From 430cac487400494c19a8b85299e979bb07b4671f Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 4 Apr 2023 15:12:16 +0200 Subject: [PATCH 001/358] xfrm: don't check the default policy if the policy allows the packet The current code doesn't let a simple "allow" policy counteract a default policy blocking all incoming packets: ip x p setdefault in block ip x p a src 192.168.2.1/32 dst 192.168.2.2/32 dir in action allow At this stage, we have an allow policy (with or without transforms) for this packet. It doesn't matter what the default policy says, since the policy we looked up lets the packet through. The case of a blocking policy is already handled separately, so we can remove this check. Fixes: 2d151d39073a ("xfrm: Add possibility to set the default to block if we have no policy") Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5c61ec04b839..62be042f2ebc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3712,12 +3712,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_nr = ti; - if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK && - !xfrm_nr) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); - goto reject; - } - if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; From 4be8ddb48b1b6c6067fb59c846b9c6e19d6efe14 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 18 Apr 2023 23:47:37 +0200 Subject: [PATCH 002/358] KVM: arm64: Slightly optimize flush_context() bitmap_zero() is faster than bitmap_clear(), so use it to save a few cycles. Signed-off-by: Christophe JAILLET Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/97bf2743f3a302b3066aced02218b9da60690dd3.1681854412.git.christophe.jaillet@wanadoo.fr --- arch/arm64/kvm/vmid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index 08978d0672e7..bbf0677cfefa 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -47,7 +47,7 @@ static void flush_context(void) int cpu; u64 vmid; - bitmap_clear(vmid_map, 0, NUM_USER_VMIDS); + bitmap_zero(vmid_map, NUM_USER_VMIDS); for_each_possible_cpu(cpu) { vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0); From a00e9e4319c2a8a8b166da028292de83190e39a4 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 18 Apr 2023 23:47:38 +0200 Subject: [PATCH 003/358] KVM: arm64: Use the bitmap API to allocate bitmaps Use bitmap_zalloc()/bitmap_free() instead of hand-writing them. It is less verbose and it improves the semantic. Signed-off-by: Christophe JAILLET Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/3c5043731db4d3635383e9326bc7e98e25de3288.1681854412.git.christophe.jaillet@wanadoo.fr --- arch/arm64/kvm/vmid.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index bbf0677cfefa..7fe8ba1a2851 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -182,8 +182,7 @@ int __init kvm_arm_vmid_alloc_init(void) */ WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus()); atomic64_set(&vmid_generation, VMID_FIRST_VERSION); - vmid_map = kcalloc(BITS_TO_LONGS(NUM_USER_VMIDS), - sizeof(*vmid_map), GFP_KERNEL); + vmid_map = bitmap_zalloc(NUM_USER_VMIDS, GFP_KERNEL); if (!vmid_map) return -ENOMEM; @@ -192,5 +191,5 @@ int __init kvm_arm_vmid_alloc_init(void) void __init kvm_arm_vmid_alloc_free(void) { - kfree(vmid_map); + bitmap_free(vmid_map); } From 94b95dfaa814f565d92f5a65f0ff12a483095522 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 19 Apr 2023 15:19:07 +0300 Subject: [PATCH 004/358] xfrm: release all offloaded policy memory Failure to add offloaded policy will cause to the following error once user will try to reload driver. Unregister_netdevice: waiting for eth3 to become free. Usage count = 2 This was caused by xfrm_dev_policy_add() which increments reference to net_device. That reference was supposed to be decremented in xfrm_dev_policy_free(). However the latter wasn't called. unregister_netdevice: waiting for eth3 to become free. Usage count = 2 leaked reference. xfrm_dev_policy_add+0xff/0x3d0 xfrm_policy_construct+0x352/0x420 xfrm_add_policy+0x179/0x320 xfrm_user_rcv_msg+0x1d2/0x3d0 netlink_rcv_skb+0xe0/0x210 xfrm_netlink_rcv+0x45/0x50 netlink_unicast+0x346/0x490 netlink_sendmsg+0x3b0/0x6c0 sock_sendmsg+0x73/0xc0 sock_write_iter+0x13b/0x1f0 vfs_write+0x528/0x5d0 ksys_write+0x120/0x150 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Fixes: 919e43fad516 ("xfrm: add an interface to offload policy") Signed-off-by: Leon Romanovsky Reviewed-by: Simon Horman Reviewed-by: Eric Dumazet Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 103af2b3e986..af8fbcbfbe69 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1978,6 +1978,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) { xfrm_dev_policy_delete(xp); + xfrm_dev_policy_free(xp); security_xfrm_policy_free(xp->security); kfree(xp); return err; From ec8f32ad9a65a8cbb465b69e154aaec9d2fe45c4 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 19 Apr 2023 15:19:08 +0300 Subject: [PATCH 005/358] xfrm: Fix leak of dev tracker At the stage of direction checks, the netdev reference tracker is already initialized, but released with wrong *_put() call. Fixes: 919e43fad516 ("xfrm: add an interface to offload policy") Signed-off-by: Leon Romanovsky Reviewed-by: Simon Horman Reviewed-by: Eric Dumazet Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 95f1436bf6a2..e2ca50bfca24 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -378,7 +378,7 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, break; default: xdo->dev = NULL; - dev_put(dev); + netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } From 1f0f4a2ef7a5693b135ce174e71f116db4bd684d Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 21 Apr 2023 07:16:05 +0000 Subject: [PATCH 006/358] KVM: arm64: Infer the PA offset from IPA in stage-2 map walker Until now, the page table walker counted increments to the PA and IPA of a walk in two separate places. While the PA is incremented as soon as a leaf PTE is installed in stage2_map_walker_try_leaf(), the IPA is actually bumped in the generic table walker context. Critically, __kvm_pgtable_visit() rereads the PTE after the LEAF callback returns to work out if a table or leaf was installed, and only bumps the IPA for a leaf PTE. This arrangement worked fine when we handled faults behind the write lock, as the walker had exclusive access to the stage-2 page tables. However, commit 1577cb5823ce ("KVM: arm64: Handle stage-2 faults in parallel") started handling all stage-2 faults behind the read lock, opening up a race where a walker could increment the PA but not the IPA of a walk. Nothing good ensues, as the walker starts mapping with the incorrect IPA -> PA relationship. For example, assume that two vCPUs took a data abort on the same IPA. One observes that dirty logging is disabled, and the other observed that it is enabled: vCPU attempting PMD mapping vCPU attempting PTE mapping ====================================== ===================================== /* install PMD */ stage2_make_pte(ctx, leaf); data->phys += granule; /* replace PMD with a table */ stage2_try_break_pte(ctx, data->mmu); stage2_make_pte(ctx, table); /* table is observed */ ctx.old = READ_ONCE(*ptep); table = kvm_pte_table(ctx.old, level); /* * map walk continues w/o incrementing * IPA. */ __kvm_pgtable_walk(..., level + 1); Bring an end to the whole mess by using the IPA as the single source of truth for how far along a walk has gotten. Work out the correct PA to map by calculating the IPA offset from the beginning of the walk and add that to the starting physical address. Cc: stable@vger.kernel.org Fixes: 1577cb5823ce ("KVM: arm64: Handle stage-2 faults in parallel") Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230421071606.1603916-2-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 1 + arch/arm64/kvm/hyp/pgtable.c | 32 ++++++++++++++++++++++++---- 2 files changed, 29 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 4cd6762bda80..dc3c072e862f 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -209,6 +209,7 @@ struct kvm_pgtable_visit_ctx { kvm_pte_t old; void *arg; struct kvm_pgtable_mm_ops *mm_ops; + u64 start; u64 addr; u64 end; u32 level; diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 3d61bd3e591d..140f82300db5 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -58,6 +58,7 @@ struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; + u64 start; u64 addr; u64 end; }; @@ -201,6 +202,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, .old = READ_ONCE(*ptep), .arg = data->walker->arg, .mm_ops = mm_ops, + .start = data->start, .addr = data->addr, .end = data->end, .level = level, @@ -293,6 +295,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker) { struct kvm_pgtable_walk_data walk_data = { + .start = ALIGN_DOWN(addr, PAGE_SIZE), .addr = ALIGN_DOWN(addr, PAGE_SIZE), .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, @@ -794,20 +797,43 @@ static bool stage2_pte_executable(kvm_pte_t pte) return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } +static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, + const struct stage2_map_data *data) +{ + u64 phys = data->phys; + + /* + * Stage-2 walks to update ownership data are communicated to the map + * walker using an invalid PA. Avoid offsetting an already invalid PA, + * which could overflow and make the address valid again. + */ + if (!kvm_phys_is_valid(phys)) + return phys; + + /* + * Otherwise, work out the correct PA based on how far the walk has + * gotten. + */ + return phys + (ctx->addr - ctx->start); +} + static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { + u64 phys = stage2_map_walker_phys_addr(ctx, data); + if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1))) return false; - return kvm_block_mapping_supported(ctx, data->phys); + return kvm_block_mapping_supported(ctx, phys); } static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; + u64 phys = stage2_map_walker_phys_addr(ctx, data); + u64 granule = kvm_granule_size(ctx->level); struct kvm_pgtable *pgt = data->mmu->pgt; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; @@ -841,8 +867,6 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, stage2_make_pte(ctx, new); - if (kvm_phys_is_valid(phys)) - data->phys += granule; return 0; } From 39bc95be3782ba88e55cd72e830f37e74395831b Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 21 Apr 2023 07:16:06 +0000 Subject: [PATCH 007/358] KVM: arm64: Infer PA offset from VA in hyp map walker Similar to the recently fixed stage-2 walker, the hyp map walker increments the PA and VA of a walk separately. Unlike stage-2, there is no bug here as the map walker has exclusive access to the stage-1 page tables. Nonetheless, in the interest of continuity throughout the page table code, tweak the hyp map walker to avoid incrementing the PA and instead use the VA as the authoritative source of how far along a table walk has gotten. Calculate the PA to use for a leaf PTE by adding the offset of the VA from the start of the walk to the starting PA. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230421071606.1603916-3-oliver.upton@linux.dev --- arch/arm64/kvm/hyp/pgtable.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 140f82300db5..356a3fd5220c 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -410,13 +410,12 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct hyp_map_data *data) { + u64 phys = data->phys + (ctx->addr - ctx->start); kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; if (!kvm_block_mapping_supported(ctx, phys)) return false; - data->phys += granule; new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); if (ctx->old == new) return true; From 1ea244158a4a20ac686f4d1d46285f3d38d4571f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 21 Apr 2023 10:18:34 +0100 Subject: [PATCH 008/358] KVM: arm64: Constify start/end/phys fields of the pgtable walker data As we are revamping the way the pgtable walker evaluates some of the data, make it clear that we rely on somew of the fields to be constant across the lifetime of a walk. For this, flag the start, end and phys fields of the walk data as 'const', which will generate an error if we were to accidentally update these fields again. Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier --- arch/arm64/kvm/hyp/pgtable.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 356a3fd5220c..5282cb9ca4cf 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -58,9 +58,9 @@ struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; - u64 start; + const u64 start; u64 addr; - u64 end; + const u64 end; }; static bool kvm_phys_is_valid(u64 phys) @@ -352,7 +352,7 @@ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, } struct hyp_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; }; @@ -578,7 +578,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) } struct stage2_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; u8 owner_id; From 3d1793562858f2bc42cc722fe00ec9b2ff0618e1 Mon Sep 17 00:00:00 2001 From: Jingyu Wang Date: Thu, 9 Mar 2023 15:59:19 +0800 Subject: [PATCH 009/358] KVM: arm64: Fix repeated words in comments Delete the redundant word 'to'. Signed-off-by: Jingyu Wang Reviewed-by: Mukesh Ojha Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230309075919.169518-1-jingyuwang_vip@163.com --- arch/arm64/kvm/inject_fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 64c3aec0d937..0bd93a5f21ce 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -204,7 +204,7 @@ void kvm_inject_size_fault(struct kvm_vcpu *vcpu) * Size Fault at level 0, as if exceeding PARange. * * Non-LPAE guests will only get the external abort, as there - * is no way to to describe the ASF. + * is no way to describe the ASF. */ if (vcpu_el1_is_32bit(vcpu) && !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) From 4c181e3d352e9280c84fb4b4c7a8940ce005374e Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 17:37:14 +0000 Subject: [PATCH 010/358] KVM: arm64: Document check for TIF_FOREIGN_FPSTATE In kvm_arch_vcpu_load_fp() we unconditionally set the current FP state to FP_STATE_HOST_OWNED, this will be overridden to FP_STATE_NONE if TIF_FOREIGN_FPSTATE is set but the check is deferred until kvm_arch_vcpu_ctxflush_fp() where we are no longer preemptable. Add a comment to this effect to help avoid people being concerned about the lack of a check and discover where the check is done. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221214-kvm-arm64-sme-context-switch-v2-1-57ba0082e9ff@kernel.org --- arch/arm64/kvm/fpsimd.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 1279949599b5..3fd0ce6a3500 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -81,6 +81,11 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) fpsimd_kvm_prepare(); + /* + * We will check TIF_FOREIGN_FPSTATE just before entering the + * guest in kvm_arch_vcpu_ctxflush_fp() and override this to + * FP_STATE_FREE if the flag set. + */ vcpu->arch.fp_state = FP_STATE_HOST_OWNED; vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); From d071cefdcca39fdbcdd4bf36868448820dbac34b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 17:37:15 +0000 Subject: [PATCH 011/358] KVM: arm64: Restructure check for SVE support in FP trap handler We share the same handler for general floating point and SVE traps with a check to make sure we don't handle any SVE traps if the system doesn't have SVE support. Since we will be adding SME support and wishing to handle that along with other FP related traps rewrite the check to be more scalable and a bit clearer too, ensuring we don't misidentify SME traps as SVE ones. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221214-kvm-arm64-sme-context-switch-v2-2-57ba0082e9ff@kernel.org --- arch/arm64/kvm/hyp/include/hyp/switch.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 07d37ff88a3f..d29d2ebf9126 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -176,9 +176,17 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) sve_guest = vcpu_has_sve(vcpu); esr_ec = kvm_vcpu_trap_get_class(vcpu); - /* Don't handle SVE traps for non-SVE vcpus here: */ - if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD) + /* Only handle traps the vCPU can support here: */ + switch (esr_ec) { + case ESR_ELx_EC_FP_ASIMD: + break; + case ESR_ELx_EC_SVE: + if (!sve_guest) + return false; + break; + default: return false; + } /* Valid trap. Switch the context: */ From aaa2f14e6f3f34de8edfb13566110a0fe0d88785 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 17:37:16 +0000 Subject: [PATCH 012/358] KVM: arm64: Clarify host SME state management Normally when running a guest we do not touch the floating point register state until first use of floating point by the guest, saving the current state and loading the guest state at that point. This has been found to offer a performance benefit in common cases. However currently if SME is active when switching to a guest then we exit streaming mode, disable ZA and invalidate the floating point register state prior to starting the guest. The exit from streaming mode is required for correct guest operation, if we leave streaming mode enabled then many non-SME operations can generate SME traps (eg, SVE operations will become streaming SVE operations). If EL1 leaves CPACR_EL1.SMEN disabled then the host is unable to intercept these traps. This will mean that a SME unaware guest will see SME exceptions which will confuse it. Disabling streaming mode also avoids creating spurious indications of usage of the SME hardware which could impact system performance, especially with shared SME implementations. Document the requirement to exit streaming mode clearly. There is no issue with guest operation caused by PSTATE.ZA so we can defer handling for that until first floating point usage, do so if the register state is not that of the current task and hence has already been saved. We could also do this for the case where the register state is that for the current task however this is very unlikely to happen and would require disproportionate effort so continue to save the state in that case. Saving this state on first use would require that we map and unmap storage for the host version of these registers for use by the hypervisor, taking care to deal with protected KVM and the fact that the host can free or reallocate the backing storage. Given that the strong recommendation is that applications should only keep PSTATE.ZA enabled when the state it enables is in active use it is difficult to see a case where a VMM would wish to do this, it would need to not only be using SME but also running the guest in the middle of SME usage. This can be revisited in the future if a use case does arises, in the interim such tasks will work but experience a performance overhead. This brings our handling of SME more into line with our handling of other floating point state and documents more clearly the constraints we have, especially around streaming mode. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221214-kvm-arm64-sme-context-switch-v2-3-57ba0082e9ff@kernel.org --- arch/arm64/kvm/fpsimd.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 3fd0ce6a3500..4c9dcd8fc939 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -92,20 +92,23 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu_set_flag(vcpu, HOST_SVE_ENABLED); - /* - * We don't currently support SME guests but if we leave - * things in streaming mode then when the guest starts running - * FPSIMD or SVE code it may generate SME traps so as a - * special case if we are in streaming mode we force the host - * state to be saved now and exit streaming mode so that we - * don't have to handle any SME traps for valid guest - * operations. Do this for ZA as well for now for simplicity. - */ if (system_supports_sme()) { vcpu_clear_flag(vcpu, HOST_SME_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) vcpu_set_flag(vcpu, HOST_SME_ENABLED); + /* + * If PSTATE.SM is enabled then save any pending FP + * state and disable PSTATE.SM. If we leave PSTATE.SM + * enabled and the guest does not enable SME via + * CPACR_EL1.SMEN then operations that should be valid + * may generate SME traps from EL1 to EL1 which we + * can't intercept and which would confuse the guest. + * + * Do the same for PSTATE.ZA in the case where there + * is state in the registers which has not already + * been saved, this is very unlikely to happen. + */ if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { vcpu->arch.fp_state = FP_STATE_FREE; fpsimd_save_and_flush_cpu_state(); From ce902336d9b3472d6104316e876e1a8752531916 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 18 Apr 2023 09:41:58 -0700 Subject: [PATCH 013/358] drm/msm/atomic: Don't try async if crtc not active For a similar reason as commit f2c7ca890182 ("drm/atomic-helper: Don't set deadline for modesets"), we need the crtc to be already active in order to compute a target vblank time for an async commit. Otherwise we get this splat reminding us that we are doing it wrong: ------------[ cut here ]------------ msm_dpu ae01000.mdp: drm_WARN_ON_ONCE(drm_drv_uses_atomic_modeset(dev)) WARNING: CPU: 7 PID: 1923 at drivers/gpu/drm/drm_vblank.c:728 drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x148/0x370 Modules linked in: snd_seq_dummy snd_seq snd_seq_device bridge stp llc tun vhost_vsock vhost vhost_iotlb vmw_vsock_virtio_transport_common vsock uinput rfcomm algif_hash algif_skcipher af_alg veth venus_dec venus_enc cros_ec_typec typec qcom_spmi_temp_alarm qcom_spmi_adc_tm5 qcom_spmi_adc5 xt_cgroup qcom_vadc_common qcom_stats hci_uart btqca xt_MASQUERADE venus_core 8021q coresight_tmc coresight_funnel coresight_etm4x coresight_replicator snd_soc_lpass_sc7180 coresight snd_soc_sc7180 ip6table_nat fuse ath10k_snoc ath10k_core ath mac80211 iio_trig_sysfs bluetooth cfg80211 cros_ec_sensors cros_ec_sensors_core ecdh_generic industrialio_triggered_buffer ecc kfifo_buf cros_ec_sensorhub r8153_ecm cdc_ether usbnet r8152 mii lzo_rle lzo_compress zram hid_vivaldi hid_google_hammer hid_vivaldi_common joydev CPU: 7 PID: 1923 Comm: DrmThread Not tainted 5.15.107-18853-g3be267609a0b-dirty #16 a1ffc1a66e79c21c3536d8c9a42e819236e39714 Hardware name: Google Wormdingler rev1+ BOE panel board (DT) pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x148/0x370 lr : drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x144/0x370 sp : ffffffc012e2b800 x29: ffffffc012e2b840 x28: ffffff8083676094 x27: ffffffc012e2bb28 x26: ffffff8084539800 x25: 0000000000000000 x24: ffffff8083676000 x23: ffffffd3c8cdc5a0 x22: ffffff80845b9d00 x21: ffffffc012e2b8b4 x20: ffffffc012e2b910 x19: 0000000000000001 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000010 x15: ffffffd3c8451a88 x14: 0000000000000003 x13: 0000000000000004 x12: 0000000000000001 x11: c0000000ffffdfff x10: ffffffd3c973ef58 x9 : 8ea3526b3cc95900 x8 : 8ea3526b3cc95900 x7 : 0000000000000000 x6 : 000000000000003a x5 : ffffffd3c99676cd x4 : 0000000000000000 x3 : ffffffc012e2b4b8 x2 : ffffffc012e2b4c0 x1 : 00000000ffffdfff x0 : 0000000000000000 Call trace: drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x148/0x370 drm_crtc_vblank_helper_get_vblank_timestamp+0x20/0x30 drm_crtc_get_last_vbltimestamp+0x68/0xb0 drm_crtc_next_vblank_start+0x5c/0xa8 msm_atomic_commit_tail+0x264/0x664 commit_tail+0xac/0x160 drm_atomic_helper_commit+0x160/0x168 drm_atomic_commit+0xfc/0x128 drm_atomic_helper_disable_plane+0x8c/0x110 __setplane_atomic+0x10c/0x138 drm_mode_cursor_common+0x3a8/0x410 drm_mode_cursor_ioctl+0x48/0x70 drm_ioctl_kernel+0xe0/0x158 drm_ioctl+0x25c/0x4d8 __arm64_sys_ioctl+0x98/0xd0 invoke_syscall+0x4c/0x100 el0_svc_common+0x98/0x104 do_el0_svc+0x30/0x90 el0_svc+0x20/0x50 el0t_64_sync_handler+0x78/0x108 el0t_64_sync+0x1a4/0x1a8 ---[ end trace a0f587e1ab9589e8 ]--- Fixes: 52ff0d3073d2 ("drm/msm/atomic: Switch to vblank_start helper") Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/532727/ Link: https://lore.kernel.org/r/20230418164158.549873-1-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_atomic.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index d77fa9793c54..9c45d641b521 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -155,6 +155,8 @@ static bool can_do_async(struct drm_atomic_state *state, for_each_new_crtc_in_state(state, crtc, crtc_state, i) { if (drm_atomic_crtc_needs_modeset(crtc_state)) return false; + if (!crtc_state->active) + return false; if (++num_crtcs > 1) return false; *async_crtc = crtc; From 16eb51aba0a72b8f60c6b98d1493844230293450 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 17 Apr 2023 15:55:04 -0700 Subject: [PATCH 014/358] drm/msm: Fix vmap madv warning Commit d6ae7d1cd58e ("drm/msm/gem: Simplify vmap vs LRU tracking") introduced a splat in the pin_pages_locked() path for buffers that had been MADV_DONTNEED. ------------[ cut here ]------------ msm_obj->madv != 0 WARNING: CPU: 1 PID: 144 at drivers/gpu/drm/msm/msm_gem.c:230 msm_gem_pin_pages_locked+0x9c/0xd4 Modules linked in: lzo_rle cros_ec_lid_angle cros_ec_sensors cros_ec_sensors_core venus_dec venus_enc videobuf2_dma_contig cdc_ether usbnet mii uvcvideo videobuf2_vmalloc hci_uart btqca qcom_spmi_adc5 uvc qcom_spmi_temp_alarm qcom_vadc_common cros_ec_sensorhub videobuf2_memops cros_ec_typec sx9324 sx_common typec joydev bluetooth industrialio_triggered_buffer ecdh_generic kfifo_buf ecc venus_core qcom_stats v4l2_mem2mem videobuf2_v4l2 videobuf2_common ath11k_ahb ath11k mac80211 cfg80211 fuse zram zsmalloc CPU: 1 PID: 144 Comm: ring0 Tainted: G W 6.3.0-rc2-debug+ #622 Hardware name: Google Villager (rev1+) with LTE (DT) pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : msm_gem_pin_pages_locked+0x9c/0xd4 lr : msm_gem_pin_pages_locked+0x9c/0xd4 sp : ffffffc009ffbab0 x29: ffffffc009ffbab0 x28: ffffffee8da75008 x27: ffffff80a10274d0 x26: ffffff8087fe3bf8 x25: ffffff8087fe3c08 x24: 0000000000000001 x23: ffffff80891d5800 x22: ffffff809d0de480 x21: ffffff8081e5a080 x20: 0000000000000002 x19: ffffff80a3564c00 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 00000000000a9620 x14: 0000000000000000 x13: 2d2d2d2d2d2d2d2d x12: 2d2d2d2d5d206572 x11: 656820747563205b x10: 2d2d2d2d2d2d2d2d x9 : ffffffee8c705dfc x8 : ffffffee8da75000 x7 : ffffffee8d34e6d0 x6 : 0000000000000000 x5 : 00000000000affa8 x4 : 000000000000000d x3 : ffffffee8da75008 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffffff8088048040 Call trace: msm_gem_pin_pages_locked+0x9c/0xd4 get_vaddr+0xb0/0x150 msm_gem_get_vaddr_active+0x1c/0x28 snapshot_buf+0x90/0x10c msm_rd_dump_submit+0x30c/0x380 msm_gpu_submit+0x88/0x174 msm_job_run+0x68/0x118 drm_sched_main+0x2b8/0x3a0 kthread+0xf0/0x100 ret_from_fork+0x10/0x20 irq event stamp: 3358 hardirqs last enabled at (3357): [] __up_console_sem+0x7c/0x80 hardirqs last disabled at (3358): [] el1_dbg+0x24/0x80 softirqs last enabled at (3330): [] __do_softirq+0x21c/0x4bc softirqs last disabled at (3325): [] ____do_softirq+0x18/0x24 ---[ end trace 0000000000000000 ]--- But, as with msm_gem_get_vaddr_active(), this is a special case because we know that the buffer won't be purged evicted until it's fence is signaled. We just forgot to propagate the logic get_vaddr() to pin_pages_locked(). Fixes: d6ae7d1cd58e ("drm/msm/gem: Simplify vmap vs LRU tracking") Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/532616/ Link: https://lore.kernel.org/r/20230417225504.494934-1-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_gem.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index db6c4e281d75..cd39b9d8abdb 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -219,7 +219,8 @@ static void put_pages(struct drm_gem_object *obj) } } -static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) +static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj, + unsigned madv) { struct msm_drm_private *priv = obj->dev->dev_private; struct msm_gem_object *msm_obj = to_msm_bo(obj); @@ -227,7 +228,9 @@ static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) msm_gem_assert_locked(obj); - if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { + if (GEM_WARN_ON(msm_obj->madv > madv)) { + DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n", + msm_obj->madv, madv); return ERR_PTR(-EBUSY); } @@ -248,7 +251,7 @@ struct page **msm_gem_pin_pages(struct drm_gem_object *obj) struct page **p; msm_gem_lock(obj); - p = msm_gem_pin_pages_locked(obj); + p = msm_gem_pin_pages_locked(obj, MSM_MADV_WILLNEED); msm_gem_unlock(obj); return p; @@ -473,10 +476,7 @@ int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma) msm_gem_assert_locked(obj); - if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) - return -EBUSY; - - pages = msm_gem_pin_pages_locked(obj); + pages = msm_gem_pin_pages_locked(obj, MSM_MADV_WILLNEED); if (IS_ERR(pages)) return PTR_ERR(pages); @@ -699,13 +699,7 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) if (obj->import_attach) return ERR_PTR(-ENODEV); - if (GEM_WARN_ON(msm_obj->madv > madv)) { - DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n", - msm_obj->madv, madv); - return ERR_PTR(-EBUSY); - } - - pages = msm_gem_pin_pages_locked(obj); + pages = msm_gem_pin_pages_locked(obj, madv); if (IS_ERR(pages)) return ERR_CAST(pages); From 5fc46f94219d1d103ffb5f0832be9da674d85a73 Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Tue, 25 Apr 2023 09:46:18 +0200 Subject: [PATCH 015/358] Revert "Fix XFRM-I support for nested ESP tunnels" This reverts commit b0355dbbf13c0052931dd14c38c789efed64d3de. The reverted commit clears the secpath on packets received via xfrm interfaces to support nested IPsec tunnels. This breaks Netfilter policy matching using xt_policy in the FORWARD chain, as the secpath is missing during forwarding. Additionally, Benedict Wong reports that it breaks Transport-in-Tunnel mode. Fix this regression by reverting the commit until we have a better approach for nested IPsec tunnels. Fixes: b0355dbbf13c ("Fix XFRM-I support for nested ESP tunnels") Link: https://lore.kernel.org/netdev/20230412085615.124791-1-martin@strongswan.org/ Signed-off-by: Martin Willi Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_interface_core.c | 54 +++------------------------------- net/xfrm/xfrm_policy.c | 3 -- 2 files changed, 4 insertions(+), 53 deletions(-) diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 35279c220bd7..1f99dc469027 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,52 +310,6 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } -static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type, unsigned short family) -{ - struct sec_path *sp; - - sp = skb_sec_path(skb); - if (sp && (sp->len || sp->olen) && - !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) - goto discard; - - XFRM_SPI_SKB_CB(skb)->family = family; - if (family == AF_INET) { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; - } else { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; - } - - return xfrm_input(skb, nexthdr, spi, encap_type); -discard: - kfree_skb(skb); - return 0; -} - -static int xfrmi4_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); -} - -static int xfrmi6_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], - 0, 0, AF_INET6); -} - -static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); -} - -static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); -} - static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -991,8 +945,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrmi6_rcv, - .input_handler = xfrmi6_input, + .handler = xfrm6_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -1042,8 +996,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrmi4_rcv, - .input_handler = xfrmi4_input, + .handler = xfrm4_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 62be042f2ebc..21a3a1cd3d6d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3739,9 +3739,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } - if (if_id) - secpath_reset(skb); - xfrm_pols_put(pols, npols); return 1; } From 85c636284cb63b7740b4ae98881ace92158068d3 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 21 Apr 2023 15:56:57 +0100 Subject: [PATCH 016/358] drm/msm/dp: unregister audio driver during unbind while binding the code always registers a audio driver, however there is no corresponding unregistration done in unbind. This leads to multiple redundant audio platform devices if dp_display_bind and dp_display_unbind happens multiple times during startup. On X13s platform this resulted in 6 to 9 audio codec device instead of just 3 codec devices for 3 dp ports. Fix this by unregistering codecs on unbind. Signed-off-by: Srinivas Kandagatla Fixes: d13e36d7d222 ("drm/msm/dp: add audio support for Display Port on MSM") Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/533324/ Link: https://lore.kernel.org/r/20230421145657.12186-1-srinivas.kandagatla@linaro.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/dp/dp_audio.c | 12 ++++++++++++ drivers/gpu/drm/msm/dp/dp_audio.h | 2 ++ drivers/gpu/drm/msm/dp/dp_display.c | 1 + 3 files changed, 15 insertions(+) diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index 6666783e1468..1245c7aa49df 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -593,6 +593,18 @@ static struct hdmi_codec_pdata codec_data = { .i2s = 1, }; +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio) +{ + struct dp_audio_private *audio_priv; + + audio_priv = container_of(dp_audio, struct dp_audio_private, dp_audio); + + if (audio_priv->audio_pdev) { + platform_device_unregister(audio_priv->audio_pdev); + audio_priv->audio_pdev = NULL; + } +} + int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio) { diff --git a/drivers/gpu/drm/msm/dp/dp_audio.h b/drivers/gpu/drm/msm/dp/dp_audio.h index 84e5f4a5d26b..4ab78880af82 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.h +++ b/drivers/gpu/drm/msm/dp/dp_audio.h @@ -53,6 +53,8 @@ struct dp_audio *dp_audio_get(struct platform_device *pdev, int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio); +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio); + /** * dp_audio_put() * diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 3e13acdfa7e5..99a38dbe51c0 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -326,6 +326,7 @@ static void dp_display_unbind(struct device *dev, struct device *master, kthread_stop(dp->ev_tsk); dp_power_client_deinit(dp->power); + dp_unregister_audio_driver(dev, dp->audio); dp_aux_unregister(dp->aux); dp->drm_dev = NULL; dp->aux->drm_dev = NULL; From a432fc31f03db2546a48bcf5dd69ca28ceb732bf Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Wed, 26 Apr 2023 01:11:09 +0200 Subject: [PATCH 017/358] drm/msm/dpu: Assign missing writeback log_mask The WB debug log mask ended up never being assigned, leading to writes to this block to never be logged even if the mask is enabled in dpu_hw_util_log_mask via debugfs. Fixes: 84a33d0fd921 ("drm/msm/dpu: add dpu_hw_wb abstraction for writeback blocks") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/533860/ Link: https://lore.kernel.org/r/20230418-dpu-drop-useless-for-lookup-v3-1-e8d869eea455@somainline.