
+ gpiod_dbg(desc, "no flags found for GPIO %s\n", name);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 94bdb5fa6ebc..1fbaf7b81d69 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4524,6 +4524,8 @@ int amdgpu_device_prepare(struct drm_device *dev)
if (r)
goto unprepare;
+ flush_delayed_work(&adev->gfx.gfx_off_delay_work);
+
for (i = 0; i < adev->num_ip_blocks; i++) {
if (!adev->ip_blocks[i].status.valid)
continue;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 3db46bdc71a3..9cbab880c623 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -384,19 +384,6 @@ static void dcn35_enable_pme_wa(struct clk_mgr *clk_mgr_base)
dcn35_smu_enable_pme_wa(clk_mgr);
}
-void dcn35_init_clocks(struct clk_mgr *clk_mgr)
-{
- uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
-
- memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
-
- // Assumption is that boot state always supports pstate
- clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk; // restore ref_dtbclk
- clk_mgr->clks.p_state_change_support = true;
- clk_mgr->clks.prev_p_state_change_support = true;
- clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
- clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
-}
bool dcn35_are_clock_states_equal(struct dc_clocks *a,
struct dc_clocks *b)
@@ -421,7 +408,19 @@ static void dcn35_dump_clk_registers(struct clk_state_registers_and_bypass *regs
struct clk_mgr_dcn35 *clk_mgr)
{
}
+void dcn35_init_clocks(struct clk_mgr *clk_mgr)
+{
+ uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
+ memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
+
+ // Assumption is that boot state always supports pstate
+ clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk; // restore ref_dtbclk
+ clk_mgr->clks.p_state_change_support = true;
+ clk_mgr->clks.prev_p_state_change_support = true;
+ clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
+ clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
+}
static struct clk_bw_params dcn35_bw_params = {
.vram_type = Ddr4MemType,
.num_channels = 1,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/Makefile b/drivers/gpu/drm/amd/display/dc/dce110/Makefile
index f0777d61c2cb..c307f040e48f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce110/Makefile
@@ -23,7 +23,7 @@
# Makefile for the 'controller' sub-component of DAL.
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = -Wno-override-init
DCE110 = dce110_timing_generator.o \
dce110_compressor.o dce110_opp_regamma_v.o \
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/Makefile b/drivers/gpu/drm/amd/display/dc/dce112/Makefile
index 7e92effec894..683866797709 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce112/Makefile
@@ -23,7 +23,7 @@
# Makefile for the 'controller' sub-component of DAL.
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = -Wno-override-init
DCE112 = dce112_compressor.o
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/Makefile b/drivers/gpu/drm/amd/display/dc/dce120/Makefile
index 1e3ef68a452a..8f508e662748 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce120/Makefile
@@ -24,7 +24,7 @@
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = -Wno-override-init
DCE120 = dce120_timing_generator.o
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/Makefile b/drivers/gpu/drm/amd/display/dc/dce60/Makefile
index fee331accc0e..eede83ad91fa 100644
--- a/drivers/gpu/drm/amd/display/dc/dce60/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce60/Makefile
@@ -23,7 +23,7 @@
# Makefile for the 'controller' sub-component of DAL.
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = -Wno-override-init
DCE60 = dce60_timing_generator.o dce60_hw_sequencer.o \
dce60_resource.o
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/Makefile b/drivers/gpu/drm/amd/display/dc/dce80/Makefile
index 7eefffbdc925..fba189d26652 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce80/Makefile
@@ -23,7 +23,7 @@
# Makefile for the 'controller' sub-component of DAL.
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = -Wno-override-init
DCE80 = dce80_timing_generator.o
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 5fdcda8f8602..04d230aa8861 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -701,7 +701,7 @@ static const struct dc_plane_cap plane_cap = {
// 6:1 downscaling ratio: 1000/6 = 166.666
.max_downscale_factor = {
- .argb8888 = 167,
+ .argb8888 = 250,
.nv12 = 167,
.fp16 = 167
},
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 7352bde299d5..03bd3c7bd0dc 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -582,7 +582,12 @@ int drm_gem_map_attach(struct dma_buf *dma_buf,
{
struct drm_gem_object *obj = dma_buf->priv;
- if (!obj->funcs->get_sg_table)
+ /*
+ * drm_gem_map_dma_buf() requires obj->get_sg_table(), but drivers
+ * that implement their own ->map_dma_buf() do not.
+ */
+ if (dma_buf->ops->map_dma_buf == drm_gem_map_dma_buf &&
+ !obj->funcs->get_sg_table)
return -ENOSYS;
return drm_gem_pin(obj);
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index c13f14edb508..2d08baa91da0 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -33,9 +33,9 @@ endif
subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror
# Fine grained warnings disable
-CFLAGS_i915_pci.o = $(call cc-disable-warning, override-init)
-CFLAGS_display/intel_display_device.o = $(call cc-disable-warning, override-init)
-CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init)
+CFLAGS_i915_pci.o = -Wno-override-init
+CFLAGS_display/intel_display_device.o = -Wno-override-init
+CFLAGS_display/intel_fbdev.o = -Wno-override-init
# Support compiling the display code separately for both i915 and xe
# drivers. Define I915 when building i915.
@@ -118,6 +118,7 @@ gt-y += \
gt/intel_ggtt_fencing.o \
gt/intel_gt.o \
gt/intel_gt_buffer_pool.o \
+ gt/intel_gt_ccs_mode.o \
gt/intel_gt_clock_utils.o \
gt/intel_gt_debugfs.o \
gt/intel_gt_engines_debugfs.o \
diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c
index dfe0b07a122d..06ec04e667e3 100644
--- a/drivers/gpu/drm/i915/display/g4x_dp.c
+++ b/drivers/gpu/drm/i915/display/g4x_dp.c
@@ -717,7 +717,6 @@ static void g4x_enable_dp(struct intel_atomic_state *state,
{
intel_enable_dp(state, encoder, pipe_config, conn_state);
intel_edp_backlight_on(pipe_config, conn_state);
- encoder->audio_enable(encoder, pipe_config, conn_state);
}
static void vlv_enable_dp(struct intel_atomic_state *state,
@@ -726,7 +725,6 @@ static void vlv_enable_dp(struct intel_atomic_state *state,
const struct drm_connector_state *conn_state)
{
intel_edp_backlight_on(pipe_config, conn_state);
- encoder->audio_enable(encoder, pipe_config, conn_state);
}
static void g4x_pre_enable_dp(struct intel_atomic_state *state,
diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h
index fe4268813786..9b1bce2624b9 100644
--- a/drivers/gpu/drm/i915/display/intel_display_device.h
+++ b/drivers/gpu/drm/i915/display/intel_display_device.h
@@ -47,6 +47,7 @@ struct drm_printer;
#define HAS_DPT(i915) (DISPLAY_VER(i915) >= 13)
#define HAS_DSB(i915) (DISPLAY_INFO(i915)->has_dsb)
#define HAS_DSC(__i915) (DISPLAY_RUNTIME_INFO(__i915)->has_dsc)
+#define HAS_DSC_MST(__i915) (DISPLAY_VER(__i915) >= 12 && HAS_DSC(__i915))
#define HAS_FBC(i915) (DISPLAY_RUNTIME_INFO(i915)->fbc_mask != 0)
#define HAS_FPGA_DBG_UNCLAIMED(i915) (DISPLAY_INFO(i915)->has_fpga_dbg)
#define HAS_FW_BLC(i915) (DISPLAY_VER(i915) >= 3)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 94d2a15d8444..360e90601ff9 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1422,7 +1422,8 @@ static bool intel_dp_source_supports_fec(struct intel_dp *intel_dp,
if (DISPLAY_VER(dev_priv) >= 12)
return true;
- if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A)
+ if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A &&
+ !intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST))
return true;
return false;
@@ -1915,8 +1916,9 @@ icl_dsc_compute_link_config(struct intel_dp *intel_dp,
dsc_max_bpp = min(dsc_max_bpp, pipe_bpp - 1);
for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp); i++) {
- if (valid_dsc_bpp[i] < dsc_min_bpp ||
- valid_dsc_bpp[i] > dsc_max_bpp)
+ if (valid_dsc_bpp[i] < dsc_min_bpp)
+ continue;
+ if (valid_dsc_bpp[i] > dsc_max_bpp)
break;
ret = dsc_compute_link_config(intel_dp,
@@ -6523,6 +6525,7 @@ intel_dp_init_connector(struct intel_digital_port *dig_port,
intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
else
intel_connector->get_hw_state = intel_connector_get_hw_state;
+ intel_connector->sync_state = intel_dp_connector_sync_state;
if (!intel_edp_init_connector(intel_dp, intel_connector)) {
intel_dp_aux_fini(intel_dp);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index a01a59f57ae5..2151e916ccfa 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1338,7 +1338,7 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector,
return 0;
}
- if (DISPLAY_VER(dev_priv) >= 10 &&
+ if (HAS_DSC_MST(dev_priv) &&
drm_dp_sink_supports_dsc(intel_connector->dp.dsc_dpcd)) {
/*
* TBD pass the connector BPC,
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 2915d7afe5cc..cc978ee6d130 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1830,8 +1830,6 @@ static void intel_disable_sdvo(struct intel_atomic_state *state,
struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
u32 temp;
- encoder->audio_disable(encoder, old_crtc_state, conn_state);
-
intel_sdvo_set_active_outputs(intel_sdvo, 0);
if (0)
intel_sdvo_set_encoder_power_state(intel_sdvo,
@@ -1923,8 +1921,6 @@ static void intel_enable_sdvo(struct intel_atomic_state *state,
intel_sdvo_set_encoder_power_state(intel_sdvo,
DRM_MODE_DPMS_ON);
intel_sdvo_set_active_outputs(intel_sdvo, intel_sdvo_connector->output_flag);
-
- encoder->audio_enable(encoder, pipe_config, conn_state);
}
static enum drm_mode_status
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index 511dc1544854..8bba6c2e5098 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -2290,6 +2290,9 @@ static u8 skl_get_plane_caps(struct drm_i915_private *i915,
if (HAS_4TILE(i915))
caps |= INTEL_PLANE_CAP_TILING_4;
+ if (!IS_ENABLED(I915) && !HAS_FLAT_CCS(i915))
+ return caps;
+
if (skl_plane_has_rc_ccs(i915, pipe, plane_id)) {
caps |= INTEL_PLANE_CAP_CCS_RC;
if (DISPLAY_VER(i915) >= 12)
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 86a04afff64b..e1bf13e3d307 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -226,7 +226,7 @@ u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs)
static int mtl_dummy_pipe_control(struct i915_request *rq)
{
/* Wa_14016712196 */
- if (IS_GFX_GT_IP_RANGE(rq->engine->gt, IP_VER(12, 70), IP_VER(12, 71)) ||
+ if (IS_GFX_GT_IP_RANGE(rq->engine->gt, IP_VER(12, 70), IP_VER(12, 74)) ||
IS_DG2(rq->i915)) {
u32 *cs;
@@ -822,7 +822,7 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
flags |= PIPE_CONTROL_FLUSH_L3;
/* Wa_14016712196 */
- if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)) || IS_DG2(i915))
+ if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)) || IS_DG2(i915))
/* dummy PIPE_CONTROL + depth flush */
cs = gen12_emit_pipe_control(cs, 0,
PIPE_CONTROL_DEPTH_CACHE_FLUSH, 0);
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index fa46d2308b0e..81bf2216371b 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -961,6 +961,9 @@ static int gen8_init_rsvd(struct i915_address_space *vm)
struct i915_vma *vma;
int ret;
+ if (!intel_gt_needs_wa_16018031267(vm->gt))
+ return 0;
+
/* The memory will be used only by GPU. */
obj = i915_gem_object_create_lmem(i915, PAGE_SIZE,
I915_BO_ALLOC_VOLATILE |
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 40687806d22a..84be97f959fa 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -908,6 +908,23 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
info->engine_mask &= ~BIT(GSC0);
}
+ /*
+ * Do not create the command streamer for CCS slices beyond the first.
+ * All the workload submitted to the first engine will be shared among
+ * all the slices.
+ *
+ * Once the user will be allowed to customize the CCS mode, then this
+ * check needs to be removed.
+ */
+ if (IS_DG2(gt->i915)) {
+ u8 first_ccs = __ffs(CCS_MASK(gt));
+
+ /* Mask off all the CCS engine */
+ info->engine_mask &= ~GENMASK(CCS3, CCS0);
+ /* Put back in the first CCS engine */
+ info->engine_mask |= BIT(_CCS(first_ccs));
+ }
+
return info->engine_mask;
}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index a425db5ed3a2..6a2c2718bcc3 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -1024,6 +1024,12 @@ enum i915_map_type intel_gt_coherent_map_type(struct intel_gt *gt,
return I915_MAP_WC;
}
+bool intel_gt_needs_wa_16018031267(struct intel_gt *gt)
+{
+ /* Wa_16018031267, Wa_16018063123 */
+ return IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 55), IP_VER(12, 71));
+}
+
bool intel_gt_needs_wa_22016122933(struct intel_gt *gt)
{
return MEDIA_VER_FULL(gt->i915) == IP_VER(13, 0) && gt->type == GT_MEDIA;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 608f5c872928..003eb93b826f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -82,17 +82,18 @@ struct drm_printer;
##__VA_ARGS__); \
} while (0)
-#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \
- IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 55), IP_VER(12, 71)) && \
- engine->class == COPY_ENGINE_CLASS && engine->instance == 0)
-
static inline bool gt_is_root(struct intel_gt *gt)
{
return !gt->info.id;
}
+bool intel_gt_needs_wa_16018031267(struct intel_gt *gt);
bool intel_gt_needs_wa_22016122933(struct intel_gt *gt);
+#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \
+ intel_gt_needs_wa_16018031267(engine->gt) && \
+ engine->class == COPY_ENGINE_CLASS && engine->instance == 0)
+
static inline struct intel_gt *uc_to_gt(struct intel_uc *uc)
{
return container_of(uc, struct intel_gt, uc);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
new file mode 100644
index 000000000000..044219c5960a
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
+#include "intel_gt_regs.h"
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt)
+{
+ int cslice;
+ u32 mode = 0;
+ int first_ccs = __ffs(CCS_MASK(gt));
+
+ if (!IS_DG2(gt->i915))
+ return;
+
+ /* Build the value for the fixed CCS load balancing */
+ for (cslice = 0; cslice < I915_MAX_CCS; cslice++) {
+ if (CCS_MASK(gt) & BIT(cslice))
+ /*
+ * If available, assign the cslice
+ * to the first available engine...
+ */
+ mode |= XEHP_CCS_MODE_CSLICE(cslice, first_ccs);
+
+ else
+ /*
+ * ... otherwise, mark the cslice as
+ * unavailable if no CCS dispatches here
+ */
+ mode |= XEHP_CCS_MODE_CSLICE(cslice,
+ XEHP_CCS_MODE_CSLICE_MASK);
+ }
+
+ intel_uncore_write(gt->uncore, XEHP_CCS_MODE, mode);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
new file mode 100644
index 000000000000..9e5549caeb26
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#ifndef __INTEL_GT_CCS_MODE_H__
+#define __INTEL_GT_CCS_MODE_H__
+
+struct intel_gt;
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt);
+
+#endif /* __INTEL_GT_CCS_MODE_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 50962cfd1353..743fe3566722 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1477,8 +1477,14 @@
#define ECOBITS_PPGTT_CACHE4B (0 << 8)
#define GEN12_RCU_MODE _MMIO(0x14800)
+#define XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE REG_BIT(1)
#define GEN12_RCU_MODE_CCS_ENABLE REG_BIT(0)
+#define XEHP_CCS_MODE _MMIO(0x14804)
+#define XEHP_CCS_MODE_CSLICE_MASK REG_GENMASK(2, 0) /* CCS0-3 + rsvd */
+#define XEHP_CCS_MODE_CSLICE_WIDTH ilog2(XEHP_CCS_MODE_CSLICE_MASK + 1)
+#define XEHP_CCS_MODE_CSLICE(cslice, ccs) (ccs << (cslice * XEHP_CCS_MODE_CSLICE_WIDTH))
+
#define CHV_FUSE_GT _MMIO(VLV_GUNIT_BASE + 0x2168)
#define CHV_FGT_DISABLE_SS0 (1 << 10)
#define CHV_FGT_DISABLE_SS1 (1 << 11)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 3eacbc50caf8..59816dd6fbfe 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -10,6 +10,7 @@
#include "intel_engine_regs.h"
#include "intel_gpu_commands.h"
#include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
#include "intel_gt_mcr.h"
#include "intel_gt_print.h"
#include "intel_gt_regs.h"
@@ -51,7 +52,8 @@
* registers belonging to BCS, VCS or VECS should be implemented in
* xcs_engine_wa_init(). Workarounds for registers not belonging to a specific
* engine's MMIO range but that are part of of the common RCS/CCS reset domain
- * should be implemented in general_render_compute_wa_init().
+ * should be implemented in general_render_compute_wa_init(). The settings
+ * about the CCS load balancing should be added in ccs_engine_wa_mode().
*
* - GT workarounds: the list of these WAs is applied whenever these registers
* revert to their default values: on GPU reset, suspend/resume [1]_, etc.
@@ -789,8 +791,13 @@ static void xelpg_ctx_gt_tuning_init(struct intel_engine_cs *engine,
dg2_ctx_gt_tuning_init(engine, wal);
- if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_B0, STEP_FOREVER) ||
- IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B0, STEP_FOREVER))
+ /*
+ * Due to Wa_16014892111, the DRAW_WATERMARK tuning must be done in
+ * gen12_emit_indirect_ctx_rcs() rather than here on some early
+ * steppings.
+ */
+ if (!(IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) ||
+ IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0)))
wa_add(wal, DRAW_WATERMARK, VERT_WM_VAL, 0x3FF, 0, false);
}
@@ -908,7 +915,7 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
if (engine->class != RENDER_CLASS)
goto done;
- if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71)))
+ if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 74)))
xelpg_ctx_workarounds_init(engine, wal);
else if (IS_PONTEVECCHIO(i915))
; /* noop; none at this time */
@@ -1643,7 +1650,8 @@ pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
static void
xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
{
- /* Wa_14018778641 / Wa_18018781329 */
+ /* Wa_14018575942 / Wa_18018781329 */
+ wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
/* Wa_22016670082 */
@@ -1710,7 +1718,7 @@ xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
*/
static void gt_tuning_settings(struct intel_gt *gt, struct i915_wa_list *wal)
{
- if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) {
+ if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74))) {
wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS);
wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS);
}
@@ -1743,7 +1751,7 @@ gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal)
return;
}
- if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)))
+ if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)))
xelpg_gt_workarounds_init(gt, wal);
else if (IS_PONTEVECCHIO(i915))
pvc_gt_workarounds_init(gt, wal);
@@ -2216,7 +2224,7 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine)
if (engine->gt->type == GT_MEDIA)
; /* none yet */
- else if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71)))
+ else if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 74)))
xelpg_whitelist_build(engine);
else if (IS_PONTEVECCHIO(i915))
pvc_whitelist_build(engine);
@@ -2828,7 +2836,7 @@ add_render_compute_tuning_settings(struct intel_gt *gt,
{
struct drm_i915_private *i915 = gt->i915;
- if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)) || IS_DG2(i915))
+ if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)) || IS_DG2(i915))
wa_mcr_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512);
/*
@@ -2844,6 +2852,28 @@ add_render_compute_tuning_settings(struct intel_gt *gt,
wa_write_clr(wal, GEN8_GARBCNTL, GEN12_BUS_HASH_CTL_BIT_EXC);
}
+static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_list *wal)
+{
+ struct intel_gt *gt = engine->gt;
+
+ if (!IS_DG2(gt->i915))
+ return;
+
+ /*
+ * Wa_14019159160: This workaround, along with others, leads to
+ * significant challenges in utilizing load balancing among the
+ * CCS slices. Consequently, an architectural decision has been
+ * made to completely disable automatic CCS load balancing.
+ */
+ wa_masked_en(wal, GEN12_RCU_MODE, XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE);
+
+ /*
+ * After having disabled automatic load balancing we need to
+ * assign all slices to a single CCS. We will call it CCS mode 1
+ */
+ intel_gt_apply_ccs_mode(gt);
+}
+
/*
* The workarounds in this function apply to shared registers in
* the general render reset domain that aren't tied to a
@@ -2881,7 +2911,8 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
}
if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_B0, STEP_FOREVER) ||
- IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B0, STEP_FOREVER))
+ IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B0, STEP_FOREVER) ||
+ IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 74), IP_VER(12, 74)))
/* Wa_14017856879 */
wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN3, MTL_DISABLE_FIX_FOR_EOT_FLUSH);
@@ -2993,8 +3024,10 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal
* to a single RCS/CCS engine's workaround list since
* they're reset as part of the general render domain reset.
*/
- if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE)
+ if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) {
general_render_compute_wa_init(engine, wal);
+ ccs_engine_wa_mode(engine, wal);
+ }
if (engine->class == COMPUTE_CLASS)
ccs_engine_wa_init(engine, wal);
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index c7d7c3b7ecc6..9967148aedf1 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -799,7 +799,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto out_cleanup_modeset2;
ret = intel_pxp_init(i915);
- if (ret != -ENODEV)
+ if (ret && ret != -ENODEV)
drm_dbg(&i915->drm, "pxp init failed with %d\n", ret);
ret = intel_display_driver_probe(i915);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2d695818f006..bd9d812b1afa 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -3225,7 +3225,7 @@ u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915)
struct intel_gt *gt = to_gt(i915);
/* Wa_18013179988 */
- if (IS_DG2(i915) || IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) {
+ if (IS_DG2(i915) || IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74))) {
intel_wakeref_t wakeref;
u32 reg, shift;
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 0a0a11dc9ec0..ee02cd833c5e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -812,15 +812,15 @@ op_remap(struct drm_gpuva_op_remap *r,
struct drm_gpuva_op_unmap *u = r->unmap;
struct nouveau_uvma *uvma = uvma_from_va(u->va);
u64 addr = uvma->va.va.addr;
- u64 range = uvma->va.va.range;
+ u64 end = uvma->va.va.addr + uvma->va.va.range;
if (r->prev)
addr = r->prev->va.addr + r->prev->va.range;
if (r->next)
- range = r->next->va.addr - addr;
+ end = r->next->va.addr;
- op_unmap_range(u, addr, range);
+ op_unmap_range(u, addr, end - addr);
}
static int
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index 9063ce254642..fd8e44992184 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -441,19 +441,19 @@ void panfrost_gpu_power_off(struct panfrost_device *pfdev)
gpu_write(pfdev, SHADER_PWROFF_LO, pfdev->features.shader_present);
ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_PWRTRANS_LO,
- val, !val, 1, 1000);
+ val, !val, 1, 2000);
if (ret)
dev_err(pfdev->dev, "shader power transition timeout");
gpu_write(pfdev, TILER_PWROFF_LO, pfdev->features.tiler_present);
ret = readl_relaxed_poll_timeout(pfdev->iomem + TILER_PWRTRANS_LO,
- val, !val, 1, 1000);
+ val, !val, 1, 2000);
if (ret)
dev_err(pfdev->dev, "tiler power transition timeout");
gpu_write(pfdev, L2_PWROFF_LO, pfdev->features.l2_present);
ret = readl_poll_timeout(pfdev->iomem + L2_PWRTRANS_LO,
- val, !val, 0, 1000);
+ val, !val, 0, 2000);
if (ret)
dev_err(pfdev->dev, "l2 power transition timeout");
}
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
index 48170694ac6b..18efb3fe1c00 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
@@ -17,9 +17,7 @@
static const uint32_t formats_cluster[] = {
DRM_FORMAT_XRGB2101010,
- DRM_FORMAT_ARGB2101010,
DRM_FORMAT_XBGR2101010,
- DRM_FORMAT_ABGR2101010,
DRM_FORMAT_XRGB8888,
DRM_FORMAT_ARGB8888,
DRM_FORMAT_XBGR8888,
diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 802c807c782c..1c9e6906b06a 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -162,8 +162,8 @@ subdir-ccflags-$(CONFIG_DRM_XE_DISPLAY) += \
-Ddrm_i915_gem_object=xe_bo \
-Ddrm_i915_private=xe_device
-CFLAGS_i915-display/intel_fbdev.o = $(call cc-disable-warning, override-init)
-CFLAGS_i915-display/intel_display_device.o = $(call cc-disable-warning, override-init)
+CFLAGS_i915-display/intel_fbdev.o = -Wno-override-init
+CFLAGS_i915-display/intel_display_device.o = -Wno-override-init
# Rule to build SOC code shared with i915
$(obj)/i915-soc/%.o: $(srctree)/drivers/gpu/drm/i915/soc/%.c FORCE
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 4d3b80ec906d..eb2c44a32827 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -140,9 +140,6 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo,
.mem_type = XE_PL_TT,
};
*c += 1;
-
- if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID)
- bo->props.preferred_mem_type = XE_PL_TT;
}
}
@@ -177,25 +174,15 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo,
}
places[*c] = place;
*c += 1;
-
- if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID)
- bo->props.preferred_mem_type = mem_type;
}
static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
u32 bo_flags, u32 *c)
{
- if (bo->props.preferred_gt == XE_GT1) {
- if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
- add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
- if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
- add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
- } else {
- if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
- add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
- if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
- add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
- }
+ if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
+ add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
+ if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
+ add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
}
static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo,
@@ -219,17 +206,8 @@ static int __xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo,
{
u32 c = 0;
- bo->props.preferred_mem_type = XE_BO_PROPS_INVALID;
-
- /* The order of placements should indicate preferred location */
-
- if (bo->props.preferred_mem_class == DRM_XE_MEM_REGION_CLASS_SYSMEM) {
- try_add_system(xe, bo, bo_flags, &c);
- try_add_vram(xe, bo, bo_flags, &c);
- } else {
- try_add_vram(xe, bo, bo_flags, &c);
- try_add_system(xe, bo, bo_flags, &c);
- }
+ try_add_vram(xe, bo, bo_flags, &c);
+ try_add_system(xe, bo, bo_flags, &c);
try_add_stolen(xe, bo, bo_flags, &c);
if (!c)
@@ -1106,19 +1084,12 @@ static void xe_gem_object_close(struct drm_gem_object *obj,
}
}
-static bool should_migrate_to_system(struct xe_bo *bo)
-{
- struct xe_device *xe = xe_bo_device(bo);
-
- return xe_device_in_fault_mode(xe) && bo->props.cpu_atomic;
-}
-
static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
{
struct ttm_buffer_object *tbo = vmf->vma->vm_private_data;
struct drm_device *ddev = tbo->base.dev;
vm_fault_t ret;
- int idx, r = 0;
+ int idx;
ret = ttm_bo_vm_reserve(tbo, vmf);
if (ret)
@@ -1129,17 +1100,8 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
trace_xe_bo_cpu_fault(bo);
- if (should_migrate_to_system(bo)) {
- r = xe_bo_migrate(bo, XE_PL_TT);
- if (r == -EBUSY || r == -ERESTARTSYS || r == -EINTR)
- ret = VM_FAULT_NOPAGE;
- else if (r)
- ret = VM_FAULT_SIGBUS;
- }
- if (!ret)
- ret = ttm_bo_vm_fault_reserved(vmf,
- vmf->vma->vm_page_prot,
- TTM_BO_VM_NUM_PREFAULT);
+ ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
+ TTM_BO_VM_NUM_PREFAULT);
drm_dev_exit(idx);
} else {
ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
@@ -1253,9 +1215,6 @@ struct xe_bo *___xe_bo_create_locked(struct xe_device *xe, struct xe_bo *bo,
bo->flags = flags;
bo->cpu_caching = cpu_caching;
bo->ttm.base.funcs = &xe_gem_object_funcs;
- bo->props.preferred_mem_class = XE_BO_PROPS_INVALID;
- bo->props.preferred_gt = XE_BO_PROPS_INVALID;
- bo->props.preferred_mem_type = XE_BO_PROPS_INVALID;
bo->ttm.priority = XE_BO_PRIORITY_NORMAL;
INIT_LIST_HEAD(&bo->pinned_link);
#ifdef CONFIG_PROC_FS
diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index 64c2249a4e40..81dca15315d5 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -56,25 +56,6 @@ struct xe_bo {
*/
struct list_head client_link;
#endif
- /** @props: BO user controlled properties */
- struct {
- /** @preferred_mem: preferred memory class for this BO */
- s16 preferred_mem_class;
- /** @prefered_gt: preferred GT for this BO */
- s16 preferred_gt;
- /** @preferred_mem_type: preferred memory type */
- s32 preferred_mem_type;
- /**
- * @cpu_atomic: the CPU expects to do atomics operations to
- * this BO
- */
- bool cpu_atomic;
- /**
- * @device_atomic: the device expects to do atomics operations
- * to this BO
- */
- bool device_atomic;
- } props;
/** @freed: List node for delayed put. */
struct llist_node freed;
/** @created: Whether the bo has passed initial creation */
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 08d8b72c7731..bf8efb44edf6 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -58,7 +58,7 @@ static inline struct xe_tile *xe_device_get_root_tile(struct xe_device *xe)
static inline struct xe_gt *xe_tile_get_gt(struct xe_tile *tile, u8 gt_id)
{
- if (drm_WARN_ON(&tile_to_xe(tile)->drm, gt_id > XE_MAX_GT_PER_TILE))
+ if (drm_WARN_ON(&tile_to_xe(tile)->drm, gt_id >= XE_MAX_GT_PER_TILE))
gt_id = 0;
return gt_id ? tile->media_gt : tile->primary_gt;
@@ -79,7 +79,7 @@ static inline struct xe_gt *xe_device_get_gt(struct xe_device *xe, u8 gt_id)
if (MEDIA_VER(xe) >= 13) {
gt = xe_tile_get_gt(root_tile, gt_id);
} else {
- if (drm_WARN_ON(&xe->drm, gt_id > XE_MAX_TILES_PER_DEVICE))
+ if (drm_WARN_ON(&xe->drm, gt_id >= XE_MAX_TILES_PER_DEVICE))
gt_id = 0;
gt = xe->tiles[gt_id].primary_gt;
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 222209b0d690..2cd4ad2fcffa 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -113,7 +113,6 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
struct drm_exec *exec = &vm_exec.exec;
u32 i, num_syncs = 0, num_ufence = 0;
struct xe_sched_job *job;
- struct dma_fence *rebind_fence;
struct xe_vm *vm;
bool write_locked, skip_retry = false;
ktime_t end = 0;
@@ -256,35 +255,11 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
* Rebind any invalidated userptr or evicted BOs in the VM, non-compute
* VM mode only.
*/
- rebind_fence = xe_vm_rebind(vm, false);
- if (IS_ERR(rebind_fence)) {
- err = PTR_ERR(rebind_fence);
+ err = xe_vm_rebind(vm, false);
+ if (err)
goto err_put_job;
- }
-
- /*
- * We store the rebind_fence in the VM so subsequent execs don't get
- * scheduled before the rebinds of userptrs / evicted BOs is complete.
- */
- if (rebind_fence) {
- dma_fence_put(vm->rebind_fence);
- vm->rebind_fence = rebind_fence;
- }
- if (vm->rebind_fence) {
- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
- &vm->rebind_fence->flags)) {
- dma_fence_put(vm->rebind_fence);
- vm->rebind_fence = NULL;
- } else {
- dma_fence_get(vm->rebind_fence);
- err = drm_sched_job_add_dependency(&job->drm,
- vm->rebind_fence);
- if (err)
- goto err_put_job;
- }
- }
- /* Wait behind munmap style rebinds */
+ /* Wait behind rebinds */
if (!xe_vm_in_lr_mode(vm)) {
err = drm_sched_job_add_resv_dependencies(&job->drm,
xe_vm_resv(vm),
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 49223026c89f..5093c56d60ab 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -66,6 +66,8 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us;
q->sched_props.preempt_timeout_us =
hwe->eclass->sched_props.preempt_timeout_us;
+ q->sched_props.job_timeout_ms =
+ hwe->eclass->sched_props.job_timeout_ms;
if (q->flags & EXEC_QUEUE_FLAG_KERNEL &&
q->flags & EXEC_QUEUE_FLAG_HIGH_PRIORITY)
q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
@@ -403,7 +405,7 @@ find_hw_engine(struct xe_device *xe,
{
u32 idx;
- if (eci.engine_class > ARRAY_SIZE(user_to_xe_engine_class))
+ if (eci.engine_class >= ARRAY_SIZE(user_to_xe_engine_class))
return NULL;
if (eci.gt_id >= xe->info.gt_count)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 36f4901d8d7e..22e1dffd0649 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -132,6 +132,8 @@ struct xe_exec_queue {
u32 timeslice_us;
/** @preempt_timeout_us: preemption timeout in micro-seconds */
u32 preempt_timeout_us;
+ /** @job_timeout_ms: job timeout in milliseconds */
+ u32 job_timeout_ms;
/** @priority: priority of this exec queue */
enum xe_exec_queue_priority priority;
} sched_props;
@@ -157,6 +159,11 @@ struct xe_exec_queue {
const struct xe_ring_ops *ring_ops;
/** @entity: DRM sched entity for this exec queue (1 to 1 relationship) */
struct drm_sched_entity *entity;
+ /**
+ * @tlb_flush_seqno: The seqno of the last rebind tlb flush performed
+ * Protected by @vm's resv. Unused if @vm == NULL.
+ */
+ u64 tlb_flush_seqno;
/** @lrc: logical ring context for this exec queue */
struct xe_lrc lrc[];
};
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index f22ae717b0b2..bd1079aa8849 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1216,7 +1216,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
init_waitqueue_head(&ge->suspend_wait);
timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT :
- q->hwe->eclass->sched_props.job_timeout_ms;
+ msecs_to_jiffies(q->sched_props.job_timeout_ms);
err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops,
get_submit_wq(guc),
q->lrc[0].ring.size / MAX_JOB_SIZE_BYTES, 64,
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 6653c045f3c9..c1a833b1cb3d 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1255,11 +1255,13 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
* non-faulting LR, in particular on user-space batch buffer chaining,
* it needs to be done here.
*/
- if ((rebind && !xe_vm_in_lr_mode(vm) && !vm->batch_invalidate_tlb) ||
- (!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) {
+ if ((!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) {
ifence = kzalloc(sizeof(*ifence), GFP_KERNEL);
if (!ifence)
return ERR_PTR(-ENOMEM);
+ } else if (rebind && !xe_vm_in_lr_mode(vm)) {
+ /* We bump also if batch_invalidate_tlb is true */
+ vm->tlb_flush_seqno++;
}
rfence = kzalloc(sizeof(*rfence), GFP_KERNEL);
@@ -1298,7 +1300,7 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
}
/* add shared fence now for pagetable delayed destroy */
- dma_resv_add_fence(xe_vm_resv(vm), fence, !rebind &&
+ dma_resv_add_fence(xe_vm_resv(vm), fence, rebind ||
last_munmap_rebind ?
DMA_RESV_USAGE_KERNEL :
DMA_RESV_USAGE_BOOKKEEP);
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 1e4c06eacd98..68495f885879 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -227,10 +227,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
{
u32 dw[MAX_JOB_SIZE_DW], i = 0;
u32 ppgtt_flag = get_ppgtt_flag(job);
- struct xe_vm *vm = job->q->vm;
struct xe_gt *gt = job->q->gt;
- if (vm && vm->batch_invalidate_tlb) {
+ if (job->ring_ops_flush_tlb) {
dw[i++] = preparser_disable(true);
i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
seqno, true, dw, i);
@@ -278,7 +277,6 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
struct xe_gt *gt = job->q->gt;
struct xe_device *xe = gt_to_xe(gt);
bool decode = job->q->class == XE_ENGINE_CLASS_VIDEO_DECODE;
- struct xe_vm *vm = job->q->vm;
dw[i++] = preparser_disable(true);
@@ -290,13 +288,13 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
i = emit_aux_table_inv(gt, VE0_AUX_INV, dw, i);
}
- if (vm && vm->batch_invalidate_tlb)
+ if (job->ring_ops_flush_tlb)
i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
seqno, true, dw, i);
dw[i++] = preparser_disable(false);
- if (!vm || !vm->batch_invalidate_tlb)
+ if (!job->ring_ops_flush_tlb)
i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
seqno, dw, i);
@@ -325,7 +323,6 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
struct xe_gt *gt = job->q->gt;
struct xe_device *xe = gt_to_xe(gt);
bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
- struct xe_vm *vm = job->q->vm;
u32 mask_flags = 0;
dw[i++] = preparser_disable(true);
@@ -335,7 +332,7 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
mask_flags = PIPE_CONTROL_3D_ENGINE_FLAGS;
/* See __xe_pt_bind_vma() for a discussion on TLB invalidations. */
- i = emit_pipe_invalidate(mask_flags, vm && vm->batch_invalidate_tlb, dw, i);
+ i = emit_pipe_invalidate(mask_flags, job->ring_ops_flush_tlb, dw, i);
/* hsdes: 1809175790 */
if (has_aux_ccs(xe))
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 4e2ccad0e52f..d07b9ee0eaa5 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -250,6 +250,16 @@ bool xe_sched_job_completed(struct xe_sched_job *job)
void xe_sched_job_arm(struct xe_sched_job *job)
{
+ struct xe_exec_queue *q = job->q;
+ struct xe_vm *vm = q->vm;
+
+ if (vm && !xe_sched_job_is_migration(q) && !xe_vm_in_lr_mode(vm) &&
+ (vm->batch_invalidate_tlb || vm->tlb_flush_seqno != q->tlb_flush_seqno)) {
+ xe_vm_assert_held(vm);
+ q->tlb_flush_seqno = vm->tlb_flush_seqno;
+ job->ring_ops_flush_tlb = true;
+ }
+
drm_sched_job_arm(&job->drm);
}
diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h
index 71213ba9735b..46ead6345956 100644
--- a/drivers/gpu/drm/xe/xe_sched_job_types.h
+++ b/drivers/gpu/drm/xe/xe_sched_job_types.h
@@ -39,6 +39,8 @@ struct xe_sched_job {
} user_fence;
/** @migrate_flush_flags: Additional flush flags for migration jobs */
u32 migrate_flush_flags;
+ /** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */
+ bool ring_ops_flush_tlb;
/** @batch_addr: batch buffer address of job */
u64 batch_addr[];
};
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index a2397f232efc..a2024247bec1 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -520,7 +520,6 @@ static void preempt_rebind_work_func(struct work_struct *w)
{
struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work);
struct drm_exec exec;
- struct dma_fence *rebind_fence;
unsigned int fence_count = 0;
LIST_HEAD(preempt_fences);
ktime_t end = 0;
@@ -566,18 +565,11 @@ static void preempt_rebind_work_func(struct work_struct *w)
if (err)
goto out_unlock;
- rebind_fence = xe_vm_rebind(vm, true);
- if (IS_ERR(rebind_fence)) {
- err = PTR_ERR(rebind_fence);
+ err = xe_vm_rebind(vm, true);
+ if (err)
goto out_unlock;
- }
-
- if (rebind_fence) {
- dma_fence_wait(rebind_fence, false);
- dma_fence_put(rebind_fence);
- }
- /* Wait on munmap style VM unbinds */
+ /* Wait on rebinds and munmap style VM unbinds */
wait = dma_resv_wait_timeout(xe_vm_resv(vm),
DMA_RESV_USAGE_KERNEL,
false, MAX_SCHEDULE_TIMEOUT);
@@ -771,14 +763,14 @@ xe_vm_bind_vma(struct xe_vma *vma, struct xe_exec_queue *q,
struct xe_sync_entry *syncs, u32 num_syncs,
bool first_op, bool last_op);
-struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
+int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
{
- struct dma_fence *fence = NULL;
+ struct dma_fence *fence;
struct xe_vma *vma, *next;
lockdep_assert_held(&vm->lock);
if (xe_vm_in_lr_mode(vm) && !rebind_worker)
- return NULL;
+ return 0;
xe_vm_assert_held(vm);
list_for_each_entry_safe(vma, next, &vm->rebind_list,
@@ -786,17 +778,17 @@ struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
xe_assert(vm->xe, vma->tile_present);
list_del_init(&vma->combined_links.rebind);
- dma_fence_put(fence);
if (rebind_worker)
trace_xe_vma_rebind_worker(vma);
else
trace_xe_vma_rebind_exec(vma);
fence = xe_vm_bind_vma(vma, NULL, NULL, 0, false, false);
if (IS_ERR(fence))
- return fence;
+ return PTR_ERR(fence);
+ dma_fence_put(fence);
}
- return fence;
+ return 0;
}
static void xe_vma_free(struct xe_vma *vma)
@@ -1575,7 +1567,6 @@ static void vm_destroy_work_func(struct work_struct *w)
XE_WARN_ON(vm->pt_root[id]);
trace_xe_vm_free(vm);
- dma_fence_put(vm->rebind_fence);
kfree(vm);
}
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 9654a0612fc2..40188a28c547 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -207,7 +207,7 @@ int __xe_vm_userptr_needs_repin(struct xe_vm *vm);
int xe_vm_userptr_check_repin(struct xe_vm *vm);
-struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker);
+int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker);
int xe_vm_invalidate_vma(struct xe_vma *vma);
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 5b9654947950..4027da3a10b3 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -171,9 +171,6 @@ struct xe_vm {
*/
struct list_head rebind_list;
- /** @rebind_fence: rebind fence from execbuf */
- struct dma_fence *rebind_fence;
-
/**
* @destroy_work: worker to destroy VM, needed as a dma_fence signaling
* from an irq context can be last put and the destroy needs to be able
@@ -282,6 +279,11 @@ struct xe_vm {
bool capture_once;
} error_capture;
+ /**
+ * @tlb_flush_seqno: Required TLB flush seqno for the next exec.
+ * protected by the vm resv.
+ */
+ u64 tlb_flush_seqno;
/** @batch_invalidate_tlb: Always invalidate TLB before batch start */
bool batch_invalidate_tlb;
/** @xef: XE file handle for tracking this VM's drm client */
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index cd1210026ac5..ad33161f2374 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -3547,6 +3547,7 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
{
/* Caller must be a probed driver on dev */
struct iommu_group *group = dev->iommu_group;
+ struct group_device *device;
void *curr;
int ret;
@@ -3556,10 +3557,18 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
if (!group)
return -ENODEV;
- if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+ if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner ||
+ pasid == IOMMU_NO_PASID)
return -EINVAL;
mutex_lock(&group->mutex);
+ for_each_group_device(group, device) {
+ if (pasid >= device->dev->iommu->max_pasids) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+ }
+
curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
if (curr) {
ret = xa_err(curr) ? : -EBUSY;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 47cf1ab34941..3b4218a2e750 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -4221,7 +4221,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
} else if (sscanf(opt_string, "sectors_per_bit:%llu%c", &llval, &dummy) == 1) {
log2_sectors_per_bitmap_bit = !llval ? 0 : __ilog2_u64(llval);
} else if (sscanf(opt_string, "bitmap_flush_interval:%u%c", &val, &dummy) == 1) {
- if (val >= (uint64_t)UINT_MAX * 1000 / HZ) {
+ if ((uint64_t)val >= (uint64_t)UINT_MAX * 1000 / HZ) {
r = -EINVAL;
ti->error = "Invalid bitmap_flush_interval argument";
goto bad;
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 614cabb5c1b0..7de8a9c9e457 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -5500,8 +5500,12 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.family = MV88E6XXX_FAMILY_6250,
.name = "Marvell 88E6020",
.num_databases = 64,
- .num_ports = 4,
+ /* Ports 2-4 are not routed to pins
+ * => usable ports 0, 1, 5, 6
+ */
+ .num_ports = 7,
.num_internal_phys = 2,
+ .invalid_port_mask = BIT(2) | BIT(3) | BIT(4),
.max_vid = 4095,
.port_base_addr = 0x8,
.phy_base_addr = 0x0,
diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c
index 833e55e4b961..52ddb4ef259e 100644
--- a/drivers/net/dsa/sja1105/sja1105_mdio.c
+++ b/drivers/net/dsa/sja1105/sja1105_mdio.c
@@ -94,7 +94,7 @@ int sja1110_pcs_mdio_read_c45(struct mii_bus *bus, int phy, int mmd, int reg)
return tmp & 0xffff;
}
-int sja1110_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int reg, int mmd,
+int sja1110_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int mmd, int reg,
u16 val)
{
struct sja1105_mdio_private *mdio_priv = bus->priv;
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 6ad1366270f7..78901e2e7303 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -391,7 +391,9 @@ static void umac_reset(struct bcmasp_intf *intf)
umac_wl(intf, 0x0, UMC_CMD);
umac_wl(intf, UMC_CMD_SW_RESET, UMC_CMD);
usleep_range(10, 100);
- umac_wl(intf, 0x0, UMC_CMD);
+ /* We hold the umac in reset and bring it out of
+ * reset when phy link is up.
+ */
}
static void umac_set_hw_addr(struct bcmasp_intf *intf,
@@ -411,6 +413,8 @@ static void umac_enable_set(struct bcmasp_intf *intf, u32 mask,
u32 reg;
reg = umac_rl(intf, UMC_CMD);
+ if (reg & UMC_CMD_SW_RESET)
+ return;
if (enable)
reg |= mask;
else
@@ -429,7 +433,6 @@ static void umac_init(struct bcmasp_intf *intf)
umac_wl(intf, 0x800, UMC_FRM_LEN);
umac_wl(intf, 0xffff, UMC_PAUSE_CNTRL);
umac_wl(intf, 0x800, UMC_RX_MAX_PKT_SZ);
- umac_enable_set(intf, UMC_CMD_PROMISC, 1);
}
static int bcmasp_tx_poll(struct napi_struct *napi, int budget)
@@ -656,6 +659,12 @@ static void bcmasp_adj_link(struct net_device *dev)
UMC_CMD_HD_EN | UMC_CMD_RX_PAUSE_IGNORE |
UMC_CMD_TX_PAUSE_IGNORE);
reg |= cmd_bits;
+ if (reg & UMC_CMD_SW_RESET) {
+ reg &= ~UMC_CMD_SW_RESET;
+ umac_wl(intf, reg, UMC_CMD);
+ udelay(2);
+ reg |= UMC_CMD_TX_EN | UMC_CMD_RX_EN | UMC_CMD_PROMISC;
+ }
umac_wl(intf, reg, UMC_CMD);
intf->eee.eee_active = phy_init_eee(phydev, 0) >= 0;
@@ -1063,9 +1072,6 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
umac_init(intf);
- /* Disable the UniMAC RX/TX */
- umac_enable_set(intf, (UMC_CMD_RX_EN | UMC_CMD_TX_EN), 0);
-
umac_set_hw_addr(intf, dev->dev_addr);
intf->old_duplex = -1;
@@ -1085,9 +1091,6 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
bcmasp_enable_rx(intf, 1);
- /* Turn on UniMAC TX/RX */
- umac_enable_set(intf, (UMC_CMD_RX_EN | UMC_CMD_TX_EN), 1);
-
intf->crc_fwd = !!(umac_rl(intf, UMC_CMD) & UMC_CMD_CRC_FWD);
bcmasp_netif_start(dev);
@@ -1324,7 +1327,14 @@ static void bcmasp_suspend_to_wol(struct bcmasp_intf *intf)
if (intf->wolopts & WAKE_FILTER)
bcmasp_netfilt_suspend(intf);
- /* UniMAC receive needs to be turned on */
+ /* Bring UniMAC out of reset if needed and enable RX */
+ reg = umac_rl(intf, UMC_CMD);
+ if (reg & UMC_CMD_SW_RESET)
+ reg &= ~UMC_CMD_SW_RESET;
+
+ reg |= UMC_CMD_RX_EN | UMC_CMD_PROMISC;
+ umac_wl(intf, reg, UMC_CMD);
+
umac_enable_set(intf, UMC_CMD_RX_EN, 1);
if (intf->parent->wol_irq > 0) {
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 432523b2c789..8decb1b072c5 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2406,8 +2406,6 @@ static int fec_enet_mii_probe(struct net_device *ndev)
fep->link = 0;
fep->full_duplex = 0;
- phy_dev->mac_managed_pm = true;
-
phy_attached_info(phy_dev);
return 0;
@@ -2419,10 +2417,12 @@ static int fec_enet_mii_init(struct platform_device *pdev)
struct net_device *ndev = platform_get_drvdata(pdev);
struct fec_enet_private *fep = netdev_priv(ndev);
bool suppress_preamble = false;
+ struct phy_device *phydev;
struct device_node *node;
int err = -ENXIO;
u32 mii_speed, holdtime;
u32 bus_freq;
+ int addr;
/*
* The i.MX28 dual fec interfaces are not equal.
@@ -2536,6 +2536,13 @@ static int fec_enet_mii_init(struct platform_device *pdev)
goto err_out_free_mdiobus;
of_node_put(node);
+ /* find all the PHY devices on the bus and set mac_managed_pm to true */
+ for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
+ phydev = mdiobus_get_phy(fep->mii_bus, addr);
+ if (phydev)
+ phydev->mac_managed_pm = true;
+ }
+
mii_cnt++;
/* save fec0 mii_bus */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c
index f3c9395d8351..618f66d9586b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c
@@ -85,7 +85,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle,
hclge_comm_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_TX_STATS,
true);
- desc.data[0] = cpu_to_le32(tqp->index & 0x1ff);
+ desc.data[0] = cpu_to_le32(tqp->index);
ret = hclge_comm_cmd_send(hw, &desc, 1);
if (ret) {
dev_err(&hw->cmq.csq.pdev->dev,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 999a0ee162a6..941cb529d671 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -78,6 +78,9 @@ static const struct hns3_stats hns3_rxq_stats[] = {
#define HNS3_NIC_LB_TEST_NO_MEM_ERR 1
#define HNS3_NIC_LB_TEST_TX_CNT_ERR 2
#define HNS3_NIC_LB_TEST_RX_CNT_ERR 3
+#define HNS3_NIC_LB_TEST_UNEXECUTED 4
+
+static int hns3_get_sset_count(struct net_device *netdev, int stringset);
static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
{
@@ -418,18 +421,26 @@ static void hns3_do_external_lb(struct net_device *ndev,
static void hns3_self_test(struct net_device *ndev,
struct ethtool_test *eth_test, u64 *data)
{
+ int cnt = hns3_get_sset_count(ndev, ETH_SS_TEST);
struct hns3_nic_priv *priv = netdev_priv(ndev);
struct hnae3_handle *h = priv->ae_handle;
int st_param[HNAE3_LOOP_NONE][2];
bool if_running = netif_running(ndev);
+ int i;
+
+ /* initialize the loopback test result, avoid marking an unexcuted
+ * loopback test as PASS.
+ */
+ for (i = 0; i < cnt; i++)
+ data[i] = HNS3_NIC_LB_TEST_UNEXECUTED;
if (hns3_nic_resetting(ndev)) {
netdev_err(ndev, "dev resetting!");
- return;
+ goto failure;
}
if (!(eth_test->flags & ETH_TEST_FL_OFFLINE))
- return;
+ goto failure;
if (netif_msg_ifdown(h))
netdev_info(ndev, "self test start\n");
@@ -451,6 +462,10 @@ static void hns3_self_test(struct net_device *ndev,
if (netif_msg_ifdown(h))
netdev_info(ndev, "self test end\n");
+ return;
+
+failure:
+ eth_test->flags |= ETH_TEST_FL_FAILED;
}
static void hns3_update_limit_promisc_mode(struct net_device *netdev,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 609d3799d773..a3b7723a97bb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -11613,6 +11613,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
if (ret)
goto err_pci_uninit;
+ devl_lock(hdev->devlink);
+
/* Firmware command queue initialize */
ret = hclge_comm_cmd_queue_init(hdev->pdev, &hdev->hw.hw);
if (ret)
@@ -11792,6 +11794,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
hclge_task_schedule(hdev, round_jiffies_relative(HZ));
+ devl_unlock(hdev->devlink);
return 0;
err_mdiobus_unreg:
@@ -11804,6 +11807,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
err_cmd_uninit:
hclge_comm_cmd_uninit(hdev->ae_dev, &hdev->hw.hw);
err_devlink_uninit:
+ devl_unlock(hdev->devlink);
hclge_devlink_uninit(hdev);
err_pci_uninit:
pcim_iounmap(pdev, hdev->hw.hw.io_base);
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index 1fef6bb5a5fb..4b6e7536170a 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -628,6 +628,7 @@ struct e1000_phy_info {
u32 id;
u32 reset_delay_us; /* in usec */
u32 revision;
+ u32 retry_count;
enum e1000_media_type media_type;
@@ -644,6 +645,7 @@ struct e1000_phy_info {
bool polarity_correction;
bool speed_downgraded;
bool autoneg_wait_to_complete;
+ bool retry_enabled;
};
struct e1000_nvm_info {
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 19e450a5bd31..f9e94be36e97 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -222,11 +222,18 @@ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw)
if (hw->mac.type >= e1000_pch_lpt) {
/* Only unforce SMBus if ME is not active */
if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) {
+ /* Switching PHY interface always returns MDI error
+ * so disable retry mechanism to avoid wasting time
+ */
+ e1000e_disable_phy_retry(hw);
+
/* Unforce SMBus mode in PHY */
e1e_rphy_locked(hw, CV_SMB_CTRL, &phy_reg);
phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS;
e1e_wphy_locked(hw, CV_SMB_CTRL, phy_reg);
+ e1000e_enable_phy_retry(hw);
+
/* Unforce SMBus mode in MAC */
mac_reg = er32(CTRL_EXT);
mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS;
@@ -310,6 +317,11 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
goto out;
}
+ /* There is no guarantee that the PHY is accessible at this time
+ * so disable retry mechanism to avoid wasting time
+ */
+ e1000e_disable_phy_retry(hw);
+
/* The MAC-PHY interconnect may be in SMBus mode. If the PHY is
* inaccessible and resetting the PHY is not blocked, toggle the
* LANPHYPC Value bit to force the interconnect to PCIe mode.
@@ -380,6 +392,8 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
break;
}
+ e1000e_enable_phy_retry(hw);
+
hw->phy.ops.release(hw);
if (!ret_val) {
@@ -449,6 +463,11 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
phy->id = e1000_phy_unknown;
+ if (hw->mac.type == e1000_pch_mtp) {
+ phy->retry_count = 2;
+ e1000e_enable_phy_retry(hw);
+ }
+
ret_val = e1000_init_phy_workarounds_pchlan(hw);
if (ret_val)
return ret_val;
@@ -1146,18 +1165,6 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx)
if (ret_val)
goto out;
- /* Force SMBus mode in PHY */
- ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
- if (ret_val)
- goto release;
- phy_reg |= CV_SMB_CTRL_FORCE_SMBUS;
- e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
-
- /* Force SMBus mode in MAC */
- mac_reg = er32(CTRL_EXT);
- mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
- ew32(CTRL_EXT, mac_reg);
-
/* Si workaround for ULP entry flow on i127/rev6 h/w. Enable
* LPLU and disable Gig speed when entering ULP
*/
@@ -1313,6 +1320,11 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force)
/* Toggle LANPHYPC Value bit */
e1000_toggle_lanphypc_pch_lpt(hw);
+ /* Switching PHY interface always returns MDI error
+ * so disable retry mechanism to avoid wasting time
+ */
+ e1000e_disable_phy_retry(hw);
+
/* Unforce SMBus mode in PHY */
ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
if (ret_val) {
@@ -1333,6 +1345,8 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force)
phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS;
e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
+ e1000e_enable_phy_retry(hw);
+
/* Unforce SMBus mode in MAC */
mac_reg = er32(CTRL_EXT);
mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index af5d9d97a0d6..3692fce20195 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6623,6 +6623,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
struct e1000_hw *hw = &adapter->hw;
u32 ctrl, ctrl_ext, rctl, status, wufc;
int retval = 0;
+ u16 smb_ctrl;
/* Runtime suspend should only enable wakeup for link changes */
if (runtime)
@@ -6688,14 +6689,31 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
if (adapter->hw.phy.type == e1000_phy_igp_3) {
e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw);
} else if (hw->mac.type >= e1000_pch_lpt) {
- if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
+ if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) {
/* ULP does not support wake from unicast, multicast
* or broadcast.
*/
retval = e1000_enable_ulp_lpt_lp(hw, !runtime);
+ if (retval)
+ return retval;
+ }
+
+ /* Force SMBUS to allow WOL */
+ /* Switching PHY interface always returns MDI error
+ * so disable retry mechanism to avoid wasting time
+ */
+ e1000e_disable_phy_retry(hw);
+
+ e1e_rphy(hw, CV_SMB_CTRL, &smb_ctrl);
+ smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS;
+ e1e_wphy(hw, CV_SMB_CTRL, smb_ctrl);
- if (retval)
- return retval;
+ e1000e_enable_phy_retry(hw);
+
+ /* Force SMBus mode in MAC */
+ ctrl_ext = er32(CTRL_EXT);
+ ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS;
+ ew32(CTRL_EXT, ctrl_ext);
}
/* Ensure that the appropriate bits are set in LPI_CTRL
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index 5e329156d1ba..93544f1cc2a5 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -107,6 +107,16 @@ s32 e1000e_phy_reset_dsp(struct e1000_hw *hw)
return e1e_wphy(hw, M88E1000_PHY_GEN_CONTROL, 0);
}
+void e1000e_disable_phy_retry(struct e1000_hw *hw)
+{
+ hw->phy.retry_enabled = false;
+}
+
+void e1000e_enable_phy_retry(struct e1000_hw *hw)
+{
+ hw->phy.retry_enabled = true;
+}
+
/**
* e1000e_read_phy_reg_mdic - Read MDI control register
* @hw: pointer to the HW structure
@@ -118,55 +128,73 @@ s32 e1000e_phy_reset_dsp(struct e1000_hw *hw)
**/
s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data)
{
+ u32 i, mdic = 0, retry_counter, retry_max;
struct e1000_phy_info *phy = &hw->phy;
- u32 i, mdic = 0;
+ bool success;
if (offset > MAX_PHY_REG_ADDRESS) {
e_dbg("PHY Address %d is out of range\n", offset);
return -E1000_ERR_PARAM;
}
+ retry_max = phy->retry_enabled ? phy->retry_count : 0;
+
/* Set up Op-code, Phy Address, and register offset in the MDI
* Control register. The MAC will take care of interfacing with the
* PHY to retrieve the desired data.
*/
- mdic = ((offset << E1000_MDIC_REG_SHIFT) |
- (phy->addr << E1000_MDIC_PHY_SHIFT) |
- (E1000_MDIC_OP_READ));
+ for (retry_counter = 0; retry_counter <= retry_max; retry_counter++) {
+ success = true;
- ew32(MDIC, mdic);
+ mdic = ((offset << E1000_MDIC_REG_SHIFT) |
+ (phy->addr << E1000_MDIC_PHY_SHIFT) |
+ (E1000_MDIC_OP_READ));
- /* Poll the ready bit to see if the MDI read completed
- * Increasing the time out as testing showed failures with
- * the lower time out
- */
- for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) {
- udelay(50);
- mdic = er32(MDIC);
- if (mdic & E1000_MDIC_READY)
- break;
- }
- if (!(mdic & E1000_MDIC_READY)) {
- e_dbg("MDI Read PHY Reg Address %d did not complete\n", offset);
- return -E1000_ERR_PHY;
- }
- if (mdic & E1000_MDIC_ERROR) {
- e_dbg("MDI Read PHY Reg Address %d Error\n", offset);
- return -E1000_ERR_PHY;
- }
- if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) {
- e_dbg("MDI Read offset error - requested %d, returned %d\n",
- offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic));
- return -E1000_ERR_PHY;
+ ew32(MDIC, mdic);
+
+ /* Poll the ready bit to see if the MDI read completed
+ * Increasing the time out as testing showed failures with
+ * the lower time out
+ */
+ for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) {
+ usleep_range(50, 60);
+ mdic = er32(MDIC);
+ if (mdic & E1000_MDIC_READY)
+ break;
+ }
+ if (!(mdic & E1000_MDIC_READY)) {
+ e_dbg("MDI Read PHY Reg Address %d did not complete\n",
+ offset);
+ success = false;
+ }
+ if (mdic & E1000_MDIC_ERROR) {
+ e_dbg("MDI Read PHY Reg Address %d Error\n", offset);
+ success = false;
+ }
+ if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) {
+ e_dbg("MDI Read offset error - requested %d, returned %d\n",
+ offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic));
+ success = false;
+ }
+
+ /* Allow some time after each MDIC transaction to avoid
+ * reading duplicate data in the next MDIC transaction.
+ */
+ if (hw->mac.type == e1000_pch2lan)
+ usleep_range(100, 150);
+
+ if (success) {
+ *data = (u16)mdic;
+ return 0;
+ }
+
+ if (retry_counter != retry_max) {
+ e_dbg("Perform retry on PHY transaction...\n");
+ mdelay(10);
+ }
}
- *data = (u16)mdic;
- /* Allow some time after each MDIC transaction to avoid
- * reading duplicate data in the next MDIC transaction.
- */
- if (hw->mac.type == e1000_pch2lan)
- udelay(100);
- return 0;
+ return -E1000_ERR_PHY;
}
/**
@@ -179,56 +207,72 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data)
**/
s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data)
{
+ u32 i, mdic = 0, retry_counter, retry_max;
struct e1000_phy_info *phy = &hw->phy;
- u32 i, mdic = 0;
+ bool success;
if (offset > MAX_PHY_REG_ADDRESS) {
e_dbg("PHY Address %d is out of range\n", offset);
return -E1000_ERR_PARAM;
}
+ retry_max = phy->retry_enabled ? phy->retry_count : 0;
+
/* Set up Op-code, Phy Address, and register offset in the MDI
* Control register. The MAC will take care of interfacing with the
* PHY to retrieve the desired data.
*/
- mdic = (((u32)data) |
- (offset << E1000_MDIC_REG_SHIFT) |
- (phy->addr << E1000_MDIC_PHY_SHIFT) |
- (E1000_MDIC_OP_WRITE));
+ for (retry_counter = 0; retry_counter <= retry_max; retry_counter++) {
+ success = true;
- ew32(MDIC, mdic);
+ mdic = (((u32)data) |
+ (offset << E1000_MDIC_REG_SHIFT) |
+ (phy->addr << E1000_MDIC_PHY_SHIFT) |
+ (E1000_MDIC_OP_WRITE));
- /* Poll the ready bit to see if the MDI read completed
- * Increasing the time out as testing showed failures with
- * the lower time out
- */
- for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) {
- udelay(50);
- mdic = er32(MDIC);
- if (mdic & E1000_MDIC_READY)
- break;
- }
- if (!(mdic & E1000_MDIC_READY)) {
- e_dbg("MDI Write PHY Reg Address %d did not complete\n", offset);
- return -E1000_ERR_PHY;
- }
- if (mdic & E1000_MDIC_ERROR) {
- e_dbg("MDI Write PHY Red Address %d Error\n", offset);
- return -E1000_ERR_PHY;
- }
- if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) {
- e_dbg("MDI Write offset error - requested %d, returned %d\n",
- offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic));
- return -E1000_ERR_PHY;
- }
+ ew32(MDIC, mdic);
- /* Allow some time after each MDIC transaction to avoid
- * reading duplicate data in the next MDIC transaction.
- */
- if (hw->mac.type == e1000_pch2lan)
- udelay(100);
+ /* Poll the ready bit to see if the MDI read completed
+ * Increasing the time out as testing showed failures with
+ * the lower time out
+ */
+ for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) {
+ usleep_range(50, 60);
+ mdic = er32(MDIC);
+ if (mdic & E1000_MDIC_READY)
+ break;
+ }
+ if (!(mdic & E1000_MDIC_READY)) {
+ e_dbg("MDI Write PHY Reg Address %d did not complete\n",
+ offset);
+ success = false;
+ }
+ if (mdic & E1000_MDIC_ERROR) {
+ e_dbg("MDI Write PHY Reg Address %d Error\n", offset);
+ success = false;
+ }
+ if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) {
+ e_dbg("MDI Write offset error - requested %d, returned %d\n",
+ offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic));
+ success = false;
+ }
- return 0;
+ /* Allow some time after each MDIC transaction to avoid
+ * reading duplicate data in the next MDIC transaction.
+ */
+ if (hw->mac.type == e1000_pch2lan)
+ usleep_range(100, 150);
+
+ if (success)
+ return 0;
+
+ if (retry_counter != retry_max) {
+ e_dbg("Perform retry on PHY transaction...\n");
+ mdelay(10);
+ }
+ }
+
+ return -E1000_ERR_PHY;
}
/**
diff --git a/drivers/net/ethernet/intel/e1000e/phy.h b/drivers/net/ethernet/intel/e1000e/phy.h
index c48777d09523..049bb325b4b1 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.h
+++ b/drivers/net/ethernet/intel/e1000e/phy.h
@@ -51,6 +51,8 @@ s32 e1000e_read_phy_reg_bm2(struct e1000_hw *hw, u32 offset, u16 *data);
s32 e1000e_write_phy_reg_bm2(struct e1000_hw *hw, u32 offset, u16 data);
void e1000_power_up_phy_copper(struct e1000_hw *hw);
void e1000_power_down_phy_copper(struct e1000_hw *hw);
+void e1000e_disable_phy_retry(struct e1000_hw *hw);
+void e1000e_enable_phy_retry(struct e1000_hw *hw);
s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data);
s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data);
s32 e1000_read_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 *data);
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 9b701615c7c6..4d2b05de6c63 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -908,6 +908,7 @@ struct i40e_q_vector {
struct rcu_head rcu; /* to avoid race with update stats on free */
char name[I40E_INT_NAME_STR_LEN];
bool arm_wb_state;
+ bool in_busy_poll;
int irq_num; /* IRQ assigned to this q_vector */
} ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 89a3401d20ab..bb4ab3a9576b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1257,8 +1257,11 @@ int i40e_count_filters(struct i40e_vsi *vsi)
int bkt;
int cnt = 0;
- hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist)
- ++cnt;
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+ if (f->state == I40E_FILTER_NEW ||
+ f->state == I40E_FILTER_ACTIVE)
+ ++cnt;
+ }
return cnt;
}
@@ -3915,6 +3918,12 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
q_vector->tx.target_itr >> 1);
q_vector->tx.current_itr = q_vector->tx.target_itr;
+ /* Set ITR for software interrupts triggered after exiting
+ * busy-loop polling.
+ */
+ wr32(hw, I40E_PFINT_ITRN(I40E_SW_ITR, vector - 1),
+ I40E_ITR_20K);
+
wr32(hw, I40E_PFINT_RATEN(vector - 1),
i40e_intrl_usec_to_reg(vsi->int_rate_limit));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 14ab642cafdb..432afbb64201 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -333,8 +333,11 @@
#define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3
#define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT)
#define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5
+#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT)
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24
#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT)
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25
+#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT)
#define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */
#define I40E_PFINT_ICR0_INTEVENT_SHIFT 0
#define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 0d7177083708..1a12b732818e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2630,7 +2630,22 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
return failure ? budget : (int)total_rx_packets;
}
-static inline u32 i40e_buildreg_itr(const int type, u16 itr)
+/**
+ * i40e_buildreg_itr - build a value for writing to I40E_PFINT_DYN_CTLN register
+ * @itr_idx: interrupt throttling index
+ * @interval: interrupt throttling interval value in usecs
+ * @force_swint: force software interrupt
+ *
+ * The function builds a value for I40E_PFINT_DYN_CTLN register that
+ * is used to update interrupt throttling interval for specified ITR index
+ * and optionally enforces a software interrupt. If the @itr_idx is equal
+ * to I40E_ITR_NONE then no interval change is applied and only @force_swint
+ * parameter is taken into account. If the interval change and enforced
+ * software interrupt are not requested then the built value just enables
+ * appropriate vector interrupt.
+ **/
+static u32 i40e_buildreg_itr(enum i40e_dyn_idx itr_idx, u16 interval,
+ bool force_swint)
{
u32 val;
@@ -2644,23 +2659,33 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
* an event in the PBA anyway so we need to rely on the automask
* to hold pending events for us until the interrupt is re-enabled
*
- * The itr value is reported in microseconds, and the register
- * value is recorded in 2 microsecond units. For this reason we
- * only need to shift by the interval shift - 1 instead of the
- * full value.
+ * We have to shift the given value as it is reported in microseconds
+ * and the register value is recorded in 2 microsecond units.
*/
- itr &= I40E_ITR_MASK;
+ interval >>= 1;
+ /* 1. Enable vector interrupt
+ * 2. Update the interval for the specified ITR index
+ * (I40E_ITR_NONE in the register is used to indicate that
+ * no interval update is requested)
+ */
val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
- (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
- (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1));
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_ITR_INDX_MASK, itr_idx) |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_INTERVAL_MASK, interval);
+
+ /* 3. Enforce software interrupt trigger if requested
+ * (These software interrupts rate is limited by ITR2 that is
+ * set to 20K interrupts per second)
+ */
+ if (force_swint)
+ val |= I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
+ I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK |
+ FIELD_PREP(I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK,
+ I40E_SW_ITR);
return val;
}
-/* a small macro to shorten up some long lines */
-#define INTREG I40E_PFINT_DYN_CTLN
-
/* The act of updating the ITR will cause it to immediately trigger. In order
* to prevent this from throwing off adaptive update statistics we defer the
* update so that it can only happen so often. So after either Tx or Rx are
@@ -2679,8 +2704,10 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr)
static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
struct i40e_q_vector *q_vector)
{
+ enum i40e_dyn_idx itr_idx = I40E_ITR_NONE;
struct i40e_hw *hw = &vsi->back->hw;
- u32 intval;
+ u16 interval = 0;
+ u32 itr_val;
/* If we don't have MSIX, then we only need to re-enable icr0 */
if (!test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) {
@@ -2702,8 +2729,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
*/
if (q_vector->rx.target_itr < q_vector->rx.current_itr) {
/* Rx ITR needs to be reduced, this is highest priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) ||
@@ -2712,25 +2739,36 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
/* Tx ITR needs to be reduced, this is second priority
* Tx ITR needs to be increased more than Rx, fourth priority
*/
- intval = i40e_buildreg_itr(I40E_TX_ITR,
- q_vector->tx.target_itr);
+ itr_idx = I40E_TX_ITR;
+ interval = q_vector->tx.target_itr;
q_vector->tx.current_itr = q_vector->tx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else if (q_vector->rx.current_itr != q_vector->rx.target_itr) {
/* Rx ITR needs to be increased, third priority */
- intval = i40e_buildreg_itr(I40E_RX_ITR,
- q_vector->rx.target_itr);
+ itr_idx = I40E_RX_ITR;
+ interval = q_vector->rx.target_itr;
q_vector->rx.current_itr = q_vector->rx.target_itr;
q_vector->itr_countdown = ITR_COUNTDOWN_START;
} else {
/* No ITR update, lowest priority */
- intval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
if (q_vector->itr_countdown)
q_vector->itr_countdown--;
}
- if (!test_bit(__I40E_VSI_DOWN, vsi->state))
- wr32(hw, INTREG(q_vector->reg_idx), intval);
+ /* Do not update interrupt control register if VSI is down */
+ if (test_bit(__I40E_VSI_DOWN, vsi->state))
+ return;
+
+ /* Update ITR interval if necessary and enforce software interrupt
+ * if we are exiting busy poll.
+ */
+ if (q_vector->in_busy_poll) {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, true);
+ q_vector->in_busy_poll = false;
+ } else {
+ itr_val = i40e_buildreg_itr(itr_idx, interval, false);
+ }
+ wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->reg_idx), itr_val);
}
/**
@@ -2845,6 +2883,8 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
*/
if (likely(napi_complete_done(napi, work_done)))
i40e_update_enable_itr(vsi, q_vector);
+ else
+ q_vector->in_busy_poll = true;
return min(work_done, budget - 1);
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index abf15067eb5d..2cdc7de6301c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -68,6 +68,7 @@ enum i40e_dyn_idx {
/* these are indexes into ITRN registers */
#define I40E_RX_ITR I40E_IDX_ITR0
#define I40E_TX_ITR I40E_IDX_ITR1
+#define I40E_SW_ITR I40E_IDX_ITR2
/* Supported RSS offloads */
#define I40E_DEFAULT_RSS_HENA ( \
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index b34c71770887..37e77163da4c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1628,8 +1628,8 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
{
struct i40e_hw *hw = &pf->hw;
struct i40e_vf *vf;
- int i, v;
u32 reg;
+ int i;
/* If we don't have any VFs, then there is nothing to reset */
if (!pf->num_alloc_vfs)
@@ -1640,11 +1640,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
return false;
/* Begin reset on all VFs at once */
- for (v = 0; v < pf->num_alloc_vfs; v++) {
- vf = &pf->vf[v];
+ for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) {
/* If VF is being reset no need to trigger reset again */
if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
- i40e_trigger_vf_reset(&pf->vf[v], flr);
+ i40e_trigger_vf_reset(vf, flr);
}
/* HW requires some time to make sure it can flush the FIFO for a VF
@@ -1653,14 +1652,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
* the VFs using a simple iterator that increments once that VF has
* finished resetting.
*/
- for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) {
+ for (i = 0, vf = &pf->vf[0]; i < 10 && vf < &pf->vf[pf->num_alloc_vfs]; ++i) {
usleep_range(10000, 20000);
/* Check each VF in sequence, beginning with the VF to fail
* the previous check.
*/
- while (v < pf->num_alloc_vfs) {
- vf = &pf->vf[v];
+ while (vf < &pf->vf[pf->num_alloc_vfs]) {
if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) {
reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK))
@@ -1670,7 +1668,7 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
/* If the current VF has finished resetting, move on
* to the next VF in sequence.
*/
- v++;
+ ++vf;
}
}
@@ -1680,39 +1678,39 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
/* Display a warning if at least one VF didn't manage to reset in
* time, but continue on with the operation.
*/
- if (v < pf->num_alloc_vfs)
+ if (vf < &pf->vf[pf->num_alloc_vfs])
dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n",
- pf->vf[v].vf_id);
+ vf->vf_id);
usleep_range(10000, 20000);
/* Begin disabling all the rings associated with VFs, but do not wait
* between each VF.
*/
- for (v = 0; v < pf->num_alloc_vfs; v++) {
+ for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) {
/* On initial reset, we don't have any queues to disable */
- if (pf->vf[v].lan_vsi_idx == 0)
+ if (vf->lan_vsi_idx == 0)
continue;
/* If VF is reset in another thread just continue */
if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
continue;
- i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]);
+ i40e_vsi_stop_rings_no_wait(pf->vsi[vf->lan_vsi_idx]);
}
/* Now that we've notified HW to disable all of the VF rings, wait
* until they finish.
*/
- for (v = 0; v < pf->num_alloc_vfs; v++) {
+ for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) {
/* On initial reset, we don't have any queues to disable */
- if (pf->vf[v].lan_vsi_idx == 0)
+ if (vf->lan_vsi_idx == 0)
continue;
/* If VF is reset in another thread just continue */
if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
continue;
- i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]);
+ i40e_vsi_wait_queues_disabled(pf->vsi[vf->lan_vsi_idx]);
}
/* Hw may need up to 50ms to finish disabling the RX queues. We
@@ -1721,12 +1719,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
mdelay(50);
/* Finish the reset on each VF */
- for (v = 0; v < pf->num_alloc_vfs; v++) {
+ for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) {
/* If VF is reset in another thread just continue */
if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
continue;
- i40e_cleanup_reset_vf(&pf->vf[v]);
+ i40e_cleanup_reset_vf(vf);
}
i40e_flush(hw);
@@ -3143,11 +3141,12 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
/* Allow to delete VF primary MAC only if it was not set
* administratively by PF or if VF is trusted.
*/
- if (ether_addr_equal(addr, vf->default_lan_addr.addr) &&
- i40e_can_vf_change_mac(vf))
- was_unimac_deleted = true;
- else
- continue;
+ if (ether_addr_equal(addr, vf->default_lan_addr.addr)) {
+ if (i40e_can_vf_change_mac(vf))
+ was_unimac_deleted = true;
+ else
+ continue;
+ }
if (i40e_del_mac_filter(vsi, al->list[i].addr)) {
ret = -EINVAL;
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 8040317c9561..1f3e7a6903e5 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -593,8 +593,9 @@ struct ice_aqc_recipe_data_elem {
struct ice_aqc_recipe_to_profile {
__le16 profile_id;
u8 rsvd[6];
- DECLARE_BITMAP(recipe_assoc, ICE_MAX_NUM_RECIPES);
+ __le64 recipe_assoc;
};
+static_assert(sizeof(struct ice_aqc_recipe_to_profile) == 16);
/* Add/Update/Remove/Get switch rules (indirect 0x02A0, 0x02A1, 0x02A2, 0x02A3)
*/
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 467372d541d2..a7a342809935 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -2041,7 +2041,7 @@ int ice_init_lag(struct ice_pf *pf)
/* associate recipes to profiles */
for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) {
err = ice_aq_get_recipe_to_profile(&pf->hw, n,
- (u8 *)&recipe_bits, NULL);
+ &recipe_bits, NULL);
if (err)
continue;
@@ -2049,7 +2049,7 @@ int ice_init_lag(struct ice_pf *pf)
recipe_bits |= BIT(lag->pf_recipe) |
BIT(lag->lport_recipe);
ice_aq_map_recipe_to_profile(&pf->hw, n,
- (u8 *)&recipe_bits, NULL);
+ recipe_bits, NULL);
}
}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index fc23dbe302b4..cfc20684f25a 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3238,7 +3238,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
{
struct ice_vsi_cfg_params params = {};
struct ice_coalesce_stored *coalesce;
- int prev_num_q_vectors = 0;
+ int prev_num_q_vectors;
struct ice_pf *pf;
int ret;
@@ -3252,13 +3252,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf))
return -EINVAL;
- coalesce = kcalloc(vsi->num_q_vectors,
- sizeof(struct ice_coalesce_stored), GFP_KERNEL);
- if (!coalesce)
- return -ENOMEM;
-
- prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce);
-
ret = ice_vsi_realloc_stat_arrays(vsi);
if (ret)
goto err_vsi_cfg;
@@ -3268,6 +3261,13 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
if (ret)
goto err_vsi_cfg;
+ coalesce = kcalloc(vsi->num_q_vectors,
+ sizeof(struct ice_coalesce_stored), GFP_KERNEL);
+ if (!coalesce)
+ return -ENOMEM;
+
+ prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce);
+
ret = ice_vsi_cfg_tc_lan(pf, vsi);
if (ret) {
if (vsi_flags & ICE_VSI_FLAG_INIT) {
@@ -3286,8 +3286,8 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
err_vsi_cfg_tc_lan:
ice_vsi_decfg(vsi);
-err_vsi_cfg:
kfree(coalesce);
+err_vsi_cfg:
return ret;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index f84bab80ca42..ba0ef91e4c19 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -2025,12 +2025,12 @@ ice_update_recipe_lkup_idx(struct ice_hw *hw,
* ice_aq_map_recipe_to_profile - Map recipe to packet profile
* @hw: pointer to the HW struct
* @profile_id: package profile ID to associate the recipe with
- * @r_bitmap: Recipe bitmap filled in and need to be returned as response
+ * @r_assoc: Recipe bitmap filled in and need to be returned as response
* @cd: pointer to command details structure or NULL
* Recipe to profile association (0x0291)
*/
int
-ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
+ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc,
struct ice_sq_cd *cd)
{
struct ice_aqc_recipe_to_profile *cmd;
@@ -2042,7 +2042,7 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
/* Set the recipe ID bit in the bitmask to let the device know which
* profile we are associating the recipe to
*/
- memcpy(cmd->recipe_assoc, r_bitmap, sizeof(cmd->recipe_assoc));
+ cmd->recipe_assoc = cpu_to_le64(r_assoc);
return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
}
@@ -2051,12 +2051,12 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
* ice_aq_get_recipe_to_profile - Map recipe to packet profile
* @hw: pointer to the HW struct
* @profile_id: package profile ID to associate the recipe with
- * @r_bitmap: Recipe bitmap filled in and need to be returned as response
+ * @r_assoc: Recipe bitmap filled in and need to be returned as response
* @cd: pointer to command details structure or NULL
* Associate profile ID with given recipe (0x0293)
*/
int
-ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
+ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc,
struct ice_sq_cd *cd)
{
struct ice_aqc_recipe_to_profile *cmd;
@@ -2069,7 +2069,7 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
if (!status)
- memcpy(r_bitmap, cmd->recipe_assoc, sizeof(cmd->recipe_assoc));
+ *r_assoc = le64_to_cpu(cmd->recipe_assoc);
return status;
}
@@ -2108,6 +2108,7 @@ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid)
static void ice_get_recp_to_prof_map(struct ice_hw *hw)
{
DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES);
+ u64 recp_assoc;
u16 i;
for (i = 0; i < hw->switch_info->max_used_prof_index + 1; i++) {
@@ -2115,8 +2116,9 @@ static void ice_get_recp_to_prof_map(struct ice_hw *hw)
bitmap_zero(profile_to_recipe[i], ICE_MAX_NUM_RECIPES);
bitmap_zero(r_bitmap, ICE_MAX_NUM_RECIPES);
- if (ice_aq_get_recipe_to_profile(hw, i, (u8 *)r_bitmap, NULL))
+ if (ice_aq_get_recipe_to_profile(hw, i, &recp_assoc, NULL))
continue;
+ bitmap_from_arr64(r_bitmap, &recp_assoc, ICE_MAX_NUM_RECIPES);
bitmap_copy(profile_to_recipe[i], r_bitmap,
ICE_MAX_NUM_RECIPES);
for_each_set_bit(j, r_bitmap, ICE_MAX_NUM_RECIPES)
@@ -5390,22 +5392,24 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
*/
list_for_each_entry(fvit, &rm->fv_list, list_entry) {
DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES);
+ u64 recp_assoc;
u16 j;
status = ice_aq_get_recipe_to_profile(hw, fvit->profile_id,
- (u8 *)r_bitmap, NULL);
+ &recp_assoc, NULL);
if (status)
goto err_unroll;
+ bitmap_from_arr64(r_bitmap, &recp_assoc, ICE_MAX_NUM_RECIPES);
bitmap_or(r_bitmap, r_bitmap, rm->r_bitmap,
ICE_MAX_NUM_RECIPES);
status = ice_acquire_change_lock(hw, ICE_RES_WRITE);
if (status)
goto err_unroll;
+ bitmap_to_arr64(&recp_assoc, r_bitmap, ICE_MAX_NUM_RECIPES);
status = ice_aq_map_recipe_to_profile(hw, fvit->profile_id,
- (u8 *)r_bitmap,
- NULL);
+ recp_assoc, NULL);
ice_release_change_lock(hw);
if (status)
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index db7e501b7e0a..89ffa1b51b5a 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -424,10 +424,10 @@ int ice_aq_add_recipe(struct ice_hw *hw,
struct ice_aqc_recipe_data_elem *s_recipe_list,
u16 num_recipes, struct ice_sq_cd *cd);
int
-ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
+ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc,
struct ice_sq_cd *cd);
int
-ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap,
+ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc,
struct ice_sq_cd *cd);
#endif /* _ICE_SWITCH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
index 80dc4bcdd3a4..b3e1bdcb80f8 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
@@ -26,24 +26,22 @@ static void ice_port_vlan_on(struct ice_vsi *vsi)
struct ice_vsi_vlan_ops *vlan_ops;
struct ice_pf *pf = vsi->back;
- if (ice_is_dvm_ena(&pf->hw)) {
- vlan_ops = &vsi->outer_vlan_ops;
-
- /* setup outer VLAN ops */
- vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan;
- vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan;
+ /* setup inner VLAN ops */
+ vlan_ops = &vsi->inner_vlan_ops;
- /* setup inner VLAN ops */
- vlan_ops = &vsi->inner_vlan_ops;
+ if (ice_is_dvm_ena(&pf->hw)) {
vlan_ops->add_vlan = noop_vlan_arg;
vlan_ops->del_vlan = noop_vlan_arg;
vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping;
vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping;
vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion;
vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion;
- } else {
- vlan_ops = &vsi->inner_vlan_ops;
+ /* setup outer VLAN ops */
+ vlan_ops = &vsi->outer_vlan_ops;
+ vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan;
+ vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan;
+ } else {
vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan;
vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan;
}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 2f8ad79ae3f0..017a081d8580 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2940,6 +2940,8 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq,
rx_ptype = le16_get_bits(rx_desc->ptype_err_fflags0,
VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M);
+ skb->protocol = eth_type_trans(skb, rxq->vport->netdev);
+
decoded = rxq->vport->rx_ptype_lkup[rx_ptype];
/* If we don't know the ptype we can't do anything else with it. Just
* pass it up the stack as-is.
@@ -2950,8 +2952,6 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq,
/* process RSS/hash */
idpf_rx_hash(rxq, skb, rx_desc, &decoded);
- skb->protocol = eth_type_trans(skb, rxq->vport->netdev);
-
if (le16_get_bits(rx_desc->hdrlen_flags,
VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M))
return idpf_rx_rsc(rxq, skb, rx_desc, &decoded);
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index e447ba037056..23bed58a9d82 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1642,10 +1642,6 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
if (unlikely(test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags) &&
skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
- /* FIXME: add support for retrieving timestamps from
- * the other timer registers before skipping the
- * timestamping request.