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c index 2d28afdf860e..a3e413d27717 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c @@ -61,6 +61,7 @@ static const struct dpu_wb_cfg *_wb_offset(enum dpu_wb wb, for (i = 0; i < m->wb_count; i++) { if (wb == m->wb[i].id) { b->blk_addr = addr + m->wb[i].base; + b->log_mask = DPU_DBG_MASK_WB; return &m->wb[i]; } } From 3f23a52fc2b890884828747111f7a3291d2a1b3d Mon Sep 17 00:00:00 2001 From: Arnaud Vrac Date: Wed, 19 Apr 2023 16:41:08 +0200 Subject: [PATCH 018/358] drm/msm/dpu: tweak msm8998 hw catalog values Match the values found in the downstream msm-4.4 kernel sde driver. Signed-off-by: Arnaud Vrac Fixes: 94391a14fc27 ("drm/msm/dpu1: Add MSM8998 to hw catalog") Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/532900/ Link: https://lore.kernel.org/r/20230419-dpu-tweaks-v1-1-d1bac46db075@freebox.fr Signed-off-by: Abhinav Kumar --- .../drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h | 8 ++++---- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c | 15 +++++---------- 2 files changed, 9 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h index 2b3ae84057df..b07e8a9941f7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h @@ -134,10 +134,10 @@ static const struct dpu_dspp_cfg msm8998_dspp[] = { }; static const struct dpu_intf_cfg msm8998_intf[] = { - INTF_BLK("intf_0", INTF_0, 0x6a000, 0x280, INTF_DP, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), - INTF_BLK("intf_1", INTF_1, 0x6a800, 0x280, INTF_DSI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), - INTF_BLK("intf_2", INTF_2, 0x6b000, 0x280, INTF_DSI, 1, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29), - INTF_BLK("intf_3", INTF_3, 0x6b800, 0x280, INTF_HDMI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31), + INTF_BLK("intf_0", INTF_0, 0x6a000, 0x280, INTF_DP, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), + INTF_BLK("intf_1", INTF_1, 0x6a800, 0x280, INTF_DSI, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), + INTF_BLK("intf_2", INTF_2, 0x6b000, 0x280, INTF_DSI, 1, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29), + INTF_BLK("intf_3", INTF_3, 0x6b800, 0x280, INTF_HDMI, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31), }; static const struct dpu_perf_cfg msm8998_perf_data = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 03f162af1a50..8d5d782a4339 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -587,12 +587,12 @@ static const u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3}; static const struct dpu_vbif_dynamic_ot_cfg msm8998_ot_rdwr_cfg[] = { { - .pps = 1088 * 1920 * 30, + .pps = 1920 * 1080 * 30, .ot_limit = 2, }, { - .pps = 1088 * 1920 * 60, - .ot_limit = 6, + .pps = 1920 * 1080 * 60, + .ot_limit = 4, }, { .pps = 3840 * 2160 * 30, @@ -705,10 +705,7 @@ static const struct dpu_qos_lut_entry msm8998_qos_linear[] = { {.fl = 10, .lut = 0x1555b}, {.fl = 11, .lut = 0x5555b}, {.fl = 12, .lut = 0x15555b}, - {.fl = 13, .lut = 0x55555b}, - {.fl = 14, .lut = 0}, - {.fl = 1, .lut = 0x1b}, - {.fl = 0, .lut = 0} + {.fl = 0, .lut = 0x55555b} }; static const struct dpu_qos_lut_entry sdm845_qos_linear[] = { @@ -730,9 +727,7 @@ static const struct dpu_qos_lut_entry msm8998_qos_macrotile[] = { {.fl = 10, .lut = 0x1aaff}, {.fl = 11, .lut = 0x5aaff}, {.fl = 12, .lut = 0x15aaff}, - {.fl = 13, .lut = 0x55aaff}, - {.fl = 1, .lut = 0x1aaff}, - {.fl = 0, .lut = 0}, + {.fl = 0, .lut = 0x55aaff}, }; static const struct dpu_qos_lut_entry sc7180_qos_linear[] = { From 686eb89b103631a41c7f69b8ac5fbca4a6b07fa0 Mon Sep 17 00:00:00 2001 From: Arnaud Vrac Date: Wed, 19 Apr 2023 16:41:17 +0200 Subject: [PATCH 019/358] drm/msm/dpu: tweak lm pairings in msm8998 hw catalog Change lm blocks pairs so that lm blocks with the same features are paired together: LM_0 and LM_1 with PP and DSPP LM_2 and LM_5 with PP LM_3 and LM_4 This matches the sdm845 configuration and allows using pp or dspp when 2 lm blocks are needed in the topology. In the previous config the reservation code could never find an lm pair without a matching feature set. Signed-off-by: Arnaud Vrac Fixes: 94391a14fc27 ("drm/msm/dpu1: Add MSM8998 to hw catalog") Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/532905/ Link: https://lore.kernel.org/r/20230419-dpu-tweaks-v1-10-d1bac46db075@freebox.fr Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h index b07e8a9941f7..bdcd554fc8a8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h @@ -98,17 +98,17 @@ static const struct dpu_sspp_cfg msm8998_sspp[] = { static const struct dpu_lm_cfg msm8998_lm[] = { LM_BLK("lm_0", LM_0, 0x44000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_0, LM_2, DSPP_0), + &msm8998_lm_sblk, PINGPONG_0, LM_1, DSPP_0), LM_BLK("lm_1", LM_1, 0x45000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_1, LM_5, DSPP_1), + &msm8998_lm_sblk, PINGPONG_1, LM_0, DSPP_1), LM_BLK("lm_2", LM_2, 0x46000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_2, LM_0, 0), + &msm8998_lm_sblk, PINGPONG_2, LM_5, 0), LM_BLK("lm_3", LM_3, 0x47000, MIXER_MSM8998_MASK, &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), LM_BLK("lm_4", LM_4, 0x48000, MIXER_MSM8998_MASK, &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), LM_BLK("lm_5", LM_5, 0x49000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_3, LM_1, 0), + &msm8998_lm_sblk, PINGPONG_3, LM_2, 0), }; static const struct dpu_pingpong_cfg msm8998_pp[] = { From f9d5bb73c260f0478f43b07d9fb3dae7d7a8b36b Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:15 +0200 Subject: [PATCH 020/358] drm/msm/dpu: Remove unused INTF0 interrupt mask from SM6115/QCM2290 Neither of these SoCs has INTF0, they only have a DSI interface on index 1. Stop enabling an interrupt that can't fire. Fixes: 3581b7062cec ("drm/msm/disp/dpu1: add support for display on SM6115") Fixes: 5334087ee743 ("drm/msm: add support for QCM2290 MDSS") Signed-off-by: Marijn Suijten Reviewed-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534204/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-1-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h | 1 - drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h index 6f04d8f85c92..988d820f7ef2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h @@ -122,7 +122,6 @@ const struct dpu_mdss_cfg dpu_sm6115_cfg = { .mdss_irqs = BIT(MDP_SSPP_TOP0_INTR) | \ BIT(MDP_SSPP_TOP0_INTR2) | \ BIT(MDP_SSPP_TOP0_HIST_INTR) | \ - BIT(MDP_INTF0_INTR) | \ BIT(MDP_INTF1_INTR), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h index 303492d62a5c..c9003dcc1a59 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h @@ -112,7 +112,6 @@ const struct dpu_mdss_cfg dpu_qcm2290_cfg = { .mdss_irqs = BIT(MDP_SSPP_TOP0_INTR) | \ BIT(MDP_SSPP_TOP0_INTR2) | \ BIT(MDP_SSPP_TOP0_HIST_INTR) | \ - BIT(MDP_INTF0_INTR) | \ BIT(MDP_INTF1_INTR), }; From cfbc21d1c0f9bc2f74acab84031fbaefdbb49ae1 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:16 +0200 Subject: [PATCH 021/358] drm/msm/dpu: Remove TE2 block and feature from DPU >= 5.0.0 hardware No hardware beyond kona (sm8250, DPU 6.0.0) defines the TE2 PINGPONG sub-block offset downstream, and according to insiders no DPU >= 5.0.0 hardware has support for it either. Especially since neither downstream nor upstream utilize these registers in any way, remove the erroneous specification from SM8150, SC8180X, SM8250, SC7180, SM8350, SC8280XP and SM8450 to prevent confusion. Note that downstream enables the PPSPLIT (split-FIFO) topology (single LM for 2 PP and 2 INTF) based on the presence of a TE2 block. Fixes: 386fced3f76f ("drm/msm/dpu: add SM8150 to hw catalog") Fixes: 7bdc0c4b8126 ("msm:disp:dpu1: add support for display for SC7180 target") Fixes: 0e91bcbb0016 ("drm/msm/dpu: Add SM8350 to hw catalog") Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP") Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534210/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-2-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- .../msm/disp/dpu1/catalog/dpu_5_0_sm8150.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_6_0_sm8250.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_6_2_sc7180.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_7_0_sm8350.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 24 +++++++++---------- .../msm/disp/dpu1/catalog/dpu_8_1_sm8450.h | 4 ++-- 7 files changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 282d410269ff..42b0e58624d0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -128,10 +128,10 @@ static const struct dpu_dspp_cfg sm8150_dspp[] = { }; static const struct dpu_pingpong_cfg sm8150_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index c57400265f28..e3bdfe7b30f1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -116,10 +116,10 @@ static const struct dpu_lm_cfg sc8180x_lm[] = { }; static const struct dpu_pingpong_cfg sc8180x_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h index 2c40229ea515..ed130582873c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h @@ -129,10 +129,10 @@ static const struct dpu_dspp_cfg sm8250_dspp[] = { }; static const struct dpu_pingpong_cfg sm8250_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h index 8799ed757119..a46b11730a4d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h @@ -80,8 +80,8 @@ static const struct dpu_dspp_cfg sc7180_dspp[] = { }; static const struct dpu_pingpong_cfg sc7180_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk_te, -1, -1), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk_te, -1, -1), + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk, -1, -1), + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk, -1, -1), }; static const struct dpu_intf_cfg sc7180_intf[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index ca107ca8de46..41ef0c8fc993 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -127,10 +127,10 @@ static const struct dpu_dspp_cfg sm8350_dspp[] = { }; static const struct dpu_pingpong_cfg sm8350_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 9aab110b8c44..f3d935f346b2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -121,18 +121,18 @@ static const struct dpu_dspp_cfg sc8280xp_dspp[] = { }; static const struct dpu_pingpong_cfg sc8280xp_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK_TE("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK_TE("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK_TE("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK_TE("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), + PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), + PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; static const struct dpu_merge_3d_cfg sc8280xp_merge_3d[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index 02a259b6b426..e409c119b0a2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -128,10 +128,10 @@ static const struct dpu_dspp_cfg sm8450_dspp[] = { }; /* FIXME: interrupts */ static const struct dpu_pingpong_cfg sm8450_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, From e9d9ce5462fecdeefec87953de71df4d025cbc72 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:17 +0200 Subject: [PATCH 022/358] drm/msm/dpu: Move non-MDP_TOP INTF_INTR offsets out of hwio header These offsets do not fall under the MDP TOP block and do not fit the comment right above. Move them to dpu_hw_interrupts.c next to the repsective MDP_INTF_x_OFF interrupt block offsets. Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Signed-off-by: Marijn Suijten Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534203/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-3-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c | 5 ++++- drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h | 3 --- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 53326f25e40e..85c0bda3ff90 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -15,7 +15,7 @@ /* * Register offsets in MDSS register file for the interrupt registers - * w.r.t. to the MDP base + * w.r.t. the MDP base */ #define MDP_SSPP_TOP0_OFF 0x0 #define MDP_INTF_0_OFF 0x6A000 @@ -24,6 +24,9 @@ #define MDP_INTF_3_OFF 0x6B800 #define MDP_INTF_4_OFF 0x6C000 #define MDP_INTF_5_OFF 0x6C800 +#define INTF_INTR_EN 0x1c0 +#define INTF_INTR_STATUS 0x1c4 +#define INTF_INTR_CLEAR 0x1c8 #define MDP_AD4_0_OFF 0x7C000 #define MDP_AD4_1_OFF 0x7D000 #define MDP_AD4_INTR_EN_OFF 0x41c diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h index feb9a729844a..5acd5683d25a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h @@ -21,9 +21,6 @@ #define HIST_INTR_EN 0x01c #define HIST_INTR_STATUS 0x020 #define HIST_INTR_CLEAR 0x024 -#define INTF_INTR_EN 0x1C0 -#define INTF_INTR_STATUS 0x1C4 -#define INTF_INTR_CLEAR 0x1C8 #define SPLIT_DISPLAY_EN 0x2F4 #define SPLIT_DISPLAY_UPPER_PIPE_CTRL 0x2F8 #define DSPP_IGC_COLOR0_RAM_LUTN 0x300 From 85340c0256f9b85b47c5867e411df37d76df5858 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:18 +0200 Subject: [PATCH 023/358] drm/msm/dpu: Reindent REV_7xxx interrupt masks with tabs Use tabs for consistency with the other interrupt register definitions, rather than spaces. Fixes: ed6154a136e4 ("drm/msm/disp/dpu1: add intf offsets for SC7280 target") Fixes: 89688e2119b2 ("drm/msm/dpu: Add more of the INTF interrupt regions") Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/534212/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-4-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- .../gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 85c0bda3ff90..17f3e7e4f194 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -32,15 +32,15 @@ #define MDP_AD4_INTR_EN_OFF 0x41c #define MDP_AD4_INTR_CLEAR_OFF 0x424 #define MDP_AD4_INTR_STATUS_OFF 0x420 -#define MDP_INTF_0_OFF_REV_7xxx 0x34000 -#define MDP_INTF_1_OFF_REV_7xxx 0x35000 -#define MDP_INTF_2_OFF_REV_7xxx 0x36000 -#define MDP_INTF_3_OFF_REV_7xxx 0x37000 -#define MDP_INTF_4_OFF_REV_7xxx 0x38000 -#define MDP_INTF_5_OFF_REV_7xxx 0x39000 -#define MDP_INTF_6_OFF_REV_7xxx 0x3a000 -#define MDP_INTF_7_OFF_REV_7xxx 0x3b000 -#define MDP_INTF_8_OFF_REV_7xxx 0x3c000 +#define MDP_INTF_0_OFF_REV_7xxx 0x34000 +#define MDP_INTF_1_OFF_REV_7xxx 0x35000 +#define MDP_INTF_2_OFF_REV_7xxx 0x36000 +#define MDP_INTF_3_OFF_REV_7xxx 0x37000 +#define MDP_INTF_4_OFF_REV_7xxx 0x38000 +#define MDP_INTF_5_OFF_REV_7xxx 0x39000 +#define MDP_INTF_6_OFF_REV_7xxx 0x3a000 +#define MDP_INTF_7_OFF_REV_7xxx 0x3b000 +#define MDP_INTF_8_OFF_REV_7xxx 0x3c000 /** * struct dpu_intr_reg - array of DPU register sets From 701f69183d4d52533fb2af0d6948b7d1b00d1a09 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:19 +0200 Subject: [PATCH 024/358] drm/msm/dpu: Fix PP_BLK_DIPHER -> DITHER typo SM8550 exclusively has a DITHER sub-block inside the PINGPONG block and no other registers, hence the DITHER name of the macro and a corresponding PINGPONG block length of zero. However, the PP_BLK_ macro name was typo'd to DIPHER rather than DITHER. Fixes: efcd0107727c ("drm/msm/dpu: add support for SM8550") Signed-off-by: Marijn Suijten Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534214/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-5-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- .../drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h | 16 ++++++++-------- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index 9e403034093f..d0ab351b6a8b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -132,28 +132,28 @@ static const struct dpu_dspp_cfg sm8550_dspp[] = { &sm8150_dspp_sblk), }; static const struct dpu_pingpong_cfg sm8550_pp[] = { - PP_BLK_DIPHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK_DIPHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK_DIPHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK_DIPHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK_DIPHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK_DIPHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK_DIPHER("pingpong_6", PINGPONG_6, 0x66000, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_6", PINGPONG_6, 0x66000, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK_DIPHER("pingpong_7", PINGPONG_7, 0x66400, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_7", PINGPONG_7, 0x66400, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 8d5d782a4339..5d994bce696f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -491,7 +491,7 @@ static const struct dpu_pingpong_sub_blks sc7280_pp_sblk = { .len = 0x20, .version = 0x20000}, }; -#define PP_BLK_DIPHER(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \ +#define PP_BLK_DITHER(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \ {\ .name = _name, .id = _id, \ .base = _base, .len = 0, \ From fe47a3084789fd653a3465ba39ea4afe33fc6d19 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:20 +0200 Subject: [PATCH 025/358] drm/msm/dpu: Use V2 DITHER PINGPONG sub-block in SM8[34]50/SC8280XP According to downstream sources this DITHER sub-block sits at an offset of 0xe0 with version 0x20000. Lets fix this by using sc7280_pp_sblk instead of sdm845_pp_sblk. Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP") Fixes: 0e91bcbb0016 ("drm/msm/dpu: Add SM8350 to hw catalog") Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534208/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-6-27ce1a5ab5c6@somainline.org [quic_abhinavk@quicinc.com: minor fix in the commit message] Signed-off-by: Abhinav Kumar --- .../drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h | 12 ++++++------ .../drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 12 ++++++------ .../drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h | 16 ++++++++-------- 3 files changed, 20 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index 41ef0c8fc993..4c1bb88029cd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -127,22 +127,22 @@ static const struct dpu_dspp_cfg sm8350_dspp[] = { }; static const struct dpu_pingpong_cfg sm8350_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index f3d935f346b2..a502e173f2c0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -121,17 +121,17 @@ static const struct dpu_dspp_cfg sc8280xp_dspp[] = { }; static const struct dpu_pingpong_cfg sc8280xp_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index e409c119b0a2..ec296a52076c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -128,28 +128,28 @@ static const struct dpu_dspp_cfg sm8450_dspp[] = { }; /* FIXME: interrupts */ static const struct dpu_pingpong_cfg sm8450_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sdm845_pp_sblk, + PP_BLK("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sdm845_pp_sblk, + PP_BLK("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; From 7557f58b6383e560dd5dc5267aceb8372f2a4426 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:21 +0200 Subject: [PATCH 026/358] drm/msm/dpu: Set PINGPONG block length to zero for DPU >= 7.0.0 Despite downstream DTS stating otherwise, the PINGPONG block has no registers starting with DPU revision 7.0.0. TEAR registers are gone since DPU 5.0.0 after being moved to the INTF block, and DSC registers are gone since 7.0.0, leaving only the dither sub-block. A future patch, part of the DSC 1.2 series, should disable DSC functions on the PINGPONG block for all DPU >= 7.0.0 hardware. Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP") Fixes: 0e91bcbb0016 ("drm/msm/dpu: Add SM8350 to hw catalog") Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534206/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-7-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- .../drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h | 12 ++++++------ .../drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h | 8 ++++---- .../drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 12 ++++++------ .../drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h | 16 ++++++++-------- 4 files changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index 4c1bb88029cd..4f6a965bcd90 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -127,22 +127,22 @@ static const struct dpu_dspp_cfg sm8350_dspp[] = { }; static const struct dpu_pingpong_cfg sm8350_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h index 5957de185984..6b2c7eae71d9 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h @@ -87,10 +87,10 @@ static const struct dpu_dspp_cfg sc7280_dspp[] = { }; static const struct dpu_pingpong_cfg sc7280_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), }; static const struct dpu_intf_cfg sc7280_intf[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index a502e173f2c0..706d0f13b598 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -121,17 +121,17 @@ static const struct dpu_dspp_cfg sc8280xp_dspp[] = { }; static const struct dpu_pingpong_cfg sc8280xp_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index ec296a52076c..4ecb3df5cbc0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -128,28 +128,28 @@ static const struct dpu_dspp_cfg sm8450_dspp[] = { }; /* FIXME: interrupts */ static const struct dpu_pingpong_cfg sm8450_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; From 202c044203ac5860e3025169105368d99f9bc6a2 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:22 +0200 Subject: [PATCH 027/358] drm/msm/dpu: Remove duplicate register defines from INTF The INTF_FRAME_LINE_COUNT_EN, INTF_FRAME_COUNT and INTF_LINE_COUNT registers are already defined higher up, in the right place when sorted numerically. Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Signed-off-by: Marijn Suijten Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534231/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-8-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index 84ee2efa9c66..b9dddf576c02 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -56,11 +56,6 @@ #define INTF_TPG_RGB_MAPPING 0x11C #define INTF_PROG_FETCH_START 0x170 #define INTF_PROG_ROT_START 0x174 - -#define INTF_FRAME_LINE_COUNT_EN 0x0A8 -#define INTF_FRAME_COUNT 0x0AC -#define INTF_LINE_COUNT 0x0B0 - #define INTF_MUX 0x25C #define INTF_STATUS 0x26C From ca29699a57ecee6084a4056f5bfd6f11dd359a71 Mon Sep 17 00:00:00 2001 From: Jianhua Lu Date: Thu, 27 Apr 2023 20:21:32 +0800 Subject: [PATCH 028/358] dt-bindings: display/msm: dsi-controller-main: Document qcom, master-dsi and qcom, sync-dual-dsi This fixes warning: sm8250-xiaomi-elish-csot.dtb: dsi@ae94000: Unevaluated properties are not allowed ('qcom,master-dsi', 'qcom,sync-dual-dsi' were unexpected) Reviewed-by: Dmitry Baryshkov Acked-by: Rob Herring Signed-off-by: Jianhua Lu Fixes: 4dbe55c97741 ("dt-bindings: msm: dsi: add yaml schemas for DSI bindings") Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534306/ Link: https://lore.kernel.org/r/20230427122132.24840-1-lujianhua000@gmail.com Signed-off-by: Abhinav Kumar --- .../bindings/display/msm/dsi-controller-main.yaml | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml index c8884a84e73d..51808b1d2726 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml @@ -82,6 +82,18 @@ properties: Indicates if the DSI controller is driving a panel which needs 2 DSI links. + qcom,master-dsi: + type: boolean + description: | + Indicates if the DSI controller is the master DSI controller when + qcom,dual-dsi-mode enabled. + + qcom,sync-dual-dsi: + type: boolean + description: | + Indicates if the DSI controller needs to sync the other DSI controller + with MIPI DCS commands when qcom,dual-dsi-mode enabled. + assigned-clocks: minItems: 2 maxItems: 4 From af97b7dfb0d4636d58f2341346fffce30c6c2259 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 1 May 2023 16:04:08 +0200 Subject: [PATCH 029/358] SUNRPC: Avoid relying on crypto API to derive CBC-CTS output IV Scott reports SUNRPC self-test failures regarding the output IV on arm64 when using the SIMD accelerated implementation of AES in CBC mode with ciphertext stealing ("cts(cbc(aes))" in crypto API speak). These failures are the result of the fact that, while RFC 3962 does specify what the output IV should be and includes test vectors for it, the general concept of an output IV is poorly defined, and generally, not specified by the various algorithms implemented by the crypto API. Only algorithms that support transparent chaining (e.g., CBC mode on a block boundary) have requirements on the output IV, but ciphertext stealing (CTS) is fundamentally about how to encapsulate CBC in a way where the length of the entire message may not be an integral multiple of the cipher block size, and the concept of an output IV does not exist here because it has no defined purpose past the end of the message. The generic CTS template takes advantage of this chaining capability of the CBC implementations, and as a result, happens to return an output IV, simply because it passes its IV buffer directly to the encapsulated CBC implementation, which operates on full blocks only, and always returns an IV. This output IV happens to match how RFC 3962 defines it, even though the CTS template itself does not contain any output IV logic whatsoever, and, for this reason, lacks any test vectors that exercise this accidental output IV generation. The arm64 SIMD implementation of cts(cbc(aes)) does not use the generic CTS template at all, but instead, implements the CBC mode and ciphertext stealing directly, and therefore does not encapsule a CBC implementation that returns an output IV in the same way. The arm64 SIMD implementation complies with the specification and passes all internal tests, but when invoked by the SUNRPC code, fails to produce the expected output IV and causes its selftests to fail. Given that the output IV is defined as the penultimate block (where the final block may smaller than the block size), we can quite easily derive it in the caller by copying the appropriate slice of ciphertext after encryption. Cc: Trond Myklebust Cc: Anna Schumaker Cc: Chuck Lever Cc: Jeff Layton Reported-by: Scott Mayhew Tested-by: Scott Mayhew Signed-off-by: Ard Biesheuvel Signed-off-by: Chuck Lever --- net/sunrpc/auth_gss/gss_krb5_crypto.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 212c5d57465a..9734e1d9f991 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -639,6 +639,16 @@ gss_krb5_cts_crypt(struct crypto_sync_skcipher *cipher, struct xdr_buf *buf, ret = write_bytes_to_xdr_buf(buf, offset, data, len); +#if IS_ENABLED(CONFIG_KUNIT) + /* + * CBC-CTS does not define an output IV but RFC 3962 defines it as the + * penultimate block of ciphertext, so copy that into the IV buffer + * before returning. + */ + if (encrypt) + memcpy(iv, data, crypto_sync_skcipher_ivsize(cipher)); +#endif + out: kfree(data); return ret; From 340086da9a87820b40601141a0e9e87c954ac006 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 2 May 2023 13:11:21 -0400 Subject: [PATCH 030/358] nfsd: define exports_proc_ops with CONFIG_PROC_FS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc with W=1 and ! CONFIG_PROC_FS fs/nfsd/nfsctl.c:161:30: error: ‘exports_proc_ops’ defined but not used [-Werror=unused-const-variable=] 161 | static const struct proc_ops exports_proc_ops = { | ^~~~~~~~~~~~~~~~ The only use of exports_proc_ops is when CONFIG_PROC_FS is defined, so its definition should be likewise conditional. Signed-off-by: Tom Rix Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/nfsctl.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7b8f17ee5224..c159817d1282 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -153,18 +153,6 @@ static int exports_net_open(struct net *net, struct file *file) return 0; } -static int exports_proc_open(struct inode *inode, struct file *file) -{ - return exports_net_open(current->nsproxy->net_ns, file); -} - -static const struct proc_ops exports_proc_ops = { - .proc_open = exports_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = seq_release, -}; - static int exports_nfsd_open(struct inode *inode, struct file *file) { return exports_net_open(inode->i_sb->s_fs_info, file); @@ -1458,6 +1446,19 @@ static struct file_system_type nfsd_fs_type = { MODULE_ALIAS_FS("nfsd"); #ifdef CONFIG_PROC_FS + +static int exports_proc_open(struct inode *inode, struct file *file) +{ + return exports_net_open(current->nsproxy->net_ns, file); +} + +static const struct proc_ops exports_proc_ops = { + .proc_open = exports_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, +}; + static int create_proc_exports_entry(void) { struct proc_dir_entry *entry; From fc412a6196a6f46ece0e6e6b118556464f165800 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 2 May 2023 14:07:13 -0400 Subject: [PATCH 031/358] lockd: define nlm_port_min,max with CONFIG_SYSCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc with W=1 and ! CONFIG_SYSCTL fs/lockd/svc.c:80:51: error: ‘nlm_port_max’ defined but not used [-Werror=unused-const-variable=] 80 | static const int nlm_port_min = 0, nlm_port_max = 65535; | ^~~~~~~~~~~~ fs/lockd/svc.c:80:33: error: ‘nlm_port_min’ defined but not used [-Werror=unused-const-variable=] 80 | static const int nlm_port_min = 0, nlm_port_max = 65535; | ^~~~~~~~~~~~ The only use of these variables is when CONFIG_SYSCTL is defined, so their definition should be likewise conditional. Signed-off-by: Tom Rix Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 9a47303b2cba..fe2f6dd9a874 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -77,9 +77,9 @@ static const unsigned long nlm_grace_period_min = 0; static const unsigned long nlm_grace_period_max = 240; static const unsigned long nlm_timeout_min = 3; static const unsigned long nlm_timeout_max = 20; -static const int nlm_port_min = 0, nlm_port_max = 65535; #ifdef CONFIG_SYSCTL +static const int nlm_port_min = 0, nlm_port_max = 65535; static struct ctl_table_header * nlm_sysctl_table; #endif From 29cd2927fb914cc53b5ba4f67d2b74695c994ba4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 2 May 2023 14:59:10 -0400 Subject: [PATCH 032/358] SUNRPC: Fix encoding of accepted but unsuccessful RPC replies Jiri Slaby says: > I bisected to this ... as it breaks nfs3-only servers in 6.3. > I.e. /etc/nfs.conf containing: > [nfsd] > vers4=no > > The client sees: > mount("10.0.2.15:/tmp", "/mnt", "nfs", 0, "vers=4.2,addr=10.0.2.15,clientad"...) = -1 EIO (Input/output error) > write(2, "mount.nfs: mount system call fai"..., 45 > mount.nfs: mount system call failed for /mnt > > And the kernel says: > nfs4_discover_server_trunking unhandled error -5. Exiting with error EIO Reported-by: Jiri Slaby Link: https://bugzilla.suse.com/show_bug.cgi?id=1210995 Fixes: 4bcf0343e8a6 ("SUNRPC: Set rq_accept_statp inside ->accept methods") Tested-by: Jiri Slaby Signed-off-by: Chuck Lever --- net/sunrpc/svc.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 26367cf4c17a..43e32129a583 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1416,7 +1416,7 @@ err_bad_rpc: /* Only RPCv2 supported */ xdr_stream_encode_u32(xdr, RPC_VERSION); xdr_stream_encode_u32(xdr, RPC_VERSION); - goto sendit; + return 1; /* don't wrap */ err_bad_auth: dprintk("svc: authentication failed (%d)\n", @@ -1432,7 +1432,7 @@ err_bad_auth: err_bad_prog: dprintk("svc: unknown program %d\n", rqstp->rq_prog); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROG_UNAVAIL); + *rqstp->rq_accept_statp = rpc_prog_unavail; goto sendit; err_bad_vers: @@ -1440,7 +1440,12 @@ err_bad_vers: rqstp->rq_vers, rqstp->rq_prog, progp->pg_name); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROG_MISMATCH); + *rqstp->rq_accept_statp = rpc_prog_mismatch; + + /* + * svc_authenticate() has already added the verifier and + * advanced the stream just past rq_accept_statp. + */ xdr_stream_encode_u32(xdr, process.mismatch.lovers); xdr_stream_encode_u32(xdr, process.mismatch.hivers); goto sendit; @@ -1449,19 +1454,19 @@ err_bad_proc: svc_printk(rqstp, "unknown procedure (%d)\n", rqstp->rq_proc); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROC_UNAVAIL); + *rqstp->rq_accept_statp = rpc_proc_unavail; goto sendit; err_garbage_args: svc_printk(rqstp, "failed to decode RPC header\n"); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_GARBAGE_ARGS); + *rqstp->rq_accept_statp = rpc_garbage_args; goto sendit; err_system_err: serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_SYSTEM_ERR); + *rqstp->rq_accept_statp = rpc_system_err; goto sendit; } From 1616d6c3717bae9041a4240d381ec56ccdaafedc Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 3 May 2023 18:57:33 +0300 Subject: [PATCH 033/358] nvme-pci: add NVME_QUIRK_BOGUS_NID for HS-SSD-FUTURE 2048G Add a quirk to fix HS-SSD-FUTURE 2048G SSD drives reporting duplicate nsids. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217384 Reported-by: Andrey God Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 593f86323e25..d8b660daf7c2 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3433,6 +3433,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1d97, 0x2269), /* Lexar NM760 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4b, 0x1602), /* HS-SSD-FUTURE 2048G */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), From bd375feeaf3408ed00e08c3bc918d6be15f691ad Mon Sep 17 00:00:00 2001 From: Hristo Venev Date: Tue, 25 Apr 2023 22:58:54 +0300 Subject: [PATCH 034/358] nvme-pci: add quirk for missing secondary temperature thresholds On Kingston KC3000 and Kingston FURY Renegade (both have the same PCI IDs) accessing temp3_{min,max} fails with an invalid field error (note that there is no problem setting the thresholds for temp1). This contradicts the NVM Express Base Specification 2.0b, page 292: The over temperature threshold and under temperature threshold features shall be implemented for all implemented temperature sensors (i.e., all Temperature Sensor fields that report a non-zero value). Define NVME_QUIRK_NO_SECONDARY_TEMP_THRESH that disables the thresholds for all but the composite temperature and set it for this device. Signed-off-by: Hristo Venev Reviewed-by: Guenter Roeck Signed-off-by: Christoph Hellwig --- drivers/nvme/host/hwmon.c | 4 +++- drivers/nvme/host/nvme.h | 5 +++++ drivers/nvme/host/pci.c | 2 ++ 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 9e6e56c20ec9..316f3e4ca7cc 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -163,7 +163,9 @@ static umode_t nvme_hwmon_is_visible(const void *_data, case hwmon_temp_max: case hwmon_temp_min: if ((!channel && data->ctrl->wctemp) || - (channel && data->log->temp_sensor[channel - 1])) { + (channel && data->log->temp_sensor[channel - 1] && + !(data->ctrl->quirks & + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH))) { if (data->ctrl->quirks & NVME_QUIRK_NO_TEMP_THRESH_CHANGE) return 0444; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index bf46f122e9e1..a2d4f59e0535 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -149,6 +149,11 @@ enum nvme_quirks { * Reports garbage in the namespace identifiers (eui64, nguid, uuid). */ NVME_QUIRK_BOGUS_NID = (1 << 18), + + /* + * No temperature thresholds for channels other than 0 (Composite). + */ + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH = (1 << 19), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d8b660daf7c2..18ca1e3ae070 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3401,6 +3401,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x2646, 0x5013), /* Kingston KC3000, Kingston FURY Renegade */ + .driver_data = NVME_QUIRK_NO_SECONDARY_TEMP_THRESH, }, { PCI_DEVICE(0x2646, 0x5018), /* KINGSTON OM8SFP4xxxxP OS21012 NVMe SSD */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x2646, 0x5016), /* KINGSTON OM3PGP4xxxxP OS21011 NVMe SSD */ From 3710e2b056cb92ad816e4d79fa54a6a5b6ad8cbd Mon Sep 17 00:00:00 2001 From: Adrian Huang Date: Fri, 21 Apr 2023 16:08:00 +0800 Subject: [PATCH 035/358] nvme-pci: clamp max_hw_sectors based on DMA optimized limitation When running the fio test on a 448-core AMD server + a NVME disk, a soft lockup or a hard lockup call trace is shown: [soft lockup] watchdog: BUG: soft lockup - CPU#126 stuck for 23s! [swapper/126:0] RIP: 0010:_raw_spin_unlock_irqrestore+0x21/0x50 ... Call Trace: fq_flush_timeout+0x7d/0xd0 ? __pfx_fq_flush_timeout+0x10/0x10 call_timer_fn+0x2e/0x150 run_timer_softirq+0x48a/0x560 ? __pfx_fq_flush_timeout+0x10/0x10 ? clockevents_program_event+0xaf/0x130 __do_softirq+0xf1/0x335 irq_exit_rcu+0x9f/0xd0 sysvec_apic_timer_interrupt+0xb4/0xd0 asm_sysvec_apic_timer_interrupt+0x1f/0x30 ... Obvisouly, fq_flush_timeout spends over 20 seconds. Here is ftrace log: | fq_flush_timeout() { | fq_ring_free() { | put_pages_list() { 0.170 us | free_unref_page_list(); 0.810 us | } | free_iova_fast() { | free_iova() { * 85622.66 us | _raw_spin_lock_irqsave(); 2.860 us | remove_iova(); 0.600 us | _raw_spin_unlock_irqrestore(); 0.470 us | lock_info_report(); 2.420 us | free_iova_mem.part.0(); * 85638.27 us | } * 85638.84 us | } | put_pages_list() { 0.230 us | free_unref_page_list(); 0.470 us | } ... ... $ 31017069 us | } Most of cores are under lock contention for acquiring iova_rbtree_lock due to the iova flush queue mechanism. [hard lockup] NMI watchdog: Watchdog detected hard LOCKUP on cpu 351 RIP: 0010:native_queued_spin_lock_slowpath+0x2d8/0x330 Call Trace: _raw_spin_lock_irqsave+0x4f/0x60 free_iova+0x27/0xd0 free_iova_fast+0x4d/0x1d0 fq_ring_free+0x9b/0x150 iommu_dma_free_iova+0xb4/0x2e0 __iommu_dma_unmap+0x10b/0x140 iommu_dma_unmap_sg+0x90/0x110 dma_unmap_sg_attrs+0x4a/0x50 nvme_unmap_data+0x5d/0x120 [nvme] nvme_pci_complete_batch+0x77/0xc0 [nvme] nvme_irq+0x2ee/0x350 [nvme] ? __pfx_nvme_pci_complete_batch+0x10/0x10 [nvme] __handle_irq_event_percpu+0x53/0x1a0 handle_irq_event_percpu+0x19/0x60 handle_irq_event+0x3d/0x60 handle_edge_irq+0xb3/0x210 __common_interrupt+0x7f/0x150 common_interrupt+0xc5/0xf0 asm_common_interrupt+0x2b/0x40 ... ftrace shows fq_ring_free spends over 10 seconds [1]. Again, most of cores are under lock contention for acquiring iova_rbtree_lock due to the iova flush queue mechanism. [Root Cause] The root cause is that the max_hw_sectors_kb of nvme disk (mdts=10) is 4096kb, which streaming DMA mappings cannot benefit from the scalable IOVA mechanism introduced by the commit 9257b4a206fc ("iommu/iova: introduce per-cpu caching to iova allocation") if the length is greater than 128kb. To fix the lock contention issue, clamp max_hw_sectors based on DMA optimized limitation in order to leverage scalable IOVA mechanism. Note: The issue does not happen with another NVME disk (mdts = 5 and max_hw_sectors_kb = 128) [1] https://gist.github.com/AdrianHuang/bf8ec7338204837631fbdaed25d19cc4 Suggested-by: Keith Busch Reported-and-tested-by: Jiwei Sun Signed-off-by: Adrian Huang Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 18ca1e3ae070..922ffe4e2822 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2956,7 +2956,7 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, * over a single page. */ dev->ctrl.max_hw_sectors = min_t(u32, - NVME_MAX_KB_SZ << 1, dma_max_mapping_size(&pdev->dev) >> 9); + NVME_MAX_KB_SZ << 1, dma_opt_mapping_size(&pdev->dev) >> 9); dev->ctrl.max_segments = NVME_MAX_SEGS; /* From 319050d4302ee9b216fb8cea847a9c4427628a98 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 4 May 2023 13:43:33 -0400 Subject: [PATCH 036/358] SUNRPC: Fix error handling in svc_setup_socket() Dan points out that sock_alloc_file() releases @sock on error, but so do all of svc_setup_socket's callers, resulting in a double- release if sock_alloc_file() returns an error. Rather than allocating a struct file for all new sockets, allocate one only for sockets created during a TCP accept. For the moment, those are the only ones that will ever be used with RPC-with-TLS. Reported-by: Dan Carpenter Fixes: ae0d77708aae ("SUNRPC: Ensure server-side sockets have a sock->file") Signed-off-by: Chuck Lever --- net/sunrpc/svcsock.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index a51c9b989d58..9989194446a5 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -895,6 +895,9 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) trace_svcsock_accept_err(xprt, serv->sv_name, err); return NULL; } + if (IS_ERR(sock_alloc_file(newsock, O_NONBLOCK, NULL))) + return NULL; + set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); err = kernel_getpeername(newsock, sin); @@ -935,7 +938,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) return &newsvsk->sk_xprt; failed: - sock_release(newsock); + sockfd_put(newsock); return NULL; } @@ -1430,7 +1433,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, struct socket *sock, int flags) { - struct file *filp = NULL; struct svc_sock *svsk; struct sock *inet; int pmap_register = !(flags & SVC_SOCK_ANONYMOUS); @@ -1439,14 +1441,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, if (!svsk) return ERR_PTR(-ENOMEM); - if (!sock->file) { - filp = sock_alloc_file(sock, O_NONBLOCK, NULL); - if (IS_ERR(filp)) { - kfree(svsk); - return ERR_CAST(filp); - } - } - inet = sock->sk; if (pmap_register) { @@ -1456,8 +1450,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, inet->sk_protocol, ntohs(inet_sk(inet)->inet_sport)); if (err < 0) { - if (filp) - fput(filp); kfree(svsk); return ERR_PTR(err); } From 0a6b36c5dc3dda0196f4fb65bdb34c38b8d060c3 Mon Sep 17 00:00:00 2001 From: Jeremy Soller Date: Fri, 5 May 2023 10:36:51 -0600 Subject: [PATCH 037/358] ALSA: hda/realtek: Add quirk for Clevo L140AU Fixes headset detection on Clevo L140AU. Signed-off-by: Jeremy Soller Signed-off-by: Tim Crawford Cc: Link: https://lore.kernel.org/r/20230505163651.21257-1-tcrawford@system76.