- */
unsigned long flags;
u32 tstamp_flags;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 13a6fca31004..866024f2b9ee 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -914,7 +914,13 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
goto err_out;
}
- xs = kzalloc(sizeof(*xs), GFP_KERNEL);
+ algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1);
+ if (unlikely(!algo)) {
+ err = -ENOENT;
+ goto err_out;
+ }
+
+ xs = kzalloc(sizeof(*xs), GFP_ATOMIC);
if (unlikely(!xs)) {
err = -ENOMEM;
goto err_out;
@@ -930,14 +936,8 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
memcpy(&xs->id.daddr.a4, sam->addr, sizeof(xs->id.daddr.a4));
xs->xso.dev = adapter->netdev;
- algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1);
- if (unlikely(!algo)) {
- err = -ENOENT;
- goto err_xs;
- }
-
aead_len = sizeof(*xs->aead) + IXGBE_IPSEC_KEY_BITS / 8;
- xs->aead = kzalloc(aead_len, GFP_KERNEL);
+ xs->aead = kzalloc(aead_len, GFP_ATOMIC);
if (unlikely(!xs->aead)) {
err = -ENOMEM;
goto err_xs;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 3c0f55b3e48e..b86f3224f0b7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -808,6 +808,11 @@ static int cgx_lmac_enadis_pause_frm(void *cgxd, int lmac_id,
if (!is_lmac_valid(cgx, lmac_id))
return -ENODEV;
+ cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL);
+ cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK;
+ cfg |= rx_pause ? CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK : 0x0;
+ cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg);
+
cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL);
cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK;
cfg |= rx_pause ? CGX_SMUX_RX_FRM_CTL_CTL_BCK : 0x0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 72e060cf6b61..e9bf9231b018 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -160,6 +160,8 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu)
continue;
lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu));
for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) {
+ if (iter >= MAX_LMAC_COUNT)
+ continue;
lmac = cgx_get_lmacid(rvu_cgx_pdata(cgx, rvu),
iter);
rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 516adb50f9f6..42b5ed02bc87 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -1657,7 +1657,7 @@ static int npc_fwdb_detect_load_prfl_img(struct rvu *rvu, uint64_t prfl_sz,
struct npc_coalesced_kpu_prfl *img_data = NULL;
int i = 0, rc = -EINVAL;
void __iomem *kpu_prfl_addr;
- u16 offset;
+ u32 offset;
img_data = (struct npc_coalesced_kpu_prfl __force *)rvu->kpu_prfl_addr;
if (le64_to_cpu(img_data->signature) == KPU_SIGN &&
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index b40bd0e46751..3f46d5e0fb2e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1933,7 +1933,7 @@ int otx2_open(struct net_device *netdev)
* mcam entries are enabled to receive the packets. Hence disable the
* packet I/O.
*/
- if (err == EIO)
+ if (err == -EIO)
goto err_disable_rxtx;
else if (err)
goto err_tx_stop_queues;
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
index 3d09fa54598f..ba303868686a 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
@@ -14,6 +14,7 @@
#include <linux/module.h>
#include <linux/phy.h>
#include <linux/platform_device.h>
+#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include "mlxbf_gige.h"
@@ -139,13 +140,10 @@ static int mlxbf_gige_open(struct net_device *netdev)
control |= MLXBF_GIGE_CONTROL_PORT_EN;
writeq(control, priv->base + MLXBF_GIGE_CONTROL);
- err = mlxbf_gige_request_irqs(priv);
- if (err)
- return err;
mlxbf_gige_cache_stats(priv);
err = mlxbf_gige_clean_port(priv);
if (err)
- goto free_irqs;
+ return err;
/* Clear driver's valid_polarity to match hardware,
* since the above call to clean_port() resets the
@@ -157,7 +155,7 @@ static int mlxbf_gige_open(struct net_device *netdev)
err = mlxbf_gige_tx_init(priv);
if (err)
- goto free_irqs;
+ goto phy_deinit;
err = mlxbf_gige_rx_init(priv);
if (err)
goto tx_deinit;
@@ -166,6 +164,10 @@ static int mlxbf_gige_open(struct net_device *netdev)
napi_enable(&priv->napi);
netif_start_queue(netdev);
+ err = mlxbf_gige_request_irqs(priv);
+ if (err)
+ goto napi_deinit;
+
/* Set bits in INT_EN that we care about */
int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR |
MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS |
@@ -182,11 +184,17 @@ static int mlxbf_gige_open(struct net_device *netdev)
return 0;
+napi_deinit:
+ netif_stop_queue(netdev);
+ napi_disable(&priv->napi);
+ netif_napi_del(&priv->napi);
+ mlxbf_gige_rx_deinit(priv);
+
tx_deinit:
mlxbf_gige_tx_deinit(priv);
-free_irqs:
- mlxbf_gige_free_irqs(priv);
+phy_deinit:
+ phy_stop(phydev);
return err;
}
@@ -485,8 +493,13 @@ static void mlxbf_gige_shutdown(struct platform_device *pdev)
{
struct mlxbf_gige *priv = platform_get_drvdata(pdev);
- writeq(0, priv->base + MLXBF_GIGE_INT_EN);
- mlxbf_gige_clean_port(priv);
+ rtnl_lock();
+ netif_device_detach(priv->netdev);
+
+ if (netif_running(priv->netdev))
+ dev_close(priv->netdev);
+
+ rtnl_unlock();
}
static const struct acpi_device_id __maybe_unused mlxbf_gige_acpi_match[] = {
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 45e209a7d083..6bf3367404eb 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -25,6 +25,8 @@
#define PCS_POWER_STATE_DOWN 0x6
#define PCS_POWER_STATE_UP 0x4
+#define RFE_RD_FIFO_TH_3_DWORDS 0x3
+
static void pci11x1x_strap_get_status(struct lan743x_adapter *adapter)
{
u32 chip_rev;
@@ -3272,6 +3274,21 @@ static void lan743x_full_cleanup(struct lan743x_adapter *adapter)
lan743x_pci_cleanup(adapter);
}
+static void pci11x1x_set_rfe_rd_fifo_threshold(struct lan743x_adapter *adapter)
+{
+ u16 rev = adapter->csr.id_rev & ID_REV_CHIP_REV_MASK_;
+
+ if (rev == ID_REV_CHIP_REV_PCI11X1X_B0_) {
+ u32 misc_ctl;
+
+ misc_ctl = lan743x_csr_read(adapter, MISC_CTL_0);
+ misc_ctl &= ~MISC_CTL_0_RFE_READ_FIFO_MASK_;
+ misc_ctl |= FIELD_PREP(MISC_CTL_0_RFE_READ_FIFO_MASK_,
+ RFE_RD_FIFO_TH_3_DWORDS);
+ lan743x_csr_write(adapter, MISC_CTL_0, misc_ctl);
+ }
+}
+
static int lan743x_hardware_init(struct lan743x_adapter *adapter,
struct pci_dev *pdev)
{
@@ -3287,6 +3304,7 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
pci11x1x_strap_get_status(adapter);
spin_lock_init(&adapter->eth_syslock_spinlock);
mutex_init(&adapter->sgmii_rw_lock);
+ pci11x1x_set_rfe_rd_fifo_threshold(adapter);
} else {
adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS;
adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS;
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index be79cb0ae5af..645bc048e52e 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -26,6 +26,7 @@
#define ID_REV_CHIP_REV_MASK_ (0x0000FFFF)
#define ID_REV_CHIP_REV_A0_ (0x00000000)
#define ID_REV_CHIP_REV_B0_ (0x00000010)
+#define ID_REV_CHIP_REV_PCI11X1X_B0_ (0x000000B0)
#define FPGA_REV (0x04)
#define FPGA_REV_GET_MINOR_(fpga_rev) (((fpga_rev) >> 8) & 0x000000FF)
@@ -311,6 +312,9 @@
#define SGMII_CTL_LINK_STATUS_SOURCE_ BIT(8)
#define SGMII_CTL_SGMII_POWER_DN_ BIT(1)
+#define MISC_CTL_0 (0x920)
+#define MISC_CTL_0_RFE_READ_FIFO_MASK_ GENMASK(6, 4)
+
/* Vendor Specific SGMII MMD details */
#define SR_VSMMD_PCS_ID1 0x0004
#define SR_VSMMD_PCS_ID2 0x0005
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 59287c6e6cee..d8af5e7e15b4 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -601,7 +601,7 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size,
*alloc_size = mtu + MANA_RXBUF_PAD + *headroom;
- *datasize = ALIGN(mtu + ETH_HLEN, MANA_RX_DATA_ALIGN);
+ *datasize = mtu + ETH_HLEN;
}
static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index dd73df6b17b0..4b6c28576a51 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1255,17 +1255,40 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
RTL_W8(tp, IBCR0, RTL_R8(tp, IBCR0) & ~0x01);
}
+static void rtl_dash_loop_wait(struct rtl8169_private *tp,
+ const struct rtl_cond *c,
+ unsigned long usecs, int n, bool high)
+{
+ if (!tp->dash_enabled)
+ return;
+ rtl_loop_wait(tp, c, usecs, n, high);
+}
+
+static void rtl_dash_loop_wait_high(struct rtl8169_private *tp,
+ const struct rtl_cond *c,
+ unsigned long d, int n)
+{
+ rtl_dash_loop_wait(tp, c, d, n, true);
+}
+
+static void rtl_dash_loop_wait_low(struct rtl8169_private *tp,
+ const struct rtl_cond *c,
+ unsigned long d, int n)
+{
+ rtl_dash_loop_wait(tp, c, d, n, false);
+}
+
static void rtl8168dp_driver_start(struct rtl8169_private *tp)
{
r8168dp_oob_notify(tp, OOB_CMD_DRIVER_START);
- rtl_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10000, 10);
+ rtl_dash_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10000, 10);
}
static void rtl8168ep_driver_start(struct rtl8169_private *tp)
{
r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START);
r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01);
- rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30);
+ rtl_dash_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30);
}
static void rtl8168_driver_start(struct rtl8169_private *tp)
@@ -1279,7 +1302,7 @@ static void rtl8168_driver_start(struct rtl8169_private *tp)
static void rtl8168dp_driver_stop(struct rtl8169_private *tp)
{
r8168dp_oob_notify(tp, OOB_CMD_DRIVER_STOP);
- rtl_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10000, 10);
+ rtl_dash_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10000, 10);
}
static void rtl8168ep_driver_stop(struct rtl8169_private *tp)
@@ -1287,7 +1310,7 @@ static void rtl8168ep_driver_stop(struct rtl8169_private *tp)
rtl8168ep_stop_cmac(tp);
r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP);
r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01);
- rtl_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10);
+ rtl_dash_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10);
}
static void rtl8168_driver_stop(struct rtl8169_private *tp)
@@ -5027,6 +5050,15 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
struct mii_bus *new_bus;
int ret;
+ /* On some boards with this chip version the BIOS is buggy and misses
+ * to reset the PHY page selector. This results in the PHY ID read
+ * accessing registers on a different page, returning a more or
+ * less random value. Fix this by resetting the page selector first.
+ */
+ if (tp->mac_version == RTL_GIGA_MAC_VER_25 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_26)
+ r8169_mdio_write(tp, 0x1f, 0);
+
new_bus = devm_mdiobus_alloc(&pdev->dev);
if (!new_bus)
return -ENOMEM;
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index f7566cfa45ca..1bdf0abb256c 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1284,25 +1284,16 @@ static int ravb_poll(struct napi_struct *napi, int budget)
struct net_device *ndev = napi->dev;
struct ravb_private *priv = netdev_priv(ndev);
const struct ravb_hw_info *info = priv->info;
- bool gptp = info->gptp || info->ccc_gac;
- struct ravb_rx_desc *desc;
unsigned long flags;
int q = napi - priv->napi;
int mask = BIT(q);
int quota = budget;
- unsigned int entry;
+ bool unmask;
- if (!gptp) {
- entry = priv->cur_rx[q] % priv->num_rx_ring[q];
- desc = &priv->gbeth_rx_ring[entry];
- }
/* Processing RX Descriptor Ring */
/* Clear RX interrupt */
ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0);
- if (gptp || desc->die_dt != DT_FEMPTY) {
- if (ravb_rx(ndev, "a, q))
- goto out;
- }
+ unmask = !ravb_rx(ndev, "a, q);
/* Processing TX Descriptor Ring */
spin_lock_irqsave(&priv->lock, flags);
@@ -1312,6 +1303,18 @@ static int ravb_poll(struct napi_struct *napi, int budget)
netif_wake_subqueue(ndev, q);
spin_unlock_irqrestore(&priv->lock, flags);
+ /* Receive error message handling */
+ priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors;
+ if (info->nc_queues)
+ priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors;
+ if (priv->rx_over_errors != ndev->stats.rx_over_errors)
+ ndev->stats.rx_over_errors = priv->rx_over_errors;
+ if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors)
+ ndev->stats.rx_fifo_errors = priv->rx_fifo_errors;
+
+ if (!unmask)
+ goto out;
+
napi_complete(napi);
/* Re-enable RX/TX interrupts */
@@ -1325,14 +1328,6 @@ static int ravb_poll(struct napi_struct *napi, int budget)
}
spin_unlock_irqrestore(&priv->lock, flags);
- /* Receive error message handling */
- priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors;
- if (info->nc_queues)
- priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors;
- if (priv->rx_over_errors != ndev->stats.rx_over_errors)
- ndev->stats.rx_over_errors = priv->rx_over_errors;
- if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors)
- ndev->stats.rx_fifo_errors = priv->rx_fifo_errors;
out:
return budget - quota;
}
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 475e1e8c1d35..0786eb0da391 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -50,7 +50,7 @@
* the macros available to do this only define GCC 8.
*/
__diag_push();
-__diag_ignore(GCC, 8, "-Woverride-init",
+__diag_ignore_all("-Woverride-init",
"logic to initialize all and then override some is OK");
static const u16 sh_eth_offset_gigabit[SH_ETH_MAX_REGISTER_OFFSET] = {
SH_ETH_OFFSET_DEFAULTS,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 6b6d0de09619..cef25efbdff9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -92,19 +92,41 @@ static void dwmac4_rx_queue_priority(struct mac_device_info *hw,
u32 prio, u32 queue)
{
void __iomem *ioaddr = hw->pcsr;
- u32 base_register;
- u32 value;
+ u32 clear_mask = 0;
+ u32 ctrl2, ctrl3;
+ int i;
- base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3;
- if (queue >= 4)
- queue -= 4;
+ ctrl2 = readl(ioaddr + GMAC_RXQ_CTRL2);
+ ctrl3 = readl(ioaddr + GMAC_RXQ_CTRL3);
- value = readl(ioaddr + base_register);
+ /* The software must ensure that the same priority
+ * is not mapped to multiple Rx queues
+ */
+ for (i = 0; i < 4; i++)
+ clear_mask |= ((prio << GMAC_RXQCTRL_PSRQX_SHIFT(i)) &
+ GMAC_RXQCTRL_PSRQX_MASK(i));
+
+ ctrl2 &= ~clear_mask;
+ ctrl3 &= ~clear_mask;
+
+ /* First assign new priorities to a queue, then
+ * clear them from others queues
+ */
+ if (queue < 4) {
+ ctrl2 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
+ GMAC_RXQCTRL_PSRQX_MASK(queue);
- value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue);
- value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
+ writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2);
+ writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3);
+ } else {
+ queue -= 4;
+
+ ctrl3 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
GMAC_RXQCTRL_PSRQX_MASK(queue);
- writel(value, ioaddr + base_register);
+
+ writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3);
+ writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2);
+ }
}
static void dwmac4_tx_queue_priority(struct mac_device_info *hw,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 1af2f89a0504..e841e312077e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -105,17 +105,41 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio,
u32 queue)
{
void __iomem *ioaddr = hw->pcsr;
- u32 value, reg;
+ u32 clear_mask = 0;
+ u32 ctrl2, ctrl3;
+ int i;
- reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3;
- if (queue >= 4)
+ ctrl2 = readl(ioaddr + XGMAC_RXQ_CTRL2);
+ ctrl3 = readl(ioaddr + XGMAC_RXQ_CTRL3);
+
+ /* The software must ensure that the same priority
+ * is not mapped to multiple Rx queues
+ */
+ for (i = 0; i < 4; i++)
+ clear_mask |= ((prio << XGMAC_PSRQ_SHIFT(i)) &
+ XGMAC_PSRQ(i));
+
+ ctrl2 &= ~clear_mask;
+ ctrl3 &= ~clear_mask;
+
+ /* First assign new priorities to a queue, then
+ * clear them from others queues
+ */
+ if (queue < 4) {
+ ctrl2 |= (prio << XGMAC_PSRQ_SHIFT(queue)) &
+ XGMAC_PSRQ(queue);
+
+ writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2);
+ writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3);
+ } else {
queue -= 4;
- value = readl(ioaddr + reg);
- value &= ~XGMAC_PSRQ(queue);
- value |= (prio << XGMAC_PSRQ_SHIFT(queue)) & XGMAC_PSRQ(queue);
+ ctrl3 |= (prio << XGMAC_PSRQ_SHIFT(queue)) &
+ XGMAC_PSRQ(queue);
- writel(value, ioaddr + reg);
+ writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3);
+ writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2);
+ }
}
static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio,
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 29997e4b2d6c..8cddc9ddb339 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -20,6 +20,8 @@
#include "txgbe_phy.h"
#include "txgbe_hw.h"
+#define TXGBE_I2C_CLK_DEV_NAME "i2c_dw"
+
static int txgbe_swnodes_register(struct txgbe *txgbe)
{
struct txgbe_nodes *nodes = &txgbe->nodes;
@@ -556,8 +558,8 @@ static int txgbe_clock_register(struct txgbe *txgbe)
char clk_name[32];
struct clk *clk;
- snprintf(clk_name, sizeof(clk_name), "i2c_dw.%d",
- pci_dev_id(pdev));
+ snprintf(clk_name, sizeof(clk_name), "%s.%d",
+ TXGBE_I2C_CLK_DEV_NAME, pci_dev_id(pdev));
clk = clk_register_fixed_rate(NULL, clk_name, NULL, 0, 156250000);
if (IS_ERR(clk))
@@ -619,7 +621,7 @@ static int txgbe_i2c_register(struct txgbe *txgbe)
info.parent = &pdev->dev;
info.fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_I2C]);
- info.name = "i2c_designware";
+ info.name = TXGBE_I2C_CLK_DEV_NAME;
info.id = pci_dev_id(pdev);
info.res = &DEFINE_RES_IRQ(pdev->irq);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index dad720138baa..1f950c824418 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -2416,6 +2416,7 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts,
struct lan8814_ptp_rx_ts *rx_ts, *tmp;
int txcfg = 0, rxcfg = 0;
int pkt_ts_enable;
+ int tx_mod;
ptp_priv->hwts_tx_type = config->tx_type;
ptp_priv->rx_filter = config->rx_filter;
@@ -2462,9 +2463,14 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts,
lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_RX_TIMESTAMP_EN, pkt_ts_enable);
lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_TIMESTAMP_EN, pkt_ts_enable);
- if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC)
+ tx_mod = lanphy_read_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD);
+ if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC) {
lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD,
- PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_);
+ tx_mod | PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_);
+ } else if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ON) {
+ lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD,
+ tx_mod & ~PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_);
+ }
if (config->rx_filter != HWTSTAMP_FILTER_NONE)
lan8814_config_ts_intr(ptp_priv->phydev, true);
@@ -2522,7 +2528,7 @@ static void lan8814_txtstamp(struct mii_timestamper *mii_ts,
}
}
-static void lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig)
+static bool lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig)
{
struct ptp_header *ptp_header;
u32 type;
@@ -2532,7 +2538,11 @@ static void lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig)
ptp_header = ptp_parse_header(skb, type);
skb_pull_inline(skb, ETH_HLEN);
+ if (!ptp_header)
+ return false;
+
*sig = (__force u16)(ntohs(ptp_header->sequence_id));
+ return true;
}
static bool lan8814_match_rx_skb(struct kszphy_ptp_priv *ptp_priv,
@@ -2544,7 +2554,8 @@ static bool lan8814_match_rx_skb(struct kszphy_ptp_priv *ptp_priv,
bool ret = false;
u16 skb_sig;
- lan8814_get_sig_rx(skb, &skb_sig);
+ if (!lan8814_get_sig_rx(skb, &skb_sig))
+ return ret;
/* Iterate over all RX timestamps and match it with the received skbs */
spin_lock_irqsave(&ptp_priv->rx_ts_lock, flags);
@@ -2824,7 +2835,7 @@ static int lan8814_ptpci_adjfine(struct ptp_clock_info *ptpci, long scaled_ppm)
return 0;
}
-static void lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig)
+static bool lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig)
{
struct ptp_header *ptp_header;
u32 type;
@@ -2832,7 +2843,11 @@ static void lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig)
type = ptp_classify_raw(skb);
ptp_header = ptp_parse_header(skb, type);
+ if (!ptp_header)
+ return false;
+
*sig = (__force u16)(ntohs(ptp_header->sequence_id));
+ return true;
}
static void lan8814_match_tx_skb(struct kszphy_ptp_priv *ptp_priv,
@@ -2846,7 +2861,8 @@ static void lan8814_match_tx_skb(struct kszphy_ptp_priv *ptp_priv,
spin_lock_irqsave(&ptp_priv->tx_queue.lock, flags);
skb_queue_walk_safe(&ptp_priv->tx_queue, skb, skb_tmp) {
- lan8814_get_sig_tx(skb, &skb_sig);
+ if (!lan8814_get_sig_tx(skb, &skb_sig))
+ continue;
if (memcmp(&skb_sig, &seq_id, sizeof(seq_id)))
continue;
@@ -2900,7 +2916,8 @@ static bool lan8814_match_skb(struct kszphy_ptp_priv *ptp_priv,
spin_lock_irqsave(&ptp_priv->rx_queue.lock, flags);
skb_queue_walk_safe(&ptp_priv->rx_queue, skb, skb_tmp) {
- lan8814_get_sig_rx(skb, &skb_sig);
+ if (!lan8814_get_sig_rx(skb, &skb_sig))
+ continue;
if (memcmp(&skb_sig, &rx_ts->seq_id, sizeof(rx_ts->seq_id)))
continue;
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index d837c1887416..e0e9b4c53cb0 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1273,6 +1273,8 @@ static void ax88179_get_mac_addr(struct usbnet *dev)
if (is_valid_ether_addr(mac)) {
eth_hw_addr_set(dev->net, mac);
+ if (!is_local_ether_addr(mac))
+ dev->net->addr_assign_type = NET_ADDR_PERM;
} else {
netdev_info(dev->net, "invalid MAC address, using random\n");
eth_hw_addr_random(dev->net);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c
index 2ecd32bed752..045c862a8fc4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c
@@ -132,14 +132,18 @@ struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm)
if (ret)
return ERR_PTR(ret);
- if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) != resp_size))
+ if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) !=
+ resp_size)) {
+ iwl_free_resp(&cmd);
return ERR_PTR(-EIO);
+ }
resp = kmemdup(cmd.resp_pkt->data, resp_size, GFP_KERNEL);
+ iwl_free_resp(&cmd);
+
if (!resp)
return ERR_PTR(-ENOMEM);
- iwl_free_resp(&cmd);
return resp;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 7bf2a5947e5e..481dfbbe4616 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -236,21 +236,13 @@ static void iwl_mvm_add_rtap_sniffer_config(struct iwl_mvm *mvm,
static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm,
struct napi_struct *napi,
struct sk_buff *skb, int queue,
- struct ieee80211_sta *sta,
- struct ieee80211_link_sta *link_sta)
+ struct ieee80211_sta *sta)
{
if (unlikely(iwl_mvm_check_pn(mvm, skb, queue, sta))) {
kfree_skb(skb);
return;
}
- if (sta && sta->valid_links && link_sta) {
- struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
-
- rx_status->link_valid = 1;
- rx_status->link_id = link_sta->link_id;
- }
-
ieee80211_rx_napi(mvm->hw, sta, skb, napi);
}
@@ -587,7 +579,7 @@ static void iwl_mvm_release_frames(struct iwl_mvm *mvm,
while ((skb = __skb_dequeue(skb_list))) {
iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb,
reorder_buf->queue,
- sta, NULL /* FIXME */);
+ sta);
reorder_buf->num_stored--;
}
}
@@ -2214,6 +2206,11 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
if (IS_ERR(sta))
sta = NULL;
link_sta = rcu_dereference(mvm->fw_id_to_link_sta[id]);
+
+ if (sta && sta->valid_links && link_sta) {
+ rx_status->link_valid = 1;
+ rx_status->link_id = link_sta->link_id;
+ }
}
} else if (!is_multicast_ether_addr(hdr->addr2)) {
/*
@@ -2357,8 +2354,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
!(desc->amsdu_info & IWL_RX_MPDU_AMSDU_LAST_SUBFRAME))
rx_status->flag |= RX_FLAG_AMSDU_MORE;
- iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta,
- link_sta);
+ iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta);
}
out:
rcu_read_unlock();
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index da00ef6e4fbc..3d96a824dbd6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -898,9 +898,8 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm,
struct iwl_rx_packet *pkt = rxb_addr(rxb);
struct iwl_mvm_session_prot_notif *notif = (void *)pkt->data;
unsigned int ver =
- iwl_fw_lookup_cmd_ver(mvm->fw,
- WIDE_ID(MAC_CONF_GROUP,
- SESSION_PROTECTION_CMD), 2);
+ iwl_fw_lookup_notif_ver(mvm->fw, MAC_CONF_GROUP,
+ SESSION_PROTECTION_NOTIF, 2);
int id = le32_to_cpu(notif->mac_link_id);
struct ieee80211_vif *vif;
struct iwl_mvm_vif *mvmvif;
diff --git a/drivers/net/wwan/t7xx/t7xx_cldma.c b/drivers/net/wwan/t7xx/t7xx_cldma.c
index 9f43f256db1d..f0a4783baf1f 100644
--- a/drivers/net/wwan/t7xx/t7xx_cldma.c
+++ b/drivers/net/wwan/t7xx/t7xx_cldma.c
@@ -106,7 +106,7 @@ bool t7xx_cldma_tx_addr_is_set(struct t7xx_cldma_hw *hw_info, unsigned int qno)
{
u32 offset = REG_CLDMA_UL_START_ADDRL_0 + qno * ADDR_SIZE;
- return ioread64(hw_info->ap_pdn_base + offset);
+ return ioread64_lo_hi(hw_info->ap_pdn_base + offset);
}
void t7xx_cldma_hw_set_start_addr(struct t7xx_cldma_hw *hw_info, unsigned int qno, u64 address,
@@ -117,7 +117,7 @@ void t7xx_cldma_hw_set_start_addr(struct t7xx_cldma_hw *hw_info, unsigned int qn
reg = tx_rx == MTK_RX ? hw_info->ap_ao_base + REG_CLDMA_DL_START_ADDRL_0 :
hw_info->ap_pdn_base + REG_CLDMA_UL_START_ADDRL_0;
- iowrite64(address, reg + offset);
+ iowrite64_lo_hi(address, reg + offset);
}
void t7xx_cldma_hw_resume_queue(struct t7xx_cldma_hw *hw_info, unsigned int qno,
diff --git a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c
index cc70360364b7..554ba4669cc8 100644
--- a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c
+++ b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c
@@ -139,8 +139,9 @@ static int t7xx_cldma_gpd_rx_from_q(struct cldma_queue *queue, int budget, bool
return -ENODEV;
}
- gpd_addr = ioread64(hw_info->ap_pdn_base + REG_CLDMA_DL_CURRENT_ADDRL_0 +
- queue->index * sizeof(u64));
+ gpd_addr = ioread64_lo_hi(hw_info->ap_pdn_base +
+ REG_CLDMA_DL_CURRENT_ADDRL_0 +
+ queue->index * sizeof(u64));
if (req->gpd_addr == gpd_addr || hwo_polling_count++ >= 100)
return 0;
@@ -318,8 +319,8 @@ static void t7xx_cldma_txq_empty_hndl(struct cldma_queue *queue)
struct t7xx_cldma_hw *hw_info = &md_ctrl->hw_info;
/* Check current processing TGPD, 64-bit address is in a table by Q index */
- ul_curr_addr = ioread64(hw_info->ap_pdn_base + REG_CLDMA_UL_CURRENT_ADDRL_0 +
- queue->index * sizeof(u64));
+ ul_curr_addr = ioread64_lo_hi(hw_info->ap_pdn_base + REG_CLDMA_UL_CURRENT_ADDRL_0 +
+ queue->index * sizeof(u64));
if (req->gpd_addr != ul_curr_addr) {
spin_unlock_irqrestore(&md_ctrl->cldma_lock, flags);
dev_err(md_ctrl->dev, "CLDMA%d queue %d is not empty\n",
diff --git a/drivers/net/wwan/t7xx/t7xx_pcie_mac.c b/drivers/net/wwan/t7xx/t7xx_pcie_mac.c
index 76da4c15e3de..f071ec7ff23d 100644
--- a/drivers/net/wwan/t7xx/t7xx_pcie_mac.c
+++ b/drivers/net/wwan/t7xx/t7xx_pcie_mac.c
@@ -75,7 +75,7 @@ static void t7xx_pcie_mac_atr_tables_dis(void __iomem *pbase, enum t7xx_atr_src_
for (i = 0; i < ATR_TABLE_NUM_PER_ATR; i++) {
offset = ATR_PORT_OFFSET * port + ATR_TABLE_OFFSET * i;
reg = pbase + ATR_PCIE_WIN0_T0_ATR_PARAM_SRC_ADDR + offset;
- iowrite64(0, reg);
+ iowrite64_lo_hi(0, reg);
}
}
@@ -112,17 +112,17 @@ static int t7xx_pcie_mac_atr_cfg(struct t7xx_pci_dev *t7xx_dev, struct t7xx_atr_
reg = pbase + ATR_PCIE_WIN0_T0_TRSL_ADDR + offset;
value = cfg->trsl_addr & ATR_PCIE_WIN0_ADDR_ALGMT;
- iowrite64(value, reg);
+ iowrite64_lo_hi(value, reg);
reg = pbase + ATR_PCIE_WIN0_T0_TRSL_PARAM + offset;
iowrite32(cfg->trsl_id, reg);
reg = pbase + ATR_PCIE_WIN0_T0_ATR_PARAM_SRC_ADDR + offset;
value = (cfg->src_addr & ATR_PCIE_WIN0_ADDR_ALGMT) | (atr_size << 1) | BIT(0);
- iowrite64(value, reg);
+ iowrite64_lo_hi(value, reg);
/* Ensure ATR is set */
- ioread64(reg);
+ ioread64_lo_hi(reg);
return 0;
}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index ad29f370034e..8d2aee88526c 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -285,6 +285,7 @@ static struct sk_buff *xennet_alloc_one_rx_buffer(struct netfront_queue *queue)
return NULL;
}
skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
+ skb_mark_for_recycle(skb);
/* Align ip header to a 16 bytes boundary */
skb_reserve(skb, NET_IP_ALIGN);
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index 3bf27052832f..4d57a4e34105 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -9,6 +9,7 @@
#define pr_fmt(fmt) "OF: " fmt
+#include <linux/device.h>
#include <linux/of.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
@@ -667,6 +668,17 @@ void of_changeset_destroy(struct of_changeset *ocs)
{
struct of_changeset_entry *ce, *cen;
+ /*
+ * When a device is deleted, the device links to/from it are also queued
+ * for deletion. Until these device links are freed, the devices
+ * themselves aren't freed. If the device being deleted is due to an
+ * overlay change, this device might be holding a reference to a device
+ * node that will be freed. So, wait until all already pending device
+ * links are deleted before freeing a device node. This ensures we don't
+ * free any device node that has a non-zero reference count.
+ */
+ device_link_wait_removal();
+
list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node)
__of_changeset_entry_destroy(ce);
}
diff --git a/drivers/of/module.c b/drivers/of/module.c
index 0e8aa974f0f2..f58e624953a2 100644
--- a/drivers/of/module.c
+++ b/drivers/of/module.c
@@ -16,6 +16,14 @@ ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len)
ssize_t csize;
ssize_t tsize;
+ /*
+ * Prevent a kernel oops in vsnprintf() -- it only allows passing a
+ * NULL ptr when the length is also 0. Also filter out the negative
+ * lengths...
+ */
+ if ((len > 0 && !str) || len < 0)
+ return -EINVAL;
+
/* Name & Type */
/* %p eats all alphanum characters, so %c must be used here */
csize = snprintf(str, len, "of:N%pOFn%c%s", np, 'T',
diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c
index c78a6fd6c57f..b4efdddb2ad9 100644
--- a/drivers/perf/riscv_pmu.c
+++ b/drivers/perf/riscv_pmu.c
@@ -313,6 +313,10 @@ static int riscv_pmu_event_init(struct perf_event *event)
u64 event_config = 0;
uint64_t cmask;
+ /* driver does not support branch stack sampling */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
hwc->flags = 0;
mapped_event = rvpmu->event_map(event, &event_config);
if (mapped_event < 0) {
diff --git a/drivers/pinctrl/aspeed/Makefile b/drivers/pinctrl/aspeed/Makefile
index 489ea1778353..db2a7600ae2b 100644
--- a/drivers/pinctrl/aspeed/Makefile
+++ b/drivers/pinctrl/aspeed/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
# Aspeed pinctrl support
-ccflags-y += $(call cc-option,-Woverride-init)
+ccflags-y += -Woverride-init
obj-$(CONFIG_PINCTRL_ASPEED) += pinctrl-aspeed.o pinmux-aspeed.o
obj-$(CONFIG_PINCTRL_ASPEED_G4) += pinctrl-aspeed-g4.o
obj-$(CONFIG_PINCTRL_ASPEED_G5) += pinctrl-aspeed-g5.o
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index cf8506d0f185..601d00e09de4 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1179,6 +1179,20 @@ static int qeth_check_irb_error(struct qeth_card *card, struct ccw_device *cdev,
}
}
+/**
+ * qeth_irq() - qeth interrupt handler
+ * @cdev: ccw device
+ * @intparm: expect pointer to iob
+ * @irb: Interruption Response Block
+ *
+ * In the good path:
+ * corresponding qeth channel is locked with last used iob as active_cmd.
+ * But this function is also called for error interrupts.
+ *
+ * Caller ensures that:
+ * Interrupts are disabled; ccw device lock is held;
+ *
+ */
static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
struct irb *irb)
{
@@ -1220,11 +1234,10 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
iob = (struct qeth_cmd_buffer *) (addr_t)intparm;
}
- qeth_unlock_channel(card, channel);
-
rc = qeth_check_irb_error(card, cdev, irb);
if (rc) {
/* IO was terminated, free its resources. */
+ qeth_unlock_channel(card, channel);
if (iob)
qeth_cancel_cmd(iob, rc);
return;
@@ -1268,6 +1281,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
rc = qeth_get_problem(card, cdev, irb);
if (rc) {
card->read_or_write_problem = 1;
+ qeth_unlock_channel(card, channel);
if (iob)
qeth_cancel_cmd(iob, rc);
qeth_clear_ipacmd_list(card);
@@ -1276,6 +1290,26 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
}
}
+ if (scsw_cmd_is_valid_cc(&irb->scsw) && irb->scsw.cmd.cc == 1 && iob) {
+ /* channel command hasn't started: retry.
+ * active_cmd is still set to last iob
+ */
+ QETH_CARD_TEXT(card, 2, "irqcc1");
+ rc = ccw_device_start_timeout(cdev, __ccw_from_cmd(iob),
+ (addr_t)iob, 0, 0, iob->timeout);
+ if (rc) {
+ QETH_DBF_MESSAGE(2,
+ "ccw retry on %x failed, rc = %i\n",
+ CARD_DEVID(card), rc);
+ QETH_CARD_TEXT_(card, 2, " err%d", rc);
+ qeth_unlock_channel(card, channel);
+ qeth_cancel_cmd(iob, rc);
+ }
+ return;
+ }
+
+ qeth_unlock_channel(card, channel);
+
if (iob) {
/* sanity check: */
if (irb->scsw.cmd.count > iob->length) {
diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c
index ca2e932dd9b7..f684eb5e0489 100644
--- a/drivers/scsi/myrb.c
+++ b/drivers/scsi/myrb.c
@@ -1775,9 +1775,9 @@ static ssize_t raid_state_show(struct device *dev,
name = myrb_devstate_name(ldev_info->state);
if (name)
- ret = snprintf(buf, 32, "%s\n", name);
+ ret = snprintf(buf, 64, "%s\n", name);
else
- ret = snprintf(buf, 32, "Invalid (%02X)\n",
+ ret = snprintf(buf, 64, "Invalid (%02X)\n",
ldev_info->state);
} else {
struct myrb_pdev_state *pdev_info = sdev->hostdata;
@@ -1796,9 +1796,9 @@ static ssize_t raid_state_show(struct device *dev,
else
name = myrb_devstate_name(pdev_info->state);
if (name)
- ret = snprintf(buf, 32, "%s\n", name);
+ ret = snprintf(buf, 64, "%s\n", name);
else
- ret = snprintf(buf, 32, "Invalid (%02X)\n",
+ ret = snprintf(buf, 64, "Invalid (%02X)\n",
pdev_info->state);
}
return ret;
@@ -1886,11 +1886,11 @@ static ssize_t raid_level_show(struct device *dev,
name = myrb_raidlevel_name(ldev_info->raid_level);
if (!name)
- return snprintf(buf, 32, "Invalid (%02X)\n",
+ return snprintf(buf, 64, "Invalid (%02X)\n",
ldev_info->state);
- return snprintf(buf, 32, "%s\n", name);
+ return snprintf(buf, 64, "%s\n", name);
}
- return snprintf(buf, 32, "Physical Drive\n");
+ return snprintf(buf, 64, "Physical Drive\n");
}
static DEVICE_ATTR_RO(raid_level);
@@ -1903,15 +1903,15 @@ static ssize_t rebuild_show(struct device *dev,
unsigned char status;
if (sdev->channel < myrb_logical_channel(sdev->host))
- return snprintf(buf, 32, "physical device - not rebuilding\n");
+ return snprintf(buf, 64, "physical device - not rebuilding\n");
status = myrb_get_rbld_progress(cb, &rbld_buf);
if (rbld_buf.ldev_num != sdev->id ||
status != MYRB_STATUS_SUCCESS)
- return snprintf(buf, 32, "not rebuilding\n");
+ return snprintf(buf, 64, "not rebuilding\n");
- return snprintf(buf, 32, "rebuilding block %u of %u\n",
+ return snprintf(buf, 64, "rebuilding block %u of %u\n",
rbld_buf.ldev_size - rbld_buf.blocks_left,
rbld_buf.ldev_size);
}
diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c
index a1eec65a9713..e824be9d9bbb 100644
--- a/drivers/scsi/myrs.c
+++ b/drivers/scsi/myrs.c
@@ -947,9 +947,9 @@ static ssize_t raid_state_show(struct device *dev,
name = myrs_devstate_name(ldev_info->dev_state);
if (name)
- ret = snprintf(buf, 32, "%s\n", name);
+ ret = snprintf(buf, 64, "%s\n", name);
else
- ret = snprintf(buf, 32, "Invalid (%02X)\n",
+ ret = snprintf(buf, 64, "Invalid (%02X)\n",
ldev_info->dev_state);
} else {
struct myrs_pdev_info *pdev_info;
@@ -958,9 +958,9 @@ static ssize_t raid_state_show(struct device *dev,
pdev_info = sdev->hostdata;
name = myrs_devstate_name(pdev_info->dev_state);
if (name)
- ret = snprintf(buf, 32, "%s\n", name);
+ ret = snprintf(buf, 64, "%s\n", name);
else
- ret = snprintf(buf, 32, "Invalid (%02X)\n",
+ ret = snprintf(buf, 64, "Invalid (%02X)\n",
pdev_info->dev_state);
}
return ret;
@@ -1066,13 +1066,13 @@ static ssize_t raid_level_show(struct device *dev,
ldev_info = sdev->hostdata;
name = myrs_raid_level_name(ldev_info->raid_level);
if (!name)
- return snprintf(buf, 32, "Invalid (%02X)\n",
+ return snprintf(buf, 64, "Invalid (%02X)\n",
ldev_info->dev_state);
} else
name = myrs_raid_level_name(MYRS_RAID_PHYSICAL);
- return snprintf(buf, 32, "%s\n", name);
+ return snprintf(buf, 64, "%s\n", name);
}
static DEVICE_ATTR_RO(raid_level);
@@ -1086,7 +1086,7 @@ static ssize_t rebuild_show(struct device *dev,
unsigned char status;
if (sdev->channel < cs->ctlr_info->physchan_present)
- return snprintf(buf, 32, "physical device - not rebuilding\n");
+ return snprintf(buf, 64, "physical device - not rebuilding\n");
ldev_info = sdev->hostdata;
ldev_num = ldev_info->ldev_num;
@@ -1098,11 +1098,11 @@ static ssize_t rebuild_show(struct device *dev,
return -EIO;
}
if (ldev_info->rbld_active) {
- return snprintf(buf, 32, "rebuilding block %zu of %zu\n",
+ return snprintf(buf, 64, "rebuilding block %zu of %zu\n",
(size_t)ldev_info->rbld_lba,
(size_t)ldev_info->cfg_devsize);
} else
- return snprintf(buf, 32, "not rebuilding\n");
+ return snprintf(buf, 64, "not rebuilding\n");
}
static ssize_t rebuild_store(struct device *dev,
@@ -1190,7 +1190,7 @@ static ssize_t consistency_check_show(struct device *dev,
unsigned short ldev_num;
if (sdev->channel < cs->ctlr_info->physchan_present)
- return snprintf(buf, 32, "physical device - not checking\n");
+ return snprintf(buf, 64, "physical device - not checking\n");
ldev_info = sdev->hostdata;
if (!ldev_info)
@@ -1198,11 +1198,11 @@ static ssize_t consistency_check_show(struct device *dev,
ldev_num = ldev_info->ldev_num;
myrs_get_ldev_info(cs, ldev_num, ldev_info);
if (ldev_info->cc_active)
- return snprintf(buf, 32, "checking block %zu of %zu\n",
+ return snprintf(buf, 64, "checking block %zu of %zu\n",
(size_t)ldev_info->cc_lba,
(size_t)ldev_info->cfg_devsize);
else
- return snprintf(buf, 32, "not checking\n");
+ return snprintf(buf, 64, "not checking\n");
}
static ssize_t consistency_check_store(struct device *dev,
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index d5d3eea006c1..35200a7a7355 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3757,7 +3757,7 @@ static int sd_probe(struct device *dev)
error = device_add_disk(dev, gd, NULL);
if (error) {
- put_device(&sdkp->disk_dev);
+ device_unregister(&sdkp->disk_dev);
put_disk(gd);
goto out;
}
diff --git a/drivers/spi/spi-pci1xxxx.c b/drivers/spi/spi-pci1xxxx.c
index 5b2d3e4e21b7..5a4226682052 100644
--- a/drivers/spi/spi-pci1xxxx.c
+++ b/drivers/spi/spi-pci1xxxx.c
@@ -275,6 +275,8 @@ static int pci1xxxx_spi_probe(struct pci_dev *pdev, const struct pci_device_id *
spi_bus->spi_int[iter] = devm_kzalloc(&pdev->dev,
sizeof(struct pci1xxxx_spi_internal),
GFP_KERNEL);
+ if (!spi_bus->spi_int[iter])
+ return -ENOMEM;
spi_sub_ptr = spi_bus->spi_int[iter];
spi_sub_ptr->spi_host = devm_spi_alloc_host(dev, sizeof(struct spi_controller));
if (!spi_sub_ptr->spi_host)
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 0e48ffd499b9..652eadbefe24 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -3,19 +3,20 @@
// Copyright (c) 2009 Samsung Electronics Co., Ltd.