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 172ffc2c332b..e7d2e20b91f5 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9618,6 +9618,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x7716, "Clevo NS50PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7717, "Clevo NS70PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7718, "Clevo L140PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x7724, "Clevo L140AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), From a4671b7fba59775845ee60cfbdfc4ba64300211b Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Sat, 6 May 2023 11:58:24 +1200 Subject: [PATCH 038/358] ALSA: hda/realtek: Add quirk for 2nd ASUS GU603 Add quirk for GU603 with 0x1c62 variant of codec. Signed-off-by: Luke D. Jones Cc: Link: https://lore.kernel.org/r/20230505235824.49607-2-luke@ljones.dev Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index e7d2e20b91f5..7082b1d220c5 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9522,6 +9522,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), From 90670ef774a8b6700c38ce1222e6aa263be54d5f Mon Sep 17 00:00:00 2001 From: Ai Chao Date: Sat, 6 May 2023 10:26:53 +0800 Subject: [PATCH 039/358] ALSA: hda/realtek: Add a quirk for HP EliteDesk 805 Add a quirk for HP EliteDesk 805 to fixup ALC3867 headset MIC no sound. Signed-off-by: Ai Chao Cc: Link: https://lore.kernel.org/r/20230506022653.2074343-1-aichao@kylinos.cn Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7082b1d220c5..bc062c0a1916 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11665,6 +11665,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x103c, 0x870c, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB), + SND_PCI_QUIRK(0x103c, 0x872b, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x885f, "HP 288 Pro G8", ALC671_FIXUP_HP_HEADSET_MIC2), From 79de36042eecb684e0f748d17ba52f365fde0d65 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 5 May 2023 12:18:17 -0500 Subject: [PATCH 040/358] powerpc/isa-bridge: Fix ISA mapping when "ranges" is not present Commit e4ab08be5b49 ("powerpc/isa-bridge: Remove open coded "ranges" parsing") broke PASemi Nemo board booting. The issue is the ISA I/O range was not getting mapped as the logic to handle no "ranges" was inverted. If phb_io_base_phys is non-zero, then the ISA range defaults to the first 64K of the PCI I/O space. phb_io_base_phys should only be 0 when looking for a non-PCI ISA region. Fixes: e4ab08be5b49 ("powerpc/isa-bridge: Remove open coded "ranges" parsing") Reported-by: Christian Zigotzky Link: https://lore.kernel.org/all/301595ad-0edf-2113-b55f-f5b8051ed24c@xenosoft.de/ Signed-off-by: Rob Herring Tested-by: Christian Zigotzky Signed-off-by: Michael Ellerman Link: https://msgid.link/20230505171816.3175865-1-robh@kernel.org --- arch/powerpc/kernel/isa-bridge.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 85bdd7d3652f..48e0eaf1ad61 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -93,11 +93,12 @@ static int process_ISA_OF_ranges(struct device_node *isa_node, } inval_range: - if (!phb_io_base_phys) { + if (phb_io_base_phys) { pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n"); remap_isa_base(phb_io_base_phys, 0x10000); + return 0; } - return 0; + return -EINVAL; } From 536d948a8dee21166d9c5b5a4189af56beba16e3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 28 Apr 2023 21:35:19 -0700 Subject: [PATCH 041/358] powerpc/fsl_uli1575: fix kconfig warnings and build errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Neither FSL_SOC_BOOKE nor PPC_86xx enables CONFIG_PCI by default, so it may be unset in some randconfigs. When that happens, FSL_ULI1575 may be set when it should not be since it is a PCI driver. When it is set, there are 3 kconfig warnings and a slew of build errors WARNING: unmet direct dependencies detected for PCI_QUIRKS Depends on [n]: PCI [=n] Selected by [y]: - FSL_PCI [=y] WARNING: unmet direct dependencies detected for GENERIC_ISA_DMA Depends on [n]: ISA_DMA_API [=n] Selected by [y]: - FSL_ULI1575 [=y] && (FSL_SOC_BOOKE [=n] || PPC_86xx [=y]) WARNING: unmet direct dependencies detected for PPC_INDIRECT_PCI Depends on [n]: PCI [=n] Selected by [y]: - FSL_PCI [=y] and 30+ build errors. Fixes: 22fdf79171e8 ("powerpc/fsl_uli1575: Allow to disable FSL_ULI1575 support") Signed-off-by: Randy Dunlap Reviewed-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230429043519.19807-1-rdunlap@infradead.org --- arch/powerpc/platforms/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 0d9b7609c7d5..3e2e252016f7 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -265,6 +265,7 @@ config CPM2 config FSL_ULI1575 bool "ULI1575 PCIe south bridge support" depends on FSL_SOC_BOOKE || PPC_86xx + depends on PCI select FSL_PCI select GENERIC_ISA_DMA help From e652be0f59d4ba4d5c636b1f7f4dcb73aae049fa Mon Sep 17 00:00:00 2001 From: Hao Zeng Date: Tue, 18 Apr 2023 09:30:56 +0800 Subject: [PATCH 042/358] cpupower:Fix resource leaks in sysfs_get_enabled() The sysfs_get_enabled() opened file processor not closed, may cause a file handle leak. Putting error handling and resource cleanup code together makes the code easy to maintain and read. Removed the unnecessary else if branch from the original function, as it should return an error in cases other than '0'. Signed-off-by: Hao Zeng Suggested-by: Shuah Khan Signed-off-by: Shuah Khan --- tools/power/cpupower/lib/powercap.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/tools/power/cpupower/lib/powercap.c b/tools/power/cpupower/lib/powercap.c index 0ce29ee4c2e4..a7a59c6bacda 100644 --- a/tools/power/cpupower/lib/powercap.c +++ b/tools/power/cpupower/lib/powercap.c @@ -40,25 +40,34 @@ static int sysfs_get_enabled(char *path, int *mode) { int fd; char yes_no; + int ret = 0; *mode = 0; fd = open(path, O_RDONLY); - if (fd == -1) - return -1; + if (fd == -1) { + ret = -1; + goto out; + } if (read(fd, &yes_no, 1) != 1) { - close(fd); - return -1; + ret = -1; + goto out_close; } if (yes_no == '1') { *mode = 1; - return 0; + goto out_close; } else if (yes_no == '0') { - return 0; + goto out_close; + } else { + ret = -1; + goto out_close; } - return -1; +out_close: + close(fd); +out: + return ret; } int powercap_get_enabled(int *mode) From c2adb1877b76fc81ae041e1db1a6ed2078c6746b Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Thu, 4 May 2023 06:25:44 +0000 Subject: [PATCH 043/358] cpupower: Make TSC read per CPU for Mperf monitor System-wide TSC read could cause a drift in C0 percentage calculation. Because if first TSC is read and then one by one mperf is read for all cpus, this introduces drift between mperf reading of later CPUs and TSC reading. To lower this drift read TSC per CPU and also just after mperf read. This technique improves C0 percentage calculation in Mperf monitor. Before fix: (System 100% busy) | Mperf || RAPL || Idle_Stats PKG|CORE| CPU| C0 | Cx | Freq || pack | core || POLL | C1 | C2 0| 0| 0| 87.15| 12.85| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 0| 256| 84.62| 15.38| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 1| 1| 87.15| 12.85| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 1| 257| 84.08| 15.92| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 2| 2| 86.61| 13.39| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 2| 258| 83.26| 16.74| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 3| 3| 86.61| 13.39| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 3| 259| 83.60| 16.40| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 4| 4| 86.33| 13.67| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 4| 260| 83.33| 16.67| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 5| 5| 86.06| 13.94| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 5| 261| 83.05| 16.95| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 6| 6| 85.51| 14.49| 2695||168659003|3970468|| 0.00| 0.00| 0.00 After fix: (System 100% busy) | Mperf || RAPL || Idle_Stats PKG|CORE| CPU| C0 | Cx | Freq || pack | core || POLL | C1 | C2 0| 0| 0| 98.03| 1.97| 2415||163295480|3811189|| 0.00| 0.00| 0.00 0| 0| 256| 98.50| 1.50| 2394||163295480|3811189|| 0.00| 0.00| 0.00 0| 1| 1| 99.99| 0.01| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 1| 257| 99.99| 0.01| 2375||163295480|3811189|| 0.00| 0.00| 0.00 0| 2| 2| 99.99| 0.01| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 2| 258|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 3| 3|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 3| 259| 99.99| 0.01| 2435||163295480|3811189|| 0.00| 0.00| 0.00 0| 4| 4|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 4| 260|100.00| 0.00| 2435||163295480|3811189|| 0.00| 0.00| 0.00 0| 5| 5| 99.99| 0.01| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 5| 261|100.00| 0.00| 2435||163295480|3811189|| 0.00| 0.00| 0.00 0| 6| 6|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 6| 262|100.00| 0.00| 2435||163295480|3811189|| 0.00| 0.00| 0.00 Cc: Thomas Renninger Cc: Shuah Khan Cc: Dominik Brodowski Fixes: 7fe2f6399a84 ("cpupowerutils - cpufrequtils extended with quite some features") Signed-off-by: Wyes Karny Signed-off-by: Shuah Khan --- .../utils/idle_monitor/mperf_monitor.c | 31 +++++++++---------- 1 file changed, 14 insertions(+), 17 deletions(-) diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index e7d48cb563c0..ae6af354a81d 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -70,8 +70,8 @@ static int max_freq_mode; */ static unsigned long max_frequency; -static unsigned long long tsc_at_measure_start; -static unsigned long long tsc_at_measure_end; +static unsigned long long *tsc_at_measure_start; +static unsigned long long *tsc_at_measure_end; static unsigned long long *mperf_previous_count; static unsigned long long *aperf_previous_count; static unsigned long long *mperf_current_count; @@ -169,7 +169,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, aperf_diff = aperf_current_count[cpu] - aperf_previous_count[cpu]; if (max_freq_mode == MAX_FREQ_TSC_REF) { - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; *percent = 100.0 * mperf_diff / tsc_diff; dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); @@ -206,7 +206,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; time_diff = timespec_diff_us(time_start, time_end); max_frequency = tsc_diff / time_diff; } @@ -225,33 +225,27 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, static int mperf_start(void) { int cpu; - unsigned long long dbg; clock_gettime(CLOCK_REALTIME, &time_start); - mperf_get_tsc(&tsc_at_measure_start); - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { + mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); + } - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start); return 0; } static int mperf_stop(void) { - unsigned long long dbg; int cpu; - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); + mperf_get_tsc(&tsc_at_measure_end[cpu]); + } - mperf_get_tsc(&tsc_at_measure_end); clock_gettime(CLOCK_REALTIME, &time_end); - - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end); - return 0; } @@ -353,7 +347,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_previous_count = calloc(cpu_count, sizeof(unsigned long long)); mperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); - + tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); + tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -364,6 +359,8 @@ void mperf_unregister(void) free(aperf_previous_count); free(mperf_current_count); free(aperf_current_count); + free(tsc_at_measure_start); + free(tsc_at_measure_end); free(is_valid); } From 4b79f76920a49fc13766b95df1df1f4d700acbad Mon Sep 17 00:00:00 2001 From: Yi Lai Date: Fri, 21 Apr 2023 11:31:23 +0800 Subject: [PATCH 044/358] selftests/sgx: Add "test_encl.elf" to TEST_FILES The "test_encl.elf" file used by test_sgx is not installed in INSTALL_PATH. Attempting to execute test_sgx causes false negative: " enclave executable open(): No such file or directory main.c:188:unclobbered_vdso:Failed to load the test enclave. " Add "test_encl.elf" to TEST_FILES so that it will be installed. Fixes: 2adcba79e69d ("selftests/x86: Add a selftest for SGX") Signed-off-by: Yi Lai Reviewed-by: Jarkko Sakkinen Signed-off-by: Shuah Khan --- tools/testing/selftests/sgx/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 75af864e07b6..50aab6b57da3 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -17,6 +17,7 @@ ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ -fno-stack-protector -mrdrnd $(INCLUDES) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx +TEST_FILES := $(OUTPUT)/test_encl.elf ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf From dbcf76390eb9a65d5d0c37b0cd57335218564e37 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 8 May 2023 22:15:42 +0900 Subject: [PATCH 045/358] selftests/ftrace: Improve integration with kselftest runner The ftrace selftests do not currently produce KTAP output, they produce a custom format much nicer for human consumption. This means that when run in automated test systems we just get a single result for the suite as a whole rather than recording results for individual test cases, making it harder to look at the test data and masking things like inappropriate skips. Address this by adding support for KTAP output to the ftracetest script and providing a trivial wrapper which will be invoked by the kselftest runner to generate output in this format by default, users using ftracetest directly will continue to get the existing output. This is not the most elegant solution but it is simple and effective. I did consider implementing this by post processing the existing output format but that felt more complex and likely to result in all output being lost if something goes seriously wrong during the run which would not be helpful. I did also consider just writing a separate runner script but there's enough going on with things like the signal handling for that to seem like it would be duplicating too much. Acked-by: Steven Rostedt (Google) Acked-by: Masami Hiramatsu (Google) Tested-by: Masami Hiramatsu (Google) Signed-off-by: Mark Brown Signed-off-by: Shuah Khan --- tools/testing/selftests/ftrace/Makefile | 3 +- tools/testing/selftests/ftrace/ftracetest | 63 ++++++++++++++++++- .../testing/selftests/ftrace/ftracetest-ktap | 8 +++ 3 files changed, 70 insertions(+), 4 deletions(-) create mode 100755 tools/testing/selftests/ftrace/ftracetest-ktap diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index d6e106fbce11..a1e955d2de4c 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 all: -TEST_PROGS := ftracetest +TEST_PROGS_EXTENDED := ftracetest +TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c3311c8c4089..2506621e75df 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" +echo " -K|--ktap Output in KTAP format" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" @@ -85,6 +86,10 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; + --ktap|-K) + KTAP=1 + shift 1 + ;; --verbose|-v|-vv|-vvv) if [ $VERBOSE -eq -1 ]; then usage "--console can not use with --verbose" @@ -178,6 +183,7 @@ TEST_DIR=$TOP_DIR/test.d TEST_CASES=`find_testcases $TEST_DIR` LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 +KTAP=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 @@ -229,7 +235,7 @@ prlog() { # messages newline= shift fi - printf "$*$newline" + [ "$KTAP" != "1" ] && printf "$*$newline" [ "$LOG_FILE" ] && printf "$*$newline" | strip_esc >> $LOG_FILE } catlog() { #file @@ -260,11 +266,11 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 +CASENAME= testcase() { # testfile CASENO=$((CASENO+1)) - desc=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` - prlog -n "[$CASENO]$INSTANCE$desc" + CASENAME=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` } checkreq() { # testfile @@ -277,40 +283,68 @@ test_on_instance() { # testfile grep -q "^#[ \t]*flags:.*instance" $1 } +ktaptest() { # result comment + if [ "$KTAP" != "1" ]; then + return + fi + + local result= + if [ "$1" = "1" ]; then + result="ok" + else + result="not ok" + fi + shift + + local comment=$* + if [ "$comment" != "" ]; then + comment="# $comment" + fi + + echo $CASENO $result $INSTANCE$CASENAME $comment +} + eval_result() { # sigval case $1 in $PASS) prlog " [${color_green}PASS${color_reset}]" + ktaptest 1 PASSED_CASES="$PASSED_CASES $CASENO" return 0 ;; $FAIL) prlog " [${color_red}FAIL${color_reset}]" + ktaptest 0 FAILED_CASES="$FAILED_CASES $CASENO" return 1 # this is a bug. ;; $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" + ktaptest 0 UNRESOLVED UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" + ktaptest 1 SKIP UNTESTED_CASES="$UNTESTED_CASES $CASENO" return 0 ;; $UNSUPPORTED) prlog " [${color_blue}UNSUPPORTED${color_reset}]" + ktaptest 1 SKIP UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) prlog " [${color_green}XFAIL${color_reset}]" + ktaptest 1 XFAIL XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; *) prlog " [${color_blue}UNDEFINED${color_reset}]" + ktaptest 0 error UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" return 1 # this must be a test bug ;; @@ -371,6 +405,7 @@ __run_test() { # testfile run_test() { # testfile local testname=`basename $1` testcase $1 + prlog -n "[$CASENO]$INSTANCE$CASENAME" if [ ! -z "$LOG_FILE" ] ; then local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX` else @@ -405,6 +440,17 @@ run_test() { # testfile # load in the helper functions . $TEST_DIR/functions +if [ "$KTAP" = "1" ]; then + echo "TAP version 13" + + casecount=`echo $TEST_CASES | wc -w` + for t in $TEST_CASES; do + test_on_instance $t || continue + casecount=$((casecount+1)) + done + echo "1..${casecount}" +fi + # Main loop for t in $TEST_CASES; do run_test $t @@ -439,6 +485,17 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +if [ "$KTAP" = "1" ]; then + echo -n "# Totals:" + echo -n " pass:"`echo $PASSED_CASES | wc -w` + echo -n " faii:"`echo $FAILED_CASES | wc -w` + echo -n " xfail:"`echo $XFAILED_CASES | wc -w` + echo -n " xpass:0" + echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w` + echo -n " error:"`echo $UNRESOLVED_CASES $UNDEFINED_CASES | wc -w` + echo +fi + cleanup # if no error, return 0 diff --git a/tools/testing/selftests/ftrace/ftracetest-ktap b/tools/testing/selftests/ftrace/ftracetest-ktap new file mode 100755 index 000000000000..b3284679ef3a --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest-ktap @@ -0,0 +1,8 @@ +#!/bin/sh -e +# SPDX-License-Identifier: GPL-2.0-only +# +# ftracetest-ktap: Wrapper to integrate ftracetest with the kselftest runner +# +# Copyright (C) Arm Ltd., 2023 + +./ftracetest -K From c4af8e3fecd03b0aedcd38145955605cfebe7e3a Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 24 Apr 2023 14:55:54 -0500 Subject: [PATCH 046/358] thunderbolt: Clear registers properly when auto clear isn't in use When `QUIRK_AUTO_CLEAR_INT` isn't set, interrupt masking should be cleared by writing to Interrupt Mask Clear (IMR) and interrupt status should be cleared properly at shutdown/init. This fixes an error where interrupts are left enabled during resume from hibernation with `CONFIG_USB4=y`. Fixes: 468c49f44759 ("thunderbolt: Disable interrupt auto clear for rings") Cc: stable@vger.kernel.org # v6.3 Reported-by: Takashi Iwai Link: https://bugzilla.kernel.org/show_bug.cgi?id=217343 Signed-off-by: Mario Limonciello Signed-off-by: Mika Westerberg --- drivers/thunderbolt/nhi.c | 29 ++++++++++++++++++++++++----- drivers/thunderbolt/nhi_regs.h | 2 ++ 2 files changed, 26 insertions(+), 5 deletions(-) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index d76e923fbc6a..c0aee5dc5237 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -54,6 +54,21 @@ static int ring_interrupt_index(const struct tb_ring *ring) return bit; } +static void nhi_mask_interrupt(struct tb_nhi *nhi, int mask, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + return; + iowrite32(mask, nhi->iobase + REG_RING_INTERRUPT_MASK_CLEAR_BASE + ring); +} + +static void nhi_clear_interrupt(struct tb_nhi *nhi, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + ring); + else + iowrite32(~0, nhi->iobase + REG_RING_INT_CLEAR + ring); +} + /* * ring_interrupt_active() - activate/deactivate interrupts for a single ring * @@ -61,8 +76,8 @@ static int ring_interrupt_index(const struct tb_ring *ring) */ static void ring_interrupt_active(struct tb_ring *ring, bool active) { - int reg = REG_RING_INTERRUPT_BASE + - ring_interrupt_index(ring) / 32 * 4; + int index = ring_interrupt_index(ring) / 32 * 4; + int reg = REG_RING_INTERRUPT_BASE + index; int interrupt_bit = ring_interrupt_index(ring) & 31; int mask = 1 << interrupt_bit; u32 old, new; @@ -123,7 +138,11 @@ static void ring_interrupt_active(struct tb_ring *ring, bool active) "interrupt for %s %d is already %s\n", RING_TYPE(ring), ring->hop, active ? "enabled" : "disabled"); - iowrite32(new, ring->nhi->iobase + reg); + + if (active) + iowrite32(new, ring->nhi->iobase + reg); + else + nhi_mask_interrupt(ring->nhi, mask, index); } /* @@ -136,11 +155,11 @@ static void nhi_disable_interrupts(struct tb_nhi *nhi) int i = 0; /* disable interrupts */ for (i = 0; i < RING_INTERRUPT_REG_COUNT(nhi); i++) - iowrite32(0, nhi->iobase + REG_RING_INTERRUPT_BASE + 4 * i); + nhi_mask_interrupt(nhi, ~0, 4 * i); /* clear interrupt status bits */ for (i = 0; i < RING_NOTIFY_REG_COUNT(nhi); i++) - ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + 4 * i); + nhi_clear_interrupt(nhi, 4 * i); } /* ring helper methods */ diff --git a/drivers/thunderbolt/nhi_regs.h b/drivers/thunderbolt/nhi_regs.h index faef165a919c..6ba295815477 100644 --- a/drivers/thunderbolt/nhi_regs.h +++ b/drivers/thunderbolt/nhi_regs.h @@ -93,6 +93,8 @@ struct ring_desc { #define REG_RING_INTERRUPT_BASE 0x38200 #define RING_INTERRUPT_REG_COUNT(nhi) ((31 + 2 * nhi->hop_count) / 32) +#define REG_RING_INTERRUPT_MASK_CLEAR_BASE 0x38208 + #define REG_INT_THROTTLING_RATE 0x38c00 /* Interrupt Vector Allocation */ From 73a23d7710331a530e972903318528b75e5a5f58 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 25 Apr 2023 10:38:37 +0200 Subject: [PATCH 047/358] um: harddog: fix modular build Since we no longer (want to) export any libc symbols the _user portions of any drivers need to be built into image rather than the module. I missed this for the watchdog. Fix the watchdog accordingly. Reported-by: kernel test robot Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger --- arch/um/drivers/Makefile | 4 +++- arch/um/drivers/harddog.h | 9 +++++++++ arch/um/drivers/harddog_kern.c | 7 +------ arch/um/drivers/harddog_user.c | 1 + arch/um/drivers/harddog_user_exp.c | 9 +++++++++ 5 files changed, 23 insertions(+), 7 deletions(-) create mode 100644 arch/um/drivers/harddog.h create mode 100644 arch/um/drivers/harddog_user_exp.c diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile index dee6f66353b3..a461a950f051 100644 --- a/arch/um/drivers/Makefile +++ b/arch/um/drivers/Makefile @@ -16,7 +16,8 @@ mconsole-objs := mconsole_kern.o mconsole_user.o hostaudio-objs := hostaudio_kern.o ubd-objs := ubd_kern.o ubd_user.o port-objs := port_kern.o port_user.o -harddog-objs := harddog_kern.o harddog_user.o +harddog-objs := harddog_kern.o +harddog-builtin-$(CONFIG_UML_WATCHDOG) := harddog_user.o harddog_user_exp.o rtc-objs := rtc_kern.o rtc_user.o LDFLAGS_pcap.o = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a) @@ -60,6 +61,7 @@ obj-$(CONFIG_PTY_CHAN) += pty.o obj-$(CONFIG_TTY_CHAN) += tty.o obj-$(CONFIG_XTERM_CHAN) += xterm.o xterm_kern.o obj-$(CONFIG_UML_WATCHDOG) += harddog.o +obj-y += $(harddog-builtin-y) $(harddog-builtin-m) obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o obj-$(CONFIG_UML_RANDOM) += random.o obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o diff --git a/arch/um/drivers/harddog.h b/arch/um/drivers/harddog.h new file mode 100644 index 000000000000..6d9ea60e7133 --- /dev/null +++ b/arch/um/drivers/harddog.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef UM_WATCHDOG_H +#define UM_WATCHDOG_H + +int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); +void stop_watchdog(int in_fd, int out_fd); +int ping_watchdog(int fd); + +#endif /* UM_WATCHDOG_H */ diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index e6d4f43deba8..60d1c6cab8a9 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -47,6 +47,7 @@ #include #include #include "mconsole.h" +#include "harddog.h" MODULE_LICENSE("GPL"); @@ -60,8 +61,6 @@ static int harddog_out_fd = -1; * Allow only one person to hold it open */ -extern int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); - static int harddog_open(struct inode *inode, struct file *file) { int err = -EBUSY; @@ -92,8 +91,6 @@ err: return err; } -extern void stop_watchdog(int in_fd, int out_fd); - static int harddog_release(struct inode *inode, struct file *file) { /* @@ -112,8 +109,6 @@ static int harddog_release(struct inode *inode, struct file *file) return 0; } -extern int ping_watchdog(int fd); - static ssize_t harddog_write(struct file *file, const char __user *data, size_t len, loff_t *ppos) { diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c index 070468d22e39..9ed89304975e 100644 --- a/arch/um/drivers/harddog_user.c +++ b/arch/um/drivers/harddog_user.c @@ -7,6 +7,7 @@ #include #include #include +#include "harddog.h" struct dog_data { int stdin_fd; diff --git a/arch/um/drivers/harddog_user_exp.c b/arch/um/drivers/harddog_user_exp.c new file mode 100644 index 000000000000..c74d4b815d14 --- /dev/null +++ b/arch/um/drivers/harddog_user_exp.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include "harddog.h" + +#if IS_MODULE(CONFIG_UML_WATCHDOG) +EXPORT_SYMBOL(start_watchdog); +EXPORT_SYMBOL(stop_watchdog); +EXPORT_SYMBOL(ping_watchdog); +#endif From 3d776e31c841ba2f69895d2255a49320bec7cea6 Mon Sep 17 00:00:00 2001 From: Tobias Brunner Date: Tue, 9 May 2023 10:59:58 +0200 Subject: [PATCH 048/358] xfrm: Reject optional tunnel/BEET mode templates in outbound policies xfrm_state_find() uses `encap_family` of the current template with the passed local and remote addresses to find a matching state. If an optional tunnel or BEET mode template is skipped in a mixed-family scenario, there could be a mismatch causing an out-of-bounds read as the addresses were not replaced to match the family of the next template. While there are theoretical use cases for optional templates in outbound policies, the only practical one is to skip IPComp states in inbound policies if uncompressed packets are received that are handled by an implicitly created IPIP state instead. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Tobias Brunner Acked-by: Herbert Xu Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index af8fbcbfbe69..6794b9dea27a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1768,7 +1768,7 @@ static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut, } static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, - struct netlink_ext_ack *extack) + int dir, struct netlink_ext_ack *extack) { u16 prev_family; int i; @@ -1794,6 +1794,10 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, switch (ut[i].mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: + if (ut[i].optional && dir == XFRM_POLICY_OUT) { + NL_SET_ERR_MSG(extack, "Mode in optional template not allowed in outbound policy"); + return -EINVAL; + } break; default: if (ut[i].family != prev_family) { @@ -1831,7 +1835,7 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, } static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs, - struct netlink_ext_ack *extack) + int dir, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_TMPL]; @@ -1842,7 +1846,7 @@ static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs, int nr = nla_len(rt) / sizeof(*utmpl); int err; - err = validate_tmpl(nr, utmpl, pol->family, extack); + err = validate_tmpl(nr, utmpl, pol->family, dir, extack); if (err) return err; @@ -1919,7 +1923,7 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, if (err) goto error; - if (!(err = copy_from_user_tmpl(xp, attrs, extack))) + if (!(err = copy_from_user_tmpl(xp, attrs, p->dir, extack))) err = copy_from_user_sec_ctx(xp, attrs); if (err) goto error; @@ -3498,7 +3502,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, return NULL; nr = ((len - sizeof(*p)) / sizeof(*ut)); - if (validate_tmpl(nr, ut, p->sel.family, NULL)) + if (validate_tmpl(nr, ut, p->sel.family, p->dir, NULL)) return NULL; if (p->dir > XFRM_POLICY_OUT) From cf3128a7aca55b2eefb68281d44749c683bdc96f Mon Sep 17 00:00:00 2001 From: Tobias Brunner Date: Tue, 9 May 2023 11:00:06 +0200 Subject: [PATCH 049/358] af_key: Reject optional tunnel/BEET mode templates in outbound policies xfrm_state_find() uses `encap_family` of the current template with the passed local and remote addresses to find a matching state. If an optional tunnel or BEET mode template is skipped in a mixed-family scenario, there could be a mismatch causing an out-of-bounds read as the addresses were not replaced to match the family of the next template. While there are theoretical use cases for optional templates in outbound policies, the only practical one is to skip IPComp states in inbound policies if uncompressed packets are received that are handled by an implicitly created IPIP state instead. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Tobias Brunner Acked-by: Herbert Xu Signed-off-by: Steffen Klassert --- net/key/af_key.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/key/af_key.c b/net/key/af_key.c index a815f5ab4c49..31ab12fd720a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1940,7 +1940,8 @@ static u32 gen_reqid(struct net *net) } static int -parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) +parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_policy *pol, + struct sadb_x_ipsecrequest *rq) { struct net *net = xp_net(xp); struct xfrm_tmpl *t = xp->xfrm_vec + xp->xfrm_nr; @@ -1958,9 +1959,12 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; - if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) + if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) { + if ((mode == XFRM_MODE_TUNNEL || mode == XFRM_MODE_BEET) && + pol->sadb_x_policy_dir == IPSEC_DIR_OUTBOUND) + return -EINVAL; t->optional = 1; - else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { + } else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { t->reqid = rq->sadb_x_ipsecrequest_reqid; if (t->reqid > IPSEC_MANUAL_REQID_MAX) t->reqid = 0; @@ -2002,7 +2006,7 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) rq->sadb_x_ipsecrequest_len < sizeof(*rq)) return -EINVAL; - if ((err = parse_ipsecrequest(xp, rq)) < 0) + if ((err = parse_ipsecrequest(xp, pol, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; rq = (void*)((u8*)rq + rq->sadb_x_ipsecrequest_len); From 8680407b6f8f5fba59e8f1d63c869abc280f04df Mon Sep 17 00:00:00 2001 From: Benedict Wong Date: Wed, 10 May 2023 01:14:14 +0000 Subject: [PATCH 050/358] xfrm: Check if_id in inbound policy/secpath match This change ensures that if configured in the policy, the if_id set in the policy and secpath states match during the inbound policy check. Without this, there is potential for ambiguity where entries in the secpath differing by only the if_id could be mismatched. Notably, this is checked in the outbound direction when resolving templates to SAs, but not on the inbound path when matching SAs and policies. Test: Tested against Android kernel unit tests & CTS Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 21a3a1cd3d6d..6d15788b5123 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3312,7 +3312,7 @@ xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, - unsigned short family) + unsigned short family, u32 if_id) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); @@ -3323,7 +3323,8 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, (tmpl->allalgs || (tmpl->aalgos & (1<props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && - xfrm_state_addr_cmp(tmpl, x, family)); + xfrm_state_addr_cmp(tmpl, x, family)) && + (if_id == 0 || if_id == x->if_id); } /* @@ -3335,7 +3336,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, - unsigned short family) + unsigned short family, u32 if_id) { int idx = start; @@ -3345,7 +3346,7 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star } else start = -1; for (; idx < sp->len; idx++) { - if (xfrm_state_ok(tmpl, sp->xvec[idx], family)) + if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (start == -1) @@ -3724,7 +3725,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * are implied between each two transformations. */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { - k = xfrm_policy_ok(tpp[i], sp, k, family); + k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ From 2a939c8695035b11e00239610d88551be34c7a61 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:08 -0700 Subject: [PATCH 051/358] perf metric: Change divide by zero and !support events behavior Division by zero causes expression parsing to fail and no metric to be generated. This can mean for short running benchmarks metrics are not shown. Change the behavior to make the value nan, which gets shown like: ''' $ perf stat -M TopdownL2 true Performance counter stats for 'true': 1,031,492 INST_RETIRED.ANY # nan % tma_fetch_bandwidth # nan % tma_heavy_operations # nan % tma_light_operations 29,304 CPU_CLK_UNHALTED.REF_XCLK # nan % tma_fetch_latency # nan % tma_branch_mispredicts # nan % tma_machine_clears # nan % tma_core_bound # nan % tma_memory_bound 2,658,319 IDQ_UOPS_NOT_DELIVERED.CORE 11,167 EXE_ACTIVITY.BOUND_ON_STORES 262,058 EXE_ACTIVITY.1_PORTS_UTIL BR_MISP_RETIRED.ALL_BRANCHES (0.00%) INT_MISC.RECOVERY_CYCLES_ANY (0.00%) CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE (0.00%) CPU_CLK_UNHALTED.THREAD (0.00%) UOPS_RETIRED.RETIRE_SLOTS (0.00%) CYCLE_ACTIVITY.STALLS_MEM_ANY (0.00%) UOPS_RETIRED.MACRO_FUSED (0.00%) IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE (0.00%) EXE_ACTIVITY.2_PORTS_UTIL (0.00%) CYCLE_ACTIVITY.STALLS_TOTAL (0.00%) MACHINE_CLEARS.COUNT (0.00%) UOPS_ISSUED.ANY (0.00%) 0.002864879 seconds time elapsed 0.003012000 seconds user 0.000000000 seconds sys ''' When events aren't supported a count of 0 can be confusing and make metrics look meaningful. Change these to be nan also which, with the next change, gets shown like: ''' $ perf stat true Performance counter stats for 'true': 1.25 msec task-clock:u # 0.387 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 46 page-faults:u # 36.702 K/sec 255,942 cycles:u # 0.204 GHz (88.66%) 123,046 instructions:u # 0.48 insn per cycle 28,301 branches:u # 22.580 M/sec 2,489 branch-misses:u # 8.79% of all branches 4,719 CPU_CLK_UNHALTED.REF_XCLK:u # 3.765 M/sec # nan % tma_frontend_bound # nan % tma_retiring # nan % tma_backend_bound # nan % tma_bad_speculation 344,855 IDQ_UOPS_NOT_DELIVERED.CORE:u # 275.147 M/sec INT_MISC.RECOVERY_CYCLES_ANY:u CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE:u (0.00%) CPU_CLK_UNHALTED.THREAD:u (0.00%) UOPS_RETIRED.RETIRE_SLOTS:u (0.00%) UOPS_ISSUED.ANY:u (0.00%) 0.003238142 seconds time elapsed 0.000000000 seconds user 0.003434000 seconds sys ''' Ensure that nan metric values are quoted as nan isn't a valid number in JSON. Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/expr.c | 3 ++- tools/perf/tests/parse-metric.c | 1 + tools/perf/util/expr.y | 6 +++++- tools/perf/util/stat-display.c | 2 +- tools/perf/util/stat-shadow.c | 25 +++++++++++++++++++------ 5 files changed, 28 insertions(+), 9 deletions(-) diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index cbf0e0c74906..733ead151c63 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -120,7 +120,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u p = "FOO/0"; ret = expr__parse(&val, ctx, p); - TEST_ASSERT_VAL("division by zero", ret == -1); + TEST_ASSERT_VAL("division by zero", ret == 0); + TEST_ASSERT_VAL("division by zero", isnan(val)); p = "BAR/"; ret = expr__parse(&val, ctx, p); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 1185b79e6274..c05148ea400c 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -38,6 +38,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); + evsel->supported = true; evsel->stats->aggr->counts.val = count; if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, count); diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 250e444bf032..4ce931cccb63 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -225,7 +225,11 @@ expr: NUMBER { if (fpclassify($3.val) == FP_ZERO) { pr_debug("division by zero\n"); - YYABORT; + assert($3.ids == NULL); + if (compute_ids) + ids__free($1.ids); + $$.val = NAN; + $$.ids = NULL; } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { assert($1.ids == NULL); assert($3.ids == NULL); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 73b2ff2ddf29..bf5a6c14dfcd 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -431,7 +431,7 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused, struct outstate *os = ctx; FILE *out = os->fh; - fprintf(out, "\"metric-value\" : %f, ", val); + fprintf(out, "\"metric-value\" : \"%f\", ", val); fprintf(out, "\"metric-unit\" : \"%s\"", unit); if (!config->metric_only) fprintf(out, "}"); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index eeccab6751d7..1566a206ba42 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -403,12 +403,25 @@ static int prepare_metric(struct evsel **metric_events, if (!aggr) break; - /* - * If an event was scaled during stat gathering, reverse - * the scale before computing the metric. - */ - val = aggr->counts.val * (1.0 / metric_events[i]->scale); - source_count = evsel__source_count(metric_events[i]); + if (!metric_events[i]->supported) { + /* + * Not supported events will have a count of 0, + * which can be confusing in a + * metric. Explicitly set the value to NAN. Not + * counted events (enable time of 0) are read as + * 0. + */ + val = NAN; + source_count = 0; + } else { + /* + * If an event was scaled during stat gathering, + * reverse the scale before computing the + * metric. + */ + val = aggr->counts.val * (1.0 / metric_events[i]->scale); + source_count = evsel__source_count(metric_events[i]); + } } n = strdup(evsel__metric_id(metric_events[i])); if (!n) From 1b114824106ca4686276c94e414e06bf58b0934f Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:09 -0700 Subject: [PATCH 052/358] perf stat: Introduce skippable evsels 'perf stat' with no arguments will use default events and metrics. These events may fail to open even with kernel and hypervisor disabled. When these fail then the permissions error appears even though they were implicitly selected. This is particularly a problem with the automatic selection of the TopdownL1 metric group on certain architectures like Skylake: $ perf stat true Error: Access to performance monitoring and observability operations is limited. Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open access to performance monitoring and observability operations for processes without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability. More information can be found at 'Perf events and tool security' document: https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html perf_event_paranoid setting is 2: -1: Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK >= 0: Disallow raw and ftrace function tracepoint access >= 1: Disallow CPU event access >= 2: Disallow kernel profiling To make the adjusted perf_event_paranoid setting permanent preserve it in /etc/sysctl.conf (e.g. kernel.perf_event_paranoid = ) $ This patch adds skippable evsels that when they fail to open won't cause termination and will appear as "" in output. The TopdownL1 events, from the metric group, are marked as skippable. This turns the failure above to: $ perf stat perf bench internals synthesize Computing performance of single threaded perf event synthesis by synthesizing events on the perf process itself: Average synthesis took: 49.287 usec (+- 0.083 usec) Average num. events: 3.000 (+- 0.000) Average time per event 16.429 usec Average data synthesis took: 49.641 usec (+- 0.085 usec) Average num. events: 11.000 (+- 0.000) Average time per event 4.513 usec Performance counter stats for 'perf bench internals synthesize': 1,222.38 msec task-clock:u # 0.993 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 162 page-faults:u # 132.529 /sec 774,445,184 cycles:u # 0.634 GHz (49.61%) 1,640,969,811 instructions:u # 2.12 insn per cycle (59.67%) 302,052,148 branches:u # 247.102 M/sec (59.69%) 1,807,718 branch-misses:u # 0.60% of all branches (59.68%) 5,218,927 CPU_CLK_UNHALTED.REF_XCLK:u # 4.269 M/sec # 17.3 % tma_frontend_bound # 56.4 % tma_retiring # nan % tma_backend_bound # nan % tma_bad_speculation (60.01%) 536,580,469 IDQ_UOPS_NOT_DELIVERED.CORE:u # 438.965 M/sec (60.33%) INT_MISC.RECOVERY_CYCLES_ANY:u 5,223,936 CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE:u # 4.274 M/sec (40.31%) 774,127,250 CPU_CLK_UNHALTED.THREAD:u # 633.297 M/sec (50.34%) 1,746,579,518 UOPS_RETIRED.RETIRE_SLOTS:u # 1.429 G/sec (50.12%) 1,940,625,702 UOPS_ISSUED.ANY:u # 1.588 G/sec (49.70%) 1.231055525 seconds time elapsed 0.258327000 seconds user 0.965749000 seconds sys $ The event INT_MISC.RECOVERY_CYCLES_ANY:u is skipped as it can't be opened with paranoia 2 on Skylake. With a lower paranoia, or as root, all events/metrics are computed. Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 38 +++++++++++++++++++++++++++++--------- tools/perf/util/evsel.c | 15 +++++++++++++-- tools/perf/util/evsel.h | 1 + 3 files changed, 43 insertions(+), 11 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index cc9fa48d636f..b9ad32f21e57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -667,6 +667,13 @@ static enum counter_recovery stat_handle_error(struct evsel *counter) evsel_list->core.threads->err_thread = -1; return COUNTER_RETRY; } + } else if (counter->skippable) { + if (verbose > 0) + ui__warning("skipping event %s that kernel failed to open .\n", + evsel__name(counter)); + counter->supported = false; + counter->errored = true; + return COUNTER_SKIP; } evsel__open_strerror(counter, &target, errno, msg, sizeof(msg)); @@ -1890,15 +1897,28 @@ static int add_default_attributes(void) * caused by exposing latent bugs. This is fixed properly in: * https://lore.kernel.org/lkml/bff481ba-e60a-763f-0aa0-3ee53302c480@linux.intel.com/ */ - if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() && - metricgroup__parse_groups(evsel_list, "TopdownL1", - /*metric_no_group=*/false, - /*metric_no_merge=*/false, - /*metric_no_threshold=*/true, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events) < 0) - return -1; + if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid()) { + struct evlist *metric_evlist = evlist__new(); + struct evsel *metric_evsel; + + if (!metric_evlist) + return -1; + + if (metricgroup__parse_groups(metric_evlist, "TopdownL1", + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) + return -1; + + evlist__for_each_entry(metric_evlist, metric_evsel) { + metric_evsel->skippable = true; + } + evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries); + evlist__delete(metric_evlist); + } /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 356c07f03be6..1cd04b5998d2 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -290,6 +290,7 @@ void evsel__init(struct evsel *evsel, evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->pmu_name = NULL; + evsel->skippable = false; } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -1725,9 +1726,13 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) return -1; fd = FD(leader, cpu_map_idx, thread); - BUG_ON(fd == -1); + BUG_ON(fd == -1 && !leader->skippable); - return fd; + /* + * When the leader has been skipped, return -2 to distinguish from no + * group leader case. + */ + return fd == -1 ? -2 : fd; } static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) @@ -2109,6 +2114,12 @@ retry_open: group_fd = get_group_fd(evsel, idx, thread); + if (group_fd == -2) { + pr_debug("broken group leader for %s\n", evsel->name); + err = -EINVAL; + goto out_close; + } + test_attr__ready(); /* Debug message used by test scripts */ diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d575390d80bc..df8928745fc6 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -95,6 +95,7 @@ struct evsel { bool weak_group; bool bpf_counter; bool use_config_name; + bool skippable; int bpf_fd; struct bpf_object *bpf_obj; struct list_head config_terms; From ccc66c6092802d682537227136dcbd0527027e6f Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:10 -0700 Subject: [PATCH 053/358] perf metric: JSON flag to not group events if gathering a metric group Some metric groups have metrics that don't have fully overlapping events, meaning that the group's events become unique event groups that may need to multiplex with each other. This can be particularly unfortunate when the groups wouldn't need to multiplex because there are sufficient hardware counters. Add a flag so that if recording a metric group then the metrics within the group needn't use groups for their events. The flag is added to Intel TopdownL1 and TopdownL2 metrics. Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/alderlake/adl-metrics.json | 26 +++++++++++++++++++ .../arch/x86/alderlaken/adln-metrics.json | 14 ++++++++++ .../arch/x86/broadwell/bdw-metrics.json | 12 +++++++++ .../arch/x86/broadwellde/bdwde-metrics.json | 12 +++++++++ .../arch/x86/broadwellx/bdx-metrics.json | 12 +++++++++ .../arch/x86/cascadelakex/clx-metrics.json | 12 +++++++++ .../arch/x86/haswell/hsw-metrics.json | 12 +++++++++ .../arch/x86/haswellx/hsx-metrics.json | 12 +++++++++ .../arch/x86/icelake/icl-metrics.json | 12 +++++++++ .../arch/x86/icelakex/icx-metrics.json | 12 +++++++++ .../arch/x86/ivybridge/ivb-metrics.json | 12 +++++++++ .../arch/x86/ivytown/ivt-metrics.json | 12 +++++++++ .../arch/x86/jaketown/jkt-metrics.json | 12 +++++++++ .../arch/x86/sandybridge/snb-metrics.json | 12 +++++++++ .../arch/x86/sapphirerapids/spr-metrics.json | 12 +++++++++ .../arch/x86/skylake/skl-metrics.json | 12 +++++++++ .../arch/x86/skylakex/skx-metrics.json | 12 +++++++++ .../arch/x86/tigerlake/tgl-metrics.json | 12 +++++++++ tools/perf/pmu-events/jevents.py | 4 ++- tools/perf/pmu-events/pmu-events.h | 1 + tools/perf/util/metricgroup.c | 8 +++--- 21 files changed, 240 insertions(+), 5 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 75d80e70e5cd..1f9047553942 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -133,6 +133,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -143,6 +144,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -153,6 +155,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -163,6 +166,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -182,6 +186,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -209,6 +214,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -255,6 +261,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -264,6 +271,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -291,6 +299,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -593,6 +602,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -611,6 +621,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -629,6 +640,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -729,6 +741,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -739,6 +752,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -848,6 +862,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -858,6 +873,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -868,6 +884,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -919,6 +936,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1031,6 +1049,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1041,6 +1060,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1121,6 +1141,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1141,6 +1162,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2023,6 +2045,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2082,6 +2105,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2112,6 +2136,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2310,6 +2335,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 1a85d935c733..0402adbf7d92 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -98,6 +98,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%" }, @@ -107,6 +108,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, @@ -125,6 +128,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -142,6 +146,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -166,6 +171,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -207,6 +213,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -215,6 +222,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -239,6 +247,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { @@ -499,6 +508,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -515,6 +525,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -531,6 +542,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%" }, @@ -620,6 +632,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%" }, @@ -629,6 +642,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 51cf8560a8d3..f9e2316601e1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -828,6 +836,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -858,6 +867,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -886,6 +896,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1048,6 +1059,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index fb57c7382408..e9c46d336a8e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -97,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -106,6 +107,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -164,6 +167,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -248,6 +252,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -257,6 +262,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -311,6 +317,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -320,6 +327,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -795,6 +803,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -825,6 +834,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -853,6 +863,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1013,6 +1024,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 65ec0c9e55d1..437b9867acb9 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -829,6 +837,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -869,6 +878,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -897,6 +907,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1079,6 +1090,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 8f7dc72accd0..875c766222e3 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1142,6 +1150,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1196,6 +1205,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1224,6 +1234,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1458,6 +1469,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 2528418200bb..9570a88d6d1c 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -663,6 +671,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -693,6 +702,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -721,6 +731,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -874,6 +885,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 11f152c346eb..a522202cf684 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -664,6 +672,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -704,6 +713,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -732,6 +742,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -905,6 +916,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index f45ae3483df4..1a2154f28b7b 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -115,6 +115,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -124,6 +125,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -141,6 +143,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -187,6 +190,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -288,6 +292,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -297,6 +302,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -369,6 +375,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -378,6 +385,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1111,6 +1119,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1164,6 +1173,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1191,6 +1201,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1360,6 +1371,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 0f9b174dfc22..1ef772b40e04 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -80,6 +80,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -89,6 +90,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -106,6 +108,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -152,6 +155,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -253,6 +257,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -262,6 +267,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -334,6 +340,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -343,6 +350,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1134,6 +1142,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1187,6 +1196,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1214,6 +1224,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1410,6 +1421,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 5247f69c13b6..11080ccffd51 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -724,6 +732,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -754,6 +763,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -782,6 +792,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -917,6 +928,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 89469b10fa30..65a46d659c0a 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -725,6 +733,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -765,6 +774,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -793,6 +803,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -948,6 +959,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index e8f4e5c01c9f..66a6f657bd6f 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -412,6 +420,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -422,6 +431,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -450,6 +460,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -487,6 +498,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 4a99fe515f4b..4b8bc19392a4 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -411,6 +419,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -421,6 +430,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -449,6 +459,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -486,6 +497,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 126300b7ae77..620fc5bd2217 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -87,6 +87,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -96,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -105,6 +107,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -151,6 +154,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -252,6 +256,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -261,6 +266,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -351,6 +357,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -369,6 +376,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, @@ -1216,6 +1224,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1269,6 +1278,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1304,6 +1314,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1509,6 +1520,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index a6d212b349f5..21ef6c9be816 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -345,6 +351,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -363,6 +370,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1065,6 +1073,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1110,6 +1119,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1138,6 +1148,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1343,6 +1354,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index fa2f7f126a30..eb6f12c0343d 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1123,6 +1131,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1177,6 +1186,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1429,6 +1440,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 4c80d6be6cf1..b442ed4acfbb 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -109,6 +109,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -118,6 +119,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -135,6 +137,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -181,6 +184,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -282,6 +286,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -291,6 +296,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -363,6 +369,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1125,6 +1133,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1178,6 +1187,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1374,6 +1385,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index ca99b9cfe4ad..f57a8f274025 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -52,7 +52,8 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', - 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' + 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode', + 'event_grouping' ] # Attributes that are bools or enum int values, encoded as '0', '1',... _json_enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] @@ -303,6 +304,7 @@ class JsonEvent: self.deprecated = jd.get('Deprecated') self.metric_name = jd.get('MetricName') self.metric_group = jd.get('MetricGroup') + self.metricgroup_no_group = jd.get('MetricgroupNoGroup') self.event_grouping = convert_metric_constraint(jd.get('MetricConstraint')) self.metric_expr = None if 'MetricExpr' in jd: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index b7dff8f1021f..80349685cf4d 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -59,6 +59,7 @@ struct pmu_metric { const char *compat; const char *desc; const char *long_desc; + const char *metricgroup_no_group; enum aggr_mode_class aggr_mode; enum metric_event_groups event_grouping; }; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index c566c6859302..4e7d41d285b4 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1144,12 +1144,12 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pm->metric_expr && - (match_metric(pm->metric_group, data->metric_name) || - match_metric(pm->metric_name, data->metric_name))) { + if (pm->metric_expr && match_pm_metric(pm, data->metric_name)) { + bool metric_no_group = data->metric_no_group || + match_metric(data->metric_name, pm->metricgroup_no_group); data->has_match = true; - ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, + ret = add_metric(data->list, pm, data->modifier, metric_no_group, data->metric_no_threshold, data->user_requested_cpu_list, data->system_wide, /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); From 327daf34554d20a6aa190dce5a625a555055435e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:11 -0700 Subject: [PATCH 054/358] perf parse-events: Don't reorder ungrouped events by PMU The pmu_group_name by default returns "cpu" which on non-hybrid/ARM means that ungrouped software, and hardware events are all going to sort by the original insertion index. However, on hybrid and ARM wildcard expansion may mean the PMU name is set and events will be unnecessarily reordered - triggering the reordering warning. Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d71019dcd614..34ba840ae19a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2140,25 +2140,32 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list int *leader_idx = state; int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; + bool lhs_has_group = false, rhs_has_group = false; /* * First sort by grouping/leader. Read the leader idx only if the evsel * is part of a group, as -1 indicates no group. */ - if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) + if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { + lhs_has_group = true; lhs_leader_idx = lhs_core->leader->idx; - if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) + } + if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { + rhs_has_group = true; rhs_leader_idx = rhs_core->leader->idx; + } if (lhs_leader_idx != rhs_leader_idx) return lhs_leader_idx - rhs_leader_idx; - /* Group by PMU. Groups can't span PMUs. */ - lhs_pmu_name = evsel__group_pmu_name(lhs); - rhs_pmu_name = evsel__group_pmu_name(rhs); - ret = strcmp(lhs_pmu_name, rhs_pmu_name); - if (ret) - return ret; + /* Group by PMU if there is a group. Groups can't span PMUs. */ + if (lhs_has_group && rhs_has_group) { + lhs_pmu_name = evsel__group_pmu_name(lhs); + rhs_pmu_name = evsel__group_pmu_name(rhs); + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; + } /* Architecture specific sorting. */ return arch_evlist__cmp(lhs, rhs); From 5f0b89e632ed81b69993f3e68ed924ca3874d0d0 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 9 May 2023 15:18:47 +0200 Subject: [PATCH 055/358] perf test java symbol: Remove needless debuginfod queries Test case 'Test java symbol' might run for a long time. On Fedora 38 the run time is very, very long: Output before: # time ./perf test 108 108: Test java symbol : Ok real 22m15.775s user 3m42.584s sys 4m30.685s # The reason is a lookup for the server for debug symbols as shown in: # cat /etc/debuginfod/elfutils.urls https://debuginfod.fedoraproject.org/ # This lookup is done for every symbol/sample, so about 3500 lookups will take place. To omit this lookup, which is not needed, unset environment variable DEBUGINFOD_URLS=''. Output after: # time ./perf test 108 108: Test java symbol : Ok real 0m6.242s user 0m4.982s sys 0m3.243s # Signed-off-by: Thomas Richter Tested-by: Arnaldo Carvalho de Melo Cc: Heiko Carstens Cc: Ian Rogers Cc: Leo Yan Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230509131847.835974-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_java_symbol.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/test_java_symbol.sh b/tools/perf/tests/shell/test_java_symbol.sh index 90cea8811926..499539d1c479 100755 --- a/tools/perf/tests/shell/test_java_symbol.sh +++ b/tools/perf/tests/shell/test_java_symbol.sh @@ -56,7 +56,7 @@ if [ $? -ne 0 ]; then exit 1 fi -if ! perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then +if ! DEBUGINFOD_URLS='' perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then echo "Fail to inject samples" exit 1 fi From b0618f38e2ab8ce3f094e4973955cfdbb55fceea Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 May 2023 15:42:38 -0300 Subject: [PATCH 056/358] perf build: Gracefully fail the build if BUILD_BPF_SKEL=1 is specified and clang isn't available Build BPF skels require having a compiler able to generate BPF bytecode, and so far this is only possible with clang, so check for its availability and fail the build when the user explicitely ask for BPF skels to be built. Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Andrii Nakryiko , Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Song Liu Yang: Yang Jihong , Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4884520f954f..70268442f7ee 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -216,6 +216,12 @@ ifeq ($(call get-executable,$(BISON)),) dummy := $(error Error: $(BISON) is missing on this system, please install it) endif +ifeq ($(BUILD_BPF_SKEL),1) + ifeq ($(call get-executable,$(CLANG)),) + dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1) + endif +endif + ifneq ($(OUTPUT),) ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1) BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)= From 5d1ac59ff7445e51a0e4958fa39ac8aa23691698 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:21:44 +0800 Subject: [PATCH 057/358] tools headers UAPI: Sync the linux/in.h with the kernel sources Picking the changes from: 91d0b78c5177f3e4 ("inet: Add IP_LOCAL_PORT_RANGE socket option") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/linux/in.h' differs from latest version at 'include/uapi/linux/in.h' diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/23aabc69956ac94fbf388b05c8be08a64e8c7ccc.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/in.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 07a4cb149305..4b7f2df66b99 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -162,6 +162,7 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 From e6232180e524e11205d285bb27045bf2c19db265 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:21:46 +0800 Subject: [PATCH 058/358] tools headers UAPI: Sync the drm/drm.h with the kernel sources Picking the changes from: 6068771673a38efc ("drm: document DRM_IOCTL_PRIME_HANDLE_TO_FD and PRIME_FD_TO_HANDLE") 61a55f8b1ebcde68 ("drm: document expectations for GETFB2 handles") 158350aae16a4e66 ("drm: document DRM_IOCTL_GEM_CLOSE") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/drm/drm.h' differs from latest version at 'include/uapi/drm/drm.h' diff -u tools/include/uapi/drm/drm.h include/uapi/drm/drm.h No changes in tooling as these are just C comment documentation changes. Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/7552c61660bf079f2979fdcbcef8e921255f877a.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/drm.h | 57 ++++++++++++++++++++++++++++++++++-- 1 file changed, 55 insertions(+), 2 deletions(-) diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 642808520d92..a87bbbbca2d4 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -972,6 +972,19 @@ extern "C" { #define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) #define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) #define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +/** + * DRM_IOCTL_GEM_CLOSE - Close a GEM handle. + * + * GEM handles are not reference-counted by the kernel. User-space is + * responsible for managing their lifetime. For example, if user-space imports + * the same memory object twice on the same DRM file description, the same GEM + * handle is returned by both imports, and user-space needs to ensure + * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen + * when a memory object is allocated, then exported and imported again on the + * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception + * and always returns fresh new GEM handles even if an existing GEM handle + * already refers to the same memory object before the IOCTL is performed. + */ #define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) #define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) #define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) @@ -1012,7 +1025,37 @@ extern "C" { #define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) #define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) +/** + * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD. + * + * User-space sets &drm_prime_handle.handle with the GEM handle to export and + * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in + * &drm_prime_handle.fd. + * + * The export can fail for any driver-specific reason, e.g. because export is + * not supported for this specific GEM handle (but might be for others). + * + * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT. + */ #define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +/** + * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle. + * + * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to + * import, and gets back a GEM handle in &drm_prime_handle.handle. + * &drm_prime_handle.flags is unused. + * + * If an existing GEM handle refers to the memory object backing the DMA-BUF, + * that GEM handle is returned. Therefore user-space which needs to handle + * arbitrary DMA-BUFs must have a user-space lookup data structure to manually + * reference-count duplicated GEM handles. For more information see + * &DRM_IOCTL_GEM_CLOSE. + * + * The import can fail for any driver-specific reason, e.g. because import is + * only supported for DMA-BUFs allocated on this DRM device. + * + * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT. + */ #define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) #define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) @@ -1104,8 +1147,13 @@ extern "C" { * struct as the output. * * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles - * will be filled with GEM buffer handles. Planes are valid until one has a - * zero handle -- this can be used to compute the number of planes. + * will be filled with GEM buffer handles. Fresh new GEM handles are always + * returned, even if another GEM handle referring to the same memory object + * already exists on the DRM file description. The caller is responsible for + * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same + * new handle will be returned for multiple planes in case they use the same + * memory object. Planes are valid until one has a zero handle -- this can be + * used to compute the number of planes. * * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid * until one has a zero &drm_mode_fb_cmd2.pitches. @@ -1113,6 +1161,11 @@ extern "C" { * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + * + * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space + * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately + * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not + * double-close handles which are specified multiple times in the array. */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) From e7ec3a249c38a9c9be3a1eeb0142fcbaa3bd02d9 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:22:49 +0800 Subject: [PATCH 059/358] tools headers UAPI: Sync the i915_drm.h with the kernel sources Picking the changes from: 1cc064dce4ed0ff1 ("drm/i915/perf: Add support for OA media units") c61d04c9eb435498 ("drm/i915/perf: Add engine class instance parameters to perf") 02abecdeebfcd384 ("drm/i915/uapi: Replace fake flex-array with flexible-array member") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h' diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/4c0c150997ae1455f49094222daa121385643ae0.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/i915_drm.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 8df261c5ab9b..dba7c5a5b25e 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2491,7 +2491,7 @@ struct i915_context_param_engines { #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ #define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ @@ -2676,6 +2676,10 @@ enum drm_i915_oa_format { I915_OAR_FORMAT_A32u40_A4u32_B8_C8, I915_OA_FORMAT_A24u40_A14u32_B8_C8, + /* MTL OAM */ + I915_OAM_FORMAT_MPEC8u64_B8_C8, + I915_OAM_FORMAT_MPEC8u32_B8_C8, + I915_OA_FORMAT_MAX /* non-ABI */ }; @@ -2758,6 +2762,25 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_POLL_OA_PERIOD, + /** + * Multiple engines may be mapped to the same OA unit. The OA unit is + * identified by class:instance of any engine mapped to it. + * + * This parameter specifies the engine class and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_CLASS, + + /** + * This parameter specifies the engine instance and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; From 92b8e61e8835109140139bc1eb60329429c32a0f Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:22:51 +0800 Subject: [PATCH 060/358] tools headers UAPI: Sync the linux/const.h with the kernel headers Picking the changes from: 31088f6f7906253e ("uapi/linux/const.h: prefer ISO-friendly __typeof__") Silencing these perf build warnings:: Warning: Kernel ABI header at 'tools/include/uapi/linux/const.h' differs from latest version at 'include/uapi/linux/const.h' diff -u tools/include/uapi/linux/const.h include/uapi/linux/const.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/33e963df304394f932d9108a1b0bb327f23a4eca.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/const.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index af2a44c08683..a429381e7ca5 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) From 8d6a41c8065e11206e03e7f9fa9018d35b398583 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:24:08 +0800 Subject: [PATCH 061/358] tools include UAPI: Sync the sound/asound.h copy with the kernel sources Picking the changes from: 102882b5c62f6bfe ("ALSA: document that struct __snd_pcm_mmap_control64 is messed up") 9f656705c5faa18a ("ALSA: pcm: rewrite snd_pcm_playback_silence()") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/sound/asound.h' differs from latest version at 'include/uapi/sound/asound.h' diff -u tools/include/uapi/sound/asound.h include/uapi/sound/asound.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/5606e7989bbb029c400117f2e455ab995208266f.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/sound/asound.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index de6810e94abe..0aa955aa8246 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -429,9 +429,14 @@ struct snd_pcm_sw_params { snd_pcm_uframes_t avail_min; /* min avail frames for wakeup */ snd_pcm_uframes_t xfer_align; /* obsolete: xfer size need to be a multiple */ snd_pcm_uframes_t start_threshold; /* min hw_avail frames for automatic start */ - snd_pcm_uframes_t stop_threshold; /* min avail frames for automatic stop */ - snd_pcm_uframes_t silence_threshold; /* min distance from noise for silence filling */ - snd_pcm_uframes_t silence_size; /* silence block size */ + /* + * The following two thresholds alleviate playback buffer underruns; when + * hw_avail drops below the threshold, the respective action is triggered: + */ + snd_pcm_uframes_t stop_threshold; /* - stop playback */ + snd_pcm_uframes_t silence_threshold; /* - pre-fill buffer with silence */ + snd_pcm_uframes_t silence_size; /* max size of silence pre-fill; when >= boundary, + * fill played area with silence immediately */ snd_pcm_uframes_t boundary; /* pointers wrap point */ unsigned int proto; /* protocol version */ unsigned int tstamp_type; /* timestamp type (req. proto >= 2.0.12) */ @@ -570,7 +575,8 @@ struct __snd_pcm_mmap_status64 { struct __snd_pcm_mmap_control64 { __pad_before_uframe __pad1; snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ - __pad_before_uframe __pad2; + __pad_before_uframe __pad2; // This should be __pad_after_uframe, but binary + // backwards compatibility constraints prevent a fix. __pad_before_uframe __pad3; snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ From 705049ca4f5b7b00a792dfb559878945a6c7e084 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:24:11 +0800 Subject: [PATCH 062/358] tools headers kvm: Sync uapi/{asm/linux} kvm.h headers with the kernel sources Picking the changes from: e65733b5c59a1ea2 ("KVM: x86: Redefine 'longmode' as a flag for KVM_EXIT_HYPERCALL") 30ec7997d175cd68 ("KVM: arm64: timers: Allow userspace to set the global counter offset") 821d935c87bc9525 ("KVM: arm64: Introduce support for userspace SMCCC filtering") 81dc9504a7006b48 ("KVM: arm64: nv: timers: Support hyp timer emulation") a8308b3fc9494953 ("KVM: arm64: Refactor hvc filtering to support different actions") 0e5c9a9d6548e9b1 ("KVM: arm64: Expose SMC/HVC width to userspace") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h' diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h' diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/ac5adb58411d23b3360d436a65038fefe91c32a8.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/kvm.h | 36 +++++++++++++++++++++++++ tools/arch/x86/include/uapi/asm/kvm.h | 3 +++ tools/include/uapi/linux/kvm.h | 12 +++++++-- 3 files changed, 49 insertions(+), 2 deletions(-) diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f8129c624b07..f7ddd73a8c0f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags { __u64 reserved[2]; }; +/* + * Counter/Timer offset structure. Describe the virtual/physical offset. + * To be used with KVM_ARM_SET_COUNTER_OFFSET. + */ +struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; +}; + #define KVM_ARM_TAGS_TO_GUEST 0 #define KVM_ARM_TAGS_FROM_GUEST 1 @@ -372,6 +381,10 @@ enum { #endif }; +/* Device Control API on vm fd */ +#define KVM_ARM_VM_SMCCC_CTRL 0 +#define KVM_ARM_VM_SMCCC_FILTER 0 + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 @@ -411,6 +424,8 @@ enum { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_TIMER_IRQ_HVTIMER 2 +#define KVM_ARM_VCPU_TIMER_IRQ_HPTIMER 3 #define KVM_ARM_VCPU_PVTIME_CTRL 2 #define KVM_ARM_VCPU_PVTIME_IPA 0 @@ -469,6 +484,27 @@ enum { /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) +enum kvm_smccc_filter_action { + KVM_SMCCC_FILTER_HANDLE = 0, + KVM_SMCCC_FILTER_DENY, + KVM_SMCCC_FILTER_FWD_TO_USER, + +#ifdef __KERNEL__ + NR_SMCCC_FILTER_ACTIONS +#endif +}; + +struct kvm_smccc_filter { + __u32 base; + __u32 nr_functions; + __u8 action; + __u8 pad[15]; +}; + +/* arm64-specific KVM_EXIT_HYPERCALL flags */ +#define KVM_HYPERCALL_EXIT_SMC (1U << 0) +#define KVM_HYPERCALL_EXIT_16BIT (1U << 1) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 7f467fe05d42..1a6a1f987949 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -559,4 +559,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ +/* x86-specific KVM_EXIT_HYPERCALL flags. */ +#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4003a166328c..737318b1c1d9 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -341,8 +341,13 @@ struct kvm_run { __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; } hypercall; /* KVM_EXIT_TPR_ACCESS */ struct { @@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 #ifdef KVM_CAP_IRQ_ROUTING @@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) From 34e82891d995ab89b494032c5ab0ee939cbb7524 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:24:52 +0800 Subject: [PATCH 063/358] tools arch x86: Sync the msr-index.h copy with the kernel sources Picking the changes from: c68e3d473988b9af ("x86/include/asm/msr-index.h: Add IFS Array test bits") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/05778ab3c168c8030f6b20e60375dc803f0cd300.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ad35355ee43e..3aedae61af4f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -206,6 +206,8 @@ /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ #define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT 2 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) From 123361659fa405de8e21bff485fe22a65d85e64e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:26 -0700 Subject: [PATCH 064/358] perf evsel: Modify group pmu name for software events If we have a group of {cycles,faults} then we need the faults software event to appear to be on the same PMU as cycles so that we don't split the group in parse_events__sort_events_and_fix_groups. This case is relatively easy as cycles is the leader and will have a PMU name. In the reverse case, {faults,cycles} we still need faults to appear to have the PMU name of cycles but the old behavior is just to return "cpu". For hybrid this fails as cycles will be on "cpu_core" or "cpu_atom", causing faults to be split into a different group. Change the behavior for software events so that the whole group is searched for the named PMU. Signed-off-by: Ian Rogers Tested-by: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-20-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1cd04b5998d2..63522322e118 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -829,23 +829,26 @@ bool evsel__name_is(struct evsel *evsel, const char *name) const char *evsel__group_pmu_name(const struct evsel *evsel) { - const struct evsel *leader; + struct evsel *leader, *pos; /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ if (evsel->pmu_name) return evsel->pmu_name; /* * Software events may be in a group with other uncore PMU events. Use - * the pmu_name of the group leader to avoid breaking the software event - * out of the group. + * the pmu_name of the first non-software event to avoid breaking the + * software event out of the group. * * Aux event leaders, like intel_pt, expect a group with events from * other PMUs, so substitute the AUX event's PMU in this case. */ leader = evsel__leader(evsel); - if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) && - leader->pmu_name) { - return leader->pmu_name; + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { + /* Starting with the leader, find the first event with a named PMU. */ + for_each_group_evsel(pos, leader) { + if (pos->pmu_name) + return pos->pmu_name; + } } return "cpu"; From a468085011ea8bba7fc605a5423d6edaf46d35cf Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 8 May 2023 12:39:51 +0300 Subject: [PATCH 065/358] perf test test_intel_pt.sh: Test sample mode with event with PMU name br_misp_retired.all_branches is supported on processors that support Intel PT, so use it to test sample mode with an event that has been given a PMU name. Please note, the test fails prior to the fix "perf parse-events: Do not break up AUX event group". Signed-off-by: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230508093952.27482-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_intel_pt.sh | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 4ddb17cb83c5..3a8b9bffa022 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -506,6 +506,13 @@ test_sample() echo "perf record failed with --aux-sample" return 1 fi + # Check with event with PMU name + if perf_record_no_decode -o "${perfdatafile}" -e br_misp_retired.all_branches:u uname ; then + if ! perf_record_no_decode -o "${perfdatafile}" -e '{intel_pt//,br_misp_retired.all_branches/aux-sample-size=8192/}:u' uname ; then + echo "perf record failed with --aux-sample-size" + return 1 + fi + fi echo OK return 0 } From 7d161165d9072dcbb1f01ce947436b7a3101c254 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 8 May 2023 12:39:52 +0300 Subject: [PATCH 066/358] perf parse-events: Do not break up AUX event group Do not assume which events may have a PMU name, allowing the logic to keep an AUX event group together. Example: Before: $ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1 WARNING: events were regrouped to match PMUs Cannot add AUX area sampling to a group leader $ After: $ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.078 MB perf.data ] $ perf script -F-dso,+addr | grep -C5 tlb_flush.stlb_any | head -11 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc82a2 dl_main+0x9a2 => 7f5350cb38f0 _dl_add_to_namespace_list+0x0 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cb3908 _dl_add_to_namespace_list+0x18 => 7f5350cbb080 rtld_mutex_dummy+0x0 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc8350 dl_main+0xa50 => 0 [unknown] sleep 20444 [003] 7939.510244: 1 branches:uH: 7f5350cc83ca dl_main+0xaca => 7f5350caeb60 _dl_process_pt_gnu_property+0x0 sleep 20444 [003] 7939.510245: 1 branches:uH: 7f5350caeb60 _dl_process_pt_gnu_property+0x0 => 0 [unknown] sleep 20444 7939.510245: 10 tlb_flush.stlb_any/aux-sample-size=8192/pp: 0 7f5350caeb60 _dl_process_pt_gnu_property+0x0 sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc87fe dl_main+0xefe => 7f5350ccd240 strcmp+0x0 sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc8862 dl_main+0xf62 => 0 [unknown] sleep 20444 [003] 7939.510255: 1 branches:uH: 7f5350cc9cdc dl_main+0x23dc => 0 [unknown] sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc89f6 dl_main+0x10f6 => 7f5350cb9530 _dl_setup_hash+0x0 sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc8a2d dl_main+0x112d => 7f5350cb3990 _dl_new_object+0x0 $ Fixes: 347c2f0a0988c59c ("perf parse-events: Sort and group parsed events") Suggested-by: Ian Rogers Signed-off-by: Adrian Hunter Tested-by: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230508093952.27482-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 63522322e118..2f5910b31fa9 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -829,11 +829,9 @@ bool evsel__name_is(struct evsel *evsel, const char *name) const char *evsel__group_pmu_name(const struct evsel *evsel) { - struct evsel *leader, *pos; + struct evsel *leader = evsel__leader(evsel); + struct evsel *pos; - /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ - if (evsel->pmu_name) - return evsel->pmu_name; /* * Software events may be in a group with other uncore PMU events. Use * the pmu_name of the first non-software event to avoid breaking the @@ -842,7 +840,6 @@ const char *evsel__group_pmu_name(const struct evsel *evsel) * Aux event leaders, like intel_pt, expect a group with events from * other PMUs, so substitute the AUX event's PMU in this case. */ - leader = evsel__leader(evsel); if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { /* Starting with the leader, find the first event with a named PMU. */ for_each_group_evsel(pos, leader) { @@ -851,7 +848,7 @@ const char *evsel__group_pmu_name(const struct evsel *evsel) } } - return "cpu"; + return evsel->pmu_name ?: "cpu"; } const char *evsel__metric_id(const struct evsel *evsel) From 5be6cecda0802f2397504fd40c3402cd8ac8022e Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Wed, 10 May 2023 06:44:01 +0000 Subject: [PATCH 067/358] perf bpf skels: Make vmlinux.h use bpf.h and perf_event.h in source directory Currently, vmlinux.h uses the bpf.h and perf_event.h header files in the system path. If the header files in compilation environment are old, compilation may fail. For example: /home/yangjihong/linux/tools/perf/util/bpf_skel/.tmp/../vmlinux.h:151:27: error: field has incomplete type 'union perf_sample_weight' union perf_sample_weight weight; Use the bpf.h and perf_event.h files in the source code directory to avoid compilation compatibility problems. Signed-off-by: Yang Jihong Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Tom Rix Link: https://lore.kernel.org/r/20230510064401.225051-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 3 ++- tools/perf/util/bpf_skel/vmlinux.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index a42a6a99c2bc..9b92749280b2 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1058,13 +1058,14 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) +TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi $(BPFTOOL): | $(SKEL_TMP_OUT) $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) - $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \ + $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux.h index 449b1ea91fc4..c7ed51b0c1ef 100644 --- a/tools/perf/util/bpf_skel/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux.h @@ -1,6 +1,7 @@ #ifndef __VMLINUX_H #define __VMLINUX_H +#include // for define __always_inline #include #include #include From a2af0f6b8ef7ea402d6a531607bd0bc3dd3b4815 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 10 May 2023 14:23:52 -0300 Subject: [PATCH 068/358] perf build: Add system include paths to BPF builds There are insufficient headers in tools/include to satisfy building BPF programs and their header dependencies. Add the system include paths from the non-BPF clang compile so that these headers can be found. This code was taken from: tools/testing/selftests/bpf/Makefile Committer notes: Had to adjust the '#ifndef NO_BPF_SKEL' to '#ifdef BUILD_BPF_SKEL' as reverted that build BPF skels by default. Also cope with the addition of -I$(srctree)/tools/include/uapi done by Yang Jihong so that we prefer using the kernel sources headers instead of older ones in the system. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Albert Ou Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Palmer Dabbelt Cc: Paul Walmsley , Cc: Peter Zijlstra Cc: Song Liu Cc: Tom Rix Cc: Yang Jihong Link: https://lore.kernel.org/lkml/20230506021450.3499232-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 9b92749280b2..1593c5dcaa9e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1057,7 +1057,24 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool -BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - &1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - Date: Fri, 5 May 2023 15:32:53 +0530 Subject: [PATCH 069/358] perf script: Skip aggregation for stat events The script command does not support aggregation modes by itself although that can be achieved using post-processing scripts. Because of this, it does not allocate memory for aggregated event values. Upon running perf stat record, the aggregation mode is set in the perf data file. If the mode is AGGR_GLOBAL, the aggregated event values are accessed and this leads to a segmentation fault since these were never allocated to begin with. Set the mode to AGGR_NONE explicitly to avoid this. E.g. $ perf stat record -e cycles true $ perf script Before: Segmentation fault (core dumped) After: CPU THREAD VAL ENA RUN TIME EVENT -1 231919 162831 362069 362069 935289 cycles:u Fixes: 8b76a3188b85724f ("perf stat: Remove unused perf_counts.aggr field") Signed-off-by: Sandipan Das Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Nick Terrell Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: stable@vger.kernel.org # v6.2+ Link: https://lore.kernel.org/r/83d6c6c05c54bf00c5a9df32ac160718efca0c7a.1683280603.git.sandipan.das@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 006f522d0e7f..c57be48d65bb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3647,6 +3647,13 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); + + /* + * Aggregation modes are not used since post-processing scripts are + * supposed to take care of such requirements + */ + stat_config.aggr_mode = AGGR_NONE; + return 0; } From 8669862388b01de7a248fea8b743aafd42169875 Mon Sep 17 00:00:00 2001 From: Sandipan Das Date: Fri, 5 May 2023 15:32:54 +0530 Subject: [PATCH 070/358] perf test: Add stat test for record and script When using the global aggregation mode, running perf script after perf stat record can result in a segmentation fault as seen with commit 8b76a3188b85 ("perf stat: Remove unused perf_counts.aggr field"). Add a basic test to the existing suite of stat-related tests for checking if that workflow runs without erroring out. Signed-off-by: Sandipan Das Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Nick Terrell Cc: Peter Zijlstra Cc: Ravi Bangoria Link: https://lore.kernel.org/r/6a5429879764e3dac984cbb11ee2d95cc1604161.1683280603.git.sandipan.das@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat.sh | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 2c1d3f704995..b154fbb15d54 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -28,6 +28,18 @@ test_stat_record_report() { echo "stat record and report test [Success]" } +test_stat_record_script() { + echo "stat record and script test" + if ! perf stat record -o - true | perf script -i - 2>&1 | \ + grep -E -q "CPU[[:space:]]+THREAD[[:space:]]+VAL[[:space:]]+ENA[[:space:]]+RUN[[:space:]]+TIME[[:space:]]+EVENT" + then + echo "stat record and script test [Failed]" + err=1 + return + fi + echo "stat record and script test [Success]" +} + test_stat_repeat_weak_groups() { echo "stat repeat weak groups test" if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \ @@ -93,6 +105,7 @@ test_topdown_weak_groups() { test_default_stat test_stat_record_report +test_stat_record_script test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups From a3cee97446cc9ee1332b5f317024ccd23ac6c48c Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 4 May 2023 17:08:45 +0100 Subject: [PATCH 071/358] perf arm64: Fix build with refcount checking With EXTRA_CFLAGS=-DREFCNT_CHECKING=1 and build-test, some unwrapped map accesses appear. Wrap it in the new accessor to fix the error: error: 'struct perf_cpu_map' has no member named 'map' Signed-off-by: James Clark Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230504160845.2065510-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/util/header.c | 4 ++-- tools/perf/arch/arm64/util/pmu.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index d730666ab95d..80b9f6287fe2 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -29,8 +29,8 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) char path[PATH_MAX]; FILE *file; - scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, - sysfs, cpus->map[cpu]); + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, + sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu); file = fopen(path, "r"); if (!file) { diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index fa143acb4c8d..ef1ed645097c 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -18,7 +18,7 @@ static struct perf_pmu *pmu__find_core_pmu(void) * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. */ - if (pmu->cpus->nr != cpu__max_cpu().cpu) + if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) return NULL; return pmu; From bfd431cb2c68cbaec7a27b8a979d031f8501301b Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 4 May 2023 15:48:22 +0100 Subject: [PATCH 072/358] perf cs-etm: Fix contextid validation Pre 5.11 kernels don't support 'contextid1' and 'contextid2' so validation would be skipped. By adding an additional check for 'contextid', old kernels will still have validation done even though contextid would either be contextid1 or contextid2. Additionally now that it's possible to override options, an existing bug in the validation is revealed. 'val' is overwritten by the contextid1 validation, and re-used for contextid2 validation causing it to always fail. '!val || val != 0x4' is the same as 'val != 0x4' because 0 is also != 4, so that expression can be simplified and the temp variable not overwritten. Fixes: 35c51f83dd1ed5db ("perf cs-etm: Validate options after applying them") Reviewed-by: Leo Yan Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/all/20230501073452.GA4660@leoy-yangtze.lan Link: https://lore.kernel.org/r/20230504144822.1938717-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/cs-etm.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 77cb03e6ff87..9ca040bfb1aa 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -78,9 +78,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, char path[PATH_MAX]; int err; u32 val; - u64 contextid = - evsel->core.attr.config & - (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | + u64 contextid = evsel->core.attr.config & + (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") | + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")); if (!contextid) @@ -114,8 +114,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, * 0b00100 Maximum of 32-bit Context ID size. * All other values are reserved. */ - val = BMVAL(val, 5, 9); - if (!val || val != 0x4) { + if (BMVAL(val, 5, 9) != 0x4) { pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n", CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); return -EINVAL; From 760ebc45746b498a36332acefd9e2838a3f8fcf0 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 May 2023 15:51:31 -0300 Subject: [PATCH 073/358] perf lock contention: Add empty 'struct rq' to satisfy libbpf 'runqueue' type verification If 'struct rq' isn't defined in lock_contention.bpf.c then the type for the 'runqueue' variable ends up being a forward declaration (BTF_KIND_FWD) while the kernel has it defined (BTF_KIND_STRUCT). This makes libbpf decide it has incompatible types and then fails to load the BPF skeleton: # perf lock con -ab sleep 1 libbpf: extern (var ksym) 'runqueues': incompatible types, expected [95] fwd rq, but kernel has [55509] struct rq libbpf: failed to load object 'lock_contention_bpf' libbpf: failed to load BPF skeleton 'lock_contention_bpf': -22 Failed to load lock-contention BPF skeleton lock contention BPF setup failed # Add it as an empty struct to satisfy that type verification: # perf lock con -ab sleep 1 contended total wait max wait avg wait type caller 2 50.64 us 25.38 us 25.32 us spinlock tick_do_update_jiffies64+0x25 1 26.18 us 26.18 us 26.18 us spinlock tick_do_update_jiffies64+0x25 # Committer notes: Extracted from a larger patch as Namhyung had already fixed the other issues in e53de7b65a3ca59a ("perf lock contention: Fix struct rq lock access"). Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Changbin Du Cc: Hao Luo Cc: Ian Rogers Cc: Namhyung Kim Cc: Song Liu Cc: Stephane Eranian Cc: Yang Jihong Link: https://lore.kernel.org/lkml/ZFVqeKLssg7uzxzI@krava Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/lock_contention.bpf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 8d3cfbb3cc65..1d48226ae75d 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -416,6 +416,8 @@ int contention_end(u64 *ctx) return 0; } +struct rq {}; + extern struct rq runqueues __ksym; struct rq___old { From 66b2ca086210732954a7790d63d35542936fc664 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 11 May 2023 21:42:24 +1000 Subject: [PATCH 074/358] powerpc/64s/radix: Fix soft dirty tracking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It was reported that soft dirty tracking doesn't work when using the Radix MMU. The tracking is supposed to work by clearing the soft dirty bit for a mapping and then write protecting the PTE. If/when the page is written to, a page fault occurs and the soft dirty bit is added back via pte_mkdirty(). For example in wp_page_reuse(): entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); Unfortunately on radix _PAGE_SOFTDIRTY is being dropped by radix__ptep_set_access_flags(), called from ptep_set_access_flags(), meaning the soft dirty bit is not set even though the page has been written to. Fix it by adding _PAGE_SOFTDIRTY to the set of bits that are able to be changed in radix__ptep_set_access_flags(). Fixes: b0b5e9b13047 ("powerpc/mm/radix: Add radix pte #defines") Cc: stable@vger.kernel.org # v4.7+ Reported-by: Dan Horák Link: https://lore.kernel.org/r/20230511095558.56663a50f86bdc4cd97700b7@danny.cz Signed-off-by: Michael Ellerman Link: https://msgid.link/20230511114224.977423-1-mpe@ellerman.id.au --- arch/powerpc/mm/book3s64/radix_pgtable.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 26245aaf12b8..2297aa764ecd 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -1040,8 +1040,8 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { struct mm_struct *mm = vma->vm_mm; - unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | - _PAGE_RW | _PAGE_EXEC); + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY | + _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); unsigned long change = pte_val(entry) ^ pte_val(*ptep); /* From e910baa9c1efdf7634519c135c6723b0fd499683 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 1 May 2023 19:21:41 +0100 Subject: [PATCH 075/358] KVM: arm64: vgic: Add Apple M2 PRO/MAX cpus to the list of broken SEIS implementations Unsurprisingly, the M2 PRO is also affected by the SEIS bug, so add it to the naughty list. And since M2 MAX is likely to be of the same ilk, flag it as well. Tested on a M2 PRO mini machine. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20230501182141.39770-1-maz@kernel.org --- arch/arm64/include/asm/cputype.h | 8 ++++++++ arch/arm64/kvm/vgic/vgic-v3.c | 4 ++++ 2 files changed, 12 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 683ca3af4084..5f6f84837a49 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -126,6 +126,10 @@ #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 #define APPLE_CPU_PART_M2_BLIZZARD 0x032 #define APPLE_CPU_PART_M2_AVALANCHE 0x033 +#define APPLE_CPU_PART_M2_BLIZZARD_PRO 0x034 +#define APPLE_CPU_PART_M2_AVALANCHE_PRO 0x035 +#define APPLE_CPU_PART_M2_BLIZZARD_MAX 0x038 +#define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -181,6 +185,10 @@ #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) #define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) #define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) +#define MIDR_APPLE_M2_BLIZZARD_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_PRO) +#define MIDR_APPLE_M2_AVALANCHE_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_PRO) +#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) +#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 469d816f356f..93a47a515c13 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -616,6 +616,10 @@ static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; From db40d2928d245f3a6cba9a6a2547ec955b00f0fc Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Mon, 8 May 2023 22:26:45 +0200 Subject: [PATCH 076/358] drm/msm/iommu: Fix null pointer dereference in no-IOMMU case In the case that no IOMMU is available, msm_iommu_new can return NULL which should be handled. Without we will get a NULL pointer dereference in the next statement when we try to use the mmu variable. Fixes: 8cceb773f565 ("drm/msm/adreno: stall translation on fault for all GPU families") Signed-off-by: Luca Weiss Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/535915/ Link: https://lore.kernel.org/r/20230508-6-4-drm-msm-iommu-fixup-v1-1-a7a21ec94f5b@z3ntu.xyz Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 418e1e06cdde..5080319ae4cf 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -410,7 +410,7 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsig struct msm_mmu *mmu; mmu = msm_iommu_new(dev, quirks); - if (IS_ERR(mmu)) + if (IS_ERR_OR_NULL(mmu)) return mmu; iommu = to_msm_iommu(mmu); From 68dc6c2d5eec45515855cce99256162f45651a0b Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 9 May 2023 13:30:41 -0700 Subject: [PATCH 077/358] drm/msm: Fix submit error-path leaks For errors after msm_submitqueue_get(), we need to drop the submitqueue reference. Additionally after get_unused_fd() we need to drop the fd. The ordering for dropping the queue lock and put_unused_fd() is not important, so just move this all into out_post_unlock. v2: Only drop queue ref if submit doesn't take it v3: Fix unitialized submit ref in error path v4: IS_ERR_OR_NULL() Reported-by: pinkperfect2021@gmail.com Fixes: f0de40a131d9 drm/msm: ("Reorder lock vs submit alloc") Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/536073/ Link: https://lore.kernel.org/r/20230509203041.440619-1-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_gem_submit.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index aff18c2f600a..9f5933c75e3d 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -722,7 +722,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_drm_private *priv = dev->dev_private; struct drm_msm_gem_submit *args = data; struct msm_file_private *ctx = file->driver_priv; - struct msm_gem_submit *submit; + struct msm_gem_submit *submit = NULL; struct msm_gpu *gpu = priv->gpu; struct msm_gpu_submitqueue *queue; struct msm_ringbuffer *ring; @@ -769,13 +769,15 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, out_fence_fd = get_unused_fd_flags(O_CLOEXEC); if (out_fence_fd < 0) { ret = out_fence_fd; - return ret; + goto out_post_unlock; } } submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds); - if (IS_ERR(submit)) - return PTR_ERR(submit); + if (IS_ERR(submit)) { + ret = PTR_ERR(submit); + goto out_post_unlock; + } trace_msm_gpu_submit(pid_nr(submit->pid), ring->id, submit->ident, args->nr_bos, args->nr_cmds); @@ -962,11 +964,20 @@ out: if (has_ww_ticket) ww_acquire_fini(&submit->ticket); out_unlock: - if (ret && (out_fence_fd >= 0)) - put_unused_fd(out_fence_fd); mutex_unlock(&queue->lock); out_post_unlock: - msm_gem_submit_put(submit); + if (ret && (out_fence_fd >= 0)) + put_unused_fd(out_fence_fd); + + if (!IS_ERR_OR_NULL(submit)) { + msm_gem_submit_put(submit); + } else { + /* + * If the submit hasn't yet taken ownership of the queue + * then we need to drop the reference ourself: + */ + msm_submitqueue_put(queue); + } if (!IS_ERR_OR_NULL(post_deps)) { for (i = 0; i < args->nr_out_syncobjs; ++i) { kfree(post_deps[i].chain); From 3e10f6ca76c4d00019badebd235c9d7f0068261e Mon Sep 17 00:00:00 2001 From: Vitaly Rodionov Date: Wed, 10 May 2023 15:22:27 +0100 Subject: [PATCH 078/358] ALSA: hda/realtek: Add quirk for HP EliteBook G10 laptops Add support for HP EliteBook 835/845/845W/865 G10 laptops with CS35L41 amplifiers on I2C/SPI bus connected to Realtek codec. Signed-off-by: Vitaly Rodionov Cc: Link: https://lore.kernel.org/r/20230510142227.32945-1-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index bc062c0a1916..5166f1eb510d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9458,7 +9458,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9469,8 +9469,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b65, "HP ProBook 455 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b66, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b70, "HP EliteBook 835 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b72, "HP EliteBook 845 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b74, "HP EliteBook 845W G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b77, "HP ElieBook 865 G10", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8b7a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b7d, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b87, "HP", ALC236_FIXUP_HP_GPIO_LED), @@ -9481,6 +9486,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c26, "HP HP EliteBook 800G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), From 4b963ae1df6426f0e51de64133d379d9bde50c48 Mon Sep 17 00:00:00 2001 From: Alexandru Sorodoc Date: Thu, 11 May 2023 19:15:10 +0300 Subject: [PATCH 079/358] ALSA: hda/realtek: Add quirks for ASUS GU604V and GU603V These models use 2 CS35L41 amplifiers using SPI for down-facing speakers. alc285_fixup_speaker2_to_dac1 is needed to fix volume control of the down-facing speakers. Pin configs are needed to enable headset mic detection. Note that these models lack the ACPI _DSD properties needed to initialize the amplifiers. They can be added during boot to get working sound out of the speakers: https://gist.github.com/lamperez/862763881c0e1c812392b5574727f6ff Signed-off-by: Alexandru Sorodoc Link: https://lore.kernel.org/r/20230511161510.315170-1-ealex95@gmail.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 5166f1eb510d..3df32eced8e4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7063,6 +7063,8 @@ enum { ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC295_FIXUP_DISABLE_DAC3, ALC285_FIXUP_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_HEADSET_MIC, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -8033,6 +8035,22 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, + [ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC245_FIXUP_CS35L41_SPI_2 + }, + [ALC285_FIXUP_ASUS_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1 + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -9506,6 +9524,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), + SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), From 21a933c79a33add3612808f3be4ad65dd4dc026b Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Wed, 10 May 2023 13:16:37 +0200 Subject: [PATCH 080/358] selftests: seg6: disable DAD on IPv6 router cfg for srv6_end_dt4_l3vpn_test The srv6_end_dt4_l3vpn_test instantiates a virtual network consisting of several routers (rt-1, rt-2) and hosts. When the IPv6 addresses of rt-{1,2} routers are configured, the Deduplicate Address Detection (DAD) kicks in when enabled in the Linux distros running the selftests. DAD is used to check whether an IPv6 address is already assigned in a network. Such a mechanism consists of sending an ICMPv6 Echo Request and waiting for a reply. As the DAD process could take too long to complete, it may cause the failing of some tests carried out by the srv6_end_dt4_l3vpn_test script. To make the srv6_end_dt4_l3vpn_test more robust, we disable DAD on routers since we configure the virtual network manually and do not need any address deduplication mechanism at all. Fixes: 2195444e09b4 ("selftests: add selftest for the SRv6 End.DT4 behavior") Signed-off-by: Andrea Mayer Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index 1003119773e5..37f08d582d2f 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -232,10 +232,14 @@ setup_rt_networking() local nsname=rt-${rt} ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link set veth-rt-${rt} netns ${nsname} ip -netns ${nsname} link set veth-rt-${rt} name veth0 - ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad ip -netns ${nsname} link set veth0 up ip -netns ${nsname} link set lo up From f97b8401e0deb46ad1e4245c21f651f64f55aaa6 Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Wed, 10 May 2023 13:16:38 +0200 Subject: [PATCH 081/358] selftets: seg6: disable rp_filter by default in srv6_end_dt4_l3vpn_test On some distributions, the rp_filter is automatically set (=1) by default on a netdev basis (also on VRFs). In an SRv6 End.DT4 behavior, decapsulated IPv4 packets are routed using the table associated with the VRF bound to that tunnel. During lookup operations, the rp_filter can lead to packet loss when activated on the VRF. Therefore, we chose to make this selftest more robust by explicitly disabling the rp_filter during tests (as it is automatically set by some Linux distributions). Fixes: 2195444e09b4 ("selftests: add selftest for the SRv6 End.DT4 behavior") Reported-by: Hangbin Liu Signed-off-by: Andrea Mayer Tested-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/srv6_end_dt4_l3vpn_test.sh | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index 37f08d582d2f..f96282362811 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -258,6 +258,12 @@ setup_hs() # set the networking for the host ip netns add ${hsname} + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} ip -netns ${hsname} link set ${rtveth} netns ${rtname} ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 @@ -276,11 +282,6 @@ setup_hs() ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 - # disable the rp_filter otherwise the kernel gets confused about how - # to route decap ipv4 packets. - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 - ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" } From e93c9378e33f68b61ea9318580d841caa22fb9ea Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 10 May 2023 16:46:21 +0200 Subject: [PATCH 082/358] devlink: change per-devlink netdev notifier to static one The commit 565b4824c39f ("devlink: change port event netdev notifier from per-net to global") changed original per-net notifier to be per-devlink instance. That fixed the issue of non-receiving events of netdev uninit if that moved to a different namespace. That worked fine in -net tree. However, later on when commit ee75f1fc44dd ("net/mlx5e: Create separate devlink instance for ethernet auxiliary device") and commit 72ed5d5624af ("net/mlx5: Suspend auxiliary devices only in case of PCI device suspend") were merged, a deadlock was introduced when removing a namespace with devlink instance with another nested instance. Here there is the bad flow example resulting in deadlock with mlx5: net_cleanup_work -> cleanup_net (takes down_read(&pernet_ops_rwsem) -> devlink_pernet_pre_exit() -> devlink_reload() -> mlx5_devlink_reload_down() -> mlx5_unload_one_devl_locked() -> mlx5_detach_device() -> del_adev() -> mlx5e_remove() -> mlx5e_destroy_devlink() -> devlink_free() -> unregister_netdevice_notifier() (takes down_write(&pernet_ops_rwsem) Steps to reproduce: $ modprobe mlx5_core $ ip netns add ns1 $ devlink dev reload pci/0000:08:00.0 netns ns1 $ ip netns del ns1 Resolve this by converting the notifier from per-devlink instance to a static one registered during init phase and leaving it registered forever. Use this notifier for all devlink port instances created later on. Note what a tree needs this fix only in case all of the cited fixes commits are present. Reported-by: Moshe Shemesh Fixes: 565b4824c39f ("devlink: change port event netdev notifier from per-net to global") Fixes: ee75f1fc44dd ("net/mlx5e: Create separate devlink instance for ethernet auxiliary device") Fixes: 72ed5d5624af ("net/mlx5: Suspend auxiliary devices only in case of PCI device suspend") Signed-off-by: Jiri Pirko Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230510144621.932017-1-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- net/devlink/core.c | 16 +++++++--------- net/devlink/devl_internal.h | 1 - net/devlink/leftover.c | 5 ++--- 3 files changed, 9 insertions(+), 13 deletions(-) diff --git a/net/devlink/core.c b/net/devlink/core.c index 777b091ef74d..0e58eee44bdb 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -204,11 +204,6 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, if (ret < 0) goto err_xa_alloc; - devlink->netdevice_nb.notifier_call = devlink_port_netdevice_event; - ret = register_netdevice_notifier(&devlink->netdevice_nb); - if (ret) - goto err_register_netdevice_notifier; - devlink->dev = dev; devlink->ops = ops; xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC); @@ -233,8 +228,6 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, return devlink; -err_register_netdevice_notifier: - xa_erase(&devlinks, devlink->index); err_xa_alloc: kfree(devlink); return NULL; @@ -266,8 +259,6 @@ void devlink_free(struct devlink *devlink) xa_destroy(&devlink->params); xa_destroy(&devlink->ports); - WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb)); - xa_erase(&devlinks, devlink->index); devlink_put(devlink); @@ -303,6 +294,10 @@ static struct pernet_operations devlink_pernet_ops __net_initdata = { .pre_exit = devlink_pernet_pre_exit, }; +static struct notifier_block devlink_port_netdevice_nb __net_initdata = { + .notifier_call = devlink_port_netdevice_event, +}; + static int __init devlink_init(void) { int err; @@ -311,6 +306,9 @@ static int __init devlink_init(void) if (err) goto out; err = register_pernet_subsys(&devlink_pernet_ops); + if (err) + goto out; + err = register_netdevice_notifier(&devlink_port_netdevice_nb); out: WARN_ON(err); diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index e133f423294a..62921b2eb0d3 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -50,7 +50,6 @@ struct devlink { u8 reload_failed:1; refcount_t refcount; struct rcu_work rwork; - struct notifier_block netdevice_nb; char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index dffca2f9bfa7..cd0254968076 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -7073,10 +7073,9 @@ int devlink_port_netdevice_event(struct notifier_block *nb, struct devlink_port *devlink_port = netdev->devlink_port; struct devlink *devlink; - devlink = container_of(nb, struct devlink, netdevice_nb); - - if (!devlink_port || devlink_port->devlink != devlink) + if (!devlink_port) return NOTIFY_OK; + devlink = devlink_port->devlink; switch (event) { case NETDEV_POST_INIT: From ef1148d4487438a3408d6face2a8360d91b4af70 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 May 2023 15:46:46 +0000 Subject: [PATCH 083/358] ipv6: remove nexthop_fib6_nh_bh() After blamed commit, nexthop_fib6_nh_bh() and nexthop_fib6_nh() are the same. Delete nexthop_fib6_nh_bh(), and convert /proc/net/ipv6_route to standard rcu to avoid this splat: [ 5723.180080] WARNING: suspicious RCU usage [ 5723.180083] ----------------------------- [ 5723.180084] include/net/nexthop.h:516 suspicious rcu_dereference_check() usage! [ 5723.180086] other info that might help us debug this: [ 5723.180087] rcu_scheduler_active = 2, debug_locks = 1 [ 5723.180089] 2 locks held by cat/55856: [ 5723.180091] #0: ffff9440a582afa8 (&p->lock){+.+.}-{3:3}, at: seq_read_iter (fs/seq_file.c:188) [ 5723.180100] #1: ffffffffaac07040 (rcu_read_lock_bh){....