// Jaswinder Singh <jassi.brar@xxxxxxxxxxx>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
+#include <linux/bitops.h>
+#include <linux/bits.h>
#include <linux/clk.h>
+#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/dmaengine.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_data/spi-s3c64xx.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/spi/spi.h>
-#include <linux/of.h>
-
-#include <linux/platform_data/spi-s3c64xx.h>
#define MAX_SPI_PORTS 12
#define S3C64XX_SPI_QUIRK_CS_AUTO (1 << 1)
@@ -76,6 +77,7 @@
#define S3C64XX_SPI_INT_RX_FIFORDY_EN (1<<1)
#define S3C64XX_SPI_INT_TX_FIFORDY_EN (1<<0)
+#define S3C64XX_SPI_ST_TX_FIFO_LVL_SHIFT 6
#define S3C64XX_SPI_ST_RX_OVERRUN_ERR (1<<5)
#define S3C64XX_SPI_ST_RX_UNDERRUN_ERR (1<<4)
#define S3C64XX_SPI_ST_TX_OVERRUN_ERR (1<<3)
@@ -106,9 +108,11 @@
#define FIFO_LVL_MASK(i) ((i)->port_conf->fifo_lvl_mask[i->port_id])
#define S3C64XX_SPI_ST_TX_DONE(v, i) (((v) & \
(1 << (i)->port_conf->tx_st_done)) ? 1 : 0)
-#define TX_FIFO_LVL(v, i) (((v) >> 6) & FIFO_LVL_MASK(i))
-#define RX_FIFO_LVL(v, i) (((v) >> (i)->port_conf->rx_lvl_offset) & \
- FIFO_LVL_MASK(i))
+#define TX_FIFO_LVL(v, sdd) (((v) & (sdd)->tx_fifomask) >> \
+ __ffs((sdd)->tx_fifomask))
+#define RX_FIFO_LVL(v, sdd) (((v) & (sdd)->rx_fifomask) >> \
+ __ffs((sdd)->rx_fifomask))
+#define FIFO_DEPTH(i) ((FIFO_LVL_MASK(i) >> 1) + 1)
#define S3C64XX_SPI_MAX_TRAILCNT 0x3ff
#define S3C64XX_SPI_TRAILCNT_OFF 19
@@ -133,6 +137,10 @@ struct s3c64xx_spi_dma_data {
* struct s3c64xx_spi_port_config - SPI Controller hardware info
* @fifo_lvl_mask: Bit-mask for {TX|RX}_FIFO_LVL bits in SPI_STATUS register.
* @rx_lvl_offset: Bit offset of RX_FIFO_LVL bits in SPI_STATUS regiter.
+ * @rx_fifomask: SPI_STATUS.RX_FIFO_LVL mask. Shifted mask defining the field's
+ * length and position.
+ * @tx_fifomask: SPI_STATUS.TX_FIFO_LVL mask. Shifted mask defining the field's
+ * length and position.
* @tx_st_done: Bit offset of TX_DONE bit in SPI_STATUS regiter.
* @clk_div: Internal clock divider
* @quirks: Bitmask of known quirks
@@ -150,6 +158,8 @@ struct s3c64xx_spi_dma_data {
struct s3c64xx_spi_port_config {
int fifo_lvl_mask[MAX_SPI_PORTS];
int rx_lvl_offset;
+ u32 rx_fifomask;
+ u32 tx_fifomask;
int tx_st_done;
int quirks;
int clk_div;
@@ -179,6 +189,11 @@ struct s3c64xx_spi_port_config {
* @tx_dma: Local transmit DMA data (e.g. chan and direction)
* @port_conf: Local SPI port configuartion data
* @port_id: Port identification number
+ * @fifo_depth: depth of the FIFO.
+ * @rx_fifomask: SPI_STATUS.RX_FIFO_LVL mask. Shifted mask defining the field's
+ * length and position.
+ * @tx_fifomask: SPI_STATUS.TX_FIFO_LVL mask. Shifted mask defining the field's
+ * length and position.
*/
struct s3c64xx_spi_driver_data {
void __iomem *regs;
@@ -198,6 +213,9 @@ struct s3c64xx_spi_driver_data {
struct s3c64xx_spi_dma_data tx_dma;
const struct s3c64xx_spi_port_config *port_conf;
unsigned int port_id;
+ unsigned int fifo_depth;
+ u32 rx_fifomask;
+ u32 tx_fifomask;
};
static void s3c64xx_flush_fifo(struct s3c64xx_spi_driver_data *sdd)
@@ -405,12 +423,10 @@ static bool s3c64xx_spi_can_dma(struct spi_controller *host,
{
struct s3c64xx_spi_driver_data *sdd = spi_controller_get_devdata(host);
- if (sdd->rx_dma.ch && sdd->tx_dma.ch) {
- return xfer->len > (FIFO_LVL_MASK(sdd) >> 1) + 1;
- } else {
- return false;
- }
+ if (sdd->rx_dma.ch && sdd->tx_dma.ch)
+ return xfer->len >= sdd->fifo_depth;
+ return false;
}
static int s3c64xx_enable_datapath(struct s3c64xx_spi_driver_data *sdd,
@@ -495,9 +511,7 @@ static u32 s3c64xx_spi_wait_for_timeout(struct s3c64xx_spi_driver_data *sdd,
void __iomem *regs = sdd->regs;
unsigned long val = 1;
u32 status;
-
- /* max fifo depth available */
- u32 max_fifo = (FIFO_LVL_MASK(sdd) >> 1) + 1;
+ u32 max_fifo = sdd->fifo_depth;
if (timeout_ms)
val = msecs_to_loops(timeout_ms);
@@ -604,7 +618,7 @@ static int s3c64xx_wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
* For any size less than the fifo size the below code is
* executed atleast once.
*/
- loops = xfer->len / ((FIFO_LVL_MASK(sdd) >> 1) + 1);
+ loops = xfer->len / sdd->fifo_depth;
buf = xfer->rx_buf;
do {
/* wait for data to be received in the fifo */
@@ -741,7 +755,7 @@ static int s3c64xx_spi_transfer_one(struct spi_controller *host,
struct spi_transfer *xfer)
{
struct s3c64xx_spi_driver_data *sdd = spi_controller_get_devdata(host);
- const unsigned int fifo_len = (FIFO_LVL_MASK(sdd) >> 1) + 1;
+ const unsigned int fifo_len = sdd->fifo_depth;
const void *tx_buf = NULL;
void *rx_buf = NULL;
int target_len = 0, origin_len = 0;
@@ -769,10 +783,9 @@ static int s3c64xx_spi_transfer_one(struct spi_controller *host,
return status;
}
- if (!is_polling(sdd) && (xfer->len > fifo_len) &&
+ if (!is_polling(sdd) && xfer->len >= fifo_len &&
sdd->rx_dma.ch && sdd->tx_dma.ch) {
use_dma = 1;
-
} else if (xfer->len >= fifo_len) {
tx_buf = xfer->tx_buf;
rx_buf = xfer->rx_buf;
@@ -1146,6 +1159,23 @@ static inline const struct s3c64xx_spi_port_config *s3c64xx_spi_get_port_config(
return (const struct s3c64xx_spi_port_config *)platform_get_device_id(pdev)->driver_data;
}
+static void s3c64xx_spi_set_fifomask(struct s3c64xx_spi_driver_data *sdd)
+{
+ const struct s3c64xx_spi_port_config *port_conf = sdd->port_conf;
+
+ if (port_conf->rx_fifomask)
+ sdd->rx_fifomask = port_conf->rx_fifomask;
+ else
+ sdd->rx_fifomask = FIFO_LVL_MASK(sdd) <<
+ port_conf->rx_lvl_offset;
+
+ if (port_conf->tx_fifomask)
+ sdd->tx_fifomask = port_conf->tx_fifomask;
+ else
+ sdd->tx_fifomask = FIFO_LVL_MASK(sdd) <<
+ S3C64XX_SPI_ST_TX_FIFO_LVL_SHIFT;
+}
+
static int s3c64xx_spi_probe(struct platform_device *pdev)
{
struct resource *mem_res;
@@ -1191,6 +1221,10 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
sdd->port_id = pdev->id;
}
+ sdd->fifo_depth = FIFO_DEPTH(sdd);
+
+ s3c64xx_spi_set_fifomask(sdd);
+
sdd->cur_bpw = 8;
sdd->tx_dma.direction = DMA_MEM_TO_DEV;
@@ -1280,7 +1314,7 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
dev_dbg(&pdev->dev, "Samsung SoC SPI Driver loaded for Bus SPI-%d with %d Targets attached\n",
sdd->port_id, host->num_chipselect);
dev_dbg(&pdev->dev, "\tIOmem=[%pR]\tFIFO %dbytes\n",
- mem_res, (FIFO_LVL_MASK(sdd) >> 1) + 1);
+ mem_res, sdd->fifo_depth);
pm_runtime_mark_last_busy(&pdev->dev);
pm_runtime_put_autosuspend(&pdev->dev);
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 81e061f183ad..38581583ad28 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -606,7 +606,7 @@ static int allocate_actors_buffer(struct power_allocator_params *params,
/* There might be no cooling devices yet. */
if (!num_actors) {
- ret = -EINVAL;
+ ret = 0;
goto clean_state;
}
@@ -679,11 +679,6 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
return -ENOMEM;
get_governor_trips(tz, params);
- if (!params->trip_max) {
- dev_warn(&tz->device, "power_allocator: missing trip_max\n");
- kfree(params);
- return -EINVAL;
- }
ret = check_power_actors(tz, params);
if (ret < 0) {
@@ -712,9 +707,10 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
if (!tz->tzp->sustainable_power)
dev_warn(&tz->device, "power_allocator: sustainable_power will be estimated\n");
- estimate_pid_constants(tz, tz->tzp->sustainable_power,
- params->trip_switch_on,
- params->trip_max->temperature);
+ if (params->trip_max)
+ estimate_pid_constants(tz, tz->tzp->sustainable_power,
+ params->trip_switch_on,
+ params->trip_max->temperature);
reset_pid_controller(params);
diff --git a/fs/aio.c b/fs/aio.c
index 9cdaa2faa536..0f4f531c9780 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1202,8 +1202,8 @@ static void aio_complete(struct aio_kiocb *iocb)
spin_lock_irqsave(&ctx->wait.lock, flags);
list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry)
if (avail >= curr->min_nr) {
- list_del_init_careful(&curr->w.entry);
wake_up_process(curr->w.private);
+ list_del_init_careful(&curr->w.entry);
}
spin_unlock_irqrestore(&ctx->wait.lock, flags);
}
diff --git a/fs/bcachefs/mean_and_variance_test.c b/fs/bcachefs/mean_and_variance_test.c
index 019583c3ca0e..51093fa84820 100644
--- a/fs/bcachefs/mean_and_variance_test.c
+++ b/fs/bcachefs/mean_and_variance_test.c
@@ -130,20 +130,8 @@ static void mean_and_variance_test_1(struct kunit *test)
d, mean, stddev, weighted_mean, weighted_stddev);
}
-static void mean_and_variance_test_2(struct kunit *test)
-{
- s64 d[] = { 100, 10, 10, 10, 10, 10, 10 };
- s64 mean[] = { 10, 10, 10, 10, 10, 10, 10 };
- s64 stddev[] = { 9, 9, 9, 9, 9, 9, 9 };
- s64 weighted_mean[] = { 32, 27, 22, 19, 17, 15, 14 };
- s64 weighted_stddev[] = { 38, 35, 31, 27, 24, 21, 18 };
-
- do_mean_and_variance_test(test, 10, 6, ARRAY_SIZE(d), 2,
- d, mean, stddev, weighted_mean, weighted_stddev);
-}
-
/* Test behaviour where we switch from one steady state to another: */
-static void mean_and_variance_test_3(struct kunit *test)
+static void mean_and_variance_test_2(struct kunit *test)
{
s64 d[] = { 100, 100, 100, 100, 100 };
s64 mean[] = { 22, 32, 40, 46, 50 };
@@ -155,18 +143,6 @@ static void mean_and_variance_test_3(struct kunit *test)
d, mean, stddev, weighted_mean, weighted_stddev);
}
-static void mean_and_variance_test_4(struct kunit *test)
-{
- s64 d[] = { 100, 100, 100, 100, 100 };
- s64 mean[] = { 10, 11, 12, 13, 14 };
- s64 stddev[] = { 9, 13, 15, 17, 19 };
- s64 weighted_mean[] = { 32, 49, 61, 71, 78 };
- s64 weighted_stddev[] = { 38, 44, 44, 41, 38 };
-
- do_mean_and_variance_test(test, 10, 6, ARRAY_SIZE(d), 2,
- d, mean, stddev, weighted_mean, weighted_stddev);
-}
-
static void mean_and_variance_fast_divpow2(struct kunit *test)
{
s64 i;
@@ -224,8 +200,6 @@ static struct kunit_case mean_and_variance_test_cases[] = {
KUNIT_CASE(mean_and_variance_weighted_advanced_test),
KUNIT_CASE(mean_and_variance_test_1),
KUNIT_CASE(mean_and_variance_test_2),
- KUNIT_CASE(mean_and_variance_test_3),
- KUNIT_CASE(mean_and_variance_test_4),
{}
};
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7d6c657e0409..692ede488254 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2888,12 +2888,9 @@ static void
nfsd4_cb_recall_any_release(struct nfsd4_callback *cb)
{
struct nfs4_client *clp = cb->cb_clp;
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- spin_lock(&nn->client_lock);
clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
- put_client_renew_locked(clp);
- spin_unlock(&nn->client_lock);
+ drop_client(clp);
}
static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
@@ -6274,7 +6271,7 @@ deleg_reaper(struct nfsd_net *nn)
list_add(&clp->cl_ra_cblist, &cblist);
/* release in nfsd4_cb_recall_any_release */
- atomic_inc(&clp->cl_rpc_users);
+ kref_get(&clp->cl_nfsdfs.cl_ref);
set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
clp->cl_ra_time = ktime_get_boottime_seconds();
}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index b7c7a9273ea0..4ed1e83defa2 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1833,7 +1833,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
trap = lock_rename(tdentry, fdentry);
if (IS_ERR(trap)) {
err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev;
- goto out;
+ goto out_want_write;
}
err = fh_fill_pre_attrs(ffhp);
if (err != nfs_ok)
@@ -1903,6 +1903,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
}
out_unlock:
unlock_rename(tdentry, fdentry);
+out_want_write:
fh_drop_write(ffhp);
/*
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index bd08616ed8ba..7b4db9c56e6a 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -5,7 +5,7 @@
obj-y += proc.o
-CFLAGS_task_mmu.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_task_mmu.o += -Wno-override-init
proc-y := nommu.o task_nommu.o
proc-$(CONFIG_MMU) := task_mmu.o
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index a0017724d523..13a9d7acf8f8 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -417,6 +417,7 @@ smb2_close_cached_fid(struct kref *ref)
{
struct cached_fid *cfid = container_of(ref, struct cached_fid,
refcount);
+ int rc;
spin_lock(&cfid->cfids->cfid_list_lock);
if (cfid->on_list) {
@@ -430,9 +431,10 @@ smb2_close_cached_fid(struct kref *ref)
cfid->dentry = NULL;
if (cfid->is_open) {
- SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid,
+ rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid,
cfid->fid.volatile_fid);
- atomic_dec(&cfid->tcon->num_remote_opens);
+ if (rc != -EBUSY && rc != -EAGAIN)
+ atomic_dec(&cfid->tcon->num_remote_opens);
}
free_cached_dir(cfid);
diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index 23d2622b969f..aa95fa95ca11 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -250,6 +250,8 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v)
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
spin_lock(&tcon->open_file_lock);
list_for_each_entry(cfile, &tcon->openFileList, tlist) {
@@ -656,6 +658,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
}
#endif /* CONFIG_CIFS_STATS2 */
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
atomic_set(&tcon->num_smbs_sent, 0);
spin_lock(&tcon->stat_lock);
@@ -735,6 +739,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
}
#endif /* STATS2 */
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
i++;
seq_printf(m, "\n%d) %s", i, tcon->tree_name);
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 0c269396ae15..501bfd3afdc6 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -160,6 +160,7 @@ struct workqueue_struct *decrypt_wq;
struct workqueue_struct *fileinfo_put_wq;
struct workqueue_struct *cifsoplockd_wq;
struct workqueue_struct *deferredclose_wq;
+struct workqueue_struct *serverclose_wq;
__u32 cifs_lock_secret;
/*
@@ -1893,6 +1894,13 @@ init_cifs(void)
goto out_destroy_cifsoplockd_wq;
}
+ serverclose_wq = alloc_workqueue("serverclose",
+ WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+ if (!serverclose_wq) {
+ rc = -ENOMEM;
+ goto out_destroy_serverclose_wq;
+ }
+
rc = cifs_init_inodecache();
if (rc)
goto out_destroy_deferredclose_wq;
@@ -1967,6 +1975,8 @@ init_cifs(void)
destroy_workqueue(decrypt_wq);
out_destroy_cifsiod_wq:
destroy_workqueue(cifsiod_wq);
+out_destroy_serverclose_wq:
+ destroy_workqueue(serverclose_wq);
out_clean_proc:
cifs_proc_clean();
return rc;
@@ -1996,6 +2006,7 @@ exit_cifs(void)
destroy_workqueue(cifsoplockd_wq);
destroy_workqueue(decrypt_wq);
destroy_workqueue(fileinfo_put_wq);
+ destroy_workqueue(serverclose_wq);
destroy_workqueue(cifsiod_wq);
cifs_proc_clean();
}
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 06e81afe31c1..844afda090d0 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -432,10 +432,10 @@ struct smb_version_operations {
/* set fid protocol-specific info */
void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32);
/* close a file */
- void (*close)(const unsigned int, struct cifs_tcon *,
+ int (*close)(const unsigned int, struct cifs_tcon *,
struct cifs_fid *);
/* close a file, returning file attributes and timestamps */
- void (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon,
+ int (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon,
struct cifsFileInfo *pfile_info);
/* send a flush request to the server */
int (*flush)(const unsigned int, struct cifs_tcon *, struct cifs_fid *);
@@ -1267,7 +1267,6 @@ struct cifs_tcon {
struct cached_fids *cfids;
/* BB add field for back pointer to sb struct(s)? */
#ifdef CONFIG_CIFS_DFS_UPCALL
- struct list_head dfs_ses_list;
struct delayed_work dfs_cache_work;
#endif
struct delayed_work query_interfaces; /* query interfaces workqueue job */
@@ -1424,6 +1423,7 @@ struct cifsFileInfo {
bool invalidHandle:1; /* file closed via session abend */
bool swapfile:1;
bool oplock_break_cancelled:1;
+ bool offload:1; /* offload final part of _put to a wq */
unsigned int oplock_epoch; /* epoch from the lease break */
__u32 oplock_level; /* oplock/lease level from the lease break */
int count;
@@ -1432,6 +1432,7 @@ struct cifsFileInfo {
struct cifs_search_info srch_inf;
struct work_struct oplock_break; /* work for oplock breaks */
struct work_struct put; /* work for the final part of _put */
+ struct work_struct serverclose; /* work for serverclose */
struct delayed_work deferred;
bool deferred_close_scheduled; /* Flag to indicate close is scheduled */
char *symlink_target;
@@ -1788,7 +1789,6 @@ struct cifs_mount_ctx {
struct TCP_Server_Info *server;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
- struct list_head dfs_ses_list;
};
static inline void __free_dfs_info_param(struct dfs_info3_param *param)
@@ -2089,6 +2089,7 @@ extern struct workqueue_struct *decrypt_wq;
extern struct workqueue_struct *fileinfo_put_wq;
extern struct workqueue_struct *cifsoplockd_wq;
extern struct workqueue_struct *deferredclose_wq;
+extern struct workqueue_struct *serverclose_wq;
extern __u32 cifs_lock_secret;
extern mempool_t *cifs_mid_poolp;
@@ -2294,4 +2295,14 @@ struct smb2_compound_vars {
struct smb2_file_link_info link_info;
};
+static inline bool cifs_ses_exiting(struct cifs_ses *ses)
+{
+ bool ret;
+
+ spin_lock(&ses->ses_lock);
+ ret = ses->ses_status == SES_EXITING;
+ spin_unlock(&ses->ses_lock);
+ return ret;
+}
+
#endif /* _CIFS_GLOB_H */
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 58cfbd450a55..996ca413dd8b 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -723,31 +723,31 @@ struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon);
void cifs_put_tcon_super(struct super_block *sb);
int cifs_wait_for_server_reconnect(struct TCP_Server_Info *server, bool retry);
-/* Put references of @ses and @ses->dfs_root_ses */
+/* Put references of @ses and its children */
static inline void cifs_put_smb_ses(struct cifs_ses *ses)
{
- struct cifs_ses *rses = ses->dfs_root_ses;
+ struct cifs_ses *next;
- __cifs_put_smb_ses(ses);
- if (rses)
- __cifs_put_smb_ses(rses);
+ do {
+ next = ses->dfs_root_ses;
+ __cifs_put_smb_ses(ses);
+ } while ((ses = next));
}
-/* Get an active reference of @ses and @ses->dfs_root_ses.
+/* Get an active reference of @ses and its children.
*
* NOTE: make sure to call this function when incrementing reference count of
* @ses to ensure that any DFS root session attached to it (@ses->dfs_root_ses)
* will also get its reference count incremented.
*
- * cifs_put_smb_ses() will put both references, so call it when you're done.
+ * cifs_put_smb_ses() will put all references, so call it when you're done.
*/
static inline void cifs_smb_ses_inc_refcount(struct cifs_ses *ses)
{
lockdep_assert_held(&cifs_tcp_ses_lock);
- ses->ses_count++;
- if (ses->dfs_root_ses)
- ses->dfs_root_ses->ses_count++;
+ for (; ses; ses = ses->dfs_root_ses)
+ ses->ses_count++;
}
static inline bool dfs_src_pathname_equal(const char *s1, const char *s2)
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 234160460615..7516c7d4558d 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -178,6 +178,8 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server,
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
spin_lock(&ses->chan_lock);
for (i = 0; i < ses->chan_count; i++) {
if (!ses->chans[i].server)
@@ -235,7 +237,13 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) {
- /* check if iface is still active */
+ spin_lock(&ses->ses_lock);
+ if (ses->ses_status == SES_EXITING) {
+ spin_unlock(&ses->ses_lock);
+ continue;
+ }
+ spin_unlock(&ses->ses_lock);
+
spin_lock(&ses->chan_lock);
if (cifs_ses_get_chan_index(ses, server) ==
CIFS_INVAL_CHAN_INDEX) {
@@ -1863,6 +1871,9 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx)
ctx->sectype != ses->sectype)
return 0;
+ if (ctx->dfs_root_ses != ses->dfs_root_ses)
+ return 0;
+
/*
* If an existing session is limited to less channels than
* requested, it should not be reused
@@ -1966,31 +1977,6 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx)
return rc;
}
-/**
- * cifs_free_ipc - helper to release the session IPC tcon
- * @ses: smb session to unmount the IPC from
- *
- * Needs to be called everytime a session is destroyed.
- *
- * On session close, the IPC is closed and the server must release all tcons of the session.
- * No need to send a tree disconnect here.
- *
- * Besides, it will make the server to not close durable and resilient files on session close, as
- * specified in MS-SMB2 3.3.5.6 Receiving an SMB2 LOGOFF Request.
- */
-static int
-cifs_free_ipc(struct cifs_ses *ses)
-{
- struct cifs_tcon *tcon = ses->tcon_ipc;
-
- if (tcon == NULL)
- return 0;
-
- tconInfoFree(tcon);
- ses->tcon_ipc = NULL;
- return 0;
-}
-
static struct cifs_ses *
cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
{
@@ -2022,48 +2008,52 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
void __cifs_put_smb_ses(struct cifs_ses *ses)
{
struct TCP_Server_Info *server = ses->server;
+ struct cifs_tcon *tcon;
unsigned int xid;
size_t i;
+ bool do_logoff;
int rc;
+ spin_lock(&cifs_tcp_ses_lock);
spin_lock(&ses->ses_lock);
- if (ses->ses_status == SES_EXITING) {
+ cifs_dbg(FYI, "%s: id=0x%llx ses_count=%d ses_status=%u ipc=%s\n",
+ __func__, ses->Suid, ses->ses_count, ses->ses_status,
+ ses->tcon_ipc ? ses->tcon_ipc->tree_name : "none");
+ if (ses->ses_status == SES_EXITING || --ses->ses_count > 0) {
spin_unlock(&ses->ses_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
return;
}
- spin_unlock(&ses->ses_lock);
+ /* ses_count can never go negative */
+ WARN_ON(ses->ses_count < 0);
- cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count);
- cifs_dbg(FYI,
- "%s: ses ipc: %s\n", __func__, ses->tcon_ipc ? ses->tcon_ipc->tree_name : "NONE");
+ spin_lock(&ses->chan_lock);
+ cifs_chan_clear_need_reconnect(ses, server);
+ spin_unlock(&ses->chan_lock);
- spin_lock(&cifs_tcp_ses_lock);
- if (--ses->ses_count > 0) {
- spin_unlock(&cifs_tcp_ses_lock);
- return;
- }
- spin_lock(&ses->ses_lock);
- if (ses->ses_status == SES_GOOD)
- ses->ses_status = SES_EXITING;
+ do_logoff = ses->ses_status == SES_GOOD && server->ops->logoff;
+ ses->ses_status = SES_EXITING;
+ tcon = ses->tcon_ipc;
+ ses->tcon_ipc = NULL;
spin_unlock(&ses->ses_lock);
spin_unlock(&cifs_tcp_ses_lock);
- /* ses_count can never go negative */
- WARN_ON(ses->ses_count < 0);
-
- spin_lock(&ses->ses_lock);
- if (ses->ses_status == SES_EXITING && server->ops->logoff) {
- spin_unlock(&ses->ses_lock);
- cifs_free_ipc(ses);
+ /*
+ * On session close, the IPC is closed and the server must release all
+ * tcons of the session. No need to send a tree disconnect here.
+ *
+ * Besides, it will make the server to not close durable and resilient
+ * files on session close, as specified in MS-SMB2 3.3.5.6 Receiving an
+ * SMB2 LOGOFF Request.
+ */
+ tconInfoFree(tcon);
+ if (do_logoff) {
xid = get_xid();
rc = server->ops->logoff(xid, ses);
if (rc)
cifs_server_dbg(VFS, "%s: Session Logoff failure rc=%d\n",
__func__, rc);
_free_xid(xid);
- } else {
- spin_unlock(&ses->ses_lock);
- cifs_free_ipc(ses);
}
spin_lock(&cifs_tcp_ses_lock);
@@ -2376,9 +2366,9 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
* need to lock before changing something in the session.
*/
spin_lock(&cifs_tcp_ses_lock);
+ if (ctx->dfs_root_ses)
+ cifs_smb_ses_inc_refcount(ctx->dfs_root_ses);
ses->dfs_root_ses = ctx->dfs_root_ses;
- if (ses->dfs_root_ses)
- ses->dfs_root_ses->ses_count++;
list_add(&ses->smb_ses_list, &server->smb_ses_list);
spin_unlock(&cifs_tcp_ses_lock);
@@ -3327,6 +3317,9 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx)
cifs_put_smb_ses(mnt_ctx->ses);
else if (mnt_ctx->server)
cifs_put_tcp_session(mnt_ctx->server, 0);
+ mnt_ctx->ses = NULL;
+ mnt_ctx->tcon = NULL;
+ mnt_ctx->server = NULL;
mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS;
free_xid(mnt_ctx->xid);
}
@@ -3605,8 +3598,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
bool isdfs;
int rc;
- INIT_LIST_HEAD(&mnt_ctx.dfs_ses_list);
-
rc = dfs_mount_share(&mnt_ctx, &isdfs);
if (rc)
goto error;
@@ -3637,7 +3628,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
return rc;
error:
- dfs_put_root_smb_sessions(&mnt_ctx.dfs_ses_list);
cifs_mount_put_conns(&mnt_ctx);
return rc;
}
@@ -3652,6 +3642,18 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
goto error;
rc = cifs_mount_get_tcon(&mnt_ctx);
+ if (!rc) {
+ /*
+ * Prevent superblock from being created with any missing
+ * connections.
+ */
+ if (WARN_ON(!mnt_ctx.server))
+ rc = -EHOSTDOWN;
+ else if (WARN_ON(!mnt_ctx.ses))
+ rc = -EACCES;
+ else if (WARN_ON(!mnt_ctx.tcon))
+ rc = -ENOENT;
+ }
if (rc)
goto error;
@@ -3989,13 +3991,14 @@ cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses)
}
static struct cifs_tcon *
-cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
+__cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
{
int rc;
struct cifs_tcon *master_tcon = cifs_sb_master_tcon(cifs_sb);
struct cifs_ses *ses;
struct cifs_tcon *tcon = NULL;
struct smb3_fs_context *ctx;
+ char *origin_fullpath = NULL;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (ctx == NULL)
@@ -4019,6 +4022,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
ctx->sign = master_tcon->ses->sign;
ctx->seal = master_tcon->seal;
ctx->witness = master_tcon->use_witness;
+ ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses;
rc = cifs_set_vol_auth(ctx, master_tcon->ses);
if (rc) {
@@ -4038,12 +4042,39 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
goto out;
}
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ spin_lock(&master_tcon->tc_lock);
+ if (master_tcon->origin_fullpath) {
+ spin_unlock(&master_tcon->tc_lock);
+ origin_fullpath = dfs_get_path(cifs_sb, cifs_sb->ctx->source);
+ if (IS_ERR(origin_fullpath)) {
+ tcon = ERR_CAST(origin_fullpath);
+ origin_fullpath = NULL;
+ cifs_put_smb_ses(ses);
+ goto out;
+ }
+ } else {
+ spin_unlock(&master_tcon->tc_lock);
+ }
+#endif
+
tcon = cifs_get_tcon(ses, ctx);
if (IS_ERR(tcon)) {
cifs_put_smb_ses(ses);
goto out;
}
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ if (origin_fullpath) {
+ spin_lock(&tcon->tc_lock);
+ tcon->origin_fullpath = origin_fullpath;
+ spin_unlock(&tcon->tc_lock);
+ origin_fullpath = NULL;
+ queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work,
+ dfs_cache_get_ttl() * HZ);
+ }
+#endif
+
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if (cap_unix(ses))
reset_cifs_unix_caps(0, tcon, NULL, ctx);
@@ -4052,11 +4083,23 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
out:
kfree(ctx->username);
kfree_sensitive(ctx->password);
+ kfree(origin_fullpath);
kfree(ctx);
return tcon;
}
+static struct cifs_tcon *
+cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
+{
+ struct cifs_tcon *ret;
+
+ cifs_mount_lock();
+ ret = __cifs_construct_tcon(cifs_sb, fsuid);
+ cifs_mount_unlock();
+ return ret;
+}
+
struct cifs_tcon *
cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb)
{
diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c
index 449c59830039..3ec965547e3d 100644
--- a/fs/smb/client/dfs.c
+++ b/fs/smb/client/dfs.c
@@ -66,33 +66,20 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path)
}
/*
- * Track individual DFS referral servers used by new DFS mount.
- *
- * On success, their lifetime will be shared by final tcon (dfs_ses_list).
- * Otherwise, they will be put by dfs_put_root_smb_sessions() in cifs_mount().
+ * Get an active reference of @ses so that next call to cifs_put_tcon() won't
+ * release it as any new DFS referrals must go through its IPC tcon.
*/
-static int add_root_smb_session(struct cifs_mount_ctx *mnt_ctx)
+static void add_root_smb_session(struct cifs_mount_ctx *mnt_ctx)
{
struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
- struct dfs_root_ses *root_ses;
struct cifs_ses *ses = mnt_ctx->ses;
if (ses) {
- root_ses = kmalloc(sizeof(*root_ses), GFP_KERNEL);
- if (!root_ses)
- return -ENOMEM;
-
- INIT_LIST_HEAD(&root_ses->list);
-
spin_lock(&cifs_tcp_ses_lock);
cifs_smb_ses_inc_refcount(ses);
spin_unlock(&cifs_tcp_ses_lock);
- root_ses->ses = ses;
- list_add_tail(&root_ses->list, &mnt_ctx->dfs_ses_list);
}
- /* Select new DFS referral server so that new referrals go through it */
ctx->dfs_root_ses = ses;
- return 0;
}
static inline int parse_dfs_target(struct smb3_fs_context *ctx,
@@ -185,11 +172,8 @@ static int __dfs_referral_walk(struct cifs_mount_ctx *mnt_ctx,
continue;
}
- if (is_refsrv) {
- rc = add_root_smb_session(mnt_ctx);
- if (rc)
- goto out;
- }
+ if (is_refsrv)
+ add_root_smb_session(mnt_ctx);
rc = ref_walk_advance(rw);
if (!rc) {
@@ -232,6 +216,7 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx)
struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
struct cifs_tcon *tcon;
char *origin_fullpath;
+ bool new_tcon = true;
int rc;
origin_fullpath = dfs_get_path(cifs_sb, ctx->source);
@@ -239,6 +224,18 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx)
return PTR_ERR(origin_fullpath);
rc = dfs_referral_walk(mnt_ctx);
+ if (!rc) {
+ /*
+ * Prevent superblock from being created with any missing
+ * connections.
+ */
+ if (WARN_ON(!mnt_ctx->server))
+ rc = -EHOSTDOWN;
+ else if (WARN_ON(!mnt_ctx->ses))
+ rc = -EACCES;
+ else if (WARN_ON(!mnt_ctx->tcon))
+ rc = -ENOENT;
+ }
if (rc)
goto out;
@@ -247,15 +244,14 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx)
if (!tcon->origin_fullpath) {
tcon->origin_fullpath = origin_fullpath;
origin_fullpath = NULL;
+ } else {
+ new_tcon = false;
}
spin_unlock(&tcon->tc_lock);
- if (list_empty(&tcon->dfs_ses_list)) {
- list_replace_init(&mnt_ctx->dfs_ses_list, &tcon->dfs_ses_list);
+ if (new_tcon) {
queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work,
dfs_cache_get_ttl() * HZ);
- } else {
- dfs_put_root_smb_sessions(&mnt_ctx->dfs_ses_list);
}
out:
@@ -298,7 +294,6 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs)
if (rc)
return rc;
- ctx->dfs_root_ses = mnt_ctx->ses;
/*
* If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally
* try to get an DFS referral (even cached) to determine whether it is an DFS mount.
@@ -324,7 +319,9 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs)
*isdfs = true;
add_root_smb_session(mnt_ctx);
- return __dfs_mount_share(mnt_ctx);
+ rc = __dfs_mount_share(mnt_ctx);
+ dfs_put_root_smb_sessions(mnt_ctx);
+ return rc;
}
/* Update dfs referral path of superblock */
diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h
index 875ab7ae57fc..e5c4dcf83750 100644
--- a/fs/smb/client/dfs.h
+++ b/fs/smb/client/dfs.h
@@ -7,7 +7,9 @@
#define _CIFS_DFS_H
#include "cifsglob.h"
+#include "cifsproto.h"
#include "fs_context.h"
+#include "dfs_cache.h"
#include "cifs_unicode.h"
#include <linux/namei.h>
@@ -114,11 +116,6 @@ static inline void ref_walk_set_tgt_hint(struct dfs_ref_walk *rw)
ref_walk_tit(rw));
}
-struct dfs_root_ses {
- struct list_head list;
- struct cifs_ses *ses;
-};
-
int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref,
struct smb3_fs_context *ctx);
int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs);
@@ -133,20 +130,32 @@ static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *p
{
struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+ struct cifs_ses *rses = ctx->dfs_root_ses ?: mnt_ctx->ses;
- return dfs_cache_find(mnt_ctx->xid, ctx->dfs_root_ses, cifs_sb->local_nls,
+ return dfs_cache_find(mnt_ctx->xid, rses, cifs_sb->local_nls,
cifs_remap(cifs_sb), path, ref, tl);
}
-static inline void dfs_put_root_smb_sessions(struct list_head *head)
+/*
+ * cifs_get_smb_ses() already guarantees an active reference of
+ * @ses->dfs_root_ses when a new session is created, so we need to put extra
+ * references of all DFS root sessions that were used across the mount process
+ * in dfs_mount_share().
+ */
+static inline void dfs_put_root_smb_sessions(struct cifs_mount_ctx *mnt_ctx)
{
- struct dfs_root_ses *root, *tmp;
+ const struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
+ struct cifs_ses *ses = ctx->dfs_root_ses;
+ struct cifs_ses *cur;
+
+ if (!ses)
+ return;
- list_for_each_entry_safe(root, tmp, head, list) {
- list_del_init(&root->list);
- cifs_put_smb_ses(root->ses);
- kfree(root);
+ for (cur = ses; cur; cur = cur->dfs_root_ses) {
+ if (cur->dfs_root_ses)
+ cifs_put_smb_ses(cur->dfs_root_ses);
}
+ cifs_put_smb_ses(ses);
}
#endif /* _CIFS_DFS_H */
diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c
index 508d831fabe3..11c8efecf7aa 100644
--- a/fs/smb/client/dfs_cache.c
+++ b/fs/smb/client/dfs_cache.c
@@ -1172,8 +1172,8 @@ static bool is_ses_good(struct cifs_ses *ses)
return ret;
}
-/* Refresh dfs referral of tcon and mark it for reconnect if needed */
-static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_refresh)
+/* Refresh dfs referral of @ses and mark it for reconnect if needed */
+static void __refresh_ses_referral(struct cifs_ses *ses, bool force_refresh)
{
struct TCP_Server_Info *server = ses->server;
DFS_CACHE_TGT_LIST(old_tl);
@@ -1181,10 +1181,21 @@ static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_ref
bool needs_refresh = false;
struct cache_entry *ce;
unsigned int xid;
+ char *path = NULL;
int rc = 0;
xid = get_xid();
+ mutex_lock(&server->refpath_lock);
+ if (server->leaf_fullpath) {
+ path = kstrdup(server->leaf_fullpath + 1, GFP_ATOMIC);
+ if (!path)
+ rc = -ENOMEM;
+ }
+ mutex_unlock(&server->refpath_lock);
+ if (!path)
+ goto out;
+
down_read(&htable_rw_lock);
ce = lookup_cache_entry(path);
needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce);
@@ -1218,19 +1229,17 @@ static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_ref
free_xid(xid);
dfs_cache_free_tgts(&old_tl);
dfs_cache_free_tgts(&new_tl);
- return rc;
+ kfree(path);
}
-static int refresh_tcon(struct cifs_tcon *tcon, bool force_refresh)
+static inline void refresh_ses_referral(struct cifs_ses *ses)
{
- struct TCP_Server_Info *server = tcon->ses->server;
- struct cifs_ses *ses = tcon->ses;
+ __refresh_ses_referral(ses, false);
+}
- mutex_lock(&server->refpath_lock);
- if (server->leaf_fullpath)
- __refresh_tcon(server->leaf_fullpath + 1, ses, force_refresh);
- mutex_unlock(&server->refpath_lock);
- return 0;
+static inline void force_refresh_ses_referral(struct cifs_ses *ses)
+{
+ __refresh_ses_referral(ses, true);
}
/**
@@ -1271,34 +1280,20 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb)
*/
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
- return refresh_tcon(tcon, true);
+ force_refresh_ses_referral(tcon->ses);
+ return 0;
}
/* Refresh all DFS referrals related to DFS tcon */
void dfs_cache_refresh(struct work_struct *work)
{
- struct TCP_Server_Info *server;
- struct dfs_root_ses *rses;
struct cifs_tcon *tcon;
struct cifs_ses *ses;
tcon = container_of(work, struct cifs_tcon, dfs_cache_work.work);
- ses = tcon->ses;
- server = ses->server;
- mutex_lock(&server->refpath_lock);
- if (server->leaf_fullpath)
- __refresh_tcon(server->leaf_fullpath + 1, ses, false);
- mutex_unlock(&server->refpath_lock);
-
- list_for_each_entry(rses, &tcon->dfs_ses_list, list) {
- ses = rses->ses;
- server = ses->server;
- mutex_lock(&server->refpath_lock);
- if (server->leaf_fullpath)
- __refresh_tcon(server->leaf_fullpath + 1, ses, false);
- mutex_unlock(&server->refpath_lock);
- }
+ for (ses = tcon->ses; ses; ses = ses->dfs_root_ses)
+ refresh_ses_referral(ses);
queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work,
atomic_read(&dfs_cache_ttl) * HZ);
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 89333d9bce36..37897b919dd5 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -189,6 +189,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
int disposition;
struct TCP_Server_Info *server = tcon->ses->server;
struct cifs_open_parms oparms;
+ int rdwr_for_fscache = 0;
*oplock = 0;
if (tcon->ses->server->oplocks)
@@ -200,6 +201,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
return PTR_ERR(full_path);
}
+ /* If we're caching, we need to be able to fill in around partial writes. */
+ if (cifs_fscache_enabled(inode) && (oflags & O_ACCMODE) == O_WRONLY)
+ rdwr_for_fscache = 1;
+
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
@@ -276,6 +281,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
desired_access |= GENERIC_READ; /* is this too little? */
if (OPEN_FMODE(oflags) & FMODE_WRITE)
desired_access |= GENERIC_WRITE;
+ if (rdwr_for_fscache == 1)
+ desired_access |= GENERIC_READ;
disposition = FILE_OVERWRITE_IF;
if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
@@ -304,6 +311,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
if (!tcon->unix_ext && (mode & S_IWUGO) == 0)
create_options |= CREATE_OPTION_READONLY;
+retry_open:
oparms = (struct cifs_open_parms) {
.tcon = tcon,
.cifs_sb = cifs_sb,
@@ -317,8 +325,15 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
rc = server->ops->open(xid, &oparms, oplock, buf);
if (rc) {
cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc);
+ if (rc == -EACCES && rdwr_for_fscache == 1) {
+ desired_access &= ~GENERIC_READ;
+ rdwr_for_fscache = 2;
+ goto retry_open;
+ }
goto out;
}
+ if (rdwr_for_fscache == 2)
+ cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE);
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
/*
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 9d42a3900907..af5c476db6e6 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -206,12 +206,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
*/
}
-static inline int cifs_convert_flags(unsigned int flags)
+static inline int cifs_convert_flags(unsigned int flags, int rdwr_for_fscache)
{
if ((flags & O_ACCMODE) == O_RDONLY)
return GENERIC_READ;
else if ((flags & O_ACCMODE) == O_WRONLY)
- return GENERIC_WRITE;
+ return rdwr_for_fscache == 1 ? (GENERIC_READ | GENERIC_WRITE) : GENERIC_WRITE;
else if ((flags & O_ACCMODE) == O_RDWR) {
/* GENERIC_ALL is too much permission to request
can cause unnecessary access denied on create */
@@ -348,11 +348,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_
int create_options = CREATE_NOT_DIR;
struct TCP_Server_Info *server = tcon->ses->server;
struct cifs_open_parms oparms;
+ int rdwr_for_fscache = 0;
if (!server->ops->open)
return -ENOSYS;
- desired_access = cifs_convert_flags(f_flags);
+ /* If we're caching, we need to be able to fill in around partial writes. */
+ if (cifs_fscache_enabled(inode) && (f_flags & O_ACCMODE) == O_WRONLY)
+ rdwr_for_fscache = 1;
+
+ desired_access = cifs_convert_flags(f_flags, rdwr_for_fscache);
/*********************************************************************
* open flag mapping table:
@@ -389,6 +394,7 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_
if (f_flags & O_DIRECT)
create_options |= CREATE_NO_BUFFER;
+retry_open:
oparms = (struct cifs_open_parms) {
.tcon = tcon,
.cifs_sb = cifs_sb,
@@ -400,8 +406,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_
};
rc = server->ops->open(xid, &oparms, oplock, buf);
- if (rc)
+ if (rc) {
+ if (rc == -EACCES && rdwr_for_fscache == 1) {
+ desired_access = cifs_convert_flags(f_flags, 0);
+ rdwr_for_fscache = 2;
+ goto retry_open;
+ }
return rc;
+ }
+ if (rdwr_for_fscache == 2)
+ cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE);
/* TODO: Add support for calling posix query info but with passing in fid */
if (tcon->unix_ext)
@@ -445,6 +459,7 @@ cifs_down_write(struct rw_semaphore *sem)
}
static void cifsFileInfo_put_work(struct work_struct *work);
+void serverclose_work(struct work_struct *work);
struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
struct tcon_link *tlink, __u32 oplock,
@@ -491,6 +506,7 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
cfile->tlink = cifs_get_tlink(tlink);
INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
INIT_WORK(&cfile->put, cifsFileInfo_put_work);
+ INIT_WORK(&cfile->serverclose, serverclose_work);
INIT_DELAYED_WORK(&cfile->deferred, smb2_deferred_work_close);
mutex_init(&cfile->fh_mutex);
spin_lock_init(&cfile->file_info_lock);
@@ -582,6 +598,40 @@ static void cifsFileInfo_put_work(struct work_struct *work)
cifsFileInfo_put_final(cifs_file);
}
+void serverclose_work(struct work_struct *work)
+{
+ struct cifsFileInfo *cifs_file = container_of(work,
+ struct cifsFileInfo, serverclose);
+
+ struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
+
+ struct TCP_Server_Info *server = tcon->ses->server;
+ int rc = 0;
+ int retries = 0;
+ int MAX_RETRIES = 4;
+
+ do {
+ if (server->ops->close_getattr)
+ rc = server->ops->close_getattr(0, tcon, cifs_file);
+ else if (server->ops->close)
+ rc = server->ops->close(0, tcon, &cifs_file->fid);
+
+ if (rc == -EBUSY || rc == -EAGAIN) {
+ retries++;
+ msleep(250);
+ }
+ } while ((rc == -EBUSY || rc == -EAGAIN) && (retries < MAX_RETRIES)
+ );
+
+ if (retries == MAX_RETRIES)
+ pr_warn("Serverclose failed %d times, giving up\n", MAX_RETRIES);
+
+ if (cifs_file->offload)
+ queue_work(fileinfo_put_wq, &cifs_file->put);
+ else
+ cifsFileInfo_put_final(cifs_file);
+}
+
/**
* cifsFileInfo_put - release a reference of file priv data
*
@@ -622,10 +672,13 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
struct cifs_fid fid = {};
struct cifs_pending_open open;
bool oplock_break_cancelled;
+ bool serverclose_offloaded = false;
spin_lock(&tcon->open_file_lock);
spin_lock(&cifsi->open_file_lock);
spin_lock(&cifs_file->file_info_lock);
+
+ cifs_file->offload = offload;
if (--cifs_file->count > 0) {
spin_unlock(&cifs_file->file_info_lock);
spin_unlock(&cifsi->open_file_lock);
@@ -667,13 +720,20 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
if (!tcon->need_reconnect && !cifs_file->invalidHandle) {
struct TCP_Server_Info *server = tcon->ses->server;
unsigned int xid;
+ int rc = 0;
xid = get_xid();
if (server->ops->close_getattr)
- server->ops->close_getattr(xid, tcon, cifs_file);
+ rc = server->ops->close_getattr(xid, tcon, cifs_file);
else if (server->ops->close)
- server->ops->close(xid, tcon, &cifs_file->fid);
+ rc = server->ops->close(xid, tcon, &cifs_file->fid);
_free_xid(xid);
+
+ if (rc == -EBUSY || rc == -EAGAIN) {
+ // Server close failed, hence offloading it as an async op
+ queue_work(serverclose_wq, &cifs_file->serverclose);
+ serverclose_offloaded = true;
+ }
}
if (oplock_break_cancelled)
@@ -681,10 +741,15 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
cifs_del_pending_open(&open);
- if (offload)
- queue_work(fileinfo_put_wq, &cifs_file->put);
- else
- cifsFileInfo_put_final(cifs_file);
+ // if serverclose has been offloaded to wq (on failure), it will
+ // handle offloading put as well. If serverclose not offloaded,
+ // we need to handle offloading put here.
+ if (!serverclose_offloaded) {
+ if (offload)
+ queue_work(fileinfo_put_wq, &cifs_file->put);
+ else
+ cifsFileInfo_put_final(cifs_file);
+ }
}
int cifs_open(struct inode *inode, struct file *file)
@@ -834,11 +899,11 @@ int cifs_open(struct inode *inode, struct file *file)
use_cache:
fscache_use_cookie(cifs_inode_cookie(file_inode(file)),
file->f_mode & FMODE_WRITE);
- if (file->f_flags & O_DIRECT &&
- (!((file->f_flags & O_ACCMODE) != O_RDONLY) ||
- file->f_flags & O_APPEND))
- cifs_invalidate_cache(file_inode(file),
- FSCACHE_INVAL_DIO_WRITE);
+ if (!(file->f_flags & O_DIRECT))
+ goto out;
+ if ((file->f_flags & (O_ACCMODE | O_APPEND)) == O_RDONLY)
+ goto out;
+ cifs_invalidate_cache(file_inode(file), FSCACHE_INVAL_DIO_WRITE);
out:
free_dentry_path(page);
@@ -903,6 +968,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
int disposition = FILE_OPEN;
int create_options = CREATE_NOT_DIR;
struct cifs_open_parms oparms;
+ int rdwr_for_fscache = 0;
xid = get_xid();
mutex_lock(&cfile->fh_mutex);
@@ -966,7 +1032,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
- desired_access = cifs_convert_flags(cfile->f_flags);
+ /* If we're caching, we need to be able to fill in around partial writes. */
+ if (cifs_fscache_enabled(inode) && (cfile->f_flags & O_ACCMODE) == O_WRONLY)
+ rdwr_for_fscache = 1;
+
+ desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache);
/* O_SYNC also has bit for O_DSYNC so following check picks up either */
if (cfile->f_flags & O_SYNC)
@@ -978,6 +1048,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
if (server->ops->get_lease_key)
server->ops->get_lease_key(inode, &cfile->fid);
+retry_open:
oparms = (struct cifs_open_parms) {
.tcon = tcon,
.cifs_sb = cifs_sb,
@@ -1003,6 +1074,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
/* indicate that we need to relock the file */
oparms.reconnect = true;
}
+ if (rc == -EACCES && rdwr_for_fscache == 1) {
+ desired_access = cifs_convert_flags(cfile->f_flags, 0);
+ rdwr_for_fscache = 2;
+ goto retry_open;
+ }
if (rc) {
mutex_unlock(&cfile->fh_mutex);
@@ -1011,6 +1087,9 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
goto reopen_error_exit;
}
+ if (rdwr_for_fscache == 2)
+ cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE);
+
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
reopen_success:
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 415e87635d5a..d9fe17b2ba37 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -37,7 +37,7 @@
#include "rfc1002pdu.h"
#include "fs_context.h"
-static DEFINE_MUTEX(cifs_mount_mutex);
+DEFINE_MUTEX(cifs_mount_mutex);
static const match_table_t cifs_smb_version_tokens = {
{ Smb_1, SMB1_VERSION_STRING },
@@ -753,9 +753,9 @@ static int smb3_get_tree(struct fs_context *fc)
if (err)
return err;
- mutex_lock(&cifs_mount_mutex);
+ cifs_mount_lock();
ret = smb3_get_tree_common(fc);
- mutex_unlock(&cifs_mount_mutex);
+ cifs_mount_unlock();
return ret;
}
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index 182ce11cbe93..b3d51b345eae 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -295,4 +295,16 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
#define MAX_CACHED_FIDS 16
extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp);
+extern struct mutex cifs_mount_mutex;
+
+static inline void cifs_mount_lock(void)
+{
+ mutex_lock(&cifs_mount_mutex);
+}
+
+static inline void cifs_mount_unlock(void)
+{
+ mutex_unlock(&cifs_mount_mutex);
+}
+
#endif
diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c
index c4a3cb736881..340efce8f052 100644
--- a/fs/smb/client/fscache.c
+++ b/fs/smb/client/fscache.c
@@ -12,6 +12,16 @@
#include "cifs_fs_sb.h"
#include "cifsproto.h"
+/*
+ * Key for fscache inode. [!] Contents must match comparisons in cifs_find_inode().
+ */
+struct cifs_fscache_inode_key {
+
+ __le64 uniqueid; /* server inode number */
+ __le64 createtime; /* creation time on server */
+ u8 type; /* S_IFMT file type */
+} __packed;
+
static void cifs_fscache_fill_volume_coherency(
struct cifs_tcon *tcon,
struct cifs_fscache_volume_coherency_data *cd)
@@ -97,15 +107,19 @@ void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon)
void cifs_fscache_get_inode_cookie(struct inode *inode)
{
struct cifs_fscache_inode_coherency_data cd;
+ struct cifs_fscache_inode_key key;
struct cifsInodeInfo *cifsi = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+ key.uniqueid = cpu_to_le64(cifsi->uniqueid);
+ key.createtime = cpu_to_le64(cifsi->createtime);
+ key.type = (inode->i_mode & S_IFMT) >> 12;
cifs_fscache_fill_coherency(&cifsi->netfs.inode, &cd);
cifsi->netfs.cache =
fscache_acquire_cookie(tcon->fscache, 0,
- &cifsi->uniqueid, sizeof(cifsi->uniqueid),
+ &key, sizeof(key),
&cd, sizeof(cd),
i_size_read(&cifsi->netfs.inode));
if (cifsi->netfs.cache)
diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h
index a3d73720914f..1f2ea9f5cc9a 100644
--- a/fs/smb/client/fscache.h
+++ b/fs/smb/client/fscache.h
@@ -109,6 +109,11 @@ static inline void cifs_readahead_to_fscache(struct inode *inode,
__cifs_readahead_to_fscache(inode, pos, len);
}
+static inline bool cifs_fscache_enabled(struct inode *inode)
+{
+ return fscache_cookie_enabled(cifs_inode_cookie(inode));
+}
+
#else /* CONFIG_CIFS_FSCACHE */
static inline
void cifs_fscache_fill_coherency(struct inode *inode,
@@ -124,6 +129,7 @@ static inline void cifs_fscache_release_inode_cookie(struct inode *inode) {}
static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) {}
static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; }
static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {}
+static inline bool cifs_fscache_enabled(struct inode *inode) { return false; }
static inline int cifs_fscache_query_occupancy(struct inode *inode,
pgoff_t first, unsigned int nr_pages,
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 7f28edf4b20f..4c3dec384f92 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -1414,6 +1414,8 @@ cifs_find_inode(struct inode *inode, void *opaque)
{
struct cifs_fattr *fattr = opaque;
+ /* [!] The compared values must be the same in struct cifs_fscache_inode_key. */
+
/* don't match inode with different uniqueid */
if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid)
return 0;
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index e2f92c21fff5..682eabdd1d6c 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -247,7 +247,9 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) {
list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) {
- if (ses_it->Suid == out.session_id) {
+ spin_lock(&ses_it->ses_lock);
+ if (ses_it->ses_status != SES_EXITING &&
+ ses_it->Suid == out.session_id) {
ses = ses_it;
/*
* since we are using the session outside the crit
@@ -255,9 +257,11 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug
* so increment its refcount
*/
cifs_smb_ses_inc_refcount(ses);
+ spin_unlock(&ses_it->ses_lock);
found = true;
goto search_end;
}
+ spin_unlock(&ses_it->ses_lock);
}
}
search_end:
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index 0748d7b757b9..74627d647818 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -141,9 +141,6 @@ tcon_info_alloc(bool dir_leases_enabled)
atomic_set(&ret_buf->num_local_opens, 0);
atomic_set(&ret_buf->num_remote_opens, 0);
ret_buf->stats_from_time = ktime_get_real_seconds();
-#ifdef CONFIG_CIFS_DFS_UPCALL
- INIT_LIST_HEAD(&ret_buf->dfs_ses_list);
-#endif
return ret_buf;
}
@@ -159,9 +156,6 @@ tconInfoFree(struct cifs_tcon *tcon)
atomic_dec(&tconInfoAllocCount);
kfree(tcon->nativeFileSystem);
kfree_sensitive(tcon->password);
-#ifdef CONFIG_CIFS_DFS_UPCALL
- dfs_put_root_smb_sessions(&tcon->dfs_ses_list);
-#endif
kfree(tcon->origin_fullpath);
kfree(tcon);
}
@@ -490,6 +484,8 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
if (tcon->tid != buf->Tid)
continue;
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index a9eaba8083b0..212ec6f66ec6 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -753,11 +753,11 @@ cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode);
}
-static void
+static int
cifs_close_file(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_fid *fid)
{
- CIFSSMBClose(xid, tcon, fid->netfid);
+ return CIFSSMBClose(xid, tcon, fid->netfid);
}
static int
diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index 82b84a4941dd..cc72be5a93a9 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -622,6 +622,8 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server)
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
spin_lock(&tcon->open_file_lock);
cifs_stats_inc(
@@ -697,6 +699,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
spin_lock(&tcon->open_file_lock);
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 3b8896987197..ab77ecb2d4f0 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -1411,14 +1411,14 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
memcpy(cfile->fid.create_guid, fid->create_guid, 16);
}
-static void
+static int
smb2_close_file(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_fid *fid)
{
- SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid);
+ return SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid);
}
-static void
+static int
smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon,
struct cifsFileInfo *cfile)
{
@@ -1429,7 +1429,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon,
rc = __SMB2_close(xid, tcon, cfile->fid.persistent_fid,
cfile->fid.volatile_fid, &file_inf);
if (rc)
- return;
+ return rc;
inode = d_inode(cfile->dentry);
@@ -1458,6 +1458,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon,
/* End of file and Attributes should not have to be updated on close */
spin_unlock(&inode->i_lock);
+ return rc;
}
static int
@@ -2479,6 +2480,8 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server)
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) {
spin_lock(&tcon->tc_lock);
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 92c3710df615..b71e32d66eba 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3606,9 +3606,9 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
memcpy(&pbuf->network_open_info,
&rsp->network_open_info,
sizeof(pbuf->network_open_info));
+ atomic_dec(&tcon->num_remote_opens);
}
- atomic_dec(&tcon->num_remote_opens);
close_exit:
SMB2_close_free(&rqst);
free_rsp_buf(resp_buftype, rsp);
diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h
index 0ebf91ffa236..4464a62228cf 100644
--- a/fs/smb/server/ksmbd_netlink.h
+++ b/fs/smb/server/ksmbd_netlink.h
@@ -166,7 +166,8 @@ struct ksmbd_share_config_response {
__u16 force_uid;
__u16 force_gid;
__s8 share_name[KSMBD_REQ_MAX_SHARE_NAME];
- __u32 reserved[112]; /* Reserved room */
+ __u32 reserved[111]; /* Reserved room */
+ __u32 payload_sz;
__u32 veto_list_sz;
__s8 ____payload[];
};
diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c
index 328a412259dc..a2f0a2edceb8 100644
--- a/fs/smb/server/mgmt/share_config.c
+++ b/fs/smb/server/mgmt/share_config.c
@@ -158,7 +158,12 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
share->name = kstrdup(name, GFP_KERNEL);
if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) {
- share->path = kstrdup(ksmbd_share_config_path(resp),
+ int path_len = PATH_MAX;
+
+ if (resp->payload_sz)
+ path_len = resp->payload_sz - resp->veto_list_sz;
+
+ share->path = kstrndup(ksmbd_share_config_path(resp), path_len,
GFP_KERNEL);
if (share->path)
share->path_sz = strlen(share->path);
diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c
index 27a9dce3e03a..8600f32c981a 100644
--- a/fs/smb/server/smb2ops.c
+++ b/fs/smb/server/smb2ops.c
@@ -228,6 +228,11 @@ void init_smb3_0_server(struct ksmbd_conn *conn)
conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)
conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
+ if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
+ (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
+ conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION))
+ conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
+
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL)
conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL;
}
@@ -275,11 +280,6 @@ int init_smb3_11_server(struct ksmbd_conn *conn)
conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
- if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
- (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
- conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION))
- conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
-
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL)
conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL;
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 88db6e207e0e..cd2ed345c3d3 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -5632,8 +5632,9 @@ static int smb2_rename(struct ksmbd_work *work,
if (!file_info->ReplaceIfExists)
flags = RENAME_NOREPLACE;
- smb_break_all_levII_oplock(work, fp, 0);
rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags);
+ if (!rc)
+ smb_break_all_levII_oplock(work, fp, 0);
out:
kfree(new_name);
return rc;
diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index f29bb03f0dc4..8752ac82c557 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -65,6 +65,7 @@ struct ipc_msg_table_entry {
struct hlist_node ipc_table_hlist;
void *response;
+ unsigned int msg_sz;
};
static struct delayed_work ipc_timer_work;
@@ -275,6 +276,7 @@ static int handle_response(int type, void *payload, size_t sz)
}
memcpy(entry->response, payload, sz);
+ entry->msg_sz = sz;
wake_up_interruptible(&entry->wait);
ret = 0;
break;
@@ -453,6 +455,34 @@ static int ipc_msg_send(struct ksmbd_ipc_msg *msg)
return ret;
}
+static int ipc_validate_msg(struct ipc_msg_table_entry *entry)
+{
+ unsigned int msg_sz = entry->msg_sz;
+
+ if (entry->type == KSMBD_EVENT_RPC_REQUEST) {
+ struct ksmbd_rpc_command *resp = entry->response;
+
+ msg_sz = sizeof(struct ksmbd_rpc_command) + resp->payload_sz;
+ } else if (entry->type == KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST) {
+ struct ksmbd_spnego_authen_response *resp = entry->response;
+
+ msg_sz = sizeof(struct ksmbd_spnego_authen_response) +
+ resp->session_key_len + resp->spnego_blob_len;
+ } else if (entry->type == KSMBD_EVENT_SHARE_CONFIG_REQUEST) {
+ struct ksmbd_share_config_response *resp = entry->response;
+
+ if (resp->payload_sz) {
+ if (resp->payload_sz < resp->veto_list_sz)
+ return -EINVAL;
+
+ msg_sz = sizeof(struct ksmbd_share_config_response) +
+ resp->payload_sz;
+ }
+ }
+
+ return entry->msg_sz != msg_sz ? -EINVAL : 0;
+}
+
static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle)
{
struct ipc_msg_table_entry entry;
@@ -477,6 +507,13 @@ static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle
ret = wait_event_interruptible_timeout(entry.wait,
entry.response != NULL,
IPC_WAIT_TIMEOUT);
+ if (entry.response) {
+ ret = ipc_validate_msg(&entry);
+ if (ret) {
+ kvfree(entry.response);
+ entry.response = NULL;
+ }
+ }
out:
down_write(&ipc_msg_table_lock);
hash_del(&entry.ipc_table_hlist);
diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index 1fb8f4df60cb..9848af78215b 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -151,7 +151,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
if (!sbi->nls) {
vbg_err("vboxsf: Count not load '%s' nls\n", nls_name);
err = -EINVAL;
- goto fail_free;
+ goto fail_destroy_idr;
}
}
@@ -224,6 +224,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id);
if (sbi->nls)
unload_nls(sbi->nls);
+fail_destroy_idr:
idr_destroy(&sbi->ino_idr);
kfree(sbi);
return err;
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 4b9d8fb393a8..df32355e3e38 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -86,7 +86,7 @@ void kvm_vcpu_pmu_resync_el0(void);
*/
#define kvm_pmu_update_vcpu_events(vcpu) \
do { \
- if (!has_vhe() && kvm_vcpu_has_pmu(vcpu)) \
+ if (!has_vhe() && kvm_arm_support_pmu_v3()) \
vcpu->arch.pmu.events = *kvm_get_pmu_events(); \
} while (0)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e30100597d0a..7d719976b564 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1568,12 +1568,26 @@ struct bpf_link {
enum bpf_link_type type;
const struct bpf_link_ops *ops;
struct bpf_prog *prog;
- struct work_struct work;
+ /* rcu is used before freeing, work can be used to schedule that
+ * RCU-based freeing before that, so they never overlap
+ */
+ union {
+ struct rcu_head rcu;
+ struct work_struct work;
+ };
};
struct bpf_link_ops {
void (*release)(struct bpf_link *link);
+ /* deallocate link resources callback, called without RCU grace period
+ * waiting
+ */
void (*dealloc)(struct bpf_link *link);
+ /* deallocate link resources callback, called after RCU grace period;
+ * if underlying BPF program is sleepable we go through tasks trace
+ * RCU GP and then "classic" RCU GP
+ */
+ void (*dealloc_deferred)(struct bpf_link *link);
int (*detach)(struct bpf_link *link);
int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
struct bpf_prog *old_prog);
diff --git a/include/linux/device.h b/include/linux/device.h
index 97c4b046c09d..b9f5464f44ed 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1247,6 +1247,7 @@ void device_link_del(struct device_link *link);
void device_link_remove(void *consumer, struct device *supplier);
void device_links_supplier_sync_state_pause(void);
void device_links_supplier_sync_state_resume(void);
+void device_link_wait_removal(void);
/* Create alias, so I can be autoloaded. */
#define MODULE_ALIAS_CHARDEV(major,minor) \
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 854ad67a5f70..73de1f6f0ab1 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -281,7 +281,6 @@ struct io_ring_ctx {
struct io_submit_state submit_state;
- struct io_buffer_list *io_bl;
struct xarray io_bl_xa;
struct io_hash_table cancel_table_locked;
diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h
index 35f3a4a8ceb1..acf7e1a3f3de 100644
--- a/include/linux/secretmem.h
+++ b/include/linux/secretmem.h
@@ -13,10 +13,10 @@ static inline bool folio_is_secretmem(struct folio *folio)
/*
* Using folio_mapping() is quite slow because of the actual call
* instruction.
- * We know that secretmem pages are not compound and LRU so we can
+ * We know that secretmem pages are not compound, so we can
* save a couple of cycles here.
*/
- if (folio_test_large(folio) || !folio_test_lru(folio))
+ if (folio_test_large(folio))
return false;
mapping = (struct address_space *)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d9a1ccfb5708..227f4514476b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -748,8 +748,6 @@ typedef unsigned char *sk_buff_data_t;
* @list: queue head
* @ll_node: anchor in an llist (eg socket defer_list)
* @sk: Socket we are owned by
- * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in
- * fragmentation management
* @dev: Device we arrived on/are leaving by
* @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
* @cb: Control buffer. Free for use by every layer. Put private vars here
@@ -870,10 +868,7 @@ struct sk_buff {
struct llist_node ll_node;
};
- union {
- struct sock *sk;
- int ip_defrag_offset;
- };
+ struct sock *sk;
union {
ktime_t tstamp;
diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index adcbb8f23600..bf0136891a0f 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -30,6 +30,52 @@ typedef u32 depot_stack_handle_t;
*/
#define STACK_DEPOT_EXTRA_BITS 5
+#define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8)
+
+#define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */
+#define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER))
+#define DEPOT_STACK_ALIGN 4
+#define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN)
+#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \
+ STACK_DEPOT_EXTRA_BITS)
+
+#ifdef CONFIG_STACKDEPOT
+/* Compact structure that stores a reference to a stack. */
+union handle_parts {
+ depot_stack_handle_t handle;
+ struct {
+ u32 pool_index_plus_1 : DEPOT_POOL_INDEX_BITS;
+ u32 offset : DEPOT_OFFSET_BITS;
+ u32 extra : STACK_DEPOT_EXTRA_BITS;
+ };
+};
+
+struct stack_record {
+ struct list_head hash_list; /* Links in the hash table */
+ u32 hash; /* Hash in hash table */
+ u32 size; /* Number of stored frames */
+ union handle_parts handle; /* Constant after initialization */
+ refcount_t count;
+ union {
+ unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES]; /* Frames */
+ struct {
+ /*
+ * An important invariant of the implementation is to
+ * only place a stack record onto the freelist iff its
+ * refcount is zero. Because stack records with a zero
+ * refcount are never considered as valid, it is safe to
+ * union @entries and freelist management state below.
+ * Conversely, as soon as an entry is off the freelist
+ * and its refcount becomes non-zero, the below must not
+ * be accessed until being placed back on the freelist.
+ */
+ struct list_head free_list; /* Links in the freelist */
+ unsigned long rcu_state; /* RCU cookie */
+ };
+ };
+};
+#endif
+
typedef u32 depot_flags_t;
/*
diff --git a/include/linux/udp.h b/include/linux/udp.h
index d04188714dca..94e63b269540 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -140,6 +140,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk,
}
}
+DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key);
+#if IS_ENABLED(CONFIG_IPV6)
+DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+#endif
+
+static inline bool udp_encap_needed(void)
+{
+ if (static_branch_unlikely(&udp_encap_needed_key))
+ return true;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (static_branch_unlikely(&udpv6_encap_needed_key))
+ return true;
+#endif
+
+ return false;
+}
+
static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb)
{
if (!skb_is_gso(skb))
@@ -153,6 +171,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb)
!udp_test_bit(ACCEPT_FRAGLIST, sk))
return true;
+ /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still
+ * land in a tunnel as the socket check in udp_gro_receive cannot be
+ * foolproof.
+ */
+ if (udp_encap_needed() &&
+ READ_ONCE(udp_sk(sk)->encap_rcv) &&
+ !(skb_shinfo(skb)->gso_type &
+ (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM)))
+ return true;
+
return false;
}
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 0d231024570a..03e68a8e229f 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -176,6 +176,15 @@ enum {
*/
HCI_QUIRK_USE_BDADDR_PROPERTY,
+ /* When this quirk is set, the Bluetooth Device Address provided by
+ * the 'local-bd-address' fwnode property is incorrectly specified in
+ * big-endian order.
+ *
+ * This quirk can be set before hci_register_dev is called or
+ * during the hdev->setup vendor callback.
+ */
+ HCI_QUIRK_BDADDR_PROPERTY_BROKEN,
+
/* When this quirk is set, the duplicate filtering during
* scanning is based on Bluetooth devices addresses. To allow
* RSSI based updates, restart scanning if needed.
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 9ab4bf704e86..ccf171f7eb60 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -175,6 +175,7 @@ void inet_csk_init_xmit_timers(struct sock *sk,
void (*delack_handler)(struct timer_list *),
void (*keepalive_handler)(struct timer_list *));
void inet_csk_clear_xmit_timers(struct sock *sk);
+void inet_csk_clear_xmit_timers_sync(struct sock *sk);
static inline void inet_csk_schedule_ack(struct sock *sk)
{
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 76147feb0d10..4eeedf14711b 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -39,7 +39,6 @@ enum TRI_STATE {
#define COMP_ENTRY_SIZE 64
#define RX_BUFFERS_PER_QUEUE 512
-#define MANA_RX_DATA_ALIGN 64
#define MAX_SEND_BUFFERS_PER_QUEUE 256
diff --git a/include/net/sock.h b/include/net/sock.h
index 54ca8dcbfb43..4afb4376c97e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1779,6 +1779,13 @@ static inline void sock_owned_by_me(const struct sock *sk)
#endif
}
+static inline void sock_not_owned_by_me(const struct sock *sk)
+{
+#ifdef CONFIG_LOCKDEP
+ WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks);
+#endif
+}
+
static inline bool sock_owned_by_user(const struct sock *sk)
{
sock_owned_by_me(sk);
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 3cb4dc9bd70e..3d54de168a6d 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -188,6 +188,8 @@ static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
{
if (!compl)
return;
+ if (!compl->tx_timestamp)
+ return;
*compl->tx_timestamp = ops->tmo_fill_timestamp(priv);
}
diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h
index a8bebac1e4b2..957295364a5e 100644
--- a/include/sound/hdaudio_ext.h
+++ b/include/sound/hdaudio_ext.h
@@ -56,6 +56,9 @@ struct hdac_ext_stream {
u32 pphcldpl;
u32 pphcldpu;
+ u32 pplcllpl;
+ u32 pplcllpu;
+
bool decoupled:1;
bool link_locked:1;
bool link_prepared;
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index adf944bb5a2f..572effd0af53 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -152,6 +152,7 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
static void io_queue_sqe(struct io_kiocb *req);
struct kmem_cache *req_cachep;
+static struct workqueue_struct *iou_wq __ro_after_init;
static int __read_mostly sysctl_io_uring_disabled;
static int __read_mostly sysctl_io_uring_group = -1;
@@ -353,7 +354,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
err:
kfree(ctx->cancel_table.hbs);
kfree(ctx->cancel_table_locked.hbs);
- kfree(ctx->io_bl);
xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
return NULL;
@@ -2906,7 +2906,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
io_wq_put_hash(ctx->hash_map);
kfree(ctx->cancel_table.hbs);
kfree(ctx->cancel_table_locked.hbs);
- kfree(ctx->io_bl);
xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
}
@@ -3141,7 +3140,7 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
* noise and overhead, there's no discernable change in runtime
* over using system_wq.
*/
- queue_work(system_unbound_wq, &ctx->exit_work);
+ queue_work(iou_wq, &ctx->exit_work);
}
static int io_uring_release(struct inode *inode, struct file *file)
@@ -3423,14 +3422,15 @@ static void *io_uring_validate_mmap_request(struct file *file,
ptr = ctx->sq_sqes;
break;
case IORING_OFF_PBUF_RING: {
+ struct io_buffer_list *bl;
unsigned int bgid;
bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT;
- rcu_read_lock();
- ptr = io_pbuf_get_address(ctx, bgid);
- rcu_read_unlock();
- if (!ptr)
- return ERR_PTR(-EINVAL);
+ bl = io_pbuf_get_bl(ctx, bgid);
+ if (IS_ERR(bl))
+ return bl;
+ ptr = bl->buf_ring;
+ io_put_bl(ctx, bl);
break;
}
default:
@@ -4166,6 +4166,8 @@ static int __init io_uring_init(void)
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT,
NULL);
+ iou_wq = alloc_workqueue("iou_exit", WQ_UNBOUND, 64);
+
#ifdef CONFIG_SYSCTL
register_sysctl_init("kernel", kernel_io_uring_disabled_table);
#endif
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 18df5a9d2f5e..b2c4f829376e 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -17,8 +17,6 @@
#define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf))
-#define BGID_ARRAY 64
-
/* BIDs are addressed by a 16-bit field in a CQE */
#define MAX_BIDS_PER_BGID (1 << 16)
@@ -40,13 +38,9 @@ struct io_buf_free {
int inuse;
};
-static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx,
- struct io_buffer_list *bl,
- unsigned int bgid)
+static inline struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx,
+ unsigned int bgid)
{
- if (bl && bgid < BGID_ARRAY)
- return &bl[bgid];
-
return xa_load(&ctx->io_bl_xa, bgid);
}
@@ -55,7 +49,7 @@ static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx,
{
lockdep_assert_held(&ctx->uring_lock);
- return __io_buffer_get_list(ctx, ctx->io_bl, bgid);
+ return __io_buffer_get_list(ctx, bgid);
}
static int io_buffer_add_list(struct io_ring_ctx *ctx,
@@ -67,11 +61,7 @@ static int io_buffer_add_list(struct io_ring_ctx *ctx,
* always under the ->uring_lock, but the RCU lookup from mmap does.
*/
bl->bgid = bgid;
- smp_store_release(&bl->is_ready, 1);
-
- if (bgid < BGID_ARRAY)
- return 0;
-
+ atomic_set(&bl->refs, 1);
return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));
}
@@ -217,24 +207,6 @@ void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
return ret;
}
-static __cold int io_init_bl_list(struct io_ring_ctx *ctx)
-{
- struct io_buffer_list *bl;
- int i;
-
- bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL);
- if (!bl)
- return -ENOMEM;
-
- for (i = 0; i < BGID_ARRAY; i++) {
- INIT_LIST_HEAD(&bl[i].buf_list);
- bl[i].bgid = i;
- }
-
- smp_store_release(&ctx->io_bl, bl);
- return 0;
-}
-
/*
* Mark the given mapped range as free for reuse
*/
@@ -303,24 +275,24 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx,
return i;
}
+void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl)
+{
+ if (atomic_dec_and_test(&bl->refs)) {
+ __io_remove_buffers(ctx, bl, -1U);
+ kfree_rcu(bl, rcu);
+ }
+}
+
void io_destroy_buffers(struct io_ring_ctx *ctx)
{
struct io_buffer_list *bl;
struct list_head *item, *tmp;
struct io_buffer *buf;
unsigned long index;
- int i;
-
- for (i = 0; i < BGID_ARRAY; i++) {
- if (!ctx->io_bl)
- break;
- __io_remove_buffers(ctx, &ctx->io_bl[i], -1U);
- }
xa_for_each(&ctx->io_bl_xa, index, bl) {
xa_erase(&ctx->io_bl_xa, bl->bgid);
- __io_remove_buffers(ctx, bl, -1U);
- kfree_rcu(bl, rcu);
+ io_put_bl(ctx, bl);
}
/*
@@ -498,12 +470,6 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
io_ring_submit_lock(ctx, issue_flags);
- if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) {
- ret = io_init_bl_list(ctx);
- if (ret)
- goto err;
- }
-
bl = io_buffer_get_list(ctx, p->bgid);
if (unlikely(!bl)) {
bl = kzalloc(sizeof(*bl), GFP_KERNEL_ACCOUNT);
@@ -516,14 +482,9 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
if (ret) {
/*
* Doesn't need rcu free as it was never visible, but
- * let's keep it consistent throughout. Also can't
- * be a lower indexed array group, as adding one
- * where lookup failed cannot happen.
+ * let's keep it consistent throughout.
*/
- if (p->bgid >= BGID_ARRAY)
- kfree_rcu(bl, rcu);
- else
- WARN_ON_ONCE(1);
+ kfree_rcu(bl, rcu);
goto err;
}
}
@@ -688,12 +649,6 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
if (reg.ring_entries >= 65536)
return -EINVAL;
- if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) {
- int ret = io_init_bl_list(ctx);
- if (ret)
- return ret;
- }
-
bl = io_buffer_get_list(ctx, reg.bgid);
if (bl) {
/* if mapped buffer ring OR classic exists, don't allow */
@@ -742,11 +697,8 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
if (!bl->is_mapped)
return -EINVAL;
- __io_remove_buffers(ctx, bl, -1U);
- if (bl->bgid >= BGID_ARRAY) {
- xa_erase(&ctx->io_bl_xa, bl->bgid);
- kfree_rcu(bl, rcu);
- }
+ xa_erase(&ctx->io_bl_xa, bl->bgid);
+ io_put_bl(ctx, bl);
return 0;
}
@@ -776,23 +728,35 @@ int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg)
return 0;
}
-void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid)
+struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx,
+ unsigned long bgid)
{
struct io_buffer_list *bl;
+ bool ret;
- bl = __io_buffer_get_list(ctx, smp_load_acquire(&ctx->io_bl), bgid);
-
- if (!bl || !bl->is_mmap)
- return NULL;
/*
- * Ensure the list is fully setup. Only strictly needed for RCU lookup
- * via mmap, and in that case only for the array indexed groups. For
- * the xarray lookups, it's either visible and ready, or not at all.
+ * We have to be a bit careful here - we're inside mmap and cannot grab
+ * the uring_lock. This means the buffer_list could be simultaneously
+ * going away, if someone is trying to be sneaky. Look it up under rcu
+ * so we know it's not going away, and attempt to grab a reference to
+ * it. If the ref is already zero, then fail the mapping. If successful,
+ * the caller will call io_put_bl() to drop the the reference at at the
+ * end. This may then safely free the buffer_list (and drop the pages)
+ * at that point, vm_insert_pages() would've already grabbed the
+ * necessary vma references.
*/
- if (!smp_load_acquire(&bl->is_ready))
- return NULL;
-
- return bl->buf_ring;
+ rcu_read_lock();
+ bl = xa_load(&ctx->io_bl_xa, bgid);
+ /* must be a mmap'able buffer ring and have pages */
+ ret = false;
+ if (bl && bl->is_mmap)
+ ret = atomic_inc_not_zero(&bl->refs);
+ rcu_read_unlock();
+
+ if (ret)
+ return bl;
+
+ return ERR_PTR(-EINVAL);
}
/*
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index 53dfaa71a397..038091a0047d 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -25,12 +25,12 @@ struct io_buffer_list {
__u16 head;
__u16 mask;
+ atomic_t refs;
+
/* ring mapped provided buffers */
__u8 is_mapped;
/* ring mapped provided buffers, but mmap'ed by application */
__u8 is_mmap;
- /* bl is visible from an RCU point of view for lookup */
- __u8 is_ready;
};
struct io_buffer {
@@ -61,7 +61,9 @@ unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
-void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid);
+void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl);
+struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx,
+ unsigned long bgid);
static inline bool io_kbuf_recycle_ring(struct io_kiocb *req)
{
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 2b84ce8a8a67..dd6fe3b328f4 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -937,6 +937,13 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
ret = __io_read(req, issue_flags);
+ /*
+ * If the file doesn't support proper NOWAIT, then disable multishot
+ * and stay in single shot mode.
+ */
+ if (!io_file_supports_nowait(req))
+ req->flags &= ~REQ_F_APOLL_MULTISHOT;
+
/*
* If we get -EAGAIN, recycle our buffer and just let normal poll
* handling arm it.
@@ -956,7 +963,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
/*
* Any successful return value will keep the multishot read armed.
*/
- if (ret > 0) {
+ if (ret > 0 && req->flags & REQ_F_APOLL_MULTISHOT) {
/*
* Put our buffer and post a CQE. If we fail to post a CQE, then
* jump to the termination path. This request is then done.
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index f526b7573e97..418a8188a8e8 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -4,7 +4,7 @@ ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y)
# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details
cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
endif
-CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
+CFLAGS_core.o += -Wno-override-init $(cflags-nogcse-yy)
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o
obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a1f18681721c..0f90b6b27430 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2895,17 +2895,46 @@ void bpf_link_inc(struct bpf_link *link)
atomic64_inc(&link->refcnt);
}
+static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu)
+{
+ struct bpf_link *link = container_of(rcu, struct bpf_link, rcu);
+
+ /* free bpf_link and its containing memory */
+ link->ops->dealloc_deferred(link);
+}
+
+static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
+{
+ if (rcu_trace_implies_rcu_gp())
+ bpf_link_defer_dealloc_rcu_gp(rcu);
+ else
+ call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp);
+}
+
/* bpf_link_free is guaranteed to be called from process context */
static void bpf_link_free(struct bpf_link *link)
{
+ bool sleepable = false;
+
bpf_link_free_id(link->id);
if (link->prog) {
+ sleepable = link->prog->aux->sleepable;
/* detach BPF program, clean up used resources */
link->ops->release(link);
bpf_prog_put(link->prog);
}
- /* free bpf_link and its containing memory */
- link->ops->dealloc(link);
+ if (link->ops->dealloc_deferred) {
+ /* schedule BPF link deallocation; if underlying BPF program
+ * is sleepable, we need to first wait for RCU tasks trace
+ * sync, then go through "classic" RCU grace period
+ */
+ if (sleepable)
+ call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
+ else
+ call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
+ }
+ if (link->ops->dealloc)
+ link->ops->dealloc(link);
}
static void bpf_link_put_deferred(struct work_struct *work)
@@ -3415,7 +3444,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_raw_tp_link_lops = {
.release = bpf_raw_tp_link_release,
- .dealloc = bpf_raw_tp_link_dealloc,
+ .dealloc_deferred = bpf_raw_tp_link_dealloc,
.show_fdinfo = bpf_raw_tp_link_show_fdinfo,
.fill_link_info = bpf_raw_tp_link_fill_link_info,
};
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ddea9567f755..19e575e6b7fe 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6618,6 +6618,11 @@ static int check_stack_access_within_bounds(
err = check_stack_slot_within_bounds(env, min_off, state, type);
if (!err && max_off > 0)
err = -EINVAL; /* out of stack access into non-negative offsets */
+ if (!err && access_size < 0)
+ /* access_size should not be negative (or overflow an int); others checks
+ * along the way should have prevented such an access.
+ */
+ err = -EFAULT; /* invalid negative access size; integer overflow? */
if (err) {
if (tnum_is_const(reg->var_off)) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7ac6c52b25eb..c8d1ebc43838 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2713,7 +2713,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
.release = bpf_kprobe_multi_link_release,
- .dealloc = bpf_kprobe_multi_link_dealloc,
+ .dealloc_deferred = bpf_kprobe_multi_link_dealloc,
.fill_link_info = bpf_kprobe_multi_link_fill_link_info,
};
@@ -3142,6 +3142,9 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link)
umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt);
+ if (umulti_link->task)
+ put_task_struct(umulti_link->task);
+ path_put(&umulti_link->path);
}
static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
@@ -3149,9 +3152,6 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
struct bpf_uprobe_multi_link *umulti_link;
umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
- if (umulti_link->task)
- put_task_struct(umulti_link->task);
- path_put(&umulti_link->path);
kvfree(umulti_link->uprobes);
kfree(umulti_link);
}
@@ -3227,7 +3227,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
.release = bpf_uprobe_multi_link_release,
- .dealloc = bpf_uprobe_multi_link_dealloc,
+ .dealloc_deferred = bpf_uprobe_multi_link_dealloc,
.fill_link_info = bpf_uprobe_multi_link_fill_link_info,
};
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index c1ec2b4b6dab..ee830f14afb7 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -36,55 +36,12 @@
#include <linux/memblock.h>
#include <linux/kasan-enabled.h>
-#define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8)
-
-#define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */
-#define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER))
-#define DEPOT_STACK_ALIGN 4
-#define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN)
-#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \
- STACK_DEPOT_EXTRA_BITS)
#define DEPOT_POOLS_CAP 8192
/* The pool_index is offset by 1 so the first record does not have a 0 handle. */
#define DEPOT_MAX_POOLS \
(((1LL << (DEPOT_POOL_INDEX_BITS)) - 1 < DEPOT_POOLS_CAP) ? \
(1LL << (DEPOT_POOL_INDEX_BITS)) - 1 : DEPOT_POOLS_CAP)
-/* Compact structure that stores a reference to a stack. */
-union handle_parts {
- depot_stack_handle_t handle;
- struct {
- u32 pool_index : DEPOT_POOL_INDEX_BITS; /* pool_index is offset by 1 */
- u32 offset : DEPOT_OFFSET_BITS;
- u32 extra : STACK_DEPOT_EXTRA_BITS;
- };
-};
-
-struct stack_record {
- struct list_head hash_list; /* Links in the hash table */
- u32 hash; /* Hash in hash table */
- u32 size; /* Number of stored frames */
- union handle_parts handle; /* Constant after initialization */
- refcount_t count;
- union {
- unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES]; /* Frames */
- struct {
- /*
- * An important invariant of the implementation is to
- * only place a stack record onto the freelist iff its
- * refcount is zero. Because stack records with a zero
- * refcount are never considered as valid, it is safe to
- * union @entries and freelist management state below.
- * Conversely, as soon as an entry is off the freelist
- * and its refcount becomes non-zero, the below must not
- * be accessed until being placed back on the freelist.