}-{1:2}, at: rcu_lock_acquire (include/linux/rcupdate.h:326) [ 5723.180109] stack backtrace: [ 5723.180111] CPU: 14 PID: 55856 Comm: cat Tainted: G S I 6.3.0-dbx-DEV #528 [ 5723.180115] Call Trace: [ 5723.180117] [ 5723.180119] dump_stack_lvl (lib/dump_stack.c:107) [ 5723.180124] dump_stack (lib/dump_stack.c:114) [ 5723.180126] lockdep_rcu_suspicious (include/linux/context_tracking.h:122) [ 5723.180132] ipv6_route_seq_show (include/net/nexthop.h:?) [ 5723.180135] ? ipv6_route_seq_next (net/ipv6/ip6_fib.c:2605) [ 5723.180140] seq_read_iter (fs/seq_file.c:272) [ 5723.180145] seq_read (fs/seq_file.c:163) [ 5723.180151] proc_reg_read (fs/proc/inode.c:316 fs/proc/inode.c:328) [ 5723.180155] vfs_read (fs/read_write.c:468) [ 5723.180160] ? up_read (kernel/locking/rwsem.c:1617) [ 5723.180164] ksys_read (fs/read_write.c:613) [ 5723.180168] __x64_sys_read (fs/read_write.c:621) [ 5723.180170] do_syscall_64 (arch/x86/entry/common.c:?) [ 5723.180174] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) [ 5723.180177] RIP: 0033:0x7fa455677d2a Fixes: 09eed1192cec ("neighbour: switch to standard rcu, instead of rcu_bh") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230510154646.370659-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/nexthop.h | 23 ----------------------- net/ipv6/ip6_fib.c | 16 ++++++++-------- 2 files changed, 8 insertions(+), 31 deletions(-) diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 9fa291a04621..2b12725de9c0 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -497,29 +497,6 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; } -/* Variant of nexthop_fib6_nh(). - * Caller should either hold rcu_read_lock(), or RTNL. - */ -static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) -{ - struct nh_info *nhi; - - if (nh->is_group) { - struct nh_group *nh_grp; - - nh_grp = rcu_dereference_rtnl(nh->nh_grp); - nh = nexthop_mpath_select(nh_grp, 0); - if (!nh) - return NULL; - } - - nhi = rcu_dereference_rtnl(nh->nh_info); - if (nhi->family == AF_INET6) - return &nhi->fib6_nh; - - return NULL; -} - static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2438da5ff6da..bac768d36cc1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2491,7 +2491,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev; if (rt->nh) - fib6_nh = nexthop_fib6_nh_bh(rt->nh); + fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); @@ -2556,14 +2556,14 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; - node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); + node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { - node = rcu_dereference_bh( + node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); @@ -2593,7 +2593,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); + n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; @@ -2619,12 +2619,12 @@ iter_table: } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU_BH) + __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; - rcu_read_lock_bh(); + rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; @@ -2645,7 +2645,7 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) - __releases(RCU_BH) + __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; @@ -2653,7 +2653,7 @@ static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); - rcu_read_unlock_bh(); + rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) From f816b9829b19394d318e01953aa3b2721bca040d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 10 May 2023 22:00:20 +0200 Subject: [PATCH 084/358] net: fec: Better handle pm_runtime_get() failing in .remove() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the (unlikely) event that pm_runtime_get() (disguised as pm_runtime_resume_and_get()) fails, the remove callback returned an error early. The problem with this is that the driver core ignores the error value and continues removing the device. This results in a resource leak. Worse the devm allocated resources are freed and so if a callback of the driver is called later the register mapping is already gone which probably results in a crash. Fixes: a31eda65ba21 ("net: fec: fix clock count mis-match") Signed-off-by: Uwe Kleine-König Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230510200020.1534610-1-u.kleine-koenig@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fec_main.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 42ec6ca3bf03..241df41d500f 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -4478,9 +4478,11 @@ fec_drv_remove(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; int ret; - ret = pm_runtime_resume_and_get(&pdev->dev); + ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) - return ret; + dev_err(&pdev->dev, + "Failed to resume device in remove callback (%pe)\n", + ERR_PTR(ret)); cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -4493,8 +4495,13 @@ fec_drv_remove(struct platform_device *pdev) of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); - clk_disable_unprepare(fep->clk_ahb); - clk_disable_unprepare(fep->clk_ipg); + /* After pm_runtime_get_sync() failed, the clks are still off, so skip + * disabling them again. + */ + if (ret >= 0) { + clk_disable_unprepare(fep->clk_ahb); + clk_disable_unprepare(fep->clk_ipg); + } pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); From 2b694fc96fe33a7c042e3a142d27d945c8c668b0 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 27 Apr 2023 12:34:53 -0700 Subject: [PATCH 085/358] powerpc/boot: Disable power10 features after BOOTAFLAGS assignment When building the boot wrapper assembly files with clang after commit 648a1783fe25 ("powerpc/boot: Fix boot wrapper code generation with CONFIG_POWER10_CPU"), the following warnings appear for each file built: '-prefixed' is not a recognized feature for this target (ignoring feature) '-pcrel' is not a recognized feature for this target (ignoring feature) While it is questionable whether or not LLVM should be emitting a warning when passed negative versions of code generation flags when building assembly files (since it does not emit a warning for the altivec and vsx flags), it is easy enough to work around this by just moving the disabled flags to BOOTCFLAGS after the assignment of BOOTAFLAGS, so that they are not added when building assembly files. Do so to silence the warnings. Fixes: 648a1783fe25 ("powerpc/boot: Fix boot wrapper code generation with CONFIG_POWER10_CPU") Link: https://github.com/ClangBuiltLinux/linux/issues/1839 Reviewed-by: Nicholas Piggin Signed-off-by: Nathan Chancellor Signed-off-by: Michael Ellerman Link: https://msgid.link/20230427-remove-power10-args-from-boot-aflags-clang-v1-1-9107f7c943bc@kernel.org --- arch/powerpc/boot/Makefile | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 85cde5bf04b7..771b79423bbc 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -34,8 +34,6 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ - $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \ - $(call cc-option,-mno-mma) \ $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE) @@ -71,6 +69,10 @@ BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc BOOTARFLAGS := -crD +BOOTCFLAGS += $(call cc-option,-mno-prefixed) \ + $(call cc-option,-mno-pcrel) \ + $(call cc-option,-mno-mma) + ifdef CONFIG_CC_IS_CLANG BOOTCFLAGS += $(CLANG_FLAGS) BOOTAFLAGS += $(CLANG_FLAGS) From 0b01db274028f5acd207332686ffc92ac77491ac Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Wed, 10 May 2023 18:21:39 +0530 Subject: [PATCH 086/358] net: phy: dp83867: add w/a for packet errors seen with short cables Introduce the W/A for packet errors seen with short cables (<1m) between two DP83867 PHYs. The W/A recommended by DM requires FFE Equalizer Configuration tuning by writing value 0x0E81 to DSP_FFE_CFG register (0x012C), surrounded by hard and soft resets as follows: write_reg(0x001F, 0x8000); //hard reset write_reg(DSP_FFE_CFG, 0x0E81); write_reg(0x001F, 0x4000); //soft reset Since DP83867 PHY DM says "Changing this register to 0x0E81, will not affect Long Cable performance.", enable the W/A by default. Fixes: 2a10154abcb7 ("net: phy: dp83867: Add TI dp83867 phy") Signed-off-by: Grygorii Strashko Signed-off-by: Siddharth Vadapalli Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/phy/dp83867.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index d75f526a20a4..76f5a2402fb0 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -44,6 +44,7 @@ #define DP83867_STRAP_STS1 0x006E #define DP83867_STRAP_STS2 0x006f #define DP83867_RGMIIDCTL 0x0086 +#define DP83867_DSP_FFE_CFG 0x012c #define DP83867_RXFCFG 0x0134 #define DP83867_RXFPMD1 0x0136 #define DP83867_RXFPMD2 0x0137 @@ -941,8 +942,27 @@ static int dp83867_phy_reset(struct phy_device *phydev) usleep_range(10, 20); - return phy_modify(phydev, MII_DP83867_PHYCTRL, + err = phy_modify(phydev, MII_DP83867_PHYCTRL, DP83867_PHYCR_FORCE_LINK_GOOD, 0); + if (err < 0) + return err; + + /* Configure the DSP Feedforward Equalizer Configuration register to + * improve short cable (< 1 meter) performance. This will not affect + * long cable performance. + */ + err = phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_DSP_FFE_CFG, + 0x0e81); + if (err < 0) + return err; + + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); + if (err < 0) + return err; + + usleep_range(10, 20); + + return 0; } static void dp83867_link_change_notify(struct phy_device *phydev) From d03a2f17627e8f94ce8c4790fede3ef7efe9be53 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 10 May 2023 19:42:43 -0300 Subject: [PATCH 087/358] MAINTAINERS: sctp: move Neil to CREDITS Neil moved away from SCTP related duties. Move him to CREDITS then and while at it, update SCTP project website. Signed-off-by: Marcelo Ricardo Leitner Acked-by: Xin Long Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- CREDITS | 4 ++++ MAINTAINERS | 3 +-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/CREDITS b/CREDITS index 2d9da9a7defa..de7e4dbbc599 100644 --- a/CREDITS +++ b/CREDITS @@ -1706,6 +1706,10 @@ S: Panoramastrasse 18 S: D-69126 Heidelberg S: Germany +N: Neil Horman +M: nhorman@tuxdriver.com +D: SCTP protocol maintainer. + N: Simon Horman M: horms@verge.net.au D: Renesas ARM/ARM64 SoC maintainer diff --git a/MAINTAINERS b/MAINTAINERS index e2fd64c2ebdc..69107014d39b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18842,12 +18842,11 @@ F: drivers/target/ F: include/target/ SCTP PROTOCOL -M: Neil Horman M: Marcelo Ricardo Leitner M: Xin Long L: linux-sctp@vger.kernel.org S: Maintained -W: http://lksctp.sourceforge.net +W: https://github.com/sctp/lksctp-tools/wiki F: Documentation/networking/sctp.rst F: include/linux/sctp.h F: include/net/sctp/ From 01e8f6cd108b8702d206c6352d919c045b842b82 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 10 May 2023 18:43:39 -0700 Subject: [PATCH 088/358] MAINTAINERS: don't CC docs@ for netlink spec changes Documentation/netlink/ contains machine-readable protocol specs in YAML. Those are much like device tree bindings, no point CCing docs@ for the changes. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 69107014d39b..13e20a9754e9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6211,6 +6211,7 @@ X: Documentation/devicetree/ X: Documentation/driver-api/media/ X: Documentation/firmware-guide/acpi/ X: Documentation/i2c/ +X: Documentation/netlink/ X: Documentation/power/ X: Documentation/spi/ X: Documentation/userspace-api/media/ @@ -14615,6 +14616,7 @@ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/core-api/netlink.rst +F: Documentation/netlink/ F: Documentation/networking/ F: Documentation/process/maintainer-netdev.rst F: Documentation/userspace-api/netlink/ From de9c1a23add9e7842ce63ce6f498a05c66344311 Mon Sep 17 00:00:00 2001 From: Huayu Chen Date: Thu, 11 May 2023 08:50:56 +0200 Subject: [PATCH 089/358] nfp: fix NFP_NET_MAX_DSCP definition error The patch corrects the NFP_NET_MAX_DSCP definition in the main.h file. The incorrect definition result DSCP bits not being mapped properly when DCB is set. When NFP_NET_MAX_DSCP was defined as 4, the next 60 DSCP bits failed to be set. Fixes: 9b7fe8046d74 ("nfp: add DCB IEEE support") Cc: stable@vger.kernel.org Signed-off-by: Huayu Chen Acked-by: Simon Horman Signed-off-by: Louis Peens Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nic/main.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.h b/drivers/net/ethernet/netronome/nfp/nic/main.h index 094374df42b8..38b8b10b03cd 100644 --- a/drivers/net/ethernet/netronome/nfp/nic/main.h +++ b/drivers/net/ethernet/netronome/nfp/nic/main.h @@ -8,7 +8,7 @@ #ifdef CONFIG_DCB /* DCB feature definitions */ -#define NFP_NET_MAX_DSCP 4 +#define NFP_NET_MAX_DSCP 64 #define NFP_NET_MAX_TC IEEE_8021QAZ_MAX_TCS #define NFP_NET_MAX_PRIO 8 #define NFP_DCB_CFG_STRIDE 256 From 47af4291711f21e1282dbc1002baebba30595aa2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 11 May 2023 09:03:10 -0700 Subject: [PATCH 090/358] MAINTAINERS: exclude wireless drivers from netdev It seems that we mostly get netdev CCed on wireless patches which are written by people who don't know any better and CC everything that get_maintainers spits out. Rather than patches which indeed could benefit from general networking review. Marking them down in patchwork as Awaiting Upstream is a bit tedious. Signed-off-by: Jakub Kicinski Acked-by: Johannes Berg Acked-by: Kalle Valo Signed-off-by: David S. Miller --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 13e20a9754e9..e884937f0e28 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14567,6 +14567,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ F: drivers/connector/ F: drivers/net/ +X: drivers/net/wireless/ F: include/dt-bindings/net/ F: include/linux/etherdevice.h F: include/linux/fcdevice.h From c0e72058d5e21982e61a29de6b098f7c1f0db498 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 9 May 2023 12:07:11 +0300 Subject: [PATCH 091/358] ALSA: firewire-digi00x: prevent potential use after free This code was supposed to return an error code if init_stream() failed, but it instead freed dg00x->rx_stream and returned success. This potentially leads to a use after free. Fixes: 9a08067ec318 ("ALSA: firewire-digi00x: support AMDTP domain") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/c224cbd5-d9e2-4cd4-9bcf-2138eb1d35c6@kili.mountain Signed-off-by: Takashi Iwai --- sound/firewire/digi00x/digi00x-stream.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/firewire/digi00x/digi00x-stream.c b/sound/firewire/digi00x/digi00x-stream.c index a15f55b0dce3..295163bb8abb 100644 --- a/sound/firewire/digi00x/digi00x-stream.c +++ b/sound/firewire/digi00x/digi00x-stream.c @@ -259,8 +259,10 @@ int snd_dg00x_stream_init_duplex(struct snd_dg00x *dg00x) return err; err = init_stream(dg00x, &dg00x->tx_stream); - if (err < 0) + if (err < 0) { destroy_stream(dg00x, &dg00x->rx_stream); + return err; + } err = amdtp_domain_init(&dg00x->domain); if (err < 0) { From 359b4315471181f108723c61612d96e383e56179 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 12 May 2023 09:58:58 +0200 Subject: [PATCH 092/358] ALSA: usb-audio: Add a sample rate workaround for Line6 Pod Go Line6 Pod Go (0e41:424b) requires the similar workaround for the fixed 48k sample rate like other Line6 models. This patch adds the corresponding entry to line6_parse_audio_format_rate_quirk(). Reported-by: John Humlick Cc: Link: https://lore.kernel.org/r/20230512075858.22813-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/format.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/format.c b/sound/usb/format.c index 4b1c5ba121f3..ab5fed9f55b6 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -423,6 +423,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ + case USB_ID(0x0e41, 0x424b): /* Line6 Pod Go */ case USB_ID(0x19f7, 0x0011): /* Rode Rodecaster Pro */ return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); } From cdc26ee89bddb9b6b2ae026a46d97855d5ba6694 Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Mon, 24 Apr 2023 05:39:05 +0800 Subject: [PATCH 093/358] wifi: mt76: mt7996: fix endianness of MT_TXD6_TX_RATE To avoid sparse warning: sparse: warning: invalid assignment: |= sparse: left side has type restricted __le32 sparse: right side has type unsigned lon Fixes: 15ee62e73705 ("wifi: mt76: mt7996: enable BSS_CHANGED_BASIC_RATES support") Signed-off-by: Ryder Lee Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/16fa938373e3b145cb07a2c98d2428fea2abadba.1682285873.git.ryder.lee@mediatek.com --- drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 130eb7b4fd91..39a4a73ef8e6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1088,7 +1088,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, else if (beacon && mvif->beacon_rates_idx) idx = mvif->beacon_rates_idx; - txwi[6] |= FIELD_PREP(MT_TXD6_TX_RATE, idx); + txwi[6] |= cpu_to_le32(FIELD_PREP(MT_TXD6_TX_RATE, idx)); txwi[3] |= cpu_to_le32(MT_TXD3_BA_DISABLE); } } From c7ab7a29ef5c0779574120d922256ce4651555d3 Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Mon, 24 Apr 2023 05:39:06 +0800 Subject: [PATCH 094/358] wifi: mt76: connac: fix stats->tx_bytes calculation The stats->tx_bytes shall subtract retry byte from tx byte. Fixes: 43eaa3689507 ("wifi: mt76: add PPDU based TxS support for WED device") Signed-off-by: Ryder Lee Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/b3cd45596943cf5a06b2e08e2fe732ab0b51311b.1682285873.git.ryder.lee@mediatek.com --- drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h | 2 +- drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h index a5ec0f631385..fabf637bdf7f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h @@ -173,7 +173,7 @@ enum { #define MT_TXS5_MPDU_TX_CNT GENMASK(31, 23) #define MT_TXS6_MPDU_FAIL_CNT GENMASK(31, 23) - +#define MT_TXS7_MPDU_RETRY_BYTE GENMASK(22, 0) #define MT_TXS7_MPDU_RETRY_CNT GENMASK(31, 23) /* RXD DW0 */ diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index ee0fbfcd07d6..d39a3cc5e381 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -608,7 +608,8 @@ bool mt76_connac2_mac_fill_txs(struct mt76_dev *dev, struct mt76_wcid *wcid, /* PPDU based reporting */ if (FIELD_GET(MT_TXS0_TXS_FORMAT, txs) > 1) { stats->tx_bytes += - le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_BYTE); + le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_BYTE) - + le32_get_bits(txs_data[7], MT_TXS7_MPDU_RETRY_BYTE); stats->tx_packets += le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_CNT); stats->tx_failed += From c0426c446d92023d344131d01d929bc25db7a24e Mon Sep 17 00:00:00 2001 From: Ping-Ke Shih Date: Wed, 26 Apr 2023 11:47:37 +0800 Subject: [PATCH 095/358] wifi: rtw89: 8852b: adjust quota to avoid SER L1 caused by access null page Though SER can recover this case, traffic can get stuck for a while. Fix it by adjusting page quota to avoid hardware access null page of CMAC/DMAC. Fixes: a1cb097168fa ("wifi: rtw89: 8852b: configure DLE mem") Fixes: 3e870b481733 ("wifi: rtw89: 8852b: add HFC quota arrays") Cc: stable@vger.kernel.org Tested-by: Larry Finger Link: https://github.com/lwfinger/rtw89/issues/226#issuecomment-1520776761 Link: https://github.com/lwfinger/rtw89/issues/240 Signed-off-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230426034737.24870-1-pkshih@realtek.com --- drivers/net/wireless/realtek/rtw89/mac.c | 4 +++ drivers/net/wireless/realtek/rtw89/mac.h | 2 ++ drivers/net/wireless/realtek/rtw89/rtw8852b.c | 28 +++++++++---------- 3 files changed, 20 insertions(+), 14 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index b8019cfc11b2..512de491a064 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -1425,6 +1425,8 @@ const struct rtw89_mac_size_set rtw89_mac_size = { .wde_size4 = {RTW89_WDE_PG_64, 0, 4096,}, /* PCIE 64 */ .wde_size6 = {RTW89_WDE_PG_64, 512, 0,}, + /* 8852B PCIE SCC */ + .wde_size7 = {RTW89_WDE_PG_64, 510, 2,}, /* DLFW */ .wde_size9 = {RTW89_WDE_PG_64, 0, 1024,}, /* 8852C DLFW */ @@ -1449,6 +1451,8 @@ const struct rtw89_mac_size_set rtw89_mac_size = { .wde_qt4 = {0, 0, 0, 0,}, /* PCIE 64 */ .wde_qt6 = {448, 48, 0, 16,}, + /* 8852B PCIE SCC */ + .wde_qt7 = {446, 48, 0, 16,}, /* 8852C DLFW */ .wde_qt17 = {0, 0, 0, 0,}, /* 8852C PCIE SCC */ diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h index a8d9847ef0b4..6ba633ccdd03 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.h +++ b/drivers/net/wireless/realtek/rtw89/mac.h @@ -792,6 +792,7 @@ struct rtw89_mac_size_set { const struct rtw89_dle_size wde_size0; const struct rtw89_dle_size wde_size4; const struct rtw89_dle_size wde_size6; + const struct rtw89_dle_size wde_size7; const struct rtw89_dle_size wde_size9; const struct rtw89_dle_size wde_size18; const struct rtw89_dle_size wde_size19; @@ -804,6 +805,7 @@ struct rtw89_mac_size_set { const struct rtw89_wde_quota wde_qt0; const struct rtw89_wde_quota wde_qt4; const struct rtw89_wde_quota wde_qt6; + const struct rtw89_wde_quota wde_qt7; const struct rtw89_wde_quota wde_qt17; const struct rtw89_wde_quota wde_qt18; const struct rtw89_ple_quota ple_qt4; diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c index eaa2ea0586bc..6da1b603a9a9 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c @@ -18,25 +18,25 @@ RTW8852B_FW_BASENAME "-" __stringify(RTW8852B_FW_FORMAT_MAX) ".bin" static const struct rtw89_hfc_ch_cfg rtw8852b_hfc_chcfg_pcie[] = { - {5, 343, grp_0}, /* ACH 0 */ - {5, 343, grp_0}, /* ACH 1 */ - {5, 343, grp_0}, /* ACH 2 */ - {5, 343, grp_0}, /* ACH 3 */ + {5, 341, grp_0}, /* ACH 0 */ + {5, 341, grp_0}, /* ACH 1 */ + {4, 342, grp_0}, /* ACH 2 */ + {4, 342, grp_0}, /* ACH 3 */ {0, 0, grp_0}, /* ACH 4 */ {0, 0, grp_0}, /* ACH 5 */ {0, 0, grp_0}, /* ACH 6 */ {0, 0, grp_0}, /* ACH 7 */ - {4, 344, grp_0}, /* B0MGQ */ - {4, 344, grp_0}, /* B0HIQ */ + {4, 342, grp_0}, /* B0MGQ */ + {4, 342, grp_0}, /* B0HIQ */ {0, 0, grp_0}, /* B1MGQ */ {0, 0, grp_0}, /* B1HIQ */ {40, 0, 0} /* FWCMDQ */ }; static const struct rtw89_hfc_pub_cfg rtw8852b_hfc_pubcfg_pcie = { - 448, /* Group 0 */ + 446, /* Group 0 */ 0, /* Group 1 */ - 448, /* Public Max */ + 446, /* Public Max */ 0 /* WP threshold */ }; @@ -49,13 +49,13 @@ static const struct rtw89_hfc_param_ini rtw8852b_hfc_param_ini_pcie[] = { }; static const struct rtw89_dle_mem rtw8852b_dle_mem_pcie[] = { - [RTW89_QTA_SCC] = {RTW89_QTA_SCC, &rtw89_mac_size.wde_size6, - &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt6, - &rtw89_mac_size.wde_qt6, &rtw89_mac_size.ple_qt18, + [RTW89_QTA_SCC] = {RTW89_QTA_SCC, &rtw89_mac_size.wde_size7, + &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt7, + &rtw89_mac_size.wde_qt7, &rtw89_mac_size.ple_qt18, &rtw89_mac_size.ple_qt58}, - [RTW89_QTA_WOW] = {RTW89_QTA_WOW, &rtw89_mac_size.wde_size6, - &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt6, - &rtw89_mac_size.wde_qt6, &rtw89_mac_size.ple_qt18, + [RTW89_QTA_WOW] = {RTW89_QTA_WOW, &rtw89_mac_size.wde_size7, + &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt7, + &rtw89_mac_size.wde_qt7, &rtw89_mac_size.ple_qt18, &rtw89_mac_size.ple_qt_52b_wow}, [RTW89_QTA_DLFW] = {RTW89_QTA_DLFW, &rtw89_mac_size.wde_size9, &rtw89_mac_size.ple_size8, &rtw89_mac_size.wde_qt4, From bcafcb959a57a6890e900199690c5fc47da1a304 Mon Sep 17 00:00:00 2001 From: Ping-Ke Shih Date: Mon, 8 May 2023 16:54:29 +0800 Subject: [PATCH 096/358] wifi: rtw88: use work to update rate to avoid RCU warning The ieee80211_ops::sta_rc_update must be atomic, because ieee80211_chan_bw_change() holds rcu_read lock while calling drv_sta_rc_update(), so create a work to do original things. Voluntary context switch within RCU read-side critical section! WARNING: CPU: 0 PID: 4621 at kernel/rcu/tree_plugin.h:318 rcu_note_context_switch+0x571/0x5d0 CPU: 0 PID: 4621 Comm: kworker/u16:2 Tainted: G W OE Workqueue: phy3 ieee80211_chswitch_work [mac80211] RIP: 0010:rcu_note_context_switch+0x571/0x5d0 Call Trace: __schedule+0xb0/0x1460 ? __mod_timer+0x116/0x360 schedule+0x5a/0xc0 schedule_timeout+0x87/0x150 ? trace_raw_output_tick_stop+0x60/0x60 wait_for_completion_timeout+0x7b/0x140 usb_start_wait_urb+0x82/0x160 [usbcore usb_control_msg+0xe3/0x140 [usbcore rtw_usb_read+0x88/0xe0 [rtw_usb rtw_usb_read8+0xf/0x10 [rtw_usb rtw_fw_send_h2c_command+0xa0/0x170 [rtw_core rtw_fw_send_ra_info+0xc9/0xf0 [rtw_core drv_sta_rc_update+0x7c/0x160 [mac80211 ieee80211_chan_bw_change+0xfb/0x110 [mac80211 ieee80211_change_chanctx+0x38/0x130 [mac80211 ieee80211_vif_use_reserved_switch+0x34e/0x900 [mac80211 ieee80211_link_use_reserved_context+0x88/0xe0 [mac80211 ieee80211_chswitch_work+0x95/0x170 [mac80211 process_one_work+0x201/0x410 worker_thread+0x4a/0x3b0 ? process_one_work+0x410/0x410 kthread+0xe1/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 Cc: stable@vger.kernel.org Fixes: c1edc86472fc ("rtw88: add ieee80211:sta_rc_update ops") Reported-by: Larry Finger Link: https://lore.kernel.org/linux-wireless/f1e31e8e-f84e-3791-50fb-663a83c5c6e9@lwfinger.net/T/#t Signed-off-by: Ping-Ke Shih Tested-by: Larry Finger Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230508085429.46653-1-pkshih@realtek.com --- drivers/net/wireless/realtek/rtw88/mac80211.c | 2 +- drivers/net/wireless/realtek/rtw88/main.c | 15 +++++++++++++++ drivers/net/wireless/realtek/rtw88/main.h | 3 +++ 3 files changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c index 7aa6edad0d01..a6c024cab7ee 100644 --- a/drivers/net/wireless/realtek/rtw88/mac80211.c +++ b/drivers/net/wireless/realtek/rtw88/mac80211.c @@ -918,7 +918,7 @@ static void rtw_ops_sta_rc_update(struct ieee80211_hw *hw, struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv; if (changed & IEEE80211_RC_BW_CHANGED) - rtw_update_sta_info(rtwdev, si, true); + ieee80211_queue_work(rtwdev->hw, &si->rc_work); } const struct ieee80211_ops rtw_ops = { diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 5bf6b4581557..d30a191c9291 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -319,6 +319,17 @@ static u8 rtw_acquire_macid(struct rtw_dev *rtwdev) return mac_id; } +static void rtw_sta_rc_work(struct work_struct *work) +{ + struct rtw_sta_info *si = container_of(work, struct rtw_sta_info, + rc_work); + struct rtw_dev *rtwdev = si->rtwdev; + + mutex_lock(&rtwdev->mutex); + rtw_update_sta_info(rtwdev, si, true); + mutex_unlock(&rtwdev->mutex); +} + int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, struct ieee80211_vif *vif) { @@ -329,12 +340,14 @@ int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, if (si->mac_id >= RTW_MAX_MAC_ID_NUM) return -ENOSPC; + si->rtwdev = rtwdev; si->sta = sta; si->vif = vif; si->init_ra_lv = 1; ewma_rssi_init(&si->avg_rssi); for (i = 0; i < ARRAY_SIZE(sta->txq); i++) rtw_txq_init(rtwdev, sta->txq[i]); + INIT_WORK(&si->rc_work, rtw_sta_rc_work); rtw_update_sta_info(rtwdev, si, true); rtw_fw_media_status_report(rtwdev, si->mac_id, true); @@ -353,6 +366,8 @@ void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv; int i; + cancel_work_sync(&si->rc_work); + rtw_release_macid(rtwdev, si->mac_id); if (fw_exist) rtw_fw_media_status_report(rtwdev, si->mac_id, false); diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h index a563285e90ed..9e841f6991a9 100644 --- a/drivers/net/wireless/realtek/rtw88/main.h +++ b/drivers/net/wireless/realtek/rtw88/main.h @@ -743,6 +743,7 @@ struct rtw_txq { DECLARE_EWMA(rssi, 10, 16); struct rtw_sta_info { + struct rtw_dev *rtwdev; struct ieee80211_sta *sta; struct ieee80211_vif *vif; @@ -767,6 +768,8 @@ struct rtw_sta_info { bool use_cfg_mask; struct cfg80211_bitrate_mask *mask; + + struct work_struct rc_work; }; enum rtw_bfee_role { From 92553ee03166ef8fa978e7683f9f4af30c9c4e6b Mon Sep 17 00:00:00 2001 From: "Ryan C. Underwood" Date: Thu, 11 May 2023 12:32:21 -0500 Subject: [PATCH 097/358] ALSA: hda/realtek: Apply HP B&O top speaker profile to Pavilion 15 The Pavilion 15 line has B&O top speakers similar to the x360 and applying the same profile produces good sound. Without this, the sound would be tinny and underpowered without either applying model=alc295-hp-x360 or booting another OS first. Signed-off-by: Ryan Underwood Fixes: 563785edfcef ("ALSA: hda/realtek - Add quirk entry for HP Pavilion 15") Link: https://lore.kernel.org/r/ZF0mpcMz3ezP9KQw@icequake.net Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3df32eced8e4..92a920f46b7c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9381,7 +9381,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x802f, "HP Z240", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8077, "HP", ALC256_FIXUP_HP_HEADSET_MIC), SND_PCI_QUIRK(0x103c, 0x8158, "HP", ALC256_FIXUP_HP_HEADSET_MIC), - SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x827f, "HP x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), From 9113302bb43cf7a6d5a414d49b29478e57451c86 Mon Sep 17 00:00:00 2001 From: Jan Sokolowski Date: Thu, 11 May 2023 08:53:19 -0700 Subject: [PATCH 098/358] ice: Fix undersized tx_flags variable As not all ICE_TX_FLAGS_* fit in current 16-bit limited tx_flags field that was introduced in the Fixes commit, VLAN-related information would be discarded completely. As such, creating a vlan and trying to run ping through would result in no traffic passing. Fix that by refactoring tx_flags variable into flags only and a separate variable that holds VLAN ID. As there is some space left, type variable can fit between those two. Pahole reports no size change to ice_tx_buf struct. Fixes: aa1d3faf71a6 ("ice: Robustify cleaning/completing XDP Tx buffers") Signed-off-by: Jan Sokolowski Reviewed-by: Alexander Lobakin Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 5 ++--- drivers/net/ethernet/intel/ice/ice_txrx.c | 8 +++----- drivers/net/ethernet/intel/ice/ice_txrx.h | 9 +++------ 3 files changed, 8 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index c6d4926f0fcf..850db8e0e6b0 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -932,10 +932,9 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN || first->tx_flags & ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN) || skb->priority != TC_PRIO_CONTROL) { - first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M; + first->vid &= ~VLAN_PRIO_MASK; /* Mask the lower 3 bits to set the 802.1p priority */ - first->tx_flags |= (skb->priority & 0x7) << - ICE_TX_FLAGS_VLAN_PR_S; + first->vid |= (skb->priority << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; /* if this is not already set it means a VLAN 0 + priority needs * to be offloaded */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 4fcf2d07eb85..059bd911c51d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1664,8 +1664,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, if (first->tx_flags & ICE_TX_FLAGS_HW_VLAN) { td_cmd |= (u64)ICE_TX_DESC_CMD_IL2TAG1; - td_tag = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + td_tag = first->vid; } dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); @@ -1998,7 +1997,7 @@ ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) * VLAN offloads exclusively so we only care about the VLAN ID here */ if (skb_vlan_tag_present(skb)) { - first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S; + first->vid = skb_vlan_tag_get(skb); if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2) first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN; else @@ -2388,8 +2387,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | (ICE_TX_CTX_DESC_IL2TAG2 << ICE_TXD_CTX_QW1_CMD_S)); - offload.cd_l2tag2 = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + offload.cd_l2tag2 = first->vid; } /* set up TSO offload */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index fff0efe28373..166413fc33f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -127,10 +127,6 @@ static inline int ice_skb_pad(void) #define ICE_TX_FLAGS_IPV6 BIT(6) #define ICE_TX_FLAGS_TUNNEL BIT(7) #define ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN BIT(8) -#define ICE_TX_FLAGS_VLAN_M 0xffff0000 -#define ICE_TX_FLAGS_VLAN_PR_M 0xe0000000 -#define ICE_TX_FLAGS_VLAN_PR_S 29 -#define ICE_TX_FLAGS_VLAN_S 16 #define ICE_XDP_PASS 0 #define ICE_XDP_CONSUMED BIT(0) @@ -182,8 +178,9 @@ struct ice_tx_buf { unsigned int gso_segs; unsigned int nr_frags; /* used for mbuf XDP */ }; - u32 type:16; /* &ice_tx_buf_type */ - u32 tx_flags:16; + u32 tx_flags:12; + u32 type:4; /* &ice_tx_buf_type */ + u32 vid:16; DEFINE_DMA_UNMAP_LEN(len); DEFINE_DMA_UNMAP_ADDR(dma); }; From 134120b066044399ef59564ff3ba66ab344cfc5b Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Thu, 11 May 2023 10:43:33 +0100 Subject: [PATCH 099/358] sfc: disable RXFCS and RXALL features by default By default we would not want RXFCS and RXALL features enabled as they are mainly intended for debugging purposes. This does not stop users from enabling them later on as needed. Fixes: 8e57daf70671 ("sfc_ef100: RX path for EF100") Signed-off-by: Pieter Jansen van Vuuren Co-developed-by: Edward Cree Signed-off-by: Edward Cree Reviewed-by: Martin Habets Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/ef100_netdev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index d916877b5a9a..be395cd8770b 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -378,7 +378,9 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data) efx->net_dev = net_dev; SET_NETDEV_DEV(net_dev, &efx->pci_dev->dev); - net_dev->features |= efx->type->offload_features; + /* enable all supported features except rx-fcs and rx-all */ + net_dev->features |= efx->type->offload_features & + ~(NETIF_F_RXFCS | NETIF_F_RXALL); net_dev->hw_features |= efx->type->offload_features; net_dev->hw_enc_features |= efx->type->offload_features; net_dev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_SG | From 6d4486efe9c69626cab423456169e250a5cd3af5 Mon Sep 17 00:00:00 2001 From: Zhuang Shengen Date: Thu, 11 May 2023 19:34:30 +0800 Subject: [PATCH 100/358] vsock: avoid to close connected socket after the timeout MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When client and server establish a connection through vsock, the client send a request to the server to initiate the connection, then start a timer to wait for the server's response. When the server's RESPONSE message arrives, the timer also times out and exits. The server's RESPONSE message is processed first, and the connection is established. However, the client's timer also times out, the original processing logic of the client is to directly set the state of this vsock to CLOSE and return ETIMEDOUT. It will not notify the server when the port is released, causing the server port remain. when client's vsock_connect timeout，it should check sk state is ESTABLISHED or not. if sk state is ESTABLISHED, it means the connection is established, the client should not set the sk state to CLOSE Note: I encountered this issue on kernel-4.18, which can be fixed by this patch. Then I checked the latest code in the community and found similar issue. Fixes: d021c344051a ("VSOCK: Introduce VM Sockets") Signed-off-by: Zhuang Shengen Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 413407bb646c..efb8a0937a13 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1462,7 +1462,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, vsock_transport_cancel_pkt(vsk); vsock_remove_connected(vsk); goto out_wait; - } else if (timeout == 0) { + } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { err = -ETIMEDOUT; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; From 9dc68a4fe70893b000fb3c92c68b9f72369cf448 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 12 May 2023 16:34:16 +0800 Subject: [PATCH 101/358] ALSA: hda/realtek: Fix mute and micmute LEDs for yet another HP laptop There's yet another laptop that needs the fixup to enable mute and micmute LEDs. So do it accordingly. Signed-off-by: Kai-Heng Feng Cc: Link: https://lore.kernel.org/r/20230512083417.157127-1-kai.heng.feng@canonical.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 92a920f46b7c..a7e4765eff80 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9503,6 +9503,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b8f, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c26, "HP HP EliteBook 800G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), From 1e306ec49a1f206fd2cc89a42fac6e6f592a8cc1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 May 2023 11:47:49 +0000 Subject: [PATCH 102/358] tcp: fix possible sk_priority leak in tcp_v4_send_reset() When tcp_v4_send_reset() is called with @sk == NULL, we do not change ctl_sk->sk_priority, which could have been set from a prior invocation. Change tcp_v4_send_reset() to set sk_priority and sk_mark fields before calling ip_send_unicast_reply(). This means tcp_v4_send_reset() and tcp_v4_send_ack() no longer have to clear ctl_sk->sk_mark after their call to ip_send_unicast_reply(). Fixes: f6c0f5d209fa ("tcp: honor SO_PRIORITY in TIME_WAIT state") Signed-off-by: Eric Dumazet Cc: Antoine Tenart Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 39bda2b1066e..06d2573685ca 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -829,6 +829,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); + } else { + ctl_sk->sk_mark = 0; + ctl_sk->sk_priority = 0; } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -836,7 +839,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) &arg, arg.iov[0].iov_len, transmit_time); - ctl_sk->sk_mark = 0; xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); @@ -935,7 +937,6 @@ static void tcp_v4_send_ack(const struct sock *sk, &arg, arg.iov[0].iov_len, transmit_time); - ctl_sk->sk_mark = 0; sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); From 53558de2b5c4f4ee6bfcfbe34e27071c2d0073d5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Jan 2023 17:10:16 +0000 Subject: [PATCH 103/358] media: pvrusb2: fix DVB_CORE dependency Now that DVB_CORE can be a loadable module, pvrusb2 can run into a link error: ld.lld: error: undefined symbol: dvb_module_probe >>> referenced by pvrusb2-devattr.c >>> drivers/media/usb/pvrusb2/pvrusb2-devattr.o:(pvr2_lgdt3306a_attach) in archive vmlinux.a ld.lld: error: undefined symbol: dvb_module_release >>> referenced by pvrusb2-devattr.c >>> drivers/media/usb/pvrusb2/pvrusb2-devattr.o:(pvr2_dual_fe_attach) in archive vmlinux.a Refine the Kconfig dependencies to avoid this case. Link: https://lore.kernel.org/linux-media/20230117171055.2714621-1-arnd@kernel.org Fixes: 7655c342dbc4 ("media: Kconfig: Make DVB_CORE=m possible when MEDIA_SUPPORT=y") Signed-off-by: Arnd Bergmann Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/pvrusb2/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/usb/pvrusb2/Kconfig b/drivers/media/usb/pvrusb2/Kconfig index 9501b10b31aa..0df10270dbdf 100644 --- a/drivers/media/usb/pvrusb2/Kconfig +++ b/drivers/media/usb/pvrusb2/Kconfig @@ -37,6 +37,7 @@ config VIDEO_PVRUSB2_DVB bool "pvrusb2 ATSC/DVB support" default y depends on VIDEO_PVRUSB2 && DVB_CORE + depends on VIDEO_PVRUSB2=m || DVB_CORE=y select DVB_LGDT330X if MEDIA_SUBDRV_AUTOSELECT select DVB_S5H1409 if MEDIA_SUBDRV_AUTOSELECT select DVB_S5H1411 if MEDIA_SUBDRV_AUTOSELECT From 7efb10d8dc70ea3000cc70dca53407c52488acd1 Mon Sep 17 00:00:00 2001 From: YongSu Yoo Date: Sun, 5 Mar 2023 21:25:19 +0000 Subject: [PATCH 104/358] media: dvb_demux: fix a bug for the continuity counter In dvb_demux.c, some logics exist which compare the expected continuity counter and the real continuity counter. If they are not matched each other, both of the expected continuity counter and the real continuity counter should be printed. But there exists a bug that the expected continuity counter is not correctly printed. The expected continuity counter is replaced with the real countinuity counter + 1 so that the epected continuity counter is not correclty printed. This is wrong. This bug is fixed. Link: https://lore.kernel.org/linux-media/20230305212519.499-1-yongsuyoo0215@gmail.com Signed-off-by: YongSu Yoo Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_demux.