- */
- struct list_head free_list; /* Links in the freelist */
- unsigned long rcu_state; /* RCU cookie */
- };
- };
-};
-
static bool stack_depot_disabled;
static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT);
static bool __stack_depot_early_init_passed __initdata;
@@ -373,7 +330,7 @@ static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size)
stack = current_pool + pool_offset;
/* Pre-initialize handle once. */
- stack->handle.pool_index = pool_index + 1;
+ stack->handle.pool_index_plus_1 = pool_index + 1;
stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN;
stack->handle.extra = 0;
INIT_LIST_HEAD(&stack->hash_list);
@@ -484,7 +441,7 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
const int pools_num_cached = READ_ONCE(pools_num);
union handle_parts parts = { .handle = handle };
void *pool;
- u32 pool_index = parts.pool_index - 1;
+ u32 pool_index = parts.pool_index_plus_1 - 1;
size_t offset = parts.offset << DEPOT_STACK_ALIGN;
struct stack_record *stack;
diff --git a/mm/Makefile b/mm/Makefile
index e4b5b75aaec9..4abb40b911ec 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -29,8 +29,7 @@ KCOV_INSTRUMENT_mmzone.o := n
KCOV_INSTRUMENT_vmstat.o := n
KCOV_INSTRUMENT_failslab.o := n
-CFLAGS_init-mm.o += $(call cc-disable-warning, override-init)
-CFLAGS_init-mm.o += $(call cc-disable-warning, initializer-overrides)
+CFLAGS_init-mm.o += -Wno-override-init
mmu-y := nommu.o
mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \
diff --git a/mm/memory.c b/mm/memory.c
index 0bfc8b007c01..296e4f05e877 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5837,6 +5837,10 @@ int follow_phys(struct vm_area_struct *vma,
goto out;
pte = ptep_get(ptep);
+ /* Never return PFNs of anon folios in COW mappings. */
+ if (vm_normal_folio(vma, address, pte))
+ goto unlock;
+
if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
diff --git a/net/9p/client.c b/net/9p/client.c
index e265a0ca6bdd..f7e90b4769bb 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -1583,7 +1583,7 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to,
received = rsize;
}
- p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
+ p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", received);
if (non_zc) {
int n = copy_to_iter(dataptr, received, to);
@@ -1609,9 +1609,6 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
int total = 0;
*err = 0;
- p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %zd\n",
- fid->fid, offset, iov_iter_count(from));
-
while (iov_iter_count(from)) {
int count = iov_iter_count(from);
int rsize = fid->iounit;
@@ -1623,6 +1620,9 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
if (count < rsize)
rsize = count;
+ p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d (/%d)\n",
+ fid->fid, offset, rsize, count);
+
/* Don't bother zerocopy for small IO (< 1024) */
if (clnt->trans_mod->zc_request && rsize > 1024) {
req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, from, 0,
@@ -1650,7 +1650,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
written = rsize;
}
- p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
+ p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", written);
p9_req_put(clnt, req);
iov_iter_revert(from, count - written - iov_iter_count(from));
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index c5462486dbca..282ec581c072 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -105,7 +105,7 @@ void ax25_dev_device_down(struct net_device *dev)
spin_lock_bh(&ax25_dev_lock);
#ifdef CONFIG_AX25_DAMA_SLAVE
- ax25_ds_del_timer(ax25_dev);
+ timer_shutdown_sync(&ax25_dev->dama.slave_timer);
#endif
/*
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index 233453807b50..ce3ff2fa72e5 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -218,10 +218,12 @@ static int conn_info_min_age_set(void *data, u64 val)
{
struct hci_dev *hdev = data;
- if (val == 0 || val > hdev->conn_info_max_age)
+ hci_dev_lock(hdev);
+ if (val == 0 || val > hdev->conn_info_max_age) {
+ hci_dev_unlock(hdev);
return -EINVAL;
+ }
- hci_dev_lock(hdev);
hdev->conn_info_min_age = val;
hci_dev_unlock(hdev);
@@ -246,10 +248,12 @@ static int conn_info_max_age_set(void *data, u64 val)
{
struct hci_dev *hdev = data;
- if (val == 0 || val < hdev->conn_info_min_age)
+ hci_dev_lock(hdev);
+ if (val == 0 || val < hdev->conn_info_min_age) {
+ hci_dev_unlock(hdev);
return -EINVAL;
+ }
- hci_dev_lock(hdev);
hdev->conn_info_max_age = val;
hci_dev_unlock(hdev);
@@ -567,10 +571,12 @@ static int sniff_min_interval_set(void *data, u64 val)
{
struct hci_dev *hdev = data;
- if (val == 0 || val % 2 || val > hdev->sniff_max_interval)
+ hci_dev_lock(hdev);
+ if (val == 0 || val % 2 || val > hdev->sniff_max_interval) {
+ hci_dev_unlock(hdev);
return -EINVAL;
+ }
- hci_dev_lock(hdev);
hdev->sniff_min_interval = val;
hci_dev_unlock(hdev);
@@ -595,10 +601,12 @@ static int sniff_max_interval_set(void *data, u64 val)
{
struct hci_dev *hdev = data;
- if (val == 0 || val % 2 || val < hdev->sniff_min_interval)
+ hci_dev_lock(hdev);
+ if (val == 0 || val % 2 || val < hdev->sniff_min_interval) {
+ hci_dev_unlock(hdev);
return -EINVAL;
+ }
- hci_dev_lock(hdev);
hdev->sniff_max_interval = val;
hci_dev_unlock(hdev);
@@ -850,10 +858,12 @@ static int conn_min_interval_set(void *data, u64 val)
{
struct hci_dev *hdev = data;
- if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval)
+ hci_dev_lock(hdev);
+ if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) {
+ hci_dev_unlock(hdev);
return -EINVAL;
+ }
- hci_dev_lock(hdev);
hdev->le_conn_min_interval = val;
hci_dev_unlock(hdev);
@@ -878,10 +888,12 @@ static int conn_max_interval_set(void *data, u64 val)
{
struct hci_dev *hdev = data;
- if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval)
+ hci_dev_lock(hdev);
+ if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) {
+ hci_dev_unlock(hdev);
return -EINVAL;
+ }
- hci_dev_lock(hdev);
hdev->le_conn_max_interval = val;
hci_dev_unlock(hdev);
@@ -990,10 +1002,12 @@ static int adv_min_interval_set(void *data, u64 val)
{
struct hci_dev *hdev = data;
- if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval)
+ hci_dev_lock(hdev);
+ if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) {
+ hci_dev_unlock(hdev);
return -EINVAL;
+ }
- hci_dev_lock(hdev);
hdev->le_adv_min_interval = val;
hci_dev_unlock(hdev);
@@ -1018,10 +1032,12 @@ static int adv_max_interval_set(void *data, u64 val)
{
struct hci_dev *hdev = data;
- if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval)
+ hci_dev_lock(hdev);
+ if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) {
+ hci_dev_unlock(hdev);
return -EINVAL;
+ }
- hci_dev_lock(hdev);
hdev->le_adv_max_interval = val;
hci_dev_unlock(hdev);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 6275b14b5692..3b63513f57ba 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3219,6 +3219,31 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
if (test_bit(HCI_ENCRYPT, &hdev->flags))
set_bit(HCI_CONN_ENCRYPT, &conn->flags);
+ /* "Link key request" completed ahead of "connect request" completes */
+ if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) &&
+ ev->link_type == ACL_LINK) {
+ struct link_key *key;
+ struct hci_cp_read_enc_key_size cp;
+
+ key = hci_find_link_key(hdev, &ev->bdaddr);
+ if (key) {
+ set_bit(HCI_CONN_ENCRYPT, &conn->flags);
+
+ if (!(hdev->commands[20] & 0x10)) {
+ conn->enc_key_size = HCI_LINK_KEY_SIZE;
+ } else {
+ cp.handle = cpu_to_le16(conn->handle);
+ if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE,
+ sizeof(cp), &cp)) {
+ bt_dev_err(hdev, "sending read key size failed");
+ conn->enc_key_size = HCI_LINK_KEY_SIZE;
+ }
+ }
+
+ hci_encrypt_cfm(conn, ev->status);
+ }
+ }
+
/* Get remote features */
if (conn->type == ACL_LINK) {
struct hci_cp_read_remote_features cp;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 44ca5ea223e3..824ce03bb361 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3224,7 +3224,10 @@ static void hci_dev_get_bd_addr_from_property(struct hci_dev *hdev)
if (ret < 0 || !bacmp(&ba, BDADDR_ANY))
return;
- bacpy(&hdev->public_addr, &ba);
+ if (test_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks))
+ baswap(&hdev->public_addr, &ba);
+ else
+ bacpy(&hdev->public_addr, &ba);
}
struct hci_init_stage {
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 99d82676f780..cbd0e3586c3f 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1111,6 +1111,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
struct ebt_table_info *newinfo;
struct ebt_replace tmp;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1423,6 +1425,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len)
{
struct ebt_replace hlp;
+ if (len < sizeof(hlp))
+ return -EINVAL;
if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
return -EFAULT;
@@ -2352,6 +2356,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg,
{
struct compat_ebt_replace hlp;
+ if (len < sizeof(hlp))
+ return -EINVAL;
if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
return -EFAULT;
diff --git a/net/core/gro.c b/net/core/gro.c
index 0759277dc14e..cefddf65f7db 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -195,8 +195,9 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
}
merge:
- /* sk owenrship - if any - completely transferred to the aggregated packet */
+ /* sk ownership - if any - completely transferred to the aggregated packet */
skb->destructor = NULL;
+ skb->sk = NULL;
delta_truesize = skb->truesize;
if (offset > headlen) {
unsigned int eat = offset - headlen;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 27d733c0f65e..8598466a3805 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -411,6 +411,9 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
struct sock *sk;
int err = 0;
+ if (irqs_disabled())
+ return -EOPNOTSUPP; /* locks here are hardirq-unsafe */
+
spin_lock_bh(&stab->lock);
sk = *psk;
if (!sk_test || sk_test == sk)
@@ -933,6 +936,9 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key)
struct bpf_shtab_elem *elem;
int ret = -ENOENT;
+ if (irqs_disabled())
+ return -EOPNOTSUPP; /* locks here are hardirq-unsafe */
+
hash = sock_hash_bucket_hash(key, key_size);
bucket = sock_hash_select_bucket(htab, hash);
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index e5742f2a2d52..1b6457f357bd 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -220,7 +220,8 @@ void hsr_del_port(struct hsr_port *port)
netdev_update_features(master->dev);
dev_set_mtu(master->dev, hsr_get_max_mtu(hsr));
netdev_rx_handler_unregister(port->dev);
- dev_set_promiscuity(port->dev, -1);
+ if (!port->hsr->fwd_offloaded)
+ dev_set_promiscuity(port->dev, -1);
netdev_upper_dev_unlink(port->dev, master->dev);
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 459af1f89739..d1492c649aea 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -203,8 +203,15 @@ static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
kuid_t sk_uid, bool relax,
bool reuseport_cb_ok, bool reuseport_ok)
{
- if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
- return false;
+ if (ipv6_only_sock(sk2)) {
+ if (sk->sk_family == AF_INET)
+ return false;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+ return false;
+#endif
+ }
return inet_bind_conflict(sk, sk2, sk_uid, relax,
reuseport_cb_ok, reuseport_ok);
@@ -287,6 +294,7 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l
struct sock_reuseport *reuseport_cb;
struct inet_bind_hashbucket *head2;
struct inet_bind2_bucket *tb2;
+ bool conflict = false;
bool reuseport_cb_ok;
rcu_read_lock();
@@ -299,18 +307,20 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l
spin_lock(&head2->lock);
- inet_bind_bucket_for_each(tb2, &head2->chain)
- if (inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk))
- break;
+ inet_bind_bucket_for_each(tb2, &head2->chain) {
+ if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk))
+ continue;
- if (tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,
- reuseport_ok)) {
- spin_unlock(&head2->lock);
- return true;
+ if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok))
+ continue;
+
+ conflict = true;
+ break;
}
spin_unlock(&head2->lock);
- return false;
+
+ return conflict;
}
/*
@@ -771,6 +781,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
}
EXPORT_SYMBOL(inet_csk_clear_xmit_timers);
+void inet_csk_clear_xmit_timers_sync(struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ /* ongoing timer handlers need to acquire socket lock. */
+ sock_not_owned_by_me(sk);
+
+ icsk->icsk_pending = icsk->icsk_ack.pending = 0;
+
+ sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer);
+ sk_stop_timer_sync(sk, &icsk->icsk_delack_timer);
+ sk_stop_timer_sync(sk, &sk->sk_timer);
+}
+
void inet_csk_delete_keepalive_timer(struct sock *sk)
{
sk_stop_timer(sk, &sk->sk_timer);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 7072fc0783ef..c88c9034d630 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -24,6 +24,8 @@
#include <net/ip.h>
#include <net/ipv6.h>
+#include "../core/sock_destructor.h"
+
/* Use skb->cb to track consecutive/adjacent fragments coming at
* the end of the queue. Nodes in the rb-tree queue will
* contain "runs" of one or more adjacent fragments.
@@ -39,6 +41,7 @@ struct ipfrag_skb_cb {
};
struct sk_buff *next_frag;
int frag_run_len;
+ int ip_defrag_offset;
};
#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
@@ -396,12 +399,12 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
*/
if (!last)
fragrun_create(q, skb); /* First fragment. */
- else if (last->ip_defrag_offset + last->len < end) {
+ else if (FRAG_CB(last)->ip_defrag_offset + last->len < end) {
/* This is the common case: skb goes to the end. */
/* Detect and discard overlaps. */
- if (offset < last->ip_defrag_offset + last->len)
+ if (offset < FRAG_CB(last)->ip_defrag_offset + last->len)
return IPFRAG_OVERLAP;
- if (offset == last->ip_defrag_offset + last->len)
+ if (offset == FRAG_CB(last)->ip_defrag_offset + last->len)
fragrun_append_to_last(q, skb);
else
fragrun_create(q, skb);
@@ -418,13 +421,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
parent = *rbn;
curr = rb_to_skb(parent);
- curr_run_end = curr->ip_defrag_offset +
+ curr_run_end = FRAG_CB(curr)->ip_defrag_offset +
FRAG_CB(curr)->frag_run_len;
- if (end <= curr->ip_defrag_offset)
+ if (end <= FRAG_CB(curr)->ip_defrag_offset)
rbn = &parent->rb_left;
else if (offset >= curr_run_end)
rbn = &parent->rb_right;
- else if (offset >= curr->ip_defrag_offset &&
+ else if (offset >= FRAG_CB(curr)->ip_defrag_offset &&
end <= curr_run_end)
return IPFRAG_DUP;
else
@@ -438,7 +441,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
rb_insert_color(&skb->rbnode, &q->rb_fragments);
}
- skb->ip_defrag_offset = offset;
+ FRAG_CB(skb)->ip_defrag_offset = offset;
return IPFRAG_OK;
}
@@ -448,13 +451,28 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
struct sk_buff *parent)
{
struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments);
- struct sk_buff **nextp;
+ void (*destructor)(struct sk_buff *);
+ unsigned int orig_truesize = 0;
+ struct sk_buff **nextp = NULL;
+ struct sock *sk = skb->sk;
int delta;
+ if (sk && is_skb_wmem(skb)) {
+ /* TX: skb->sk might have been passed as argument to
+ * dst->output and must remain valid until tx completes.
+ *
+ * Move sk to reassembled skb and fix up wmem accounting.
+ */
+ orig_truesize = skb->truesize;
+ destructor = skb->destructor;
+ }
+
if (head != skb) {
fp = skb_clone(skb, GFP_ATOMIC);
- if (!fp)
- return NULL;
+ if (!fp) {
+ head = skb;
+ goto out_restore_sk;
+ }
FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
if (RB_EMPTY_NODE(&skb->rbnode))
FRAG_CB(parent)->next_frag = fp;
@@ -463,6 +481,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
&q->rb_fragments);
if (q->fragments_tail == skb)
q->fragments_tail = fp;
+
+ if (orig_truesize) {
+ /* prevent skb_morph from releasing sk */
+ skb->sk = NULL;
+ skb->destructor = NULL;
+ }
skb_morph(skb, head);
FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
rb_replace_node(&head->rbnode, &skb->rbnode,
@@ -470,13 +494,13 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
consume_skb(head);
head = skb;
}
- WARN_ON(head->ip_defrag_offset != 0);
+ WARN_ON(FRAG_CB(head)->ip_defrag_offset != 0);
delta = -head->truesize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
- return NULL;
+ goto out_restore_sk;
delta += head->truesize;
if (delta)
@@ -492,7 +516,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
- return NULL;
+ goto out_restore_sk;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
@@ -509,6 +533,21 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
nextp = &skb_shinfo(head)->frag_list;
}
+out_restore_sk:
+ if (orig_truesize) {
+ int ts_delta = head->truesize - orig_truesize;
+
+ /* if this reassembled skb is fragmented later,
+ * fraglist skbs will get skb->sk assigned from head->sk,
+ * and each frag skb will be released via sock_wfree.
+ *
+ * Update sk_wmem_alloc.
+ */
+ head->sk = sk;
+ head->destructor = destructor;
+ refcount_add(ts_delta, &sk->sk_wmem_alloc);
+ }
+
return nextp;
}
EXPORT_SYMBOL(inet_frag_reasm_prepare);
@@ -516,6 +555,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare);
void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
void *reasm_data, bool try_coalesce)
{
+ struct sock *sk = is_skb_wmem(head) ? head->sk : NULL;
+ const unsigned int head_truesize = head->truesize;
struct sk_buff **nextp = reasm_data;
struct rb_node *rbn;
struct sk_buff *fp;
@@ -579,6 +620,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
head->prev = NULL;
head->tstamp = q->stamp;
head->mono_delivery_time = q->mono_delivery_time;
+
+ if (sk)
+ refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc);
}
EXPORT_SYMBOL(inet_frag_reasm_finish);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a4941f53b523..fb947d1613fe 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -384,6 +384,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
}
skb_dst_drop(skb);
+ skb_orphan(skb);
return -EINPROGRESS;
insert_error:
@@ -487,7 +488,6 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
struct ipq *qp;
__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
- skb_orphan(skb);
/* Lookup (or create) queue header */
qp = ip_find(net, ip_hdr(skb), user, vif);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 6b9cf5a24c19..1954a56fec6b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -280,8 +280,13 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
tpi->flags | TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
} else {
+ if (unlikely(!pskb_may_pull(skb,
+ gre_hdr_len + sizeof(*ershdr))))
+ return PACKET_REJECT;
+
ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
ver = ershdr->ver;
+ iph = ip_hdr(skb);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
tpi->flags | TUNNEL_KEY,
iph->saddr, iph->daddr, tpi->key);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 2407066b0fec..b150c9929b12 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -956,6 +956,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct arpt_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1254,6 +1256,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct arpt_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 7da1df4997d0..487670759578 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1108,6 +1108,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct ipt_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1492,6 +1494,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct ipt_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a4f418592314..5887eac87bd2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2930,6 +2930,8 @@ void tcp_close(struct sock *sk, long timeout)
lock_sock(sk);
__tcp_close(sk, timeout);
release_sock(sk);
+ if (!sk->sk_net_refcnt)
+ inet_csk_clear_xmit_timers_sync(sk);
sock_put(sk);
}
EXPORT_SYMBOL(tcp_close);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 17231c0f8830..a505ba383863 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -584,6 +584,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk,
}
DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
+EXPORT_SYMBOL(udp_encap_needed_key);
+
+#if IS_ENABLED(CONFIG_IPV6)
+DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+EXPORT_SYMBOL(udpv6_encap_needed_key);
+#endif
+
void udp_encap_enable(void)
{
static_branch_inc(&udp_encap_needed_key);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 6c95d28d0c4a..c3d67423ae18 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -449,8 +449,9 @@ static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
NAPI_GRO_CB(p)->count++;
p->data_len += skb->len;
- /* sk owenrship - if any - completely transferred to the aggregated packet */
+ /* sk ownership - if any - completely transferred to the aggregated packet */
skb->destructor = NULL;
+ skb->sk = NULL;
p->truesize += skb->truesize;
p->len += skb->len;
@@ -551,11 +552,19 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
unsigned int off = skb_gro_offset(skb);
int flush = 1;
- /* we can do L4 aggregation only if the packet can't land in a tunnel
- * otherwise we could corrupt the inner stream
+ /* We can do L4 aggregation only if the packet can't land in a tunnel
+ * otherwise we could corrupt the inner stream. Detecting such packets
+ * cannot be foolproof and the aggregation might still happen in some
+ * cases. Such packets should be caught in udp_unexpected_gso later.
*/
NAPI_GRO_CB(skb)->is_flist = 0;
if (!sk || !udp_sk(sk)->gro_receive) {
+ /* If the packet was locally encapsulated in a UDP tunnel that
+ * wasn't detected above, do not GRO.
+ */
+ if (skb->encapsulation)
+ goto out;
+
if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1;
@@ -719,13 +728,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
- if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
- if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
- skb->csum_level++;
- } else {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- skb->csum_level = 0;
- }
+ __skb_incr_checksum_unnecessary(skb);
return 0;
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 4fc2cae0d116..54294f6a8ec5 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -645,19 +645,19 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
if (!w) {
/* New dump:
*
- * 1. hook callback destructor.
- */
- cb->args[3] = (long)cb->done;
- cb->done = fib6_dump_done;
-
- /*
- * 2. allocate and initialize walker.
+ * 1. allocate and initialize walker.
*/
w = kzalloc(sizeof(*w), GFP_ATOMIC);
if (!w)
return -ENOMEM;
w->func = fib6_dump_node;
cb->args[2] = (long)w;
+
+ /* 2. hook callback destructor.
+ */
+ cb->args[3] = (long)cb->done;
+ cb->done = fib6_dump_done;
+
}
arg.skb = skb;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 070d87abf7c0..26c3287beb29 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -528,6 +528,9 @@ static int ip6erspan_rcv(struct sk_buff *skb,
struct ip6_tnl *tunnel;
u8 ver;
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr))))
+ return PACKET_REJECT;
+
ipv6h = ipv6_hdr(skb);
ershdr = (struct erspan_base_hdr *)skb->data;
ver = ershdr->ver;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index fd9f049d6d41..636b360311c5 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1125,6 +1125,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct ip6t_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1501,6 +1503,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct ip6t_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index b2dd48911c8d..efbec7ee27d0 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -294,6 +294,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
}
skb_dst_drop(skb);
+ skb_orphan(skb);
return -EINPROGRESS;
insert_error:
@@ -469,7 +470,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
hdr = ipv6_hdr(skb);
fhdr = (struct frag_hdr *)skb_transport_header(skb);
- skb_orphan(skb);
fq = fq_find(net, fhdr->identification, user, hdr,
skb->dev ? skb->dev->ifindex : 0);
if (fq == NULL) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3f2249b4cd5f..26d9bd287b23 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -450,7 +450,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
goto try_again;
}
-DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
void udpv6_encap_enable(void)
{
static_branch_inc(&udpv6_encap_needed_key);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 6b95ba241ebe..626d7b362dc7 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -174,13 +174,7 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff)
skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
- if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
- if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
- skb->csum_level++;
- } else {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- skb->csum_level = 0;
- }
+ __skb_incr_checksum_unnecessary(skb);
return 0;
}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7833a49f6214..2b921af2718d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3916,8 +3916,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
mptcp_set_state(newsk, TCP_CLOSE);
}
} else {
- MPTCP_INC_STATS(sock_net(ssk),
- MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
tcpfallback:
newsk->sk_kern_sock = kern;
lock_sock(newsk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index c40f1428e602..ef3edba754a3 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -1500,6 +1500,10 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)
struct mptcp_subflow_context *subflow;
int space, cap;
+ /* bpf can land here with a wrong sk type */
+ if (sk->sk_protocol == IPPROTO_TCP)
+ return -EINVAL;
+
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
cap = sk->sk_rcvbuf >> 1;
else
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 71ba86246ff8..13f66d11b7a0 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -905,6 +905,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
return child;
fallback:
+ if (fallback)
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
mptcp_subflow_drop_ctx(child);
return child;
}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ec6266c1972c..21581bae700c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1198,6 +1198,26 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table)
#define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \
__NFT_TABLE_F_WAS_AWAKEN)
+static bool nft_table_pending_update(const struct nft_ctx *ctx)
+{
+ struct nftables_pernet *nft_net = nft_pernet(ctx->net);
+ struct nft_trans *trans;
+
+ if (ctx->table->flags & __NFT_TABLE_F_UPDATE)
+ return true;
+
+ list_for_each_entry(trans, &nft_net->commit_list, list) {
+ if (trans->ctx.table == ctx->table &&
+ ((trans->msg_type == NFT_MSG_NEWCHAIN &&
+ nft_trans_chain_update(trans)) ||
+ (trans->msg_type == NFT_MSG_DELCHAIN &&
+ nft_is_base_chain(trans->ctx.chain))))
+ return true;
+ }
+
+ return false;
+}
+
static int nf_tables_updtable(struct nft_ctx *ctx)
{
struct nft_trans *trans;
@@ -1221,7 +1241,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
return -EOPNOTSUPP;
/* No dormant off/on/off/on games in single transaction */
- if (ctx->table->flags & __NFT_TABLE_F_UPDATE)
+ if (nft_table_pending_update(ctx))
return -EINVAL;
trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE,
@@ -2418,6 +2438,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
struct nft_stats __percpu *stats = NULL;
struct nft_chain_hook hook = {};
+ if (table->flags & __NFT_TABLE_F_UPDATE)
+ return -EINVAL;
+
if (flags & NFT_CHAIN_BINDING)
return -EOPNOTSUPP;
@@ -2619,6 +2642,13 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
}
}
+ if (table->flags & __NFT_TABLE_F_UPDATE &&
+ !list_empty(&hook.list)) {
+ NL_SET_BAD_ATTR(extack, attr);
+ err = -EOPNOTSUPP;
+ goto err_hooks;
+ }
+
if (!(table->flags & NFT_TABLE_F_DORMANT) &&
nft_is_base_chain(chain) &&
!list_empty(&hook.list)) {
@@ -2848,6 +2878,9 @@ static int nft_delchain_hook(struct nft_ctx *ctx,
struct nft_trans *trans;
int err;
+ if (ctx->table->flags & __NFT_TABLE_F_UPDATE)
+ return -EOPNOTSUPP;
+
err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook,
ctx->family, chain->flags, extack);
if (err < 0)
@@ -2932,7 +2965,8 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info,
nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla);
if (nla[NFTA_CHAIN_HOOK]) {
- if (chain->flags & NFT_CHAIN_HW_OFFLOAD)
+ if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN ||
+ chain->flags & NFT_CHAIN_HW_OFFLOAD)
return -EOPNOTSUPP;
if (nft_is_base_chain(chain)) {
@@ -8259,11 +8293,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx,
return err;
}
+/* call under rcu_read_lock */
static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family)
{
const struct nf_flowtable_type *type;
- list_for_each_entry(type, &nf_tables_flowtables, list) {
+ list_for_each_entry_rcu(type, &nf_tables_flowtables, list) {
if (family == type->family)
return type;
}
@@ -8275,9 +8310,13 @@ nft_flowtable_type_get(struct net *net, u8 family)
{
const struct nf_flowtable_type *type;
+ rcu_read_lock();
type = __nft_flowtable_type_get(family);
- if (type != NULL && try_module_get(type->owner))
+ if (type != NULL && try_module_get(type->owner)) {
+ rcu_read_unlock();
return type;
+ }
+ rcu_read_unlock();
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
@@ -10178,9 +10217,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
if (nft_trans_chain_update(trans)) {
nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN,
&nft_trans_chain_hooks(trans));
- nft_netdev_unregister_hooks(net,
- &nft_trans_chain_hooks(trans),
- true);
+ if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) {
+ nft_netdev_unregister_hooks(net,
+ &nft_trans_chain_hooks(trans),
+ true);
+ }
} else {
nft_chain_del(trans->ctx.chain);
nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN,
@@ -10419,10 +10460,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
struct nft_trans *trans, *next;
LIST_HEAD(set_update_list);
struct nft_trans_elem *te;
+ int err = 0;
if (action == NFNL_ABORT_VALIDATE &&
nf_tables_validate(net) < 0)
- return -EAGAIN;
+ err = -EAGAIN;
list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list,
list) {
@@ -10452,9 +10494,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
break;
case NFT_MSG_NEWCHAIN:
if (nft_trans_chain_update(trans)) {
- nft_netdev_unregister_hooks(net,
- &nft_trans_chain_hooks(trans),
- true);
+ if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) {
+ nft_netdev_unregister_hooks(net,
+ &nft_trans_chain_hooks(trans),
+ true);
+ }
free_percpu(nft_trans_chain_stats(trans));
kfree(nft_trans_chain_name(trans));
nft_trans_destroy(trans);
@@ -10608,12 +10652,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
nf_tables_abort_release(trans);
}
- if (action == NFNL_ABORT_AUTOLOAD)
- nf_tables_module_autoload(net);
- else
- nf_tables_module_autoload_cleanup(net);
-
- return 0;
+ return err;
}
static int nf_tables_abort(struct net *net, struct sk_buff *skb,
@@ -10626,6 +10665,17 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb,
gc_seq = nft_gc_seq_begin(nft_net);
ret = __nf_tables_abort(net, action);
nft_gc_seq_end(nft_net, gc_seq);
+
+ WARN_ON_ONCE(!list_empty(&nft_net->commit_list));
+
+ /* module autoload needs to happen after GC sequence update because it
+ * temporarily releases and grabs mutex again.
+ */
+ if (action == NFNL_ABORT_AUTOLOAD)
+ nf_tables_module_autoload(net);
+ else
+ nf_tables_module_autoload_cleanup(net);
+
mutex_unlock(&nft_net->commit_mutex);
return ret;
@@ -11427,9 +11477,10 @@ static void __net_exit nf_tables_exit_net(struct net *net)
gc_seq = nft_gc_seq_begin(nft_net);
- if (!list_empty(&nft_net->commit_list) ||
- !list_empty(&nft_net->module_list))
- __nf_tables_abort(net, NFNL_ABORT_NONE);
+ WARN_ON_ONCE(!list_empty(&nft_net->commit_list));
+
+ if (!list_empty(&nft_net->module_list))
+ nf_tables_module_autoload_cleanup(net);
__nft_release_tables(net);
@@ -11521,6 +11572,7 @@ static void __exit nf_tables_module_exit(void)
unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
nft_chain_filter_fini();
nft_chain_route_fini();
+ nf_tables_trans_destroy_flush_work();
unregister_pernet_subsys(&nf_tables_net_ops);
cancel_work_sync(&trans_gc_work);
cancel_work_sync(&trans_destroy_work);
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index cdad47b140fa..0d26c8ec9993 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1516,6 +1516,11 @@ static void nci_rx_work(struct work_struct *work)
nfc_send_to_raw_sock(ndev->nfc_dev, skb,
RAW_PAYLOAD_NCI, NFC_DIRECTION_RX);
+ if (!nci_plen(skb->data)) {
+ kfree_skb(skb);
+ break;
+ }
+
/* Process frame */
switch (nci_mt(skb->data)) {
case NCI_MT_RSP_PKT:
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index a4e3c5de998b..00dbcd4d28e6 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -302,7 +302,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
}
ret = PTR_ERR(trans_private);
/* Trigger connection so that its ready for the next retry */
- if (ret == -ENODEV)
+ if (ret == -ENODEV && cp)
rds_conn_connect_if_down(cp->cp_conn);
goto out;
}
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index bcb673ab0008..001539391082 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -241,13 +241,13 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_skbmod *d = to_skbmod(a);
unsigned char *b = skb_tail_pointer(skb);
struct tcf_skbmod_params *p;
- struct tc_skbmod opt = {
- .index = d->tcf_index,
- .refcnt = refcount_read(&d->tcf_refcnt) - ref,
- .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
- };
+ struct tc_skbmod opt;
struct tcf_t t;
+ memset(&opt, 0, sizeof(opt));
+ opt.index = d->tcf_index;
+ opt.refcnt = refcount_read(&d->tcf_refcnt) - ref,
+ opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind;
spin_lock_bh(&d->tcf_lock);
opt.action = d->tcf_action;
p = rcu_dereference_protected(d->skbmod_p,
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 36b025cc4fd2..31e38a614f33 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -809,7 +809,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len)
notify = !sch->q.qlen && !WARN_ON_ONCE(!n &&
!qdisc_is_offloaded);
/* TODO: perform the search on a per txq basis */
- sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
+ sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid));
if (sch == NULL) {
WARN_ON_ONCE(parentid != TC_H_ROOT);
break;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 545017a3daa4..6b3f01beb294 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1206,15 +1206,6 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
* MSG_SPLICE_PAGES is used exclusively to reduce the number of
* copy operations in this path. Therefore the caller must ensure
* that the pages backing @xdr are unchanging.
- *
- * Note that the send is non-blocking. The caller has incremented
- * the reference count on each page backing the RPC message, and
- * the network layer will "put" these pages when transmission is
- * complete.
- *
- * This is safe for our RPC services because the memory backing
- * the head and tail components is never kmalloc'd. These always
- * come from pages in the svc_rqst::rq_pages array.
*/
static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
rpc_fraghdr marker, unsigned int *sentp)
@@ -1244,6 +1235,7 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
1 + count, sizeof(marker) + rqstp->rq_res.len);
ret = sock_sendmsg(svsk->sk_sock, &msg);
+ page_frag_free(buf);
if (ret < 0)
return ret;
*sentp += ret;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 211f57164cb6..b783231668c6 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1976,10 +1976,10 @@ int tls_sw_recvmsg(struct sock *sk,
if (unlikely(flags & MSG_ERRQUEUE))
return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR);
- psock = sk_psock_get(sk);
err = tls_rx_reader_lock(sk, ctx, flags & MSG_DONTWAIT);
if (err < 0)
return err;
+ psock = sk_psock_get(sk);
bpf_strp_enabled = sk_psock_strp_enabled(psock);
/* If crypto failed the connection is broken */
@@ -2152,12 +2152,15 @@ int tls_sw_recvmsg(struct sock *sk,
}
/* Drain records from the rx_list & copy if required */
- if (is_peek || is_kvec)
+ if (is_peek)
err = process_rx_list(ctx, msg, &control, copied + peeked,
decrypted - peeked, is_peek, NULL);
else
err = process_rx_list(ctx, msg, &control, 0,
async_copy_bytes, is_peek, NULL);
+
+ /* we could have copied less than we wanted, and possibly nothing */
+ decrypted += max(err, 0) - async_copy_bytes;
}
copied += decrypted;
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 1748268e0694..ee5d306a96d0 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -120,7 +120,6 @@ virtio_transport_send_pkt_work(struct work_struct *work)
if (!skb)
break;
- virtio_transport_deliver_tap_pkt(skb);
reply = virtio_vsock_skb_reply(skb);
sgs = vsock->out_sgs;
sg_init_one(sgs[out_sg], virtio_vsock_hdr(skb),
@@ -170,6 +169,8 @@ virtio_transport_send_pkt_work(struct work_struct *work)
break;
}
+ virtio_transport_deliver_tap_pkt(skb);
+
if (reply) {
struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX];
int val;
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 2f25a1de129d..5660b96213e4 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -114,6 +114,8 @@ KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow)
KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation)
KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
+KBUILD_CFLAGS += -Wno-override-init # alias for -Wno-initializer-overrides in clang
+
ifdef CONFIG_CC_IS_CLANG
# Clang before clang-16 would warn on default argument promotions.
ifneq ($(call clang-min-version, 160000),y)
@@ -151,10 +153,6 @@ KBUILD_CFLAGS += -Wtype-limits
KBUILD_CFLAGS += $(call cc-option, -Wmaybe-uninitialized)
KBUILD_CFLAGS += $(call cc-option, -Wunused-macros)
-ifdef CONFIG_CC_IS_CLANG
-KBUILD_CFLAGS += -Winitializer-overrides
-endif
-
KBUILD_CPPFLAGS += -DKBUILD_EXTRA_WARN2
else
@@ -164,9 +162,7 @@ KBUILD_CFLAGS += -Wno-missing-field-initializers
KBUILD_CFLAGS += -Wno-type-limits
KBUILD_CFLAGS += -Wno-shift-negative-value
-ifdef CONFIG_CC_IS_CLANG
-KBUILD_CFLAGS += -Wno-initializer-overrides
-else
+ifdef CONFIG_CC_IS_GCC
KBUILD_CFLAGS += -Wno-maybe-uninitialized
endif
diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index 0669bac5e900..3f899cc7e99a 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -414,8 +414,8 @@ class PrinterRST(Printer):
version = version.stdout.decode().rstrip()
except:
try:
- version = subprocess.run(['make', 'kernelversion'], cwd=linuxRoot,
- capture_output=True, check=True)
+ version = subprocess.run(['make', '-s', '--no-print-directory', 'kernelversion'],
+ cwd=linuxRoot, capture_output=True, check=True)
version = version.stdout.decode().rstrip()
except:
return 'Linux'
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 267b9a0a3abc..6568f8177e39 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1007,6 +1007,8 @@ static Elf_Sym *find_fromsym(struct elf_info *elf, Elf_Addr addr,
static Elf_Sym *find_tosym(struct elf_info *elf, Elf_Addr addr, Elf_Sym *sym)
{
+ Elf_Sym *new_sym;
+
/* If the supplied symbol has a valid name, return it */
if (is_valid_name(elf, sym))
return sym;
@@ -1015,8 +1017,9 @@ static Elf_Sym *find_tosym(struct elf_info *elf, Elf_Addr addr, Elf_Sym *sym)
* Strive to find a better symbol name, but the resulting name may not
* match the symbol referenced in the original code.
*/
- return symsearch_find_nearest(elf, addr, get_secindex(elf, sym),
- true, 20);
+ new_sym = symsearch_find_nearest(elf, addr, get_secindex(elf, sym),
+ true, 20);
+ return new_sym ? new_sym : sym;
}
static bool is_executable_section(struct elf_info *elf, unsigned int secndx)
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 0619a1cbbfbe..074d6c2714eb 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -2123,7 +2123,6 @@ static struct file_system_type sel_fs_type = {
.kill_sb = sel_kill_sb,
};
-static struct vfsmount *selinuxfs_mount __ro_after_init;
struct path selinux_null __ro_after_init;
static int __init init_sel_fs(void)
@@ -2145,18 +2144,21 @@ static int __init init_sel_fs(void)
return err;
}
- selinux_null.mnt = selinuxfs_mount = kern_mount(&sel_fs_type);
- if (IS_ERR(selinuxfs_mount)) {
+ selinux_null.mnt = kern_mount(&sel_fs_type);
+ if (IS_ERR(selinux_null.mnt)) {
pr_err("selinuxfs: could not mount!\n");
- err = PTR_ERR(selinuxfs_mount);
- selinuxfs_mount = NULL;
+ err = PTR_ERR(selinux_null.mnt);
+ selinux_null.mnt = NULL;
+ return err;
}
+
selinux_null.dentry = d_hash_and_lookup(selinux_null.mnt->mnt_root,
&null_name);
if (IS_ERR(selinux_null.dentry)) {
pr_err("selinuxfs: could not lookup null!\n");
err = PTR_ERR(selinux_null.dentry);
selinux_null.dentry = NULL;
+ return err;
}
return err;
diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c
index d36234b88fb4..941bfbf812ed 100644
--- a/sound/pci/emu10k1/emu10k1_callback.c
+++ b/sound/pci/emu10k1/emu10k1_callback.c
@@ -255,7 +255,7 @@ lookup_voices(struct snd_emux *emu, struct snd_emu10k1 *hw,
/* check if sample is finished playing (non-looping only) */
if (bp != best + V_OFF && bp != best + V_FREE &&
(vp->reg.sample_mode & SNDRV_SFNT_SAMPLE_SINGLESHOT)) {
- val = snd_emu10k1_ptr_read(hw, CCCA_CURRADDR, vp->ch) - 64;
+ val = snd_emu10k1_ptr_read(hw, CCCA_CURRADDR, vp->ch);
if (val >= vp->reg.loopstart)
bp = best + V_OFF;
}
@@ -362,7 +362,7 @@ start_voice(struct snd_emux_voice *vp)
map = (hw->silent_page.addr << hw->address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0);
- addr = vp->reg.start + 64;
+ addr = vp->reg.start;
temp = vp->reg.parm.filterQ;
ccca = (temp << 28) | addr;
if (vp->apitch < 0xe400)
@@ -430,9 +430,6 @@ start_voice(struct snd_emux_voice *vp)
/* Q & current address (Q 4bit value, MSB) */
CCCA, ccca,
- /* cache */
- CCR, REG_VAL_PUT(CCR_CACHEINVALIDSIZE, 64),
-
/* reset volume */
VTFT, vtarget | vp->ftarget,
CVCF, vtarget | CVCF_CURRENTFILTER_MASK,
diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index 86ddaff915de..4d1f8734d13f 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -97,7 +97,10 @@ static const struct cs35l41_config cs35l41_config_table[] = {
{ "10431F12", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
{ "10431F1F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 },
{ "10431F62", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+ { "10433A60", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
{ "17AA386F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
+ { "17AA3877", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
+ { "17AA3878", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
{ "17AA38A9", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 },
{ "17AA38AB", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 },
{ "17AA38B4", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
@@ -434,7 +437,10 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
{ "CSC3551", "10431F12", generic_dsd_config },
{ "CSC3551", "10431F1F", generic_dsd_config },
{ "CSC3551", "10431F62", generic_dsd_config },
+ { "CSC3551", "10433A60", generic_dsd_config },
{ "CSC3551", "17AA386F", generic_dsd_config },
+ { "CSC3551", "17AA3877", generic_dsd_config },
+ { "CSC3551", "17AA3878", generic_dsd_config },
{ "CSC3551", "17AA38A9", generic_dsd_config },
{ "CSC3551", "17AA38AB", generic_dsd_config },
{ "CSC3551", "17AA38B4", generic_dsd_config },
diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index 75a14ba54fcd..43a445bd961f 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -1017,14 +1017,14 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int id)
pm_runtime_mark_last_busy(cs35l56->base.dev);
pm_runtime_enable(cs35l56->base.dev);
+ cs35l56->base.init_done = true;
+
ret = component_add(cs35l56->base.dev, &cs35l56_hda_comp_ops);
if (ret) {
dev_err(cs35l56->base.dev, "Register component failed: %d\n", ret);
goto pm_err;
}
- cs35l56->base.init_done = true;
-
return 0;
pm_err:
diff --git a/sound/pci/hda/cs35l56_hda_i2c.c b/sound/pci/hda/cs35l56_hda_i2c.c
index a9ef6d86de83..09a810a50a12 100644
--- a/sound/pci/hda/cs35l56_hda_i2c.c
+++ b/sound/pci/hda/cs35l56_hda_i2c.c
@@ -53,10 +53,19 @@ static const struct i2c_device_id cs35l56_hda_i2c_id[] = {
{}
};
+static const struct acpi_device_id cs35l56_acpi_hda_match[] = {
+ { "CSC3554", 0 },
+ { "CSC3556", 0 },
+ { "CSC3557", 0 },
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, cs35l56_acpi_hda_match);
+
static struct i2c_driver cs35l56_hda_i2c_driver = {
.driver = {
- .name = "cs35l56-hda",
- .pm = &cs35l56_hda_pm_ops,
+ .name = "cs35l56-hda",
+ .acpi_match_table = cs35l56_acpi_hda_match,
+ .pm = &cs35l56_hda_pm_ops,
},
.id_table = cs35l56_hda_i2c_id,
.probe = cs35l56_hda_i2c_probe,
diff --git a/sound/pci/hda/cs35l56_hda_spi.c b/sound/pci/hda/cs35l56_hda_spi.c
index 080426de9083..04f9fe6197dc 100644
--- a/sound/pci/hda/cs35l56_hda_spi.c
+++ b/sound/pci/hda/cs35l56_hda_spi.c
@@ -53,10 +53,19 @@ static const struct spi_device_id cs35l56_hda_spi_id[] = {
{}
};
+static const struct acpi_device_id cs35l56_acpi_hda_match[] = {
+ { "CSC3554", 0 },
+ { "CSC3556", 0 },
+ { "CSC3557", 0 },
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, cs35l56_acpi_hda_match);
+
static struct spi_driver cs35l56_hda_spi_driver = {
.driver = {
- .name = "cs35l56-hda",
- .pm = &cs35l56_hda_pm_ops,
+ .name = "cs35l56-hda",
+ .acpi_match_table = cs35l56_acpi_hda_match,
+ .pm = &cs35l56_hda_pm_ops,
},
.id_table = cs35l56_hda_spi_id,
.probe = cs35l56_hda_spi_probe,
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 1dc5eb92ddca..f4a02bf1abb1 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10164,7 +10164,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
@@ -10189,7 +10189,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
SND_PCI_QUIRK(0x10ec, 0x12cc, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
- SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
+ SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
@@ -10361,6 +10361,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
SND_PCI_QUIRK(0x17aa, 0x386f, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C),
+ SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x17aa, 0x3878, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x3881, "YB9 dual power mode2 YC", ALC287_FIXUP_TAS2781_I2C),
@@ -10427,6 +10429,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1d05, 0x1147, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP),
+ SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
diff --git a/sound/soc/amd/acp/acp-pci.c b/sound/soc/amd/acp/acp-pci.c
index 8c8b1dcac628..5f35b90eab8d 100644
--- a/sound/soc/amd/acp/acp-pci.c
+++ b/sound/soc/amd/acp/acp-pci.c
@@ -115,7 +115,10 @@ static int acp_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id
goto unregister_dmic_dev;
}
- acp_init(chip);
+ ret = acp_init(chip);
+ if (ret)
+ goto unregister_dmic_dev;
+
res = devm_kcalloc(&pci->dev, num_res, sizeof(struct resource), GFP_KERNEL);
if (!res) {
ret = -ENOMEM;
@@ -133,11 +136,9 @@ static int acp_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id
}
}
- if (flag == FLAG_AMD_LEGACY_ONLY_DMIC) {
- ret = check_acp_pdm(pci, chip);
- if (ret < 0)
- goto skip_pdev_creation;
- }
+ ret = check_acp_pdm(pci, chip);
+ if (ret < 0)
+ goto skip_pdev_creation;
chip->flag = flag;
memset(&pdevinfo, 0, sizeof(pdevinfo));
diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index a97ccb512deb..a24b52c9dda6 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -2338,7 +2338,8 @@ static int cs42l43_codec_runtime_resume(struct device *dev)
static int cs42l43_codec_suspend(struct device *dev)
{
- struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+ struct cs42l43_codec *priv = dev_get_drvdata(dev);
+ struct cs42l43 *cs42l43 = priv->core;
disable_irq(cs42l43->irq);
@@ -2347,7 +2348,8 @@ static int cs42l43_codec_suspend(struct device *dev)
static int cs42l43_codec_suspend_noirq(struct device *dev)
{
- struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+ struct cs42l43_codec *priv = dev_get_drvdata(dev);
+ struct cs42l43 *cs42l43 = priv->core;
enable_irq(cs42l43->irq);
@@ -2356,7 +2358,8 @@ static int cs42l43_codec_suspend_noirq(struct device *dev)
static int cs42l43_codec_resume(struct device *dev)
{
- struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+ struct cs42l43_codec *priv = dev_get_drvdata(dev);
+ struct cs42l43 *cs42l43 = priv->core;
enable_irq(cs42l43->irq);
@@ -2365,7 +2368,8 @@ static int cs42l43_codec_resume(struct device *dev)
static int cs42l43_codec_resume_noirq(struct device *dev)
{
- struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+ struct cs42l43_codec *priv = dev_get_drvdata(dev);
+ struct cs42l43 *cs42l43 = priv->core;
disable_irq(cs42l43->irq);
diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c
index e67c2e19cb1a..1fdbef5fd6cb 100644
--- a/sound/soc/codecs/rt5682-sdw.c
+++ b/sound/soc/codecs/rt5682-sdw.c
@@ -763,12 +763,12 @@ static int __maybe_unused rt5682_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt5682->disable_irq_lock);
if (rt5682->disable_irq == true) {
- mutex_lock(&rt5682->disable_irq_lock);
sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF);
rt5682->disable_irq = false;
- mutex_unlock(&rt5682->disable_irq_lock);
}
+ mutex_unlock(&rt5682->disable_irq_lock);
goto regmap_sync;
}
diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c
index 935e597022d3..b8471b2d8f4f 100644
--- a/sound/soc/codecs/rt711-sdca-sdw.c
+++ b/sound/soc/codecs/rt711-sdca-sdw.c
@@ -438,13 +438,13 @@ static int __maybe_unused rt711_sdca_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt711->disable_irq_lock);
if (rt711->disable_irq == true) {
- mutex_lock(&rt711->disable_irq_lock);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_0);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8);
rt711->disable_irq = false;
- mutex_unlock(&rt711->disable_irq_lock);
}
+ mutex_unlock(&rt711->disable_irq_lock);
goto regmap_sync;
}
diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c
index 3f5773310ae8..988451f24a75 100644
--- a/sound/soc/codecs/rt711-sdw.c
+++ b/sound/soc/codecs/rt711-sdw.c
@@ -536,12 +536,12 @@ static int __maybe_unused rt711_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt711->disable_irq_lock);
if (rt711->disable_irq == true) {
- mutex_lock(&rt711->disable_irq_lock);
sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF);
rt711->disable_irq = false;
- mutex_unlock(&rt711->disable_irq_lock);
}
+ mutex_unlock(&rt711->disable_irq_lock);
goto regmap_sync;
}
diff --git a/sound/soc/codecs/rt712-sdca-sdw.c b/sound/soc/codecs/rt712-sdca-sdw.c
index 6b644a89c589..ba877432cea6 100644
--- a/sound/soc/codecs/rt712-sdca-sdw.c
+++ b/sound/soc/codecs/rt712-sdca-sdw.c
@@ -438,13 +438,14 @@ static int __maybe_unused rt712_sdca_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt712->disable_irq_lock);
if (rt712->disable_irq == true) {
- mutex_lock(&rt712->disable_irq_lock);
+
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_0);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8);
rt712->disable_irq = false;
- mutex_unlock(&rt712->disable_irq_lock);
}
+ mutex_unlock(&rt712->disable_irq_lock);
goto regmap_sync;
}
diff --git a/sound/soc/codecs/rt722-sdca-sdw.c b/sound/soc/codecs/rt722-sdca-sdw.c
index e24b9cbdc10c..e33836fffd5f 100644
--- a/sound/soc/codecs/rt722-sdca-sdw.c
+++ b/sound/soc/codecs/rt722-sdca-sdw.c
@@ -467,13 +467,13 @@ static int __maybe_unused rt722_sdca_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt722->disable_irq_lock);
if (rt722->disable_irq == true) {
- mutex_lock(&rt722->disable_irq_lock);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_6);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8);
rt722->disable_irq = false;
- mutex_unlock(&rt722->disable_irq_lock);
}
+ mutex_unlock(&rt722->disable_irq_lock);
goto regmap_sync;
}
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 36ea0dcdc7ab..9cb9068c0462 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -683,11 +683,12 @@ static void wm_adsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl)
int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type,
unsigned int alg, void *buf, size_t len)
{
- struct cs_dsp_coeff_ctl *cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg);
+ struct cs_dsp_coeff_ctl *cs_ctl;
struct wm_coeff_ctl *ctl;
int ret;
mutex_lock(&dsp->cs_dsp.pwr_lock);
+ cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg);
ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, buf, len);
mutex_unlock(&dsp->cs_dsp.pwr_lock);
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index 2d25748ca706..b27e89ff6a16 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -263,7 +263,7 @@ int snd_soc_get_volsw(struct snd_kcontrol *kcontrol,
int max = mc->max;
int min = mc->min;
int sign_bit = mc->sign_bit;
- unsigned int mask = (1 << fls(max)) - 1;
+ unsigned int mask = (1ULL << fls(max)) - 1;
unsigned int invert = mc->invert;
int val;
int ret;
diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c
index 4db8cdc91daa..2c242ef9f23c 100644
--- a/sound/soc/sof/amd/acp.c
+++ b/sound/soc/sof/amd/acp.c
@@ -537,6 +537,10 @@ int amd_sof_acp_probe(struct snd_sof_dev *sdev)
goto unregister_dev;
}
+ ret = acp_init(sdev);
+ if (ret < 0)
+ goto free_smn_dev;
+
sdev->ipc_irq = pci->irq;
ret = request_threaded_irq(sdev->ipc_irq, acp_irq_handler, acp_irq_thread,
IRQF_SHARED, "AudioDSP", sdev);
@@ -546,10 +550,6 @@ int amd_sof_acp_probe(struct snd_sof_dev *sdev)
goto free_smn_dev;
}
- ret = acp_init(sdev);
- if (ret < 0)
- goto free_ipc_irq;
-
sdev->dsp_box.offset = 0;
sdev->dsp_box.size = BOX_SIZE_512;
diff --git a/sound/soc/sof/intel/hda-common-ops.c b/sound/soc/sof/intel/hda-common-ops.c
index 26105d8f1bdc..88c236b9a045 100644
--- a/sound/soc/sof/intel/hda-common-ops.c
+++ b/sound/soc/sof/intel/hda-common-ops.c
@@ -57,6 +57,9 @@ struct snd_sof_dsp_ops sof_hda_common_ops = {
.pcm_pointer = hda_dsp_pcm_pointer,
.pcm_ack = hda_dsp_pcm_ack,
+ .get_dai_frame_counter = hda_dsp_get_stream_llp,
+ .get_host_byte_counter = hda_dsp_get_stream_ldp,
+
/* firmware loading */
.load_firmware = snd_sof_load_firmware_raw,
diff --git a/sound/soc/sof/intel/hda-dai-ops.c b/sound/soc/sof/intel/hda-dai-ops.c
index 55ce75db23e5..92ec5db4677d 100644
--- a/sound/soc/sof/intel/hda-dai-ops.c
+++ b/sound/soc/sof/intel/hda-dai-ops.c
@@ -7,6 +7,7 @@
#include <sound/pcm_params.h>
#include <sound/hdaudio_ext.h>
+#include <sound/hda_register.h>
#include <sound/hda-mlink.h>
#include <sound/sof/ipc4/header.h>
#include <uapi/sound/sof/header.h>
@@ -362,6 +363,16 @@ static int hda_trigger(struct snd_sof_dev *sdev, struct snd_soc_dai *cpu_dai,
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
snd_hdac_ext_stream_clear(hext_stream);
+
+ /*
+ * Save the LLP registers in case the stream is
+ * restarting due PAUSE_RELEASE, or START without a pcm
+ * close/open since in this case the LLP register is not reset
+ * to 0 and the delay calculation will return with invalid
+ * results.
+ */
+ hext_stream->pplcllpl = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPL);
+ hext_stream->pplcllpu = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPU);
break;
default:
dev_err(sdev->dev, "unknown trigger command %d\n", cmd);
diff --git a/sound/soc/sof/intel/hda-pcm.c b/sound/soc/sof/intel/hda-pcm.c
index 18f07364d219..d7b446f3f973 100644
--- a/sound/soc/sof/intel/hda-pcm.c
+++ b/sound/soc/sof/intel/hda-pcm.c
@@ -259,8 +259,37 @@ int hda_dsp_pcm_open(struct snd_sof_dev *sdev,
snd_pcm_hw_constraint_mask64(substream->runtime, SNDRV_PCM_HW_PARAM_FORMAT,
SNDRV_PCM_FMTBIT_S16 | SNDRV_PCM_FMTBIT_S32);
+ /*
+ * The dsp_max_burst_size_in_ms is the length of the maximum burst size
+ * of the host DMA in the ALSA buffer.
+ *
+ * On playback start the DMA will transfer dsp_max_burst_size_in_ms
+ * amount of data in one initial burst to fill up the host DMA buffer.
+ * Consequent DMA burst sizes are shorter and their length can vary.
+ * To make sure that userspace allocate large enough ALSA buffer we need
+ * to place a constraint on the buffer time.
+ *
+ * On capture the DMA will transfer 1ms chunks.
+ *
+ * Exact dsp_max_burst_size_in_ms constraint is racy, so set the
+ * constraint to a minimum of 2x dsp_max_burst_size_in_ms.
+ */
+ if (spcm->stream[direction].dsp_max_burst_size_in_ms)
+ snd_pcm_hw_constraint_minmax(substream->runtime,
+ SNDRV_PCM_HW_PARAM_BUFFER_TIME,
+ spcm->stream[direction].dsp_max_burst_size_in_ms * USEC_PER_MSEC * 2,
+ UINT_MAX);
+
/* binding pcm substream to hda stream */
substream->runtime->private_data = &dsp_stream->hstream;
+
+ /*
+ * Reset the llp cache values (they are used for LLP compensation in
+ * case the counter is not reset)
+ */
+ dsp_stream->pplcllpl = 0;
+ dsp_stream->pplcllpu = 0;
+
return 0;
}
diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c
index f2ebadbbcc10..c603aaf0ca77 100644
--- a/sound/soc/sof/intel/hda-stream.c
+++ b/sound/soc/sof/intel/hda-stream.c
@@ -1054,3 +1054,73 @@ snd_pcm_uframes_t hda_dsp_stream_get_position(struct hdac_stream *hstream,
return pos;
}
+
+#define merge_u64(u32_u, u32_l) (((u64)(u32_u) << 32) | (u32_l))
+
+/**
+ * hda_dsp_get_stream_llp - Retrieve the LLP (Linear Link Position) of the stream
+ * @sdev: SOF device
+ * @component: ASoC component
+ * @substream: PCM substream
+ *
+ * Returns the raw Linear Link Position value
+ */
+u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
+{
+ struct hdac_stream *hstream = substream->runtime->private_data;
+ struct hdac_ext_stream *hext_stream = stream_to_hdac_ext_stream(hstream);
+ u32 llp_l, llp_u;
+
+ /*
+ * The pplc_addr have been calculated during probe in
+ * hda_dsp_stream_init():
+ * pplc_addr = sdev->bar[HDA_DSP_PP_BAR] +
+ * SOF_HDA_PPLC_BASE +
+ * SOF_HDA_PPLC_MULTI * total_stream +
+ * SOF_HDA_PPLC_INTERVAL * stream_index
+ *
+ * Use this pre-calculated address to avoid repeated re-calculation.
+ */
+ llp_l = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPL);
+ llp_u = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPU);
+
+ /* Compensate the LLP counter with the saved offset */
+ if (hext_stream->pplcllpl || hext_stream->pplcllpu)
+ return merge_u64(llp_u, llp_l) -
+ merge_u64(hext_stream->pplcllpu, hext_stream->pplcllpl);
+
+ return merge_u64(llp_u, llp_l);
+}
+
+/**
+ * hda_dsp_get_stream_ldp - Retrieve the LDP (Linear DMA Position) of the stream
+ * @sdev: SOF device
+ * @component: ASoC component
+ * @substream: PCM substream
+ *
+ * Returns the raw Linear Link Position value
+ */
+u64 hda_dsp_get_stream_ldp(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
+{
+ struct hdac_stream *hstream = substream->runtime->private_data;
+ struct hdac_ext_stream *hext_stream = stream_to_hdac_ext_stream(hstream);
+ u32 ldp_l, ldp_u;
+
+ /*
+ * The pphc_addr have been calculated during probe in
+ * hda_dsp_stream_init():
+ * pphc_addr = sdev->bar[HDA_DSP_PP_BAR] +
+ * SOF_HDA_PPHC_BASE +
+ * SOF_HDA_PPHC_INTERVAL * stream_index
+ *
+ * Use this pre-calculated address to avoid repeated re-calculation.
+ */
+ ldp_l = readl(hext_stream->pphc_addr + AZX_REG_PPHCLDPL);
+ ldp_u = readl(hext_stream->pphc_addr + AZX_REG_PPHCLDPU);
+
+ return ((u64)ldp_u << 32) | ldp_l;
+}
diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h
index 1592e27bc14d..efb42117df79 100644
--- a/sound/soc/sof/intel/hda.h
+++ b/sound/soc/sof/intel/hda.h
@@ -657,6 +657,12 @@ bool hda_dsp_check_stream_irq(struct snd_sof_dev *sdev);
snd_pcm_uframes_t hda_dsp_stream_get_position(struct hdac_stream *hstream,
int direction, bool can_sleep);
+u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream);
+u64 hda_dsp_get_stream_ldp(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream);
struct hdac_ext_stream *
hda_dsp_stream_get(struct snd_sof_dev *sdev, int direction, u32 flags);
diff --git a/sound/soc/sof/intel/lnl.c b/sound/soc/sof/intel/lnl.c
index 30712ea05a7a..555a51c688dc 100644
--- a/sound/soc/sof/intel/lnl.c
+++ b/sound/soc/sof/intel/lnl.c
@@ -118,8 +118,6 @@ int sof_lnl_ops_init(struct snd_sof_dev *sdev)
sof_lnl_ops.resume = lnl_hda_dsp_resume;
sof_lnl_ops.runtime_resume = lnl_hda_dsp_runtime_resume;
- sof_lnl_ops.get_stream_position = mtl_dsp_get_stream_hda_link_position;
-
/* dsp core get/put */
sof_lnl_ops.core_get = mtl_dsp_core_get;
sof_lnl_ops.core_put = mtl_dsp_core_put;
diff --git a/sound/soc/sof/intel/mtl.c b/sound/soc/sof/intel/mtl.c
index df05dc77b8d5..060c34988e90 100644
--- a/sound/soc/sof/intel/mtl.c
+++ b/sound/soc/sof/intel/mtl.c
@@ -626,18 +626,6 @@ static int mtl_dsp_disable_interrupts(struct snd_sof_dev *sdev)
return mtl_enable_interrupts(sdev, false);
}
-u64 mtl_dsp_get_stream_hda_link_position(struct snd_sof_dev *sdev,
- struct snd_soc_component *component,
- struct snd_pcm_substream *substream)
-{
- struct hdac_stream *hstream = substream->runtime->private_data;
- u32 llp_l, llp_u;
-
- llp_l = snd_sof_dsp_read(sdev, HDA_DSP_HDA_BAR, MTL_PPLCLLPL(hstream->index));
- llp_u = snd_sof_dsp_read(sdev, HDA_DSP_HDA_BAR, MTL_PPLCLLPU(hstream->index));
- return ((u64)llp_u << 32) | llp_l;
-}
-
int mtl_dsp_core_get(struct snd_sof_dev *sdev, int core)
{
const struct sof_ipc_pm_ops *pm_ops = sdev->ipc->ops->pm;
@@ -707,8 +695,6 @@ int sof_mtl_ops_init(struct snd_sof_dev *sdev)
sof_mtl_ops.core_get = mtl_dsp_core_get;
sof_mtl_ops.core_put = mtl_dsp_core_put;
- sof_mtl_ops.get_stream_position = mtl_dsp_get_stream_hda_link_position;
-
sdev->private = kzalloc(sizeof(struct sof_ipc4_fw_data), GFP_KERNEL);
if (!sdev->private)
return -ENOMEM;
diff --git a/sound/soc/sof/intel/mtl.h b/sound/soc/sof/intel/mtl.h
index cc5a1f46fd09..ea8c1b83f712 100644
--- a/sound/soc/sof/intel/mtl.h
+++ b/sound/soc/sof/intel/mtl.h
@@ -6,12 +6,6 @@
* Copyright(c) 2020-2022 Intel Corporation. All rights reserved.
*/
-/* HDA Registers */
-#define MTL_PPLCLLPL_BASE 0x948
-#define MTL_PPLCLLPU_STRIDE 0x10
-#define MTL_PPLCLLPL(x) (MTL_PPLCLLPL_BASE + (x) * MTL_PPLCLLPU_STRIDE)
-#define MTL_PPLCLLPU(x) (MTL_PPLCLLPL_BASE + 0x4 + (x) * MTL_PPLCLLPU_STRIDE)
-
/* DSP Registers */
#define MTL_HFDSSCS 0x1000
#define MTL_HFDSSCS_SPA_MASK BIT(16)
@@ -103,9 +97,5 @@ int mtl_dsp_ipc_get_window_offset(struct snd_sof_dev *sdev, u32 id);
void mtl_ipc_dump(struct snd_sof_dev *sdev);
-u64 mtl_dsp_get_stream_hda_link_position(struct snd_sof_dev *sdev,
- struct snd_soc_component *component,
- struct snd_pcm_substream *substream);
-
int mtl_dsp_core_get(struct snd_sof_dev *sdev, int core);
int mtl_dsp_core_put(struct snd_sof_dev *sdev, int core);
diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 07eb5c6d4adf..a99fced90825 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -15,6 +15,28 @@
#include "ipc4-topology.h"
#include "ipc4-fw-reg.h"
+/**
+ * struct sof_ipc4_timestamp_info - IPC4 timestamp info
+ * @host_copier: the host copier of the pcm stream
+ * @dai_copier: the dai copier of the pcm stream
+ * @stream_start_offset: reported by fw in memory window (converted to frames)
+ * @stream_end_offset: reported by fw in memory window (converted to frames)
+ * @llp_offset: llp offset in memory window
+ * @boundary: wrap boundary should be used for the LLP frame counter
+ * @delay: Calculated and stored in pointer callback. The stored value is
+ * returned in the delay callback.
+ */
+struct sof_ipc4_timestamp_info {
+ struct sof_ipc4_copier *host_copier;
+ struct sof_ipc4_copier *dai_copier;
+ u64 stream_start_offset;
+ u64 stream_end_offset;
+ u32 llp_offset;
+
+ u64 boundary;
+ snd_pcm_sframes_t delay;
+};
+
static int sof_ipc4_set_multi_pipeline_state(struct snd_sof_dev *sdev, u32 state,
struct ipc4_pipeline_set_state_data *trigger_list)
{
@@ -406,8 +428,19 @@ static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component,
}
/* return if this is the final state */
- if (state == SOF_IPC4_PIPE_PAUSED)
+ if (state == SOF_IPC4_PIPE_PAUSED) {
+ struct sof_ipc4_timestamp_info *time_info;
+
+ /*
+ * Invalidate the stream_start_offset to make sure that it is
+ * going to be updated if the stream resumes
+ */
+ time_info = spcm->stream[substream->stream].private;
+ if (time_info)
+ time_info->stream_start_offset = SOF_IPC4_INVALID_STREAM_POSITION;
+
goto free;
+ }
skip_pause_transition:
/* else set the RUNNING/RESET state in the DSP */
ret = sof_ipc4_set_multi_pipeline_state(sdev, state, trigger_list);
@@ -447,14 +480,12 @@ static int sof_ipc4_pcm_trigger(struct snd_soc_component *component,
/* determine the pipeline state */
switch (cmd) {
- case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
- state = SOF_IPC4_PIPE_PAUSED;
- break;
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
case SNDRV_PCM_TRIGGER_RESUME:
case SNDRV_PCM_TRIGGER_START:
state = SOF_IPC4_PIPE_RUNNING;
break;
+ case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
case SNDRV_PCM_TRIGGER_SUSPEND:
case SNDRV_PCM_TRIGGER_STOP:
state = SOF_IPC4_PIPE_PAUSED;
@@ -686,6 +717,10 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm
if (abi_version < SOF_IPC4_FW_REGS_ABI_VER)
support_info = false;
+ /* For delay reporting the get_host_byte_counter callback is needed */
+ if (!sof_ops(sdev) || !sof_ops(sdev)->get_host_byte_counter)
+ support_info = false;
+
for_each_pcm_streams(stream) {
pipeline_list = &spcm->stream[stream].pipeline_list;
@@ -818,7 +853,6 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
struct sof_ipc4_copier *host_copier = time_info->host_copier;
struct sof_ipc4_copier *dai_copier = time_info->dai_copier;
struct sof_ipc4_pipeline_registers ppl_reg;
- u64 stream_start_position;
u32 dai_sample_size;
u32 ch, node_index;
u32 offset;
@@ -835,38 +869,51 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
if (ppl_reg.stream_start_offset == SOF_IPC4_INVALID_STREAM_POSITION)
return -EINVAL;
- stream_start_position = ppl_reg.stream_start_offset;
ch = dai_copier->data.out_format.fmt_cfg;
ch = SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(ch);
dai_sample_size = (dai_copier->data.out_format.bit_depth >> 3) * ch;
- /* convert offset to sample count */
- do_div(stream_start_position, dai_sample_size);
- time_info->stream_start_offset = stream_start_position;
+
+ /* convert offsets to frame count */
+ time_info->stream_start_offset = ppl_reg.stream_start_offset;
+ do_div(time_info->stream_start_offset, dai_sample_size);
+ time_info->stream_end_offset = ppl_reg.stream_end_offset;
+ do_div(time_info->stream_end_offset, dai_sample_size);
+
+ /*
+ * Calculate the wrap boundary need to be used for delay calculation
+ * The host counter is in bytes, it will wrap earlier than the frames
+ * based link counter.
+ */
+ time_info->boundary = div64_u64(~((u64)0),
+ frames_to_bytes(substream->runtime, 1));
+ /* Initialize the delay value to 0 (no delay) */
+ time_info->delay = 0;
return 0;
}
-static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component,
- struct snd_pcm_substream *substream)
+static int sof_ipc4_pcm_pointer(struct snd_soc_component *component,
+ struct snd_pcm_substream *substream,
+ snd_pcm_uframes_t *pointer)
{
struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
struct sof_ipc4_timestamp_info *time_info;
struct sof_ipc4_llp_reading_slot llp;
- snd_pcm_uframes_t head_ptr, tail_ptr;
+ snd_pcm_uframes_t head_cnt, tail_cnt;
struct snd_sof_pcm_stream *stream;
+ u64 dai_cnt, host_cnt, host_ptr;
struct snd_sof_pcm *spcm;
- u64 tmp_ptr;
int ret;
spcm = snd_sof_find_spcm_dai(component, rtd);
if (!spcm)
- return 0;
+ return -EOPNOTSUPP;
stream = &spcm->stream[substream->stream];
time_info = stream->private;
if (!time_info)
- return 0;
+ return -EOPNOTSUPP;
/*
* stream_start_offset is updated to memory window by FW based on
@@ -876,45 +923,116 @@ static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component,
if (time_info->stream_start_offset == SOF_IPC4_INVALID_STREAM_POSITION) {
ret = sof_ipc4_get_stream_start_offset(sdev, substream, stream, time_info);
if (ret < 0)
- return 0;
+ return -EOPNOTSUPP;
}
+ /* For delay calculation we need the host counter */
+ host_cnt = snd_sof_pcm_get_host_byte_counter(sdev, component, substream);
+ host_ptr = host_cnt;
+
+ /* convert the host_cnt to frames */
+ host_cnt = div64_u64(host_cnt, frames_to_bytes(substream->runtime, 1));
+
/*
- * HDaudio links don't support the LLP counter reported by firmware
- * the link position is read directly from hardware registers.
+ * If the LLP counter is not reported by firmware in the SRAM window
+ * then read the dai (link) counter via host accessible means if
+ * available.
*/
if (!time_info->llp_offset) {
- tmp_ptr = snd_sof_pcm_get_stream_position(sdev, component, substream);
- if (!tmp_ptr)
- return 0;
+ dai_cnt = snd_sof_pcm_get_dai_frame_counter(sdev, component, substream);
+ if (!dai_cnt)
+ return -EOPNOTSUPP;
} else {
sof_mailbox_read(sdev, time_info->llp_offset, &llp, sizeof(llp));
- tmp_ptr = ((u64)llp.reading.llp_u << 32) | llp.reading.llp_l;
+ dai_cnt = ((u64)llp.reading.llp_u << 32) | llp.reading.llp_l;
}
+ dai_cnt += time_info->stream_end_offset;
- /* In two cases dai dma position is not accurate
+ /* In two cases dai dma counter is not accurate
* (1) dai pipeline is started before host pipeline
- * (2) multiple streams mixed into one. Each stream has the same dai dma position
+ * (2) multiple streams mixed into one. Each stream has the same dai dma
+ * counter
*
- * Firmware calculates correct stream_start_offset for all cases including above two.
- * Driver subtracts stream_start_offset from dai dma position to get accurate one
+ * Firmware calculates correct stream_start_offset for all cases
+ * including above two.
+ * Driver subtracts stream_start_offset from dai dma counter to get
+ * accurate one
*/
- tmp_ptr -= time_info->stream_start_offset;
- /* Calculate the delay taking into account that both pointer can wrap */
- div64_u64_rem(tmp_ptr, substream->runtime->boundary, &tmp_ptr);
+ /*
+ * On stream start the dai counter might not yet have reached the
+ * stream_start_offset value which means that no frames have left the
+ * DSP yet from the audio stream (on playback, capture streams have
+ * offset of 0 as we start capturing right away).
+ * In this case we need to adjust the distance between the counters by
+ * increasing the host counter by (offset - dai_counter).
+ * Otherwise the dai_counter needs to be adjusted to reflect the number
+ * of valid frames passed on the DAI side.
+ *
+ * The delay is the difference between the counters on the two
+ * sides of the DSP.
+ */
+ if (dai_cnt < time_info->stream_start_offset) {
+ host_cnt += time_info->stream_start_offset - dai_cnt;
+ dai_cnt = 0;
+ } else {
+ dai_cnt -= time_info->stream_start_offset;
+ }
+
+ /* Wrap the dai counter at the boundary where the host counter wraps */
+ div64_u64_rem(dai_cnt, time_info->boundary, &dai_cnt);
+
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
- head_ptr = substream->runtime->status->hw_ptr;
- tail_ptr = tmp_ptr;
+ head_cnt = host_cnt;
+ tail_cnt = dai_cnt;
} else {
- head_ptr = tmp_ptr;
- tail_ptr = substream->runtime->status->hw_ptr;
+ head_cnt = dai_cnt;
+ tail_cnt = host_cnt;
+ }
+
+ if (head_cnt < tail_cnt) {
+ time_info->delay = time_info->boundary - tail_cnt + head_cnt;
+ goto out;
}
- if (head_ptr < tail_ptr)
- return substream->runtime->boundary - tail_ptr + head_ptr;
+ time_info->delay = head_cnt - tail_cnt;
+
+out:
+ /*
+ * Convert the host byte counter to PCM pointer which wraps in buffer
+ * and it is in frames
+ */
+ div64_u64_rem(host_ptr, snd_pcm_lib_buffer_bytes(substream), &host_ptr);
+ *pointer = bytes_to_frames(substream->runtime, host_ptr);
+
+ return 0;
+}
+
+static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
+{
+ struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
+ struct sof_ipc4_timestamp_info *time_info;
+ struct snd_sof_pcm_stream *stream;
+ struct snd_sof_pcm *spcm;
+
+ spcm = snd_sof_find_spcm_dai(component, rtd);
+ if (!spcm)
+ return 0;
+
+ stream = &spcm->stream[substream->stream];
+ time_info = stream->private;
+ /*
+ * Report the stored delay value calculated in the pointer callback.
+ * In the unlikely event that the calculation was skipped/aborted, the
+ * default 0 delay returned.
+ */
+ if (time_info)
+ return time_info->delay;
+
+ /* No delay information available, report 0 as delay */
+ return 0;
- return head_ptr - tail_ptr;
}
const struct sof_ipc_pcm_ops ipc4_pcm_ops = {
@@ -924,6 +1042,7 @@ const struct sof_ipc_pcm_ops ipc4_pcm_ops = {
.dai_link_fixup = sof_ipc4_pcm_dai_link_fixup,
.pcm_setup = sof_ipc4_pcm_setup,
.pcm_free = sof_ipc4_pcm_free,
+ .pointer = sof_ipc4_pcm_pointer,
.delay = sof_ipc4_pcm_delay,
.ipc_first_on_start = true,
.platform_stop_during_hw_free = true,
diff --git a/sound/soc/sof/ipc4-priv.h b/sound/soc/sof/ipc4-priv.h
index 1d39836d5efa..9db9002b44d6 100644
--- a/sound/soc/sof/ipc4-priv.h
+++ b/sound/soc/sof/ipc4-priv.h
@@ -88,20 +88,6 @@ struct sof_ipc4_fw_data {
struct mutex pipeline_state_mutex; /* protect pipeline triggers, ref counts and states */
};
-/**
- * struct sof_ipc4_timestamp_info - IPC4 timestamp info
- * @host_copier: the host copier of the pcm stream
- * @dai_copier: the dai copier of the pcm stream
- * @stream_start_offset: reported by fw in memory window
- * @llp_offset: llp offset in memory window
- */
-struct sof_ipc4_timestamp_info {
- struct sof_ipc4_copier *host_copier;
- struct sof_ipc4_copier *dai_copier;
- u64 stream_start_offset;
- u32 llp_offset;
-};
-
extern const struct sof_ipc_fw_loader_ops ipc4_loader_ops;
extern const struct sof_ipc_tplg_ops ipc4_tplg_ops;
extern const struct sof_ipc_tplg_control_ops tplg_ipc4_control_ops;
diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index f779156fe0e6..4d3d415179c0 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -412,8 +412,9 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget)
struct sof_ipc4_available_audio_format *available_fmt;
struct snd_soc_component *scomp = swidget->scomp;
struct sof_ipc4_copier *ipc4_copier;
+ struct snd_sof_pcm *spcm;
int node_type = 0;
- int ret;
+ int ret, dir;
ipc4_copier = kzalloc(sizeof(*ipc4_copier), GFP_KERNEL);
if (!ipc4_copier)
@@ -447,6 +448,25 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget)
}
dev_dbg(scomp->dev, "host copier '%s' node_type %u\n", swidget->widget->name, node_type);
+ spcm = snd_sof_find_spcm_comp(scomp, swidget->comp_id, &dir);
+ if (!spcm)
+ goto skip_gtw_cfg;
+
+ if (dir == SNDRV_PCM_STREAM_PLAYBACK) {
+ struct snd_sof_pcm_stream *sps = &spcm->stream[dir];
+
+ sof_update_ipc_object(scomp, &sps->dsp_max_burst_size_in_ms,
+ SOF_COPIER_DEEP_BUFFER_TOKENS,
+ swidget->tuples,
+ swidget->num_tuples, sizeof(u32), 1);
+ /* Set default DMA buffer size if it is not specified in topology */
+ if (!sps->dsp_max_burst_size_in_ms)
+ sps->dsp_max_burst_size_in_ms = SOF_IPC4_MIN_DMA_BUFFER_SIZE;
+ } else {
+ /* Capture data is copied from DSP to host in 1ms bursts */
+ spcm->stream[dir].dsp_max_burst_size_in_ms = 1;
+ }
+
skip_gtw_cfg:
ipc4_copier->gtw_attr = kzalloc(sizeof(*ipc4_copier->gtw_attr), GFP_KERNEL);
if (!ipc4_copier->gtw_attr) {
diff --git a/sound/soc/sof/ops.h b/sound/soc/sof/ops.h
index 6538d9f4fe96..2505a1e1ce34 100644
--- a/sound/soc/sof/ops.h
+++ b/sound/soc/sof/ops.h
@@ -523,12 +523,26 @@ static inline int snd_sof_pcm_platform_ack(struct snd_sof_dev *sdev,
return 0;
}
-static inline u64 snd_sof_pcm_get_stream_position(struct snd_sof_dev *sdev,
- struct snd_soc_component *component,
- struct snd_pcm_substream *substream)
+static inline u64
+snd_sof_pcm_get_dai_frame_counter(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
{
- if (sof_ops(sdev) && sof_ops(sdev)->get_stream_position)
- return sof_ops(sdev)->get_stream_position(sdev, component, substream);
+ if (sof_ops(sdev) && sof_ops(sdev)->get_dai_frame_counter)
+ return sof_ops(sdev)->get_dai_frame_counter(sdev, component,
+ substream);
+
+ return 0;
+}
+
+static inline u64
+snd_sof_pcm_get_host_byte_counter(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
+{
+ if (sof_ops(sdev) && sof_ops(sdev)->get_host_byte_counter)
+ return sof_ops(sdev)->get_host_byte_counter(sdev, component,
+ substream);
return 0;
}
diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c
index 33d576b17647..f03cee94bce6 100644
--- a/sound/soc/sof/pcm.c
+++ b/sound/soc/sof/pcm.c
@@ -388,13 +388,21 @@ static snd_pcm_uframes_t sof_pcm_pointer(struct snd_soc_component *component,
{
struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
+ const struct sof_ipc_pcm_ops *pcm_ops = sof_ipc_get_ops(sdev, pcm);
struct snd_sof_pcm *spcm;
snd_pcm_uframes_t host, dai;
+ int ret = -EOPNOTSUPP;
/* nothing to do for BE */
if (rtd->dai_link->no_pcm)
return 0;
+ if (pcm_ops && pcm_ops->pointer)
+ ret = pcm_ops->pointer(component, substream, &host);
+
+ if (ret != -EOPNOTSUPP)
+ return ret ? ret : host;
+
/* use dsp ops pointer callback directly if set */
if (sof_ops(sdev)->pcm_pointer)
return sof_ops(sdev)->pcm_pointer(sdev, substream);
diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index 8874ee5f557f..85b26e3fefa8 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -103,7 +103,10 @@ struct snd_sof_dai_config_data {
* additional memory in the SOF PCM stream structure
* @pcm_free: Function pointer for PCM free that can be used for freeing any
* additional memory in the SOF PCM stream structure
- * @delay: Function pointer for pcm delay calculation
+ * @pointer: Function pointer for pcm pointer
+ * Note: the @pointer callback may return -EOPNOTSUPP which should be
+ * handled in a same way as if the callback is not provided
+ * @delay: Function pointer for pcm delay reporting
* @reset_hw_params_during_stop: Flag indicating whether the hw_params should be reset during the
* STOP pcm trigger
* @ipc_first_on_start: Send IPC before invoking platform trigger during
@@ -124,6 +127,9 @@ struct sof_ipc_pcm_ops {
int (*dai_link_fixup)(struct snd_soc_pcm_runtime *rtd, struct snd_pcm_hw_params *params);
int (*pcm_setup)(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm);
void (*pcm_free)(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm);
+ int (*pointer)(struct snd_soc_component *component,
+ struct snd_pcm_substream *substream,
+ snd_pcm_uframes_t *pointer);
snd_pcm_sframes_t (*delay)(struct snd_soc_component *component,
struct snd_pcm_substream *substream);
bool reset_hw_params_during_stop;
@@ -321,6 +327,7 @@ struct snd_sof_pcm_stream {
struct work_struct period_elapsed_work;
struct snd_soc_dapm_widget_list *list; /* list of connected DAPM widgets */
bool d0i3_compatible; /* DSP can be in D0I3 when this pcm is opened */
+ unsigned int dsp_max_burst_size_in_ms; /* The maximum size of the host DMA burst in ms */
/*
* flag to indicate that the DSP pipelines should be kept
* active or not while suspending the stream
diff --git a/sound/soc/sof/sof-priv.h b/sound/soc/sof/sof-priv.h
index 6d7897bf9607..09eb2de445fe 100644
--- a/sound/soc/sof/sof-priv.h
+++ b/sound/soc/sof/sof-priv.h
@@ -255,13 +255,25 @@ struct snd_sof_dsp_ops {
int (*pcm_ack)(struct snd_sof_dev *sdev, struct snd_pcm_substream *substream); /* optional */
/*
- * optional callback to retrieve the link DMA position for the substream
- * when the position is not reported in the shared SRAM windows but
- * instead from a host-accessible hardware counter.
+ * optional callback to retrieve the number of frames left/arrived from/to
+ * the DSP on the DAI side (link/codec/DMIC/etc).
+ *
+ * The callback is used when the firmware does not provide this information
+ * via the shared SRAM window and it can be retrieved by host.
*/
- u64 (*get_stream_position)(struct snd_sof_dev *sdev,
- struct snd_soc_component *component,
- struct snd_pcm_substream *substream); /* optional */
+ u64 (*get_dai_frame_counter)(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream); /* optional */
+
+ /*
+ * Optional callback to retrieve the number of bytes left/arrived from/to
+ * the DSP on the host side (bytes between host ALSA buffer and DSP).
+ *
+ * The callback is needed for ALSA delay reporting.
+ */
+ u64 (*get_host_byte_counter)(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream); /* optional */
/* host read DSP stream data */
int (*ipc_msg_data)(struct snd_sof_dev *sdev,
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 7fc1aa788f6f..c19dec239491 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -243,8 +243,11 @@ class Type(SpecAttr):
presence = ''
for i in range(0, len(ref)):
presence = f"{var}->{'.'.join(ref[:i] + [''])}_present.{ref[i]}"
- if self.presence_type() == 'bit':
- code.append(presence + ' = 1;')
+ # Every layer below last is a nest, so we know it uses bit presence
+ # last layer is "self" and may be a complex type
+ if i == len(ref) - 1 and self.presence_type() != 'bit':
+ continue
+ code.append(presence + ' = 1;')
code += self._setter_lines(ri, member, presence)
func_name = f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}"
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index c02990bbd56f..9007c420d52c 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -3,7 +3,7 @@
#include <stdbool.h>
#include <sys/mman.h>
#include <err.h>
-#include <string.h> /* ffsl() */
+#include <strings.h> /* ffsl() */
#include <unistd.h> /* _SC_PAGESIZE */
#define BIT_ULL(nr) (1ULL << (nr))
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 7898d62fce0b..713de8182222 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -1,6 +1,11 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+# Double quotes to prevent globbing and word splitting is recommended in new
+# code but we accept it, especially because there were too many before having
+# address all other issues detected by shellcheck.
+#shellcheck disable=SC2086
+
. "$(dirname "${0}")/mptcp_lib.sh"
time_start=$(date +%s)
@@ -13,7 +18,6 @@ sout=""
cin_disconnect=""
cin=""
cout=""
-ksft_skip=4
capture=false
timeout_poll=30
timeout_test=$((timeout_poll * 2 + 1))
@@ -131,6 +135,8 @@ ns4="ns4-$rndh"
TEST_COUNT=0
TEST_GROUP=""
+# This function is used in the cleanup trap
+#shellcheck disable=SC2317
cleanup()
{
rm -f "$cin_disconnect" "$cout_disconnect"
@@ -225,8 +231,9 @@ set_ethtool_flags() {
local dev="$2"
local flags="$3"
- ip netns exec $ns ethtool -K $dev $flags 2>/dev/null
- [ $? -eq 0 ] && echo "INFO: set $ns dev $dev: ethtool -K $flags"
+ if ip netns exec $ns ethtool -K $dev $flags 2>/dev/null; then
+ echo "INFO: set $ns dev $dev: ethtool -K $flags"
+ fi
}
set_random_ethtool_flags() {
@@ -321,19 +328,19 @@ do_transfer()
local extra_args="$7"
local port
- port=$((10000+$TEST_COUNT))
+ port=$((10000+TEST_COUNT))
TEST_COUNT=$((TEST_COUNT+1))
if [ "$rcvbuf" -gt 0 ]; then
- extra_args="$extra_args -R $rcvbuf"
+ extra_args+=" -R $rcvbuf"
fi
if [ "$sndbuf" -gt 0 ]; then
- extra_args="$extra_args -S $sndbuf"
+ extra_args+=" -S $sndbuf"
fi
if [ -n "$testmode" ]; then
- extra_args="$extra_args -m $testmode"
+ extra_args+=" -m $testmode"
fi
if [ -n "$extra_args" ] && $options_log; then
@@ -378,12 +385,20 @@ do_transfer()
nstat -n
fi
- local stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
- local stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
- local stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
- local stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
- local stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
- local stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+ local stat_synrx_last_l
+ local stat_ackrx_last_l
+ local stat_cookietx_last
+ local stat_cookierx_last
+ local stat_csum_err_s
+ local stat_csum_err_c
+ local stat_tcpfb_last_l
+ stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
+ stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
+ stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
+ stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
+ stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
+ stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+ stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
timeout ${timeout_test} \
ip netns exec ${listener_ns} \
@@ -446,11 +461,19 @@ do_transfer()
mptcp_lib_check_transfer $cin $sout "file received by server"
rets=$?