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c index 398c86279b5b..7c4d86bfdd6c 100644 --- a/drivers/media/dvb-core/dvb_demux.c +++ b/drivers/media/dvb-core/dvb_demux.c @@ -115,12 +115,12 @@ static inline int dvb_dmx_swfilter_payload(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (!ccok) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("missed packet: %d instead of %d!\n", cc, (feed->cc + 1) & 0x0f); } + feed->cc = cc; if (buf[1] & 0x40) // PUSI ? feed->peslen = 0xfffa; @@ -300,7 +300,6 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (buf[3] & 0x20) { /* adaption field present, check for discontinuity_indicator */ @@ -336,6 +335,7 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, feed->pusi_seen = false; dvb_dmx_swfilter_section_new(feed); } + feed->cc = cc; if (buf[1] & 0x40) { /* PUSI=1 (is set), section boundary is here */ From 94d25e9128988c6a1fc9070f6e98215a95795bd8 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 1 May 2023 14:22:35 -0400 Subject: [PATCH 105/358] USB: usbtmc: Fix direction for 0-length ioctl control messages The syzbot fuzzer found a problem in the usbtmc driver: When a user submits an ioctl for a 0-length control transfer, the driver does not check that the direction is set to OUT: ------------[ cut here ]------------ usb 3-1: BOGUS control dir, pipe 80000b80 doesn't match bRequestType fd WARNING: CPU: 0 PID: 5100 at drivers/usb/core/urb.c:411 usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 Modules linked in: CPU: 0 PID: 5100 Comm: syz-executor428 Not tainted 6.3.0-syzkaller-12049-g58390c8ce1bd #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023 RIP: 0010:usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 Code: 7c 24 40 e8 1b 13 5c fb 48 8b 7c 24 40 e8 21 1d f0 fe 45 89 e8 44 89 f1 4c 89 e2 48 89 c6 48 c7 c7 e0 b5 fc 8a e8 19 c8 23 fb <0f> 0b e9 9f ee ff ff e8 ed 12 5c fb 0f b6 1d 12 8a 3c 08 31 ff 41 RSP: 0018:ffffc90003d2fb00 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff8880789e9058 RCX: 0000000000000000 RDX: ffff888029593b80 RSI: ffffffff814c1447 RDI: 0000000000000001 RBP: ffff88801ea742f8 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff88802915e528 R13: 00000000000000fd R14: 0000000080000b80 R15: ffff8880222b3100 FS: 0000555556ca63c0(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f9ef4d18150 CR3: 0000000073e5b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: usb_start_wait_urb+0x101/0x4b0 drivers/usb/core/message.c:58 usb_internal_control_msg drivers/usb/core/message.c:102 [inline] usb_control_msg+0x320/0x4a0 drivers/usb/core/message.c:153 usbtmc_ioctl_request drivers/usb/class/usbtmc.c:1954 [inline] usbtmc_ioctl+0x1b3d/0x2840 drivers/usb/class/usbtmc.c:2097 To fix this, we must override the direction in the bRequestType field of the control request structure when the length is 0. Reported-and-tested-by: syzbot+ce77725b89b7bd52425c@syzkaller.appspotmail.com Signed-off-by: Alan Stern Link: https://lore.kernel.org/linux-usb/000000000000716a3705f9adb8ee@google.com/ CC: Link: https://lore.kernel.org/r/ede1ee02-b718-49e7-a44c-51339fec706b@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/usbtmc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 4bb6d304eb4b..311007b1d904 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -1928,6 +1928,8 @@ static int usbtmc_ioctl_request(struct usbtmc_device_data *data, if (request.req.wLength > USBTMC_BUFSIZE) return -EMSGSIZE; + if (request.req.wLength == 0) /* Length-0 requests are never IN */ + request.req.bRequestType &= ~USB_DIR_IN; is_in = request.req.bRequestType & USB_DIR_IN; From c8540870af4ce6ddeb27a7bb5498b75fb29b643c Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Wed, 3 May 2023 14:00:48 +0300 Subject: [PATCH 106/358] usb: dwc3: gadget: Improve dwc3_gadget_suspend() and dwc3_gadget_resume() Prevent -ETIMEDOUT error on .suspend(). e.g. If gadget driver is loaded and we are connected to a USB host, all transfers must be stopped before stopping the controller else we will not get a clean stop i.e. dwc3_gadget_run_stop() will take several seconds to complete and will return -ETIMEDOUT. Handle error cases properly in dwc3_gadget_suspend(). Simplify dwc3_gadget_resume() by using the introduced helper function. Fixes: 9f8a67b65a49 ("usb: dwc3: gadget: fix gadget suspend/resume") Cc: stable@vger.kernel.org Suggested-by: Thinh Nguyen Signed-off-by: Roger Quadros Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230503110048.30617-1-rogerq@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 67 ++++++++++++++++++++------------------- 1 file changed, 34 insertions(+), 33 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index c0ca4d12f95d..2996bcb4d53d 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2699,6 +2699,21 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) return ret; } +static int dwc3_gadget_soft_connect(struct dwc3 *dwc) +{ + /* + * In the Synopsys DWC_usb31 1.90a programming guide section + * 4.1.9, it specifies that for a reconnect after a + * device-initiated disconnect requires a core soft reset + * (DCTL.CSftRst) before enabling the run/stop bit. + */ + dwc3_core_soft_reset(dwc); + + dwc3_event_buffers_setup(dwc); + __dwc3_gadget_start(dwc); + return dwc3_gadget_run_stop(dwc, true); +} + static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) { struct dwc3 *dwc = gadget_to_dwc(g); @@ -2737,21 +2752,10 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) synchronize_irq(dwc->irq_gadget); - if (!is_on) { + if (!is_on) ret = dwc3_gadget_soft_disconnect(dwc); - } else { - /* - * In the Synopsys DWC_usb31 1.90a programming guide section - * 4.1.9, it specifies that for a reconnect after a - * device-initiated disconnect requires a core soft reset - * (DCTL.CSftRst) before enabling the run/stop bit. - */ - dwc3_core_soft_reset(dwc); - - dwc3_event_buffers_setup(dwc); - __dwc3_gadget_start(dwc); - ret = dwc3_gadget_run_stop(dwc, true); - } + else + ret = dwc3_gadget_soft_connect(dwc); pm_runtime_put(dwc->dev); @@ -4655,42 +4659,39 @@ void dwc3_gadget_exit(struct dwc3 *dwc) int dwc3_gadget_suspend(struct dwc3 *dwc) { unsigned long flags; + int ret; if (!dwc->gadget_driver) return 0; - dwc3_gadget_run_stop(dwc, false); + ret = dwc3_gadget_soft_disconnect(dwc); + if (ret) + goto err; spin_lock_irqsave(&dwc->lock, flags); dwc3_disconnect_gadget(dwc); - __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return 0; + +err: + /* + * Attempt to reset the controller's state. Likely no + * communication can be established until the host + * performs a port reset. + */ + if (dwc->softconnect) + dwc3_gadget_soft_connect(dwc); + + return ret; } int dwc3_gadget_resume(struct dwc3 *dwc) { - int ret; - if (!dwc->gadget_driver || !dwc->softconnect) return 0; - ret = __dwc3_gadget_start(dwc); - if (ret < 0) - goto err0; - - ret = dwc3_gadget_run_stop(dwc, true); - if (ret < 0) - goto err1; - - return 0; - -err1: - __dwc3_gadget_stop(dwc); - -err0: - return ret; + return dwc3_gadget_soft_connect(dwc); } void dwc3_gadget_process_pending_events(struct dwc3 *dwc) From 4e8ef34e36f2839ef8c8da521ab7035956436818 Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Fri, 12 May 2023 08:45:24 +0800 Subject: [PATCH 107/358] usb: dwc3: fix gadget mode suspend interrupt handler issue When work in gadget mode, currently driver doesn't update software level link_state correctly as link state change event is not enabled for most devices, in function dwc3_gadget_suspend_interrupt(), it will only pass suspend event to UDC core when software level link state changes, so when interrupt generated in sequences of suspend -> reset -> conndone -> suspend, link state is not updated during reset and conndone, so second suspend interrupt event will not pass to UDC core. Remove link_state compare in dwc3_gadget_suspend_interrupt() and add a suspended flag to replace the compare function. Fixes: 799e9dc82968 ("usb: dwc3: gadget: conditionally disable Link State change events") Cc: stable Acked-by: Thinh Nguyen Signed-off-by: Linyu Yuan Link: https://lore.kernel.org/r/20230512004524.31950-1-quic_linyyuan@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.h | 2 ++ drivers/usb/dwc3/gadget.c | 12 +++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index d56457c02996..1f043c31a096 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1116,6 +1116,7 @@ struct dwc3_scratchpad_array { * @dis_metastability_quirk: set to disable metastability quirk. * @dis_split_quirk: set to disable split boundary. * @wakeup_configured: set if the device is configured for remote wakeup. + * @suspended: set to track suspend event due to U3/L2. * @imod_interval: set the interrupt moderation interval in 250ns * increments or 0 to disable. * @max_cfg_eps: current max number of IN eps used across all USB configs. @@ -1332,6 +1333,7 @@ struct dwc3 { unsigned dis_split_quirk:1; unsigned async_callbacks:1; unsigned wakeup_configured:1; + unsigned suspended:1; u16 imod_interval; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 2996bcb4d53d..d831f5acf7b5 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2440,6 +2440,7 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id) return -EINVAL; } dwc3_resume_gadget(dwc); + dwc->suspended = false; dwc->link_state = DWC3_LINK_STATE_U0; } @@ -3942,6 +3943,8 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) { int reg; + dwc->suspended = false; + dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RX_DET); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -3966,6 +3969,8 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) { u32 reg; + dwc->suspended = false; + /* * Ideally, dwc3_reset_gadget() would trigger the function * drivers to stop any active transfers through ep disable. @@ -4184,6 +4189,8 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc, unsigned int evtinfo) { + dwc->suspended = false; + /* * TODO take core out of low power mode when that's * implemented. @@ -4281,6 +4288,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, if (dwc->gadget->wakeup_armed) { dwc3_gadget_enable_linksts_evts(dwc, false); dwc3_resume_gadget(dwc); + dwc->suspended = false; } break; case DWC3_LINK_STATE_U1: @@ -4307,8 +4315,10 @@ static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc, { enum dwc3_link_state next = evtinfo & DWC3_LINK_STATE_MASK; - if (dwc->link_state != next && next == DWC3_LINK_STATE_U3) + if (!dwc->suspended && next == DWC3_LINK_STATE_U3) { + dwc->suspended = true; dwc3_suspend_gadget(dwc); + } dwc->link_state = next; } From dddb342b5b9e482bb213aecc08cbdb201ea4f8da Mon Sep 17 00:00:00 2001 From: Weitao Wang Date: Sun, 23 Apr 2023 18:59:52 +0800 Subject: [PATCH 108/358] USB: UHCI: adjust zhaoxin UHCI controllers OverCurrent bit value OverCurrent condition is not standardized in the UHCI spec. Zhaoxin UHCI controllers report OverCurrent bit active off. In order to handle OverCurrent condition correctly, the uhci-hcd driver needs to be told to expect the active-off behavior. Suggested-by: Alan Stern Cc: stable@vger.kernel.org Signed-off-by: Weitao Wang Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230423105952.4526-1-WeitaoWang-oc@zhaoxin.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/uhci-pci.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index 3592f757fe05..7bd2fddde770 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -119,11 +119,13 @@ static int uhci_pci_init(struct usb_hcd *hcd) uhci->rh_numports = uhci_count_ports(hcd); - /* Intel controllers report the OverCurrent bit active on. - * VIA controllers report it active off, so we'll adjust the - * bit value. (It's not standardized in the UHCI spec.) + /* + * Intel controllers report the OverCurrent bit active on. VIA + * and ZHAOXIN controllers report it active off, so we'll adjust + * the bit value. (It's not standardized in the UHCI spec.) */ - if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA) + if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA || + to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_ZHAOXIN) uhci->oc_low = 1; /* HP's server management chip requires a longer port reset delay. */ From 614ce6a2ea50068b45339257891e51e639ac9001 Mon Sep 17 00:00:00 2001 From: Udipto Goswami Date: Tue, 9 May 2023 20:18:36 +0530 Subject: [PATCH 109/358] usb: dwc3: debugfs: Resume dwc3 before accessing registers When the dwc3 device is runtime suspended, various required clocks are in disabled state and it is not guaranteed that access to any registers would work. Depending on the SoC glue, a register read could be as benign as returning 0 or be fatal enough to hang the system. In order to prevent such scenarios of fatal errors, make sure to resume dwc3 then allow the function to proceed. Fixes: 72246da40f37 ("usb: Introduce DesignWare USB3 DRD Driver") Cc: stable@vger.kernel.org #3.2: 30332eeefec8: debugfs: regset32: Add Runtime PM support Signed-off-by: Udipto Goswami Reviewed-by: Johan Hovold Tested-by: Johan Hovold Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230509144836.6803-1-quic_ugoswami@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/debugfs.c | 109 +++++++++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index e4a2560b9dc0..ebf03468fac4 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -332,6 +332,11 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) unsigned int current_mode; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); @@ -350,6 +355,8 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) } spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -395,6 +402,11 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GCTL); @@ -414,6 +426,8 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %08x\n", DWC3_GCTL_PRTCAP(reg)); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -463,6 +477,11 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -493,6 +512,8 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %d\n", reg); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -509,6 +530,7 @@ static ssize_t dwc3_testmode_write(struct file *file, unsigned long flags; u32 testmode = 0; char buf[32]; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -526,10 +548,16 @@ static ssize_t dwc3_testmode_write(struct file *file, else testmode = 0; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); dwc3_gadget_set_test_mode(dwc, testmode); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -548,12 +576,18 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) enum dwc3_link_state state; u32 reg; u8 speed; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { seq_puts(s, "Not available\n"); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return 0; } @@ -566,6 +600,8 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) dwc3_gadget_hs_link_string(state)); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -584,6 +620,7 @@ static ssize_t dwc3_link_state_write(struct file *file, char buf[32]; u32 reg; u8 speed; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -603,10 +640,15 @@ static ssize_t dwc3_link_state_write(struct file *file, else return -EINVAL; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } @@ -616,12 +658,15 @@ static ssize_t dwc3_link_state_write(struct file *file, if (speed < DWC3_DSTS_SUPERSPEED && state != DWC3_LINK_STATE_RECOV) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } dwc3_gadget_set_link_state(dwc, state); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -645,6 +690,11 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXFIFO); @@ -657,6 +707,8 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -667,6 +719,11 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXFIFO); @@ -679,6 +736,8 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -688,12 +747,19 @@ static int dwc3_tx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -703,12 +769,19 @@ static int dwc3_rx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -718,12 +791,19 @@ static int dwc3_rx_info_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXINFOQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -733,12 +813,19 @@ static int dwc3_descriptor_fetch_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_DESCFETCHQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -748,12 +835,19 @@ static int dwc3_event_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_EVENTQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -798,6 +892,11 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; int i; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); if (dep->number <= 1) { @@ -827,6 +926,8 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) out: spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -839,6 +940,11 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) u32 lower_32_bits; u32 upper_32_bits; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = DWC3_GDBGLSPMUX_EPSELECT(dep->number); @@ -851,6 +957,8 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) seq_printf(s, "0x%016llx\n", ep_info); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -910,6 +1018,7 @@ void dwc3_debugfs_init(struct dwc3 *dwc) dwc->regset->regs = dwc3_regs; dwc->regset->nregs = ARRAY_SIZE(dwc3_regs); dwc->regset->base = dwc->regs - DWC3_GLOBALS_REGS_START; + dwc->regset->dev = dwc->dev; root = debugfs_create_dir(dev_name(dwc->dev), usb_debug_root); dwc->debug_root = root; From 8432a15cd810c99db464b7e7858d559f3e1920e3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=B3=20=C3=81gila=20Bitsch?= Date: Sat, 22 Apr 2023 18:05:32 +0200 Subject: [PATCH 110/358] usb: gadget: drop superfluous ':' in doc string MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There was one superfluous ':' that kernel-doc complained about. Reported-by: Randy Dunlap Closes: https://lore.kernel.org/all/c718a490-028d-2682-9ad7-8256d16504bf@infradead.org/ Fixes: fb6211f1584a ("usb: gadget: add doc to struct usb_composite_dev") Signed-off-by: Jó Ágila Bitsch Reviewed-by: Randy Dunlap Link: https://lore.kernel.org/r/ZEQFzMntIrwvZl4+@jo-einhundert Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a2448e98854f..07531c4f4350 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -443,7 +443,7 @@ static inline struct usb_composite_driver *to_cdriver( * @bcd_webusb_version: 0x0100 by default, WebUSB specification version * @b_webusb_vendor_code: 0x0 by default, vendor code for WebUSB * @landing_page: empty by default, landing page to announce in WebUSB - * @use_webusb:: false by default, interested gadgets set it + * @use_webusb: false by default, interested gadgets set it * @os_desc_config: the configuration to be used with OS descriptors * @setup_pending: true when setup request is queued but not completed * @os_desc_pending: true when os_desc request is queued but not completed From 5e1617210aede9f1b91bb9819c93097b6da481f9 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Fri, 12 May 2023 15:14:34 +0200 Subject: [PATCH 111/358] Revert "usb: gadget: udc: core: Prevent redundant calls to pullup" This reverts commit a3afbf5cc887fc3401f012fe629810998ed61859. This depends on commit 0db213ea8eed ("usb: gadget: udc: core: Invoke usb_gadget_connect only when started") that introduces a regression, revert it till the issue is fixed. Cc: stable@vger.kernel.org Reported-by: Stephan Gerhold Reported-by: Francesco Dolcini Link: https://lore.kernel.org/all/ZF4BvgsOyoKxdPFF@francesco-nb.int.toradex.com/ Signed-off-by: Francesco Dolcini Link: https://lore.kernel.org/r/20230512131435.205464-2-francesco@dolcini.it Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/core.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 4641153e9706..583c339876ab 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -703,9 +703,6 @@ static int usb_gadget_connect_locked(struct usb_gadget *gadget) goto out; } - if (gadget->connected) - goto out; - if (gadget->deactivated || !gadget->udc->started) { /* * If gadget is deactivated we only save new state. From f22e9b67f19ccc73de1ae04375d4b30684e261f8 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Fri, 12 May 2023 15:14:35 +0200 Subject: [PATCH 112/358] Revert "usb: gadget: udc: core: Invoke usb_gadget_connect only when started" This reverts commit 0db213ea8eed5534a5169e807f28103cbc9d23df. It introduces an issues with configuring the USB gadget hangs forever on multiple Qualcomm and NXP i.MX SoC at least. Cc: stable@vger.kernel.org Fixes: 0db213ea8eed ("usb: gadget: udc: core: Invoke usb_gadget_connect only when started") Reported-by: Stephan Gerhold Reported-by: Francesco Dolcini Link: https://lore.kernel.org/all/ZF4BvgsOyoKxdPFF@francesco-nb.int.toradex.com/ Signed-off-by: Francesco Dolcini Link: https://lore.kernel.org/r/20230512131435.205464-3-francesco@dolcini.it Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/core.c | 184 ++++++++++++---------------------- 1 file changed, 62 insertions(+), 122 deletions(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 583c339876ab..52e6d2e84e35 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -37,10 +37,6 @@ static const struct bus_type gadget_bus_type; * @vbus: for udcs who care about vbus status, this value is real vbus status; * for udcs who do not care about vbus status, this value is always true * @started: the UDC's started state. True if the UDC had started. - * @connect_lock: protects udc->vbus, udc->started, gadget->connect, gadget->deactivate related - * functions. usb_gadget_connect_locked, usb_gadget_disconnect_locked, - * usb_udc_connect_control_locked, usb_gadget_udc_start_locked, usb_gadget_udc_stop_locked are - * called with this lock held. * * This represents the internal data structure which is used by the UDC-class * to hold information about udc driver and gadget together. @@ -52,7 +48,6 @@ struct usb_udc { struct list_head list; bool vbus; bool started; - struct mutex connect_lock; }; static struct class *udc_class; @@ -692,9 +687,17 @@ out: } EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); -/* Internal version of usb_gadget_connect needs to be called with connect_lock held. */ -static int usb_gadget_connect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) +/** + * usb_gadget_connect - software-controlled connect to USB host + * @gadget:the peripheral being connected + * + * Enables the D+ (or potentially D-) pullup. The host will start + * enumerating this gadget when the pullup is active and a VBUS session + * is active (the link is powered). + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_connect(struct usb_gadget *gadget) { int ret = 0; @@ -703,12 +706,10 @@ static int usb_gadget_connect_locked(struct usb_gadget *gadget) goto out; } - if (gadget->deactivated || !gadget->udc->started) { + if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will be connected automatically after activation. - * - * udc first needs to be started before gadget can be pulled up. */ gadget->connected = true; goto out; @@ -723,69 +724,8 @@ out: return ret; } - -/** - * usb_gadget_connect - software-controlled connect to USB host - * @gadget:the peripheral being connected - * - * Enables the D+ (or potentially D-) pullup. The host will start - * enumerating this gadget when the pullup is active and a VBUS session - * is active (the link is powered). - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_connect(struct usb_gadget *gadget) -{ - int ret; - - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); - - return ret; -} EXPORT_SYMBOL_GPL(usb_gadget_connect); -/* Internal version of usb_gadget_disconnect needs to be called with connect_lock held. */ -static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) -{ - int ret = 0; - - if (!gadget->ops->pullup) { - ret = -EOPNOTSUPP; - goto out; - } - - if (!gadget->connected) - goto out; - - if (gadget->deactivated || !gadget->udc->started) { - /* - * If gadget is deactivated we only save new state. - * Gadget will stay disconnected after activation. - * - * udc should have been started before gadget being pulled down. - */ - gadget->connected = false; - goto out; - } - - ret = gadget->ops->pullup(gadget, 0); - if (!ret) - gadget->connected = 0; - - mutex_lock(&udc_lock); - if (gadget->udc->driver) - gadget->udc->driver->disconnect(gadget); - mutex_unlock(&udc_lock); - -out: - trace_usb_gadget_disconnect(gadget, ret); - - return ret; -} - /** * usb_gadget_disconnect - software-controlled disconnect from USB host * @gadget:the peripheral being disconnected @@ -801,11 +741,36 @@ out: */ int usb_gadget_disconnect(struct usb_gadget *gadget) { - int ret; + int ret = 0; - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_disconnect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); + if (!gadget->ops->pullup) { + ret = -EOPNOTSUPP; + goto out; + } + + if (!gadget->connected) + goto out; + + if (gadget->deactivated) { + /* + * If gadget is deactivated we only save new state. + * Gadget will stay disconnected after activation. + */ + gadget->connected = false; + goto out; + } + + ret = gadget->ops->pullup(gadget, 0); + if (!ret) + gadget->connected = 0; + + mutex_lock(&udc_lock); + if (gadget->udc->driver) + gadget->udc->driver->disconnect(gadget); + mutex_unlock(&udc_lock); + +out: + trace_usb_gadget_disconnect(gadget, ret); return ret; } @@ -829,11 +794,10 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) if (gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); if (gadget->connected) { - ret = usb_gadget_disconnect_locked(gadget); + ret = usb_gadget_disconnect(gadget); if (ret) - goto unlock; + goto out; /* * If gadget was being connected before deactivation, we want @@ -843,8 +807,6 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) } gadget->deactivated = true; -unlock: - mutex_unlock(&gadget->udc->connect_lock); out: trace_usb_gadget_deactivate(gadget, ret); @@ -868,7 +830,6 @@ int usb_gadget_activate(struct usb_gadget *gadget) if (!gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); gadget->deactivated = false; /* @@ -876,8 +837,7 @@ int usb_gadget_activate(struct usb_gadget *gadget) * while it was being deactivated, we call usb_gadget_connect(). */ if (gadget->connected) - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); + ret = usb_gadget_connect(gadget); out: trace_usb_gadget_activate(gadget, ret); @@ -1118,13 +1078,12 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ -/* Acquire connect_lock before calling this function. */ -static void usb_udc_connect_control_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) +static void usb_udc_connect_control(struct usb_udc *udc) { - if (udc->vbus && udc->started) - usb_gadget_connect_locked(udc->gadget); + if (udc->vbus) + usb_gadget_connect(udc->gadget); else - usb_gadget_disconnect_locked(udc->gadget); + usb_gadget_disconnect(udc->gadget); } /** @@ -1140,12 +1099,10 @@ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) { struct usb_udc *udc = gadget->udc; - mutex_lock(&udc->connect_lock); if (udc) { udc->vbus = status; - usb_udc_connect_control_locked(udc); + usb_udc_connect_control(udc); } - mutex_unlock(&udc->connect_lock); } EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); @@ -1167,7 +1124,7 @@ void usb_gadget_udc_reset(struct usb_gadget *gadget, EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); /** - * usb_gadget_udc_start_locked - tells usb device controller to start up + * usb_gadget_udc_start - tells usb device controller to start up * @udc: The UDC to be started * * This call is issued by the UDC Class driver when it's about @@ -1178,11 +1135,8 @@ EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); * necessary to have it powered on. * * Returns zero on success, else negative errno. - * - * Caller should acquire connect_lock before invoking this function. */ -static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline int usb_gadget_udc_start(struct usb_udc *udc) { int ret; @@ -1199,7 +1153,7 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) } /** - * usb_gadget_udc_stop_locked - tells usb device controller we don't need it anymore + * usb_gadget_udc_stop - tells usb device controller we don't need it anymore * @udc: The UDC to be stopped * * This call is issued by the UDC Class driver after calling @@ -1208,11 +1162,8 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) * The details are implementation specific, but it can go as * far as powering off UDC completely and disable its data * line pullups. - * - * Caller should acquire connect lock before invoking this function. */ -static inline void usb_gadget_udc_stop_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline void usb_gadget_udc_stop(struct usb_udc *udc) { if (!udc->started) { dev_err(&udc->dev, "UDC had already stopped\n"); @@ -1371,7 +1322,6 @@ int usb_add_gadget(struct usb_gadget *gadget) udc->gadget = gadget; gadget->udc = udc; - mutex_init(&udc->connect_lock); udc->started = false; @@ -1573,15 +1523,11 @@ static int gadget_bind_driver(struct device *dev) if (ret) goto err_bind; - mutex_lock(&udc->connect_lock); - ret = usb_gadget_udc_start_locked(udc); - if (ret) { - mutex_unlock(&udc->connect_lock); + ret = usb_gadget_udc_start(udc); + if (ret) goto err_start; - } usb_gadget_enable_async_callbacks(udc); - usb_udc_connect_control_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_udc_connect_control(udc); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; @@ -1612,14 +1558,12 @@ static void gadget_unbind_driver(struct device *dev) kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(gadget); + usb_gadget_disconnect(gadget); usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); udc->driver->unbind(gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_stop(udc); mutex_lock(&udc_lock); driver->is_bound = false; @@ -1705,15 +1649,11 @@ static ssize_t soft_connect_store(struct device *dev, } if (sysfs_streq(buf, "connect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_udc_start_locked(udc); - usb_gadget_connect_locked(udc->gadget); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_start(udc); + usb_gadget_connect(udc->gadget); } else if (sysfs_streq(buf, "disconnect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(udc->gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_disconnect(udc->gadget); + usb_gadget_udc_stop(udc); } else { dev_err(dev, "unsupported command '%s'\n", buf); ret = -EINVAL; From d8f28269dd4bf9b55c3fb376ae31512730a96fce Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Mon, 8 May 2023 21:44:43 +0000 Subject: [PATCH 113/358] usb: typec: altmodes/displayport: fix pin_assignment_show This patch fixes negative indexing of buf array in pin_assignment_show when get_current_pin_assignments returns 0 i.e. no compatible pin assignments are found. BUG: KASAN: use-after-free in pin_assignment_show+0x26c/0x33c ... Call trace: dump_backtrace+0x110/0x204 dump_stack_lvl+0x84/0xbc print_report+0x358/0x974 kasan_report+0x9c/0xfc __do_kernel_fault+0xd4/0x2d4 do_bad_area+0x48/0x168 do_tag_check_fault+0x24/0x38 do_mem_abort+0x6c/0x14c el1_abort+0x44/0x68 el1h_64_sync_handler+0x64/0xa4 el1h_64_sync+0x78/0x7c pin_assignment_show+0x26c/0x33c dev_attr_show+0x50/0xc0 Fixes: 0e3bb7d6894d ("usb: typec: Add driver for DisplayPort alternate mode") Cc: stable@vger.kernel.org Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230508214443.893436-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 8f3e884222ad..66de880b28d0 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -516,6 +516,10 @@ static ssize_t pin_assignment_show(struct device *dev, mutex_unlock(&dp->lock); + /* get_current_pin_assignments can return 0 when no matching pin assignments are found */ + if (len == 0) + len++; + buf[len - 1] = '\n'; return len; } From 3c0f4f09c063e143822393d99cb2b19a85451c07 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Konrad=20Gr=C3=A4fe?= Date: Fri, 5 May 2023 16:36:40 +0200 Subject: [PATCH 114/358] usb: gadget: u_ether: Fix host MAC address case MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CDC-ECM specification [1] requires to send the host MAC address as an uppercase hexadecimal string in chapter "5.4 Ethernet Networking Functional Descriptor": The Unicode character is chosen from the set of values 30h through 39h and 41h through 46h (0-9 and A-F). However, snprintf(.., "%pm", ..) generates a lowercase MAC address string. While most host drivers are tolerant to this, UsbNcm.sys on Windows 10 is not. Instead it uses a different MAC address with all bytes set to zero including and after the first byte containing a lowercase letter. On Windows 11 Microsoft fixed it, but apparently they did not backport the fix. This change fixes the issue by upper-casing the MAC to comply with the specification. [1]: https://www.usb.org/document-library/class-definitions-communication-devices-12, file ECM120.pdf Fixes: bcd4a1c40bee ("usb: gadget: u_ether: construct with default values and add setters/getters") Cc: stable@vger.kernel.org Signed-off-by: Konrad Gräfe Link: https://lore.kernel.org/r/20230505143640.443014-1-k.graefe@gateware.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_ether.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 6956ad8ba8dd..a366abb45623 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include "u_ether.h" @@ -965,6 +966,8 @@ int gether_get_host_addr_cdc(struct net_device *net, char *host_addr, int len) dev = netdev_priv(net); snprintf(host_addr, len, "%pm", dev->host_mac); + string_upper(host_addr, host_addr); + return strlen(host_addr); } EXPORT_SYMBOL_GPL(gether_get_host_addr_cdc); From 94ea04ec790887b5b0e43429a92c18a1e692ec08 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 21 Apr 2023 13:17:20 +0300 Subject: [PATCH 115/358] usb: typec: tps6598x: Fix fault at module removal We need to cancel the delayed workqueue if it is being used else it will cause paging request fault during module removal. Fixes: 0d6a119cecd7 ("usb: typec: tps6598x: Add support for polling interrupts status") Signed-off-by: Roger Quadros Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230421101720.34318-1-rogerq@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tipd/core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 8b075ca82ef6..438cc40660a1 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -886,6 +886,9 @@ static void tps6598x_remove(struct i2c_client *client) { struct tps6598x *tps = i2c_get_clientdata(client); + if (!client->irq) + cancel_delayed_work_sync(&tps->wq_poll); + tps6598x_disconnect(tps, 0); typec_unregister_port(tps->port); usb_role_switch_put(tps->role_sw); From 8018018d9c56473067e5358986ce0ee9ce56949f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 4 May 2023 17:59:24 +0300 Subject: [PATCH 116/358] usb: dwc3: fix a test for error in dwc3_core_init() This was refactored recently and the "ret = " was accidentally deleted so the errors aren't checked. Fixes: 1d72fab47656 ("USB: dwc3: refactor phy handling") Signed-off-by: Dan Carpenter Reviewed-by: Johan Hovold Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/d0c5a04f-deee-4ebe-9b0b-dc5492564519@kili.mountain Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 0beaab932e7d..7b2ce013cc5b 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1137,7 +1137,7 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_set_incr_burst_type(dwc); - dwc3_phy_power_on(dwc); + ret = dwc3_phy_power_on(dwc); if (ret) goto err_exit_phy; From a398d5eac6984316e71474e25b975688f282379b Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Fri, 5 May 2023 13:47:59 +0200 Subject: [PATCH 117/358] usb-storage: fix deadlock when a scsi command timeouts more than once With faulty usb-storage devices, read/write can timeout, in that case the SCSI layer will abort and re-issue the command. USB storage has no internal timeout, it relies on SCSI layer aborting commands via .eh_abort_handler() for non those responsive devices. After two consecutive timeouts of the same command, SCSI layer calls .eh_device_reset_handler(), without calling .eh_abort_handler() first. With usb-storage, this causes a deadlock: -> .eh_device_reset_handler -> device_reset -> mutex_lock(&(us->dev_mutex)); mutex already by usb_stor_control_thread(), which is waiting for command completion: -> usb_stor_control_thread (mutex taken here) -> usb_stor_invoke_transport -> usb_stor_Bulk_transport -> usb_stor_bulk_srb -> usb_stor_bulk_transfer_sglist -> usb_sg_wait Make sure we cancel any pending command in .eh_device_reset_handler() to avoid this. Signed-off-by: Maxime Bizon Cc: linux-usb@vger.kernel.org Cc: stable Link: https://lore.kernel.org/all/ZEllnjMKT8ulZbJh@sakura/ Reviewed-by: Alan Stern Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230505114759.1189741-1-mbizon@freebox.fr Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/scsiglue.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 8931df5a85fd..c54e9805da53 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -406,22 +406,25 @@ static DEF_SCSI_QCMD(queuecommand) ***********************************************************************/ /* Command timeout and abort */ -static int command_abort(struct scsi_cmnd *srb) +static int command_abort_matching(struct us_data *us, struct scsi_cmnd *srb_match) { - struct us_data *us = host_to_us(srb->device->host); - - usb_stor_dbg(us, "%s called\n", __func__); - /* * us->srb together with the TIMED_OUT, RESETTING, and ABORTING * bits are protected by the host lock. */ scsi_lock(us_to_host(us)); - /* Is this command still active? */ - if (us->srb != srb) { + /* is there any active pending command to abort ? */ + if (!us->srb) { scsi_unlock(us_to_host(us)); usb_stor_dbg(us, "-- nothing to abort\n"); + return SUCCESS; + } + + /* Does the command match the passed srb if any ? */ + if (srb_match && us->srb != srb_match) { + scsi_unlock(us_to_host(us)); + usb_stor_dbg(us, "-- pending command mismatch\n"); return FAILED; } @@ -444,6 +447,14 @@ static int command_abort(struct scsi_cmnd *srb) return SUCCESS; } +static int command_abort(struct scsi_cmnd *srb) +{ + struct us_data *us = host_to_us(srb->device->host); + + usb_stor_dbg(us, "%s called\n", __func__); + return command_abort_matching(us, srb); +} + /* * This invokes the transport reset mechanism to reset the state of the * device @@ -455,6 +466,9 @@ static int device_reset(struct scsi_cmnd *srb) usb_stor_dbg(us, "%s called\n", __func__); + /* abort any pending command before reset */ + command_abort_matching(us, NULL); + /* lock the device pointers and do the reset */ mutex_lock(&(us->dev_mutex)); result = us->transport_reset(us); From 95d698869b404772cc8b72560df71548491c10bc Mon Sep 17 00:00:00 2001 From: Andrew Davis Date: Thu, 20 Apr 2023 11:02:09 -0500 Subject: [PATCH 118/358] serial: 8250_exar: Add support for USR298x PCI Modems Possibly the last PCI controller-based (i.e. not a soft/winmodem) dial-up modem one can still buy. Looks to have a stock XR17C154 PCI UART chip for communication, but for some reason when provisioning the PCI IDs they swapped the vendor and subvendor IDs. Otherwise this card would have worked out of the box. Searching online, some folks seem to not have this issue and others do, so it is possible only some batches of cards have this error. Create a new macro to handle the switched IDs and add support here. Signed-off-by: Andrew Davis Cc: stable Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230420160209.28221-1-afd@ti.