- local stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
- local stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
- local stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
- local stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
- local stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue")
+ local extra=""
+ local stat_synrx_now_l
+ local stat_ackrx_now_l
+ local stat_cookietx_now
+ local stat_cookierx_now
+ local stat_ooo_now
+ local stat_tcpfb_now_l
+ stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
+ stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
+ stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent")
+ stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv")
+ stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue")
+ stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK")
expect_synrx=$((stat_synrx_last_l))
expect_ackrx=$((stat_ackrx_last_l))
@@ -459,8 +482,8 @@ do_transfer()
cookies=${cookies##*=}
if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then
- expect_synrx=$((stat_synrx_last_l+$connect_per_transfer))
- expect_ackrx=$((stat_ackrx_last_l+$connect_per_transfer))
+ expect_synrx=$((stat_synrx_last_l+connect_per_transfer))
+ expect_ackrx=$((stat_ackrx_last_l+connect_per_transfer))
fi
if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then
@@ -468,66 +491,75 @@ do_transfer()
"${stat_synrx_now_l}" "${expect_synrx}" 1>&2
retc=1
fi
- if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then
+ if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ] && [ ${stat_ooo_now} -eq 0 ]; then
if [ ${stat_ooo_now} -eq 0 ]; then
printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \
"${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2
rets=1
else
- printf "[ Note ] fallback due to TCP OoO"
+ extra+=" [ Note ] fallback due to TCP OoO"
fi
fi
if $checksum; then
- local csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
- local csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
+ local csum_err_s
+ local csum_err_c
+ csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr")
+ csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr")
local csum_err_s_nr=$((csum_err_s - stat_csum_err_s))
if [ $csum_err_s_nr -gt 0 ]; then
- printf "[ FAIL ]\nserver got $csum_err_s_nr data checksum error[s]"
+ printf "[ FAIL ]\nserver got %d data checksum error[s]" ${csum_err_s_nr}
rets=1
fi
local csum_err_c_nr=$((csum_err_c - stat_csum_err_c))
if [ $csum_err_c_nr -gt 0 ]; then
- printf "[ FAIL ]\nclient got $csum_err_c_nr data checksum error[s]"
+ printf "[ FAIL ]\nclient got %d data checksum error[s]" ${csum_err_c_nr}
retc=1
fi
fi
- if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then
- printf "[ OK ]"
- mptcp_lib_result_pass "${TEST_GROUP}: ${result_msg}"
- else
- mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}"
+ if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then
+ mptcp_lib_pr_fail "unexpected fallback to TCP"
+ rets=1
fi
if [ $cookies -eq 2 ];then
if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then
- printf " WARN: CookieSent: did not advance"
+ extra+=" WARN: CookieSent: did not advance"
fi
if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then
- printf " WARN: CookieRecv: did not advance"
+ extra+=" WARN: CookieRecv: did not advance"
fi
else
if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then
- printf " WARN: CookieSent: changed"
+ extra+=" WARN: CookieSent: changed"
fi
if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then
- printf " WARN: CookieRecv: changed"
+ extra+=" WARN: CookieRecv: changed"
fi
fi
if [ ${stat_synrx_now_l} -gt ${expect_synrx} ]; then
- printf " WARN: SYNRX: expect %d, got %d (probably retransmissions)" \
- "${expect_synrx}" "${stat_synrx_now_l}"
+ extra+=" WARN: SYNRX: expect ${expect_synrx},"
+ extra+=" got ${stat_synrx_now_l} (probably retransmissions)"
fi
if [ ${stat_ackrx_now_l} -gt ${expect_ackrx} ]; then
- printf " WARN: ACKRX: expect %d, got %d (probably retransmissions)" \
- "${expect_ackrx}" "${stat_ackrx_now_l}"
+ extra+=" WARN: ACKRX: expect ${expect_ackrx},"
+ extra+=" got ${stat_ackrx_now_l} (probably retransmissions)"
+ fi
+
+ if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then
+ printf "[ OK ]%s\n" "${extra:1}"
+ mptcp_lib_result_pass "${TEST_GROUP}: ${result_msg}"
+ else
+ if [ -n "${extra}" ]; then
+ printf "%s\n" "${extra:1}"
+ fi
+ mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}"
fi
- echo
cat "$capout"
[ $retc -eq 0 ] && [ $rets -eq 0 ]
}
@@ -658,7 +690,7 @@ run_test_transparent()
return
fi
-ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF"
+ if ! ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF"
flush ruleset
table inet mangle {
chain divert {
@@ -669,7 +701,7 @@ table inet mangle {
}
}
EOF
- if [ $? -ne 0 ]; then
+ then
echo "SKIP: $msg, could not load nft ruleset"
mptcp_lib_fail_if_expected_feature "nft rules"
mptcp_lib_result_skip "${TEST_GROUP}"
@@ -684,8 +716,7 @@ EOF
local_addr="0.0.0.0"
fi
- ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100
- if [ $? -ne 0 ]; then
+ if ! ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100; then
ip netns exec "$listener_ns" nft flush ruleset
echo "SKIP: $msg, ip $r6flag rule failed"
mptcp_lib_fail_if_expected_feature "ip rule"
@@ -693,8 +724,7 @@ EOF
return
fi
- ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100
- if [ $? -ne 0 ]; then
+ if ! ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100; then
ip netns exec "$listener_ns" nft flush ruleset
ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100
echo "SKIP: $msg, ip route add local $local_addr failed"
@@ -854,10 +884,10 @@ mptcp_lib_result_code "${ret}" "ping tests"
stop_if_error "Could not even run ping tests"
[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms
-echo -n "INFO: Using loss of $tc_loss "
-test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms "
+tc_info="loss of $tc_loss "
+test "$tc_delay" -gt 0 && tc_info+="delay $tc_delay ms "
-reorder_delay=$(($tc_delay / 4))
+reorder_delay=$((tc_delay / 4))
if [ -z "${tc_reorder}" ]; then
reorder1=$((RANDOM%10))
@@ -866,17 +896,17 @@ if [ -z "${tc_reorder}" ]; then
if [ $reorder_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then
tc_reorder="reorder ${reorder1}% ${reorder2}%"
- echo -n "$tc_reorder with delay ${reorder_delay}ms "
+ tc_info+="$tc_reorder with delay ${reorder_delay}ms "
fi
elif [ "$tc_reorder" = "0" ];then
tc_reorder=""
elif [ "$reorder_delay" -gt 0 ];then
# reordering requires some delay
tc_reorder="reorder $tc_reorder"
- echo -n "$tc_reorder with delay ${reorder_delay}ms "
+ tc_info+="$tc_reorder with delay ${reorder_delay}ms "
fi
-echo "on ns3eth4"
+echo "INFO: Using ${tc_info}on ns3eth4"
tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index e4581b0dfb96..24be952b4d4a 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -773,7 +773,7 @@ pm_nl_check_endpoint()
[ -n "$_flags" ]; flags="flags $_flags"
shift
elif [ $1 = "dev" ]; then
- [ -n "$2" ]; dev="dev $1"
+ [ -n "$2" ]; dev="dev $2"
shift
elif [ $1 = "id" ]; then
_id=$2
@@ -799,18 +799,18 @@ pm_nl_check_endpoint()
line="${line% }"
# the dump order is: address id flags port dev
[ -n "$addr" ] && expected_line="$addr"
- expected_line="$expected_line $id"
- [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}"
- [ -n "$dev" ] && expected_line="$expected_line $dev"
- [ -n "$port" ] && expected_line="$expected_line $port"
+ expected_line+=" $id"
+ [ -n "$_flags" ] && expected_line+=" ${_flags//","/" "}"
+ [ -n "$dev" ] && expected_line+=" $dev"
+ [ -n "$port" ] && expected_line+=" $port"
else
line=$(ip netns exec $ns ./pm_nl_ctl get $_id)
# the dump order is: id flags dev address port
expected_line="$id"
- [ -n "$flags" ] && expected_line="$expected_line $flags"
- [ -n "$dev" ] && expected_line="$expected_line $dev"
- [ -n "$addr" ] && expected_line="$expected_line $addr"
- [ -n "$_port" ] && expected_line="$expected_line $_port"
+ [ -n "$flags" ] && expected_line+=" $flags"
+ [ -n "$dev" ] && expected_line+=" $dev"
+ [ -n "$addr" ] && expected_line+=" $addr"
+ [ -n "$_port" ] && expected_line+=" $_port"
fi
if [ "$line" = "$expected_line" ]; then
print_ok
@@ -1261,7 +1261,7 @@ chk_csum_nr()
print_check "sum"
count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr")
if [ "$count" != "$csum_ns1" ]; then
- extra_msg="$extra_msg ns1=$count"
+ extra_msg+=" ns1=$count"
fi
if [ -z "$count" ]; then
print_skip
@@ -1274,7 +1274,7 @@ chk_csum_nr()
print_check "csum"
count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr")
if [ "$count" != "$csum_ns2" ]; then
- extra_msg="$extra_msg ns2=$count"
+ extra_msg+=" ns2=$count"
fi
if [ -z "$count" ]; then
print_skip
@@ -1318,7 +1318,7 @@ chk_fail_nr()
print_check "ftx"
count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx")
if [ "$count" != "$fail_tx" ]; then
- extra_msg="$extra_msg,tx=$count"
+ extra_msg+=",tx=$count"
fi
if [ -z "$count" ]; then
print_skip
@@ -1332,7 +1332,7 @@ chk_fail_nr()
print_check "failrx"
count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx")
if [ "$count" != "$fail_rx" ]; then
- extra_msg="$extra_msg,rx=$count"
+ extra_msg+=",rx=$count"
fi
if [ -z "$count" ]; then
print_skip
@@ -1367,7 +1367,7 @@ chk_fclose_nr()
if [ -z "$count" ]; then
print_skip
elif [ "$count" != "$fclose_tx" ]; then
- extra_msg="$extra_msg,tx=$count"
+ extra_msg+=",tx=$count"
fail_test "got $count MP_FASTCLOSE[s] TX expected $fclose_tx"
else
print_ok
@@ -1378,7 +1378,7 @@ chk_fclose_nr()
if [ -z "$count" ]; then
print_skip
elif [ "$count" != "$fclose_rx" ]; then
- extra_msg="$extra_msg,rx=$count"
+ extra_msg+=",rx=$count"
fail_test "got $count MP_FASTCLOSE[s] RX expected $fclose_rx"
else
print_ok
@@ -1747,7 +1747,7 @@ chk_rm_nr()
count=$((count + cnt))
if [ "$count" != "$rm_subflow_nr" ]; then
suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]"
- extra_msg="$extra_msg simult"
+ extra_msg+=" simult"
fi
if [ $count -ge "$rm_subflow_nr" ] && \
[ "$count" -le "$((rm_subflow_nr *2 ))" ]; then
@@ -3589,6 +3589,8 @@ endpoint_tests()
local tests_pid=$!
wait_mpj $ns2
+ pm_nl_check_endpoint "creation" \
+ $ns2 10.0.2.2 id 2 flags subflow dev ns2eth2
chk_subflow_nr "before delete" 2
chk_mptcp_info subflows 1 subflows 1
diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c
index 7c5b12664b03..bfb07dc49518 100644
--- a/tools/testing/selftests/net/reuseaddr_conflict.c
+++ b/tools/testing/selftests/net/reuseaddr_conflict.c
@@ -109,6 +109,6 @@ int main(void)
fd1 = open_port(0, 1);
if (fd1 >= 0)
error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6");
- fprintf(stderr, "Success");
+ fprintf(stderr, "Success\n");
return 0;
}
diff --git a/tools/testing/selftests/net/test_vxlan_mdb.sh b/tools/testing/selftests/net/test_vxlan_mdb.sh
index 84a05a9e46d8..04fb17a92e99 100755
--- a/tools/testing/selftests/net/test_vxlan_mdb.sh
+++ b/tools/testing/selftests/net/test_vxlan_mdb.sh
@@ -1177,6 +1177,7 @@ encap_params_common()
local plen=$1; shift
local enc_ethtype=$1; shift
local grp=$1; shift
+ local grp_dmac=$1; shift
local src=$1; shift
local mz=$1; shift
@@ -1195,11 +1196,11 @@ encap_params_common()
run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent dst $vtep2_ip src_vni 10020"
run_cmd "tc -n $ns2 filter replace dev vx0 ingress pref 1 handle 101 proto all flower enc_dst_ip $vtep1_ip action pass"
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Destination IP - match"
- run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Destination IP - no match"
@@ -1212,20 +1213,20 @@ encap_params_common()
run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent dst $vtep1_ip dst_port 1111 src_vni 10020"
run_cmd "tc -n $ns2 filter replace dev veth0 ingress pref 1 handle 101 proto $enc_ethtype flower ip_proto udp dst_port 4789 action pass"
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev veth0 ingress" 101 1
log_test $? 0 "Default destination port - match"
- run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev veth0 ingress" 101 1
log_test $? 0 "Default destination port - no match"
run_cmd "tc -n $ns2 filter replace dev veth0 ingress pref 1 handle 101 proto $enc_ethtype flower ip_proto udp dst_port 1111 action pass"
- run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev veth0 ingress" 101 1
log_test $? 0 "Non-default destination port - match"
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev veth0 ingress" 101 1
log_test $? 0 "Non-default destination port - no match"
@@ -1238,11 +1239,11 @@ encap_params_common()
run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent dst $vtep1_ip src_vni 10020"
run_cmd "tc -n $ns2 filter replace dev vx0 ingress pref 1 handle 101 proto all flower enc_key_id 10010 action pass"
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Default destination VNI - match"
- run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Default destination VNI - no match"
@@ -1250,11 +1251,11 @@ encap_params_common()
run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent dst $vtep1_ip vni 10010 src_vni 10020"
run_cmd "tc -n $ns2 filter replace dev vx0 ingress pref 1 handle 101 proto all flower enc_key_id 10020 action pass"
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Non-default destination VNI - match"
- run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Non-default destination VNI - no match"
@@ -1272,6 +1273,7 @@ encap_params_ipv4_ipv4()
local plen=32
local enc_ethtype="ip"
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local src=192.0.2.129
echo
@@ -1279,7 +1281,7 @@ encap_params_ipv4_ipv4()
echo "------------------------------------------------------------------"
encap_params_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $enc_ethtype \
- $grp $src "mausezahn"
+ $grp $grp_dmac $src "mausezahn"
}
encap_params_ipv6_ipv4()
@@ -1291,6 +1293,7 @@ encap_params_ipv6_ipv4()
local plen=32
local enc_ethtype="ip"
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local src=2001:db8:100::1
echo
@@ -1298,7 +1301,7 @@ encap_params_ipv6_ipv4()
echo "------------------------------------------------------------------"
encap_params_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $enc_ethtype \
- $grp $src "mausezahn -6"
+ $grp $grp_dmac $src "mausezahn -6"
}
encap_params_ipv4_ipv6()
@@ -1310,6 +1313,7 @@ encap_params_ipv4_ipv6()
local plen=128
local enc_ethtype="ipv6"
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local src=192.0.2.129
echo
@@ -1317,7 +1321,7 @@ encap_params_ipv4_ipv6()
echo "------------------------------------------------------------------"
encap_params_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $enc_ethtype \
- $grp $src "mausezahn"
+ $grp $grp_dmac $src "mausezahn"
}
encap_params_ipv6_ipv6()
@@ -1329,6 +1333,7 @@ encap_params_ipv6_ipv6()
local plen=128
local enc_ethtype="ipv6"
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local src=2001:db8:100::1
echo
@@ -1336,7 +1341,7 @@ encap_params_ipv6_ipv6()
echo "------------------------------------------------------------------"
encap_params_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $enc_ethtype \
- $grp $src "mausezahn -6"
+ $grp $grp_dmac $src "mausezahn -6"
}
starg_exclude_ir_common()
@@ -1347,6 +1352,7 @@ starg_exclude_ir_common()
local vtep2_ip=$1; shift
local plen=$1; shift
local grp=$1; shift
+ local grp_dmac=$1; shift
local valid_src=$1; shift
local invalid_src=$1; shift
local mz=$1; shift
@@ -1368,14 +1374,14 @@ starg_exclude_ir_common()
run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $invalid_src dst $vtep2_ip src_vni 10010"
# Check that invalid source is not forwarded to any VTEP.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 0
log_test $? 0 "Block excluded source - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 0
log_test $? 0 "Block excluded source - second VTEP"
# Check that valid source is forwarded to both VTEPs.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Forward valid source - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 1
@@ -1385,14 +1391,14 @@ starg_exclude_ir_common()
run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep2_ip src_vni 10010"
# Check that invalid source is not forwarded to any VTEP.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Block excluded source after removal - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 1
log_test $? 0 "Block excluded source after removal - second VTEP"
# Check that valid source is forwarded to the remaining VTEP.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 2
log_test $? 0 "Forward valid source after removal - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 1
@@ -1407,6 +1413,7 @@ starg_exclude_ir_ipv4_ipv4()
local vtep2_ip=198.51.100.200
local plen=32
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local valid_src=192.0.2.129
local invalid_src=192.0.2.145
@@ -1415,7 +1422,7 @@ starg_exclude_ir_ipv4_ipv4()
echo "-------------------------------------------------------------"
starg_exclude_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \
- $valid_src $invalid_src "mausezahn"
+ $grp_dmac $valid_src $invalid_src "mausezahn"
}
starg_exclude_ir_ipv6_ipv4()
@@ -1426,6 +1433,7 @@ starg_exclude_ir_ipv6_ipv4()
local vtep2_ip=198.51.100.200
local plen=32
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local valid_src=2001:db8:100::1
local invalid_src=2001:db8:200::1
@@ -1434,7 +1442,7 @@ starg_exclude_ir_ipv6_ipv4()
echo "-------------------------------------------------------------"
starg_exclude_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \
- $valid_src $invalid_src "mausezahn -6"
+ $grp_dmac $valid_src $invalid_src "mausezahn -6"
}
starg_exclude_ir_ipv4_ipv6()
@@ -1445,6 +1453,7 @@ starg_exclude_ir_ipv4_ipv6()
local vtep2_ip=2001:db8:2000::1
local plen=128
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local valid_src=192.0.2.129
local invalid_src=192.0.2.145
@@ -1453,7 +1462,7 @@ starg_exclude_ir_ipv4_ipv6()
echo "-------------------------------------------------------------"
starg_exclude_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \
- $valid_src $invalid_src "mausezahn"
+ $grp_dmac $valid_src $invalid_src "mausezahn"
}
starg_exclude_ir_ipv6_ipv6()
@@ -1464,6 +1473,7 @@ starg_exclude_ir_ipv6_ipv6()
local vtep2_ip=2001:db8:2000::1
local plen=128
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local valid_src=2001:db8:100::1
local invalid_src=2001:db8:200::1
@@ -1472,7 +1482,7 @@ starg_exclude_ir_ipv6_ipv6()
echo "-------------------------------------------------------------"
starg_exclude_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \
- $valid_src $invalid_src "mausezahn -6"
+ $grp_dmac $valid_src $invalid_src "mausezahn -6"
}
starg_include_ir_common()
@@ -1483,6 +1493,7 @@ starg_include_ir_common()
local vtep2_ip=$1; shift
local plen=$1; shift
local grp=$1; shift
+ local grp_dmac=$1; shift
local valid_src=$1; shift
local invalid_src=$1; shift
local mz=$1; shift
@@ -1504,14 +1515,14 @@ starg_include_ir_common()
run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode include source_list $valid_src dst $vtep2_ip src_vni 10010"
# Check that invalid source is not forwarded to any VTEP.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 0
log_test $? 0 "Block excluded source - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 0
log_test $? 0 "Block excluded source - second VTEP"
# Check that valid source is forwarded to both VTEPs.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Forward valid source - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 1
@@ -1521,14 +1532,14 @@ starg_include_ir_common()
run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep2_ip src_vni 10010"
# Check that invalid source is not forwarded to any VTEP.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Block excluded source after removal - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 1
log_test $? 0 "Block excluded source after removal - second VTEP"
# Check that valid source is forwarded to the remaining VTEP.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 2
log_test $? 0 "Forward valid source after removal - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 1
@@ -1543,6 +1554,7 @@ starg_include_ir_ipv4_ipv4()
local vtep2_ip=198.51.100.200
local plen=32
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local valid_src=192.0.2.129
local invalid_src=192.0.2.145
@@ -1551,7 +1563,7 @@ starg_include_ir_ipv4_ipv4()
echo "-------------------------------------------------------------"
starg_include_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \
- $valid_src $invalid_src "mausezahn"
+ $grp_dmac $valid_src $invalid_src "mausezahn"
}
starg_include_ir_ipv6_ipv4()
@@ -1562,6 +1574,7 @@ starg_include_ir_ipv6_ipv4()
local vtep2_ip=198.51.100.200
local plen=32
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local valid_src=2001:db8:100::1
local invalid_src=2001:db8:200::1
@@ -1570,7 +1583,7 @@ starg_include_ir_ipv6_ipv4()
echo "-------------------------------------------------------------"
starg_include_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \
- $valid_src $invalid_src "mausezahn -6"
+ $grp_dmac $valid_src $invalid_src "mausezahn -6"
}
starg_include_ir_ipv4_ipv6()
@@ -1581,6 +1594,7 @@ starg_include_ir_ipv4_ipv6()
local vtep2_ip=2001:db8:2000::1
local plen=128
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local valid_src=192.0.2.129
local invalid_src=192.0.2.145
@@ -1589,7 +1603,7 @@ starg_include_ir_ipv4_ipv6()
echo "-------------------------------------------------------------"
starg_include_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \
- $valid_src $invalid_src "mausezahn"
+ $grp_dmac $valid_src $invalid_src "mausezahn"
}
starg_include_ir_ipv6_ipv6()
@@ -1600,6 +1614,7 @@ starg_include_ir_ipv6_ipv6()
local vtep2_ip=2001:db8:2000::1
local plen=128
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local valid_src=2001:db8:100::1
local invalid_src=2001:db8:200::1
@@ -1608,7 +1623,7 @@ starg_include_ir_ipv6_ipv6()
echo "-------------------------------------------------------------"
starg_include_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \
- $valid_src $invalid_src "mausezahn -6"
+ $grp_dmac $valid_src $invalid_src "mausezahn -6"
}
starg_exclude_p2mp_common()
@@ -1618,6 +1633,7 @@ starg_exclude_p2mp_common()
local mcast_grp=$1; shift
local plen=$1; shift
local grp=$1; shift
+ local grp_dmac=$1; shift
local valid_src=$1; shift
local invalid_src=$1; shift
local mz=$1; shift
@@ -1635,12 +1651,12 @@ starg_exclude_p2mp_common()
run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $invalid_src dst $mcast_grp src_vni 10010 via veth0"
# Check that invalid source is not forwarded.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 0
log_test $? 0 "Block excluded source"
# Check that valid source is forwarded.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Forward valid source"
@@ -1648,7 +1664,7 @@ starg_exclude_p2mp_common()
run_cmd "ip -n $ns2 address del $mcast_grp/$plen dev veth0"
# Check that valid source is not received anymore.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Receive of valid source after removal from group"
}
@@ -1660,6 +1676,7 @@ starg_exclude_p2mp_ipv4_ipv4()
local mcast_grp=238.1.1.1
local plen=32
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local valid_src=192.0.2.129
local invalid_src=192.0.2.145
@@ -1667,7 +1684,7 @@ starg_exclude_p2mp_ipv4_ipv4()
echo "Data path: (*, G) EXCLUDE - P2MP - IPv4 overlay / IPv4 underlay"
echo "---------------------------------------------------------------"
- starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \
+ starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \
$valid_src $invalid_src "mausezahn"
}
@@ -1678,6 +1695,7 @@ starg_exclude_p2mp_ipv6_ipv4()
local mcast_grp=238.1.1.1
local plen=32
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local valid_src=2001:db8:100::1
local invalid_src=2001:db8:200::1
@@ -1685,7 +1703,7 @@ starg_exclude_p2mp_ipv6_ipv4()
echo "Data path: (*, G) EXCLUDE - P2MP - IPv6 overlay / IPv4 underlay"
echo "---------------------------------------------------------------"
- starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \
+ starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \
$valid_src $invalid_src "mausezahn -6"
}
@@ -1696,6 +1714,7 @@ starg_exclude_p2mp_ipv4_ipv6()
local mcast_grp=ff0e::2
local plen=128
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local valid_src=192.0.2.129
local invalid_src=192.0.2.145
@@ -1703,7 +1722,7 @@ starg_exclude_p2mp_ipv4_ipv6()
echo "Data path: (*, G) EXCLUDE - P2MP - IPv4 overlay / IPv6 underlay"
echo "---------------------------------------------------------------"
- starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \
+ starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \
$valid_src $invalid_src "mausezahn"
}
@@ -1714,6 +1733,7 @@ starg_exclude_p2mp_ipv6_ipv6()
local mcast_grp=ff0e::2
local plen=128
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local valid_src=2001:db8:100::1
local invalid_src=2001:db8:200::1
@@ -1721,7 +1741,7 @@ starg_exclude_p2mp_ipv6_ipv6()
echo "Data path: (*, G) EXCLUDE - P2MP - IPv6 overlay / IPv6 underlay"
echo "---------------------------------------------------------------"
- starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \
+ starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \
$valid_src $invalid_src "mausezahn -6"
}
@@ -1732,6 +1752,7 @@ starg_include_p2mp_common()
local mcast_grp=$1; shift
local plen=$1; shift
local grp=$1; shift
+ local grp_dmac=$1; shift
local valid_src=$1; shift
local invalid_src=$1; shift
local mz=$1; shift
@@ -1749,12 +1770,12 @@ starg_include_p2mp_common()
run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode include source_list $valid_src dst $mcast_grp src_vni 10010 via veth0"
# Check that invalid source is not forwarded.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 0
log_test $? 0 "Block excluded source"
# Check that valid source is forwarded.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Forward valid source"
@@ -1762,7 +1783,7 @@ starg_include_p2mp_common()
run_cmd "ip -n $ns2 address del $mcast_grp/$plen dev veth0"
# Check that valid source is not received anymore.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Receive of valid source after removal from group"
}
@@ -1774,6 +1795,7 @@ starg_include_p2mp_ipv4_ipv4()
local mcast_grp=238.1.1.1
local plen=32
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local valid_src=192.0.2.129
local invalid_src=192.0.2.145
@@ -1781,7 +1803,7 @@ starg_include_p2mp_ipv4_ipv4()
echo "Data path: (*, G) INCLUDE - P2MP - IPv4 overlay / IPv4 underlay"
echo "---------------------------------------------------------------"
- starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \
+ starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \
$valid_src $invalid_src "mausezahn"
}
@@ -1792,6 +1814,7 @@ starg_include_p2mp_ipv6_ipv4()
local mcast_grp=238.1.1.1
local plen=32
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local valid_src=2001:db8:100::1
local invalid_src=2001:db8:200::1
@@ -1799,7 +1822,7 @@ starg_include_p2mp_ipv6_ipv4()
echo "Data path: (*, G) INCLUDE - P2MP - IPv6 overlay / IPv4 underlay"
echo "---------------------------------------------------------------"
- starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \
+ starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \
$valid_src $invalid_src "mausezahn -6"
}
@@ -1810,6 +1833,7 @@ starg_include_p2mp_ipv4_ipv6()
local mcast_grp=ff0e::2
local plen=128
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local valid_src=192.0.2.129
local invalid_src=192.0.2.145
@@ -1817,7 +1841,7 @@ starg_include_p2mp_ipv4_ipv6()
echo "Data path: (*, G) INCLUDE - P2MP - IPv4 overlay / IPv6 underlay"
echo "---------------------------------------------------------------"
- starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \
+ starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \
$valid_src $invalid_src "mausezahn"
}
@@ -1828,6 +1852,7 @@ starg_include_p2mp_ipv6_ipv6()
local mcast_grp=ff0e::2
local plen=128
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local valid_src=2001:db8:100::1
local invalid_src=2001:db8:200::1
@@ -1835,7 +1860,7 @@ starg_include_p2mp_ipv6_ipv6()
echo "Data path: (*, G) INCLUDE - P2MP - IPv6 overlay / IPv6 underlay"
echo "---------------------------------------------------------------"
- starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \
+ starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \
$valid_src $invalid_src "mausezahn -6"
}
@@ -1847,6 +1872,7 @@ egress_vni_translation_common()
local plen=$1; shift
local proto=$1; shift
local grp=$1; shift
+ local grp_dmac=$1; shift
local src=$1; shift
local mz=$1; shift
@@ -1882,20 +1908,20 @@ egress_vni_translation_common()
# Make sure that packets sent from the first VTEP over VLAN 10 are
# received by the SVI corresponding to the L3VNI (14000 / VLAN 4000) on
# the second VTEP, since it is configured as PVID.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev br0.4000 ingress" 101 1
log_test $? 0 "Egress VNI translation - PVID configured"
# Remove PVID flag from VLAN 4000 on the second VTEP and make sure
# packets are no longer received by the SVI interface.
run_cmd "bridge -n $ns2 vlan add vid 4000 dev vx0"
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev br0.4000 ingress" 101 1
log_test $? 0 "Egress VNI translation - no PVID configured"
# Reconfigure the PVID and make sure packets are received again.
run_cmd "bridge -n $ns2 vlan add vid 4000 dev vx0 pvid"
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev br0.4000 ingress" 101 2
log_test $? 0 "Egress VNI translation - PVID reconfigured"
}
@@ -1908,6 +1934,7 @@ egress_vni_translation_ipv4_ipv4()
local plen=32
local proto="ipv4"
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local src=192.0.2.129
echo
@@ -1915,7 +1942,7 @@ egress_vni_translation_ipv4_ipv4()
echo "----------------------------------------------------------------"
egress_vni_translation_common $ns1 $ns2 $mcast_grp $plen $proto $grp \
- $src "mausezahn"
+ $grp_dmac $src "mausezahn"
}
egress_vni_translation_ipv6_ipv4()
@@ -1926,6 +1953,7 @@ egress_vni_translation_ipv6_ipv4()
local plen=32
local proto="ipv6"
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local src=2001:db8:100::1
echo
@@ -1933,7 +1961,7 @@ egress_vni_translation_ipv6_ipv4()
echo "----------------------------------------------------------------"
egress_vni_translation_common $ns1 $ns2 $mcast_grp $plen $proto $grp \
- $src "mausezahn -6"
+ $grp_dmac $src "mausezahn -6"
}
egress_vni_translation_ipv4_ipv6()
@@ -1944,6 +1972,7 @@ egress_vni_translation_ipv4_ipv6()
local plen=128
local proto="ipv4"
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local src=192.0.2.129
echo
@@ -1951,7 +1980,7 @@ egress_vni_translation_ipv4_ipv6()
echo "----------------------------------------------------------------"
egress_vni_translation_common $ns1 $ns2 $mcast_grp $plen $proto $grp \
- $src "mausezahn"
+ $grp_dmac $src "mausezahn"
}
egress_vni_translation_ipv6_ipv6()
@@ -1962,6 +1991,7 @@ egress_vni_translation_ipv6_ipv6()
local plen=128
local proto="ipv6"
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local src=2001:db8:100::1
echo
@@ -1969,7 +1999,7 @@ egress_vni_translation_ipv6_ipv6()
echo "----------------------------------------------------------------"
egress_vni_translation_common $ns1 $ns2 $mcast_grp $plen $proto $grp \
- $src "mausezahn -6"
+ $grp_dmac $src "mausezahn -6"
}
all_zeros_mdb_common()
@@ -1982,12 +2012,18 @@ all_zeros_mdb_common()
local vtep4_ip=$1; shift
local plen=$1; shift
local ipv4_grp=239.1.1.1
+ local ipv4_grp_dmac=01:00:5e:01:01:01
local ipv4_unreg_grp=239.2.2.2
+ local ipv4_unreg_grp_dmac=01:00:5e:02:02:02
local ipv4_ll_grp=224.0.0.100
+ local ipv4_ll_grp_dmac=01:00:5e:00:00:64
local ipv4_src=192.0.2.129
local ipv6_grp=ff0e::1
+ local ipv6_grp_dmac=33:33:00:00:00:01
local ipv6_unreg_grp=ff0e::2
+ local ipv6_unreg_grp_dmac=33:33:00:00:00:02
local ipv6_ll_grp=ff02::1
+ local ipv6_ll_grp_dmac=33:33:00:00:00:01
local ipv6_src=2001:db8:100::1
# Install all-zeros (catchall) MDB entries for IPv4 and IPv6 traffic
@@ -2023,7 +2059,7 @@ all_zeros_mdb_common()
# Send registered IPv4 multicast and make sure it only arrives to the
# first VTEP.
- run_cmd "ip netns exec $ns1 mausezahn br0.10 -A $ipv4_src -B $ipv4_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 mausezahn br0.10 -a own -b $ipv4_grp_dmac -A $ipv4_src -B $ipv4_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "Registered IPv4 multicast - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 0
@@ -2031,7 +2067,7 @@ all_zeros_mdb_common()
# Send unregistered IPv4 multicast that is not link-local and make sure
# it arrives to the first and second VTEPs.
- run_cmd "ip netns exec $ns1 mausezahn br0.10 -A $ipv4_src -B $ipv4_unreg_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 mausezahn br0.10 -a own -b $ipv4_unreg_grp_dmac -A $ipv4_src -B $ipv4_unreg_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 2
log_test $? 0 "Unregistered IPv4 multicast - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 1
@@ -2039,7 +2075,7 @@ all_zeros_mdb_common()
# Send IPv4 link-local multicast traffic and make sure it does not
# arrive to any VTEP.
- run_cmd "ip netns exec $ns1 mausezahn br0.10 -A $ipv4_src -B $ipv4_ll_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 mausezahn br0.10 -a own -b $ipv4_ll_grp_dmac -A $ipv4_src -B $ipv4_ll_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 2
log_test $? 0 "Link-local IPv4 multicast - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 1
@@ -2074,7 +2110,7 @@ all_zeros_mdb_common()
# Send registered IPv6 multicast and make sure it only arrives to the
# third VTEP.
- run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -A $ipv6_src -B $ipv6_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -a own -b $ipv6_grp_dmac -A $ipv6_src -B $ipv6_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 103 1
log_test $? 0 "Registered IPv6 multicast - third VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 104 0
@@ -2082,7 +2118,7 @@ all_zeros_mdb_common()
# Send unregistered IPv6 multicast that is not link-local and make sure
# it arrives to the third and fourth VTEPs.
- run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -A $ipv6_src -B $ipv6_unreg_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -a own -b $ipv6_unreg_grp_dmac -A $ipv6_src -B $ipv6_unreg_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 103 2
log_test $? 0 "Unregistered IPv6 multicast - third VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 104 1
@@ -2090,7 +2126,7 @@ all_zeros_mdb_common()
# Send IPv6 link-local multicast traffic and make sure it does not
# arrive to any VTEP.
- run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -A $ipv6_src -B $ipv6_ll_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -a own -b $ipv6_ll_grp_dmac -A $ipv6_src -B $ipv6_ll_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 103 2
log_test $? 0 "Link-local IPv6 multicast - third VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 104 1
@@ -2165,6 +2201,7 @@ mdb_fdb_common()
local plen=$1; shift
local proto=$1; shift
local grp=$1; shift
+ local grp_dmac=$1; shift
local src=$1; shift
local mz=$1; shift
@@ -2188,7 +2225,7 @@ mdb_fdb_common()
# Send IP multicast traffic and make sure it is forwarded by the MDB
# and only arrives to the first VTEP.
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "IP multicast - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 0
@@ -2205,7 +2242,7 @@ mdb_fdb_common()
# Remove the MDB entry and make sure that IP multicast is now forwarded
# by the FDB to the second VTEP.
run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep1_ip src_vni 10010"
- run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
+ run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q"
tc_check_packets "$ns2" "dev vx0 ingress" 101 1
log_test $? 0 "IP multicast after removal - first VTEP"
tc_check_packets "$ns2" "dev vx0 ingress" 102 2
@@ -2221,14 +2258,15 @@ mdb_fdb_ipv4_ipv4()
local plen=32
local proto="ipv4"
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local src=192.0.2.129
echo
echo "Data path: MDB with FDB - IPv4 overlay / IPv4 underlay"
echo "------------------------------------------------------"
- mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp $src \
- "mausezahn"
+ mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp \
+ $grp_dmac $src "mausezahn"
}
mdb_fdb_ipv6_ipv4()
@@ -2240,14 +2278,15 @@ mdb_fdb_ipv6_ipv4()
local plen=32
local proto="ipv6"
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local src=2001:db8:100::1
echo
echo "Data path: MDB with FDB - IPv6 overlay / IPv4 underlay"
echo "------------------------------------------------------"
- mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp $src \
- "mausezahn -6"
+ mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp \
+ $grp_dmac $src "mausezahn -6"
}
mdb_fdb_ipv4_ipv6()
@@ -2259,14 +2298,15 @@ mdb_fdb_ipv4_ipv6()
local plen=128
local proto="ipv4"
local grp=239.1.1.1
+ local grp_dmac=01:00:5e:01:01:01
local src=192.0.2.129
echo
echo "Data path: MDB with FDB - IPv4 overlay / IPv6 underlay"
echo "------------------------------------------------------"
- mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp $src \
- "mausezahn"
+ mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp \
+ $grp_dmac $src "mausezahn"
}
mdb_fdb_ipv6_ipv6()
@@ -2278,14 +2318,15 @@ mdb_fdb_ipv6_ipv6()
local plen=128
local proto="ipv6"
local grp=ff0e::1
+ local grp_dmac=33:33:00:00:00:01
local src=2001:db8:100::1
echo
echo "Data path: MDB with FDB - IPv6 overlay / IPv6 underlay"
echo "------------------------------------------------------"
- mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp $src \
- "mausezahn -6"
+ mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp \
+ $grp_dmac $src "mausezahn -6"
}
mdb_grp1_loop()
@@ -2320,7 +2361,9 @@ mdb_torture_common()
local vtep1_ip=$1; shift
local vtep2_ip=$1; shift
local grp1=$1; shift
+ local grp1_dmac=$1; shift
local grp2=$1; shift
+ local grp2_dmac=$1; shift
local src=$1; shift
local mz=$1; shift
local pid1
@@ -2345,9 +2388,9 @@ mdb_torture_common()
pid1=$!
mdb_grp2_loop $ns1 $vtep1_ip $vtep2_ip $grp2 &
pid2=$!
- ip netns exec $ns1 $mz br0.10 -A $src -B $grp1 -t udp sp=12345,dp=54321 -p 100 -c 0 -q &
+ ip netns exec $ns1 $mz br0.10 -a own -b $grp1_dmac -A $src -B $grp1 -t udp sp=12345,dp=54321 -p 100 -c 0 -q &
pid3=$!
- ip netns exec $ns1 $mz br0.10 -A $src -B $grp2 -t udp sp=12345,dp=54321 -p 100 -c 0 -q &
+ ip netns exec $ns1 $mz br0.10 -a own -b $grp2_dmac -A $src -B $grp2 -t udp sp=12345,dp=54321 -p 100 -c 0 -q &
pid4=$!
sleep 30
@@ -2363,15 +2406,17 @@ mdb_torture_ipv4_ipv4()
local vtep1_ip=198.51.100.100
local vtep2_ip=198.51.100.200
local grp1=239.1.1.1
+ local grp1_dmac=01:00:5e:01:01:01
local grp2=239.2.2.2
+ local grp2_dmac=01:00:5e:02:02:02
local src=192.0.2.129
echo
echo "Data path: MDB torture test - IPv4 overlay / IPv4 underlay"
echo "----------------------------------------------------------"
- mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp2 $src \
- "mausezahn"
+ mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp1_dmac $grp2 \
+ $grp2_dmac $src "mausezahn"
}
mdb_torture_ipv6_ipv4()
@@ -2380,15 +2425,17 @@ mdb_torture_ipv6_ipv4()
local vtep1_ip=198.51.100.100
local vtep2_ip=198.51.100.200
local grp1=ff0e::1
+ local grp1_dmac=33:33:00:00:00:01
local grp2=ff0e::2
+ local grp2_dmac=33:33:00:00:00:02
local src=2001:db8:100::1
echo
echo "Data path: MDB torture test - IPv6 overlay / IPv4 underlay"
echo "----------------------------------------------------------"
- mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp2 $src \
- "mausezahn -6"
+ mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp1_dmac $grp2 \
+ $grp2_dmac $src "mausezahn -6"
}
mdb_torture_ipv4_ipv6()
@@ -2397,15 +2444,17 @@ mdb_torture_ipv4_ipv6()
local vtep1_ip=2001:db8:1000::1
local vtep2_ip=2001:db8:2000::1
local grp1=239.1.1.1
+ local grp1_dmac=01:00:5e:01:01:01
local grp2=239.2.2.2
+ local grp2_dmac=01:00:5e:02:02:02
local src=192.0.2.129
echo
echo "Data path: MDB torture test - IPv4 overlay / IPv6 underlay"
echo "----------------------------------------------------------"
- mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp2 $src \
- "mausezahn"
+ mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp1_dmac $grp2 \
+ $grp2_dmac $src "mausezahn"
}
mdb_torture_ipv6_ipv6()
@@ -2414,15 +2463,17 @@ mdb_torture_ipv6_ipv6()
local vtep1_ip=2001:db8:1000::1
local vtep2_ip=2001:db8:2000::1
local grp1=ff0e::1
+ local grp1_dmac=33:33:00:00:00:01
local grp2=ff0e::2
+ local grp2_dmac=33:33:00:00:00:02
local src=2001:db8:100::1
echo
echo "Data path: MDB torture test - IPv6 overlay / IPv6 underlay"
echo "----------------------------------------------------------"
- mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp2 $src \
- "mausezahn -6"
+ mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp1_dmac $grp2 \
+ $grp2_dmac $src "mausezahn -6"
}
################################################################################
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index 9cd5e885e91f..f4549e6894dd 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -241,7 +241,7 @@ for family in 4 6; do
create_vxlan_pair
ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on
- run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1
+ run_test "GRO frag list over UDP tunnel" $OL_NET$DST 10 10
cleanup
# use NAT to circumvent GRO FWD check
@@ -254,13 +254,7 @@ for family in 4 6; do
# load arp cache before running the test to reduce the amount of
# stray traffic on top of the UDP tunnel
ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null
- run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST
- cleanup
-
- create_vxlan_pair
- run_bench "UDP tunnel fwd perf" $OL_NET$DST
- ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
- run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST
+ run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 10 10 $OL_NET$DST
cleanup
done