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_exar.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 64770c62bbec..b406cba10b0e 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -40,9 +40,13 @@ #define PCI_DEVICE_ID_COMMTECH_4224PCIE 0x0020 #define PCI_DEVICE_ID_COMMTECH_4228PCIE 0x0021 #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 + #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 +#define PCI_SUBDEVICE_ID_USR_2980 0x0128 +#define PCI_SUBDEVICE_ID_USR_2981 0x0129 + #define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001 #define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002 #define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004 @@ -829,6 +833,15 @@ static const struct exar8250_board pbn_exar_XR17V8358 = { (kernel_ulong_t)&bd \ } +#define USR_DEVICE(devid, sdevid, bd) { \ + PCI_DEVICE_SUB( \ + PCI_VENDOR_ID_USR, \ + PCI_DEVICE_ID_EXAR_##devid, \ + PCI_VENDOR_ID_EXAR, \ + PCI_SUBDEVICE_ID_USR_##sdevid), 0, 0, \ + (kernel_ulong_t)&bd \ + } + static const struct pci_device_id exar_pci_tbl[] = { EXAR_DEVICE(ACCESSIO, COM_2S, pbn_exar_XR17C15x), EXAR_DEVICE(ACCESSIO, COM_4S, pbn_exar_XR17C15x), @@ -853,6 +866,10 @@ static const struct pci_device_id exar_pci_tbl[] = { IBM_DEVICE(XR17C152, SATURN_SERIAL_ONE_PORT, pbn_exar_ibm_saturn), + /* USRobotics USR298x-OEM PCI Modems */ + USR_DEVICE(XR17C152, 2980, pbn_exar_XR17C15x), + USR_DEVICE(XR17C152, 2981, pbn_exar_XR17C15x), + /* Exar Corp. XR17C15[248] Dual/Quad/Octal UART */ EXAR_DEVICE(EXAR, XR17C152, pbn_exar_XR17C15x), EXAR_DEVICE(EXAR, XR17C154, pbn_exar_XR17C15x), From d2b00516de0e1d696724247098f6733a6ea53908 Mon Sep 17 00:00:00 2001 From: Vitaliy Tomin Date: Sun, 23 Apr 2023 11:45:12 +0800 Subject: [PATCH 119/358] serial: Add support for Advantech PCI-1611U card Add support for Advantech PCI-1611U card Advantech provides opensource drivers for this and many others card based on legacy copy of 8250_pci driver called adv950 https://www.advantech.com/emt/support/details/driver?id=1-TDOIMJ It is hard to maintain to run as out of tree module on newer kernels. Just adding PCI ID to kernel 8250_pci works perfect. Signed-off-by: Vitaliy Tomin Cc: stable Link: https://lore.kernel.org/r/20230423034512.2671157-1-tomin@iszf.irk.ru Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index c55be6fda0ca..e80c4f6551a1 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1920,6 +1920,8 @@ pci_moxa_setup(struct serial_private *priv, #define PCI_SUBDEVICE_ID_SIIG_DUAL_30 0x2530 #define PCI_VENDOR_ID_ADVANTECH 0x13fe #define PCI_DEVICE_ID_INTEL_CE4100_UART 0x2e66 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600 0x1600 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600_1611 0x1611 #define PCI_DEVICE_ID_ADVANTECH_PCI3620 0x3620 #define PCI_DEVICE_ID_ADVANTECH_PCI3618 0x3618 #define PCI_DEVICE_ID_ADVANTECH_PCIf618 0xf618 @@ -4085,6 +4087,9 @@ static SIMPLE_DEV_PM_OPS(pciserial_pm_ops, pciserial_suspend_one, pciserial_resume_one); static const struct pci_device_id serial_pci_tbl[] = { + { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI1600, + PCI_DEVICE_ID_ADVANTECH_PCI1600_1611, PCI_ANY_ID, 0, 0, + pbn_b0_4_921600 }, /* Advantech use PCI_DEVICE_ID_ADVANTECH_PCI3620 (0x3620) as 'PCI_SUBVENDOR_ID' */ { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI3620, PCI_DEVICE_ID_ADVANTECH_PCI3620, 0x0001, 0, 0, From f16182ed9d8430adfab77f5929c23756c94b0230 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 21 Apr 2023 11:58:06 +0200 Subject: [PATCH 120/358] serial: 8250: Document termios parameter of serial8250_em485_config() With W=1: drivers/tty/serial/8250/8250_port.c:679: warning: Function parameter or member 'termios' not described in 'serial8250_em485_config' Fix this by documenting the parameter. Fixes: ae50bb2752836277 ("serial: take termios_rwsem for ->rs485_config() & pass termios as param") Signed-off-by: Geert Uytterhoeven Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/2bd1e62be1d5d33333002910372feecc6d52e78f.1682071013.git.geert+renesas@glider.be Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fe8d79c4ae95..c153ba3a018a 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -669,6 +669,7 @@ EXPORT_SYMBOL_GPL(serial8250_em485_supported); /** * serial8250_em485_config() - generic ->rs485_config() callback * @port: uart port + * @termios: termios structure * @rs485: rs485 settings * * Generic callback usable by 8250 uart drivers to activate rs485 settings From 8ab5fc55d7f65d58a3c3aeadf11bdf60267cd2bd Mon Sep 17 00:00:00 2001 From: Ke Zhang Date: Fri, 28 Apr 2023 11:16:36 +0800 Subject: [PATCH 121/358] serial: arc_uart: fix of_iomap leak in `arc_serial_probe` Smatch reports: drivers/tty/serial/arc_uart.c:631 arc_serial_probe() warn: 'port->membase' from of_iomap() not released on lines: 631. In arc_serial_probe(), if uart_add_one_port() fails, port->membase is not released, which would cause a resource leak. To fix this, I replace of_iomap with devm_platform_ioremap_resource. Fixes: 8dbe1d5e09a7 ("serial/arc: inline the probe helper") Signed-off-by: Ke Zhang Reviewed-by: Dongliang Mu Link: https://lore.kernel.org/r/20230428031636.44642-1-m202171830@hust.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/arc_uart.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/arc_uart.c b/drivers/tty/serial/arc_uart.c index 59e25f2b6632..4b2512eef577 100644 --- a/drivers/tty/serial/arc_uart.c +++ b/drivers/tty/serial/arc_uart.c @@ -606,10 +606,11 @@ static int arc_serial_probe(struct platform_device *pdev) } uart->baud = val; - port->membase = of_iomap(np, 0); - if (!port->membase) + port->membase = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(port->membase)) { /* No point of dev_err since UART itself is hosed here */ - return -ENXIO; + return PTR_ERR(port->membase); + } port->irq = irq_of_parse_and_map(np, 0); From 8a3b5477256a54ae4a470dcebbcf8cdc18e4696d Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Thu, 27 Apr 2023 11:19:15 -0700 Subject: [PATCH 122/358] serial: 8250_bcm7271: balance clk_enable calls The sw_baud clock must be disabled when the device driver is not connected to the device. This now occurs when probe fails and upon remove. Fixes: 41a469482de2 ("serial: 8250: Add new 8250-core based Broadcom STB driver") Reported-by: XuDong Liu Link: https://lore.kernel.org/lkml/20230424125100.4783-1-m202071377@hust.edu.cn/ Signed-off-by: Doug Berger Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20230427181916.2983697-2-opendmb@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_bcm7271.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index f801b1f5b46c..90ee7bc12f77 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -1032,7 +1032,7 @@ static int brcmuart_probe(struct platform_device *pdev) if (clk_rate == 0) { dev_err(dev, "clock-frequency or clk not defined\n"); ret = -EINVAL; - goto release_dma; + goto err_clk_disable; } dev_dbg(dev, "DMA is %senabled\n", priv->dma_enabled ? "" : "not "); @@ -1119,6 +1119,8 @@ err1: serial8250_unregister_port(priv->line); err: brcmuart_free_bufs(dev, priv); +err_clk_disable: + clk_disable_unprepare(baud_mux_clk); release_dma: if (priv->dma_enabled) brcmuart_arbitration(priv, 0); @@ -1133,6 +1135,7 @@ static int brcmuart_remove(struct platform_device *pdev) hrtimer_cancel(&priv->hrt); serial8250_unregister_port(priv->line); brcmuart_free_bufs(&pdev->dev, priv); + clk_disable_unprepare(priv->baud_mux_clk); if (priv->dma_enabled) brcmuart_arbitration(priv, 0); return 0; From f264f2f6f4788dc031cef60a0cf2881902736709 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Thu, 27 Apr 2023 11:19:16 -0700 Subject: [PATCH 123/358] serial: 8250_bcm7271: fix leak in `brcmuart_probe` Smatch reports: drivers/tty/serial/8250/8250_bcm7271.c:1120 brcmuart_probe() warn: 'baud_mux_clk' from clk_prepare_enable() not released on lines: 1032. The issue is fixed by using a managed clock. Fixes: 41a469482de2 ("serial: 8250: Add new 8250-core based Broadcom STB driver") Reported-by: XuDong Liu Link: https://lore.kernel.org/lkml/20230424125100.4783-1-m202071377@hust.edu.cn/ Signed-off-by: Doug Berger Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20230427181916.2983697-3-opendmb@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_bcm7271.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index 90ee7bc12f77..af0e1c070187 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -1012,7 +1012,7 @@ static int brcmuart_probe(struct platform_device *pdev) of_property_read_u32(np, "clock-frequency", &clk_rate); /* See if a Baud clock has been specified */ - baud_mux_clk = of_clk_get_by_name(np, "sw_baud"); + baud_mux_clk = devm_clk_get(dev, "sw_baud"); if (IS_ERR(baud_mux_clk)) { if (PTR_ERR(baud_mux_clk) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; From 5f949f140f73696f64acb89a1f16ff9153d017e0 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 5 May 2023 17:23:01 +0200 Subject: [PATCH 124/358] serial: qcom-geni: fix enabling deactivated interrupt The driver have a race, experienced only with PREEMPT_RT patchset: CPU0 | CPU1 ================================================================== qcom_geni_serial_probe | uart_add_one_port | | serdev_drv_probe | qca_serdev_probe | serdev_device_open | uart_open | uart_startup | qcom_geni_serial_startup | enable_irq | __irq_startup | WARN_ON() | IRQ not activated request_threaded_irq | irq_domain_activate_irq | The warning: 894000.serial: ttyHS1 at MMIO 0x894000 (irq = 144, base_baud = 0) is a MSM serial serial0: tty port ttyHS1 registered WARNING: CPU: 7 PID: 107 at kernel/irq/chip.c:241 __irq_startup+0x78/0xd8 ... qcom_geni_serial 894000.serial: serial engine reports 0 RX bytes in! Adding UART port triggers probe of child serial devices - serdev and eventually Qualcomm Bluetooth hci_qca driver. This opens UART port which enables the interrupt before it got activated in request_threaded_irq(). The issue originates in commit f3974413cf02 ("tty: serial: qcom_geni_serial: Wakeup IRQ cleanup") and discussion on mailing list [1]. However the above commit does not explain why the uart_add_one_port() is moved above requesting interrupt. [1] https://lore.kernel.org/all/5d9f3dfa.1c69fb81.84c4b.30bf@mx.google.com/ Fixes: f3974413cf02 ("tty: serial: qcom_geni_serial: Wakeup IRQ cleanup") Cc: Cc: Stephen Boyd Signed-off-by: Krzysztof Kozlowski Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/20230505152301.2181270-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/qcom_geni_serial.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 08dc3e2a729c..8582479f0211 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1664,19 +1664,18 @@ static int qcom_geni_serial_probe(struct platform_device *pdev) uport->private_data = &port->private_data; platform_set_drvdata(pdev, port); - ret = uart_add_one_port(drv, uport); - if (ret) - return ret; - irq_set_status_flags(uport->irq, IRQ_NOAUTOEN); ret = devm_request_irq(uport->dev, uport->irq, qcom_geni_serial_isr, IRQF_TRIGGER_HIGH, port->name, uport); if (ret) { dev_err(uport->dev, "Failed to get IRQ ret %d\n", ret); - uart_remove_one_port(drv, uport); return ret; } + ret = uart_add_one_port(drv, uport); + if (ret) + return ret; + /* * Set pm_runtime status as ACTIVE so that wakeup_irq gets * enabled/disabled from dev_pm_arm_wake_irq during system From 8fb9ea65c9d1338b0d2bb0a9122dc942cdd32357 Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Fri, 12 May 2023 06:08:48 -0500 Subject: [PATCH 125/358] vc_screen: reload load of struct vc_data pointer in vcs_write() to avoid UAF MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After a call to console_unlock() in vcs_write() the vc_data struct can be freed by vc_port_destruct(). Because of that, the struct vc_data pointer must be reloaded in the while loop in vcs_write() after console_lock() to avoid a UAF when vcs_size() is called. Syzkaller reported a UAF in vcs_size(). BUG: KASAN: slab-use-after-free in vcs_size (drivers/tty/vt/vc_screen.c:215) Read of size 4 at addr ffff8880beab89a8 by task repro_vcs_size/4119 Call Trace: __asan_report_load4_noabort (mm/kasan/report_generic.c:380) vcs_size (drivers/tty/vt/vc_screen.c:215) vcs_write (drivers/tty/vt/vc_screen.c:664) vfs_write (fs/read_write.c:582 fs/read_write.c:564) ... Allocated by task 1213: kmalloc_trace (mm/slab_common.c:1064) vc_allocate (./include/linux/slab.h:559 ./include/linux/slab.h:680 drivers/tty/vt/vt.c:1078 drivers/tty/vt/vt.c:1058) con_install (drivers/tty/vt/vt.c:3334) tty_init_dev (drivers/tty/tty_io.c:1303 drivers/tty/tty_io.c:1415 drivers/tty/tty_io.c:1392) tty_open (drivers/tty/tty_io.c:2082 drivers/tty/tty_io.c:2128) chrdev_open (fs/char_dev.c:415) do_dentry_open (fs/open.c:921) vfs_open (fs/open.c:1052) ... Freed by task 4116: kfree (mm/slab_common.c:1016) vc_port_destruct (drivers/tty/vt/vt.c:1044) tty_port_destructor (drivers/tty/tty_port.c:296) tty_port_put (drivers/tty/tty_port.c:312) vt_disallocate_all (drivers/tty/vt/vt_ioctl.c:662 (discriminator 2)) vt_ioctl (drivers/tty/vt/vt_ioctl.c:903) tty_ioctl (drivers/tty/tty_io.c:2778) ... The buggy address belongs to the object at ffff8880beab8800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 424 bytes inside of freed 1024-byte region [ffff8880beab8800, ffff8880beab8c00) The buggy address belongs to the physical page: page:00000000afc77580 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xbeab8 head:00000000afc77580 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) page_type: 0xffffffff() raw: 000fffffc0010200 ffff888100042dc0 ffffea000426de00 dead000000000002 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880beab8880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880beab8900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880beab8980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880beab8a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880beab8a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Disabling lock debugging due to kernel taint Fixes: ac751efa6a0d ("console: rename acquire/release_console_sem() to console_lock/unlock()") Cc: stable Reported-by: syzkaller Signed-off-by: George Kennedy Reviewed-by: Thomas Weißschuh Link: https://lore.kernel.org/r/1683889728-10411-1-git-send-email-george.kennedy@oracle.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vc_screen.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 498ba9c0ee93..829c4be66f3b 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -656,10 +656,17 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) } } - /* The vcs_size might have changed while we slept to grab - * the user buffer, so recheck. + /* The vc might have been freed or vcs_size might have changed + * while we slept to grab the user buffer, so recheck. * Return data written up to now on failure. */ + vc = vcs_vc(inode, &viewed); + if (!vc) { + if (written) + break; + ret = -ENXIO; + goto unlock_out; + } size = vcs_size(vc, attr, false); if (size < 0) { if (written) From d80fc101d2eb9b3188c228d61223890aeea480a4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 11 May 2023 19:22:11 -0400 Subject: [PATCH 126/358] erspan: get the proto with the md version for collect_md In commit 20704bd1633d ("erspan: build the header with the right proto according to erspan_ver"), it gets the proto with t->parms.erspan_ver, but t->parms.erspan_ver is not used by collect_md branch, and instead it should get the proto with md->version for collect_md. Thanks to Kevin for pointing this out. Fixes: 20704bd1633d ("erspan: build the header with the right proto according to erspan_ver") Fixes: 94d7d8f29287 ("ip6_gre: add erspan v2 support") Reported-by: Kevin Traynor Signed-off-by: Xin Long Reviewed-by: Simon Horman Reviewed-by: William Tu Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a4ecfc9d2593..da80974ad23a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1015,12 +1015,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, ntohl(tun_id), ntohl(md->u.index), truncate, false); + proto = htons(ETH_P_ERSPAN); } else if (md->version == 2) { erspan_build_header_v2(skb, ntohl(tun_id), md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + proto = htons(ETH_P_ERSPAN2); } else { goto tx_err; } @@ -1043,24 +1045,25 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, break; } - if (t->parms.erspan_ver == 1) + if (t->parms.erspan_ver == 1) { erspan_build_header(skb, ntohl(t->parms.o_key), t->parms.index, truncate, false); - else if (t->parms.erspan_ver == 2) + proto = htons(ETH_P_ERSPAN); + } else if (t->parms.erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(t->parms.o_key), t->parms.dir, t->parms.hwid, truncate, false); - else + proto = htons(ETH_P_ERSPAN2); + } else { goto tx_err; + } fl6.daddr = t->parms.raddr; } /* Push GRE header. */ - proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) - : htons(ETH_P_ERSPAN2); gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ From 9e4b45f20c5aac786c728619e5ee746bffce1798 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Fri, 12 May 2023 09:27:10 +0200 Subject: [PATCH 127/358] net: dsa: rzn1-a5psw: enable management frames for CPU port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, management frame were discarded before reaching the CPU port due to a misconfiguration of the MGMT_CONFIG register. Enable them by setting the correct value in this register in order to correctly receive management frame and handle STP. Fixes: 888cdb892b61 ("net: dsa: rzn1-a5psw: add Renesas RZ/N1 advanced 5 port switch driver") Signed-off-by: Clément Léger Signed-off-by: Alexis Lothoré Reviewed-by: Piotr Raczynski Signed-off-by: David S. Miller --- drivers/net/dsa/rzn1_a5psw.c | 2 +- drivers/net/dsa/rzn1_a5psw.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index 919027cf2012..8a419e2ffe2a 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -673,7 +673,7 @@ static int a5psw_setup(struct dsa_switch *ds) } /* Configure management port */ - reg = A5PSW_CPU_PORT | A5PSW_MGMT_CFG_DISCARD; + reg = A5PSW_CPU_PORT | A5PSW_MGMT_CFG_ENABLE; a5psw_reg_writel(a5psw, A5PSW_MGMT_CFG, reg); /* Set pattern 0 to forward all frame to mgmt port */ diff --git a/drivers/net/dsa/rzn1_a5psw.h b/drivers/net/dsa/rzn1_a5psw.h index c67abd49c013..b4fbf453ff74 100644 --- a/drivers/net/dsa/rzn1_a5psw.h +++ b/drivers/net/dsa/rzn1_a5psw.h @@ -36,7 +36,7 @@ #define A5PSW_INPUT_LEARN_BLOCK(p) BIT(p) #define A5PSW_MGMT_CFG 0x20 -#define A5PSW_MGMT_CFG_DISCARD BIT(7) +#define A5PSW_MGMT_CFG_ENABLE BIT(6) #define A5PSW_MODE_CFG 0x24 #define A5PSW_MODE_STATS_RESET BIT(31) From ebe9bc50952757b4b25eaf514da7c464196c9606 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= Date: Fri, 12 May 2023 09:27:11 +0200 Subject: [PATCH 128/358] net: dsa: rzn1-a5psw: fix STP states handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit stp_set_state() should actually allow receiving BPDU while in LEARNING mode which is not the case. Additionally, the BLOCKEN bit does not actually forbid sending forwarded frames from that port. To fix this, add a5psw_port_tx_enable() function which allows to disable TX. However, while its name suggest that TX is totally disabled, it is not and can still allow to send BPDUs even if disabled. This can be done by using forced forwarding with the switch tagging mechanism but keeping "filtering" disabled (which is already the case in the rzn1-a5sw tag driver). With these fixes, STP support is now functional. Fixes: 888cdb892b61 ("net: dsa: rzn1-a5psw: add Renesas RZ/N1 advanced 5 port switch driver") Signed-off-by: Clément Léger Signed-off-by: Alexis Lothoré Signed-off-by: David S. Miller --- drivers/net/dsa/rzn1_a5psw.c | 57 ++++++++++++++++++++++++++++++------ drivers/net/dsa/rzn1_a5psw.h | 1 + 2 files changed, 49 insertions(+), 9 deletions(-) diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index 8a419e2ffe2a..e2549cb31d00 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -120,6 +120,22 @@ static void a5psw_port_mgmtfwd_set(struct a5psw *a5psw, int port, bool enable) a5psw_port_pattern_set(a5psw, port, A5PSW_PATTERN_MGMTFWD, enable); } +static void a5psw_port_tx_enable(struct a5psw *a5psw, int port, bool enable) +{ + u32 mask = A5PSW_PORT_ENA_TX(port); + u32 reg = enable ? mask : 0; + + /* Even though the port TX is disabled through TXENA bit in the + * PORT_ENA register, it can still send BPDUs. This depends on the tag + * configuration added when sending packets from the CPU port to the + * switch port. Indeed, when using forced forwarding without filtering, + * even disabled ports will be able to send packets that are tagged. + * This allows to implement STP support when ports are in a state where + * forwarding traffic should be stopped but BPDUs should still be sent. + */ + a5psw_reg_rmw(a5psw, A5PSW_PORT_ENA, mask, reg); +} + static void a5psw_port_enable_set(struct a5psw *a5psw, int port, bool enable) { u32 port_ena = 0; @@ -292,6 +308,22 @@ static int a5psw_set_ageing_time(struct dsa_switch *ds, unsigned int msecs) return 0; } +static void a5psw_port_learning_set(struct a5psw *a5psw, int port, bool learn) +{ + u32 mask = A5PSW_INPUT_LEARN_DIS(port); + u32 reg = !learn ? mask : 0; + + a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); +} + +static void a5psw_port_rx_block_set(struct a5psw *a5psw, int port, bool block) +{ + u32 mask = A5PSW_INPUT_LEARN_BLOCK(port); + u32 reg = block ? mask : 0; + + a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); +} + static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port, bool set) { @@ -344,28 +376,35 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, static void a5psw_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { - u32 mask = A5PSW_INPUT_LEARN_DIS(port) | A5PSW_INPUT_LEARN_BLOCK(port); + bool learning_enabled, rx_enabled, tx_enabled; struct a5psw *a5psw = ds->priv; - u32 reg = 0; switch (state) { case BR_STATE_DISABLED: case BR_STATE_BLOCKING: - reg |= A5PSW_INPUT_LEARN_DIS(port); - reg |= A5PSW_INPUT_LEARN_BLOCK(port); - break; case BR_STATE_LISTENING: - reg |= A5PSW_INPUT_LEARN_DIS(port); + rx_enabled = false; + tx_enabled = false; + learning_enabled = false; break; case BR_STATE_LEARNING: - reg |= A5PSW_INPUT_LEARN_BLOCK(port); + rx_enabled = false; + tx_enabled = false; + learning_enabled = true; break; case BR_STATE_FORWARDING: - default: + rx_enabled = true; + tx_enabled = true; + learning_enabled = true; break; + default: + dev_err(ds->dev, "invalid STP state: %d\n", state); + return; } - a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); + a5psw_port_learning_set(a5psw, port, learning_enabled); + a5psw_port_rx_block_set(a5psw, port, !rx_enabled); + a5psw_port_tx_enable(a5psw, port, tx_enabled); } static void a5psw_port_fast_age(struct dsa_switch *ds, int port) diff --git a/drivers/net/dsa/rzn1_a5psw.h b/drivers/net/dsa/rzn1_a5psw.h index b4fbf453ff74..b869192eef3f 100644 --- a/drivers/net/dsa/rzn1_a5psw.h +++ b/drivers/net/dsa/rzn1_a5psw.h @@ -19,6 +19,7 @@ #define A5PSW_PORT_OFFSET(port) (0x400 * (port)) #define A5PSW_PORT_ENA 0x8 +#define A5PSW_PORT_ENA_TX(port) BIT(port) #define A5PSW_PORT_ENA_RX_SHIFT 16 #define A5PSW_PORT_ENA_TX_RX(port) (BIT((port) + A5PSW_PORT_ENA_RX_SHIFT) | \ BIT(port)) From ec52b69c046a6219011af780aca155a96719637b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Fri, 12 May 2023 09:27:12 +0200 Subject: [PATCH 129/358] net: dsa: rzn1-a5psw: disable learning for standalone ports MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When ports are in standalone mode, they should have learning disabled to avoid adding new entries in the MAC lookup table which might be used by other bridge ports to forward packets. While adding that, also make sure learning is enabled for CPU port. Fixes: 888cdb892b61 ("net: dsa: rzn1-a5psw: add Renesas RZ/N1 advanced 5 port switch driver") Signed-off-by: Clément Léger Signed-off-by: Alexis Lothoré Reviewed-by: Piotr Raczynski Signed-off-by: David S. Miller --- drivers/net/dsa/rzn1_a5psw.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index e2549cb31d00..c37d2e537230 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -340,6 +340,14 @@ static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port, a5psw_reg_writel(a5psw, offsets[i], a5psw->bridged_ports); } +static void a5psw_port_set_standalone(struct a5psw *a5psw, int port, + bool standalone) +{ + a5psw_port_learning_set(a5psw, port, !standalone); + a5psw_flooding_set_resolution(a5psw, port, !standalone); + a5psw_port_mgmtfwd_set(a5psw, port, standalone); +} + static int a5psw_port_bridge_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, @@ -355,8 +363,7 @@ static int a5psw_port_bridge_join(struct dsa_switch *ds, int port, } a5psw->br_dev = bridge.dev; - a5psw_flooding_set_resolution(a5psw, port, true); - a5psw_port_mgmtfwd_set(a5psw, port, false); + a5psw_port_set_standalone(a5psw, port, false); return 0; } @@ -366,8 +373,7 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, { struct a5psw *a5psw = ds->priv; - a5psw_flooding_set_resolution(a5psw, port, false); - a5psw_port_mgmtfwd_set(a5psw, port, true); + a5psw_port_set_standalone(a5psw, port, true); /* No more ports bridged */ if (a5psw->bridged_ports == BIT(A5PSW_CPU_PORT)) @@ -761,13 +767,15 @@ static int a5psw_setup(struct dsa_switch *ds) if (dsa_port_is_unused(dp)) continue; - /* Enable egress flooding for CPU port */ - if (dsa_port_is_cpu(dp)) + /* Enable egress flooding and learning for CPU port */ + if (dsa_port_is_cpu(dp)) { a5psw_flooding_set_resolution(a5psw, port, true); + a5psw_port_learning_set(a5psw, port, true); + } - /* Enable management forward only for user ports */ + /* Enable standalone mode for user ports */ if (dsa_port_is_user(dp)) - a5psw_port_mgmtfwd_set(a5psw, port, true); + a5psw_port_set_standalone(a5psw, port, true); } return 0; From 89f6bfb071182f05d7188c255b0e7251c3806f16 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Fri, 12 May 2023 18:00:11 +0800 Subject: [PATCH 130/358] net: hns3: fix output information incomplete for dumping tx queue info with debugfs In function hns3_dump_tx_queue_info, The print buffer is not enough when the tx BD number is configured to 32760. As a result several BD information wouldn't be displayed. So fix it by increasing the tx queue print buffer length. Fixes: 630a6738da82 ("net: hns3: adjust string spaces of some parameters of tx bd info in debugfs") Signed-off-by: Jie Wang Signed-off-by: Hao Lan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 4c3e90a1c4d0..d385ffc21876 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -130,7 +130,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "tx_bd_queue", .cmd = HNAE3_DBG_CMD_TX_BD, .dentry = HNS3_DBG_DENTRY_TX_BD, - .buf_len = HNS3_DBG_READ_LEN_4MB, + .buf_len = HNS3_DBG_READ_LEN_5MB, .init = hns3_dbg_bd_file_init, }, { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h index 97578eabb7d8..4a5ef8a90a10 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h @@ -10,6 +10,7 @@ #define HNS3_DBG_READ_LEN_128KB 0x20000 #define HNS3_DBG_READ_LEN_1MB 0x100000 #define HNS3_DBG_READ_LEN_4MB 0x400000 +#define HNS3_DBG_READ_LEN_5MB 0x500000 #define HNS3_DBG_WRITE_LEN 1024 #define HNS3_DBG_DATA_STR_LEN 32 From f14db07064727dd3bc0906c77a6d2759c1bbb395 Mon Sep 17 00:00:00 2001 From: Jijie Shao Date: Fri, 12 May 2023 18:00:12 +0800 Subject: [PATCH 131/358] net: hns3: fix sending pfc frames after reset issue To prevent the system from abnormally sending PFC frames after an abnormal reset. The hns3 driver notifies the firmware to disable pfc before reset. Fixes: 35d93a30040c ("net: hns3: adjust the process of PF reset") Signed-off-by: Jijie Shao Signed-off-by: Hao Lan Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 15 +++++++++------ .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 4 ++-- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h | 5 +++++ 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 4fb5406c1951..2689b108f7df 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8053,12 +8053,15 @@ static void hclge_ae_stop(struct hnae3_handle *handle) /* If it is not PF reset or FLR, the firmware will disable the MAC, * so it only need to stop phy here. */ - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && - hdev->reset_type != HNAE3_FUNC_RESET && - hdev->reset_type != HNAE3_FLR_RESET) { - hclge_mac_stop_phy(hdev); - hclge_update_link_status(hdev); - return; + if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) { + hclge_pfc_pause_en_cfg(hdev, HCLGE_PFC_TX_RX_DISABLE, + HCLGE_PFC_DISABLE); + if (hdev->reset_type != HNAE3_FUNC_RESET && + hdev->reset_type != HNAE3_FLR_RESET) { + hclge_mac_stop_phy(hdev); + hclge_update_link_status(hdev); + return; + } } hclge_reset_tqp(handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 4a33f65190e2..922c0da3660c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -171,8 +171,8 @@ int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx) return hclge_cmd_send(&hdev->hw, &desc, 1); } -static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, - u8 pfc_bitmap) +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap) { struct hclge_desc desc; struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)desc.data; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 68f28a98e380..dd6f1fd486cf 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -164,6 +164,9 @@ struct hclge_bp_to_qs_map_cmd { u32 rsvd1; }; +#define HCLGE_PFC_DISABLE 0 +#define HCLGE_PFC_TX_RX_DISABLE 0 + struct hclge_pfc_en_cmd { u8 tx_rx_en_bitmap; u8 pri_en_bitmap; @@ -235,6 +238,8 @@ void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc); void hclge_tm_pfc_info_update(struct hclge_dev *hdev); int hclge_tm_dwrr_cfg(struct hclge_dev *hdev); int hclge_tm_init_hw(struct hclge_dev *hdev, bool init); +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); From 814d0c786068e858d889ada3153bff82f64223ad Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Fri, 12 May 2023 18:00:13 +0800 Subject: [PATCH 132/358] net: hns3: fix reset delay time to avoid configuration timeout Currently the hns3 vf function reset delays 5000ms before vf rebuild process. In product applications, this delay is too long for application configurations and causes configuration timeout. According to the tests, 500ms delay is enough for reset process except PF FLR. So this patch modifies delay to 500ms in these scenarios. Fixes: 6988eb2a9b77 ("net: hns3: Add support to reset the enet/ring mgmt layer") Signed-off-by: Jie Wang Signed-off-by: Hao Lan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index f24046250341..dd08989a4c7c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1436,7 +1436,10 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) * might happen in case reset assertion was made by PF. Yes, this also * means we might end up waiting bit more even for VF reset. */ - msleep(5000); + if (hdev->reset_type == HNAE3_VF_FULL_RESET) + msleep(5000); + else + msleep(500); return 0; } From 6b45d5ff8c2c61baddd67d7510075ae121c5e704 Mon Sep 17 00:00:00 2001 From: Jijie Shao Date: Fri, 12 May 2023 18:00:14 +0800 Subject: [PATCH 133/358] net: hns3: fix reset timeout when enable full VF The timeout of the cmdq reset command has been increased to resolve the reset timeout issue in the full VF scenario. The timeout of other cmdq commands remains unchanged. Fixes: 8d307f8e8cf1 ("net: hns3: create new set of unified hclge_comm_cmd_send APIs") Signed-off-by: Jijie Shao Signed-off-by: Hao Lan Signed-off-by: David S. Miller --- .../hns3/hns3_common/hclge_comm_cmd.c | 25 ++++++++++++++++--- .../hns3/hns3_common/hclge_comm_cmd.h | 8 +++++- 2 files changed, 28 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c index cbbab5b2b402..b85c412683dd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c @@ -331,9 +331,25 @@ static int hclge_comm_cmd_csq_done(struct hclge_comm_hw *hw) return head == hw->cmq.csq.next_to_use; } -static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, +static u32 hclge_get_cmdq_tx_timeout(u16 opcode, u32 tx_timeout) +{ + static const struct hclge_cmdq_tx_timeout_map cmdq_tx_timeout_map[] = { + {HCLGE_OPC_CFG_RST_TRIGGER, HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS}, + }; + u32 i; + + for (i = 0; i < ARRAY_SIZE(cmdq_tx_timeout_map); i++) + if (cmdq_tx_timeout_map[i].opcode == opcode) + return cmdq_tx_timeout_map[i].tx_timeout; + + return tx_timeout; +} + +static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, u16 opcode, bool *is_completed) { + u32 cmdq_tx_timeout = hclge_get_cmdq_tx_timeout(opcode, + hw->cmq.tx_timeout); u32 timeout = 0; do { @@ -343,7 +359,7 @@ static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, } udelay(1); timeout++; - } while (timeout < hw->cmq.tx_timeout); + } while (timeout < cmdq_tx_timeout); } static int hclge_comm_cmd_convert_err_code(u16 desc_ret) @@ -407,7 +423,8 @@ static int hclge_comm_cmd_check_result(struct hclge_comm_hw *hw, * if multi descriptors to be sent, use the first one to check */ if (HCLGE_COMM_SEND_SYNC(le16_to_cpu(desc->flag))) - hclge_comm_wait_for_resp(hw, &is_completed); + hclge_comm_wait_for_resp(hw, le16_to_cpu(desc->opcode), + &is_completed); if (!is_completed) ret = -EBADE; @@ -529,7 +546,7 @@ int hclge_comm_cmd_queue_init(struct pci_dev *pdev, struct hclge_comm_hw *hw) cmdq->crq.desc_num = HCLGE_COMM_NIC_CMQ_DESC_NUM; /* Setup Tx write back timeout */ - cmdq->tx_timeout = HCLGE_COMM_CMDQ_TX_TIMEOUT; + cmdq->tx_timeout = HCLGE_COMM_CMDQ_TX_TIMEOUT_DEFAULT; /* Setup queue rings */ ret = hclge_comm_alloc_cmd_queue(hw, HCLGE_COMM_TYPE_CSQ); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h index de72ecbfd5ad..18f1b4bf362d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h @@ -54,7 +54,8 @@ #define HCLGE_COMM_NIC_SW_RST_RDY BIT(HCLGE_COMM_NIC_SW_RST_RDY_B) #define HCLGE_COMM_NIC_CMQ_DESC_NUM_S 3 #define HCLGE_COMM_NIC_CMQ_DESC_NUM 1024 -#define HCLGE_COMM_CMDQ_TX_TIMEOUT 30000 +#define HCLGE_COMM_CMDQ_TX_TIMEOUT_DEFAULT 30000 +#define HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS 500000 enum hclge_opcode_type { /* Generic commands */ @@ -360,6 +361,11 @@ struct hclge_comm_caps_bit_map { u16 local_bit; }; +struct hclge_cmdq_tx_timeout_map { + u32 opcode; + u32 tx_timeout; +}; + struct hclge_comm_firmware_compat_cmd { __le32 compat; u8 rsv[20]; From 0f5bb36bf9b39a2a96e730bf4455095b50713f63 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Wed, 8 Mar 2023 12:55:14 +0000 Subject: [PATCH 134/358] media: netup_unidvb: fix use-after-free at del_timer() When Universal DVB card is detaching, netup_unidvb_dma_fini() uses del_timer() to stop dma->timeout timer. But when timer handler netup_unidvb_dma_timeout() is running, del_timer() could not stop it. As a result, the use-after-free bug could happen. The process is shown below: (cleanup routine) | (timer routine) | mod_timer(&dev->tx_sim_timer, ..) netup_unidvb_finidev() | (wait a time) netup_unidvb_dma_fini() | netup_unidvb_dma_timeout() del_timer(&dma->timeout); | | ndev->pci_dev->dev //USE Fix by changing del_timer() to del_timer_sync(). Link: https://lore.kernel.org/linux-media/20230308125514.4208-1-duoming@zju.edu.cn Fixes: 52b1eaf4c59a ("[media] netup_unidvb: NetUP Universal DVB-S/S2/T/T2/C PCI-E card driver") Signed-off-by: Duoming Zhou Signed-off-by: Mauro Carvalho Chehab --- drivers/media/pci/netup_unidvb/netup_unidvb_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index 8287851b5ffd..aaa1d2dedebd 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -697,7 +697,7 @@ static void netup_unidvb_dma_fini(struct netup_unidvb_dev *ndev, int num) netup_unidvb_dma_enable(dma, 0); msleep(50); cancel_work_sync(&dma->work); - del_timer(&dma->timeout); + del_timer_sync(&dma->timeout); } static int netup_unidvb_dma_setup(struct netup_unidvb_dev *ndev) From 858e97d7956d17a2cb56a9413468704a4d5abfe1 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Fri, 10 Mar 2023 16:56:04 +0000 Subject: [PATCH 135/358] media: dvb-usb: az6027: fix three null-ptr-deref in az6027_i2c_xfer() In az6027_i2c_xfer, msg is controlled by user. When msg[i].buf is null, commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") fix the null-ptr-deref bug when msg[i].addr is 0x99. However, null-ptr-deref also happens when msg[i].addr is 0xd0 and 0xc0. We add check on msg[i].len to prevent null-ptr-deref. Link: https://lore.kernel.org/linux-media/20230310165604.3093483-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb/az6027.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/media/usb/dvb-usb/az6027.c b/drivers/media/usb/dvb-usb/az6027.c index 7d78ee09be5e..a31c6f82f4e9 100644 --- a/drivers/media/usb/dvb-usb/az6027.c +++ b/drivers/media/usb/dvb-usb/az6027.c @@ -988,6 +988,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* write/read request */ if (i + 1 < num && (msg[i + 1].flags & I2C_M_RD)) { req = 0xB9; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (msg[i].len << 8); length = msg[i + 1].len + 6; @@ -1001,6 +1005,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* demod 16bit addr */ req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (2 << 8); length = msg[i].len - 2; @@ -1026,6 +1034,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n } else { req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = msg[i].buf[0] & 0x00FF; value = msg[i].addr + (1 << 8); length = msg[i].len - 1; From a6dcefcc08eca1bf4e3d213c97c3cfb75f377935 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Mon, 13 Mar 2023 08:58:53 +0000 Subject: [PATCH 136/358] media: dvb-usb-v2: ec168: fix null-ptr-deref in ec168_i2c_xfer() In ec168_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. If accessing msg[i].buf[0] without sanity check, null pointer deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/20230313085853.3252349-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb-v2/ec168.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/ec168.c b/drivers/media/usb/dvb-usb-v2/ec168.c index 7ed0ab9e429b..0e4773fc025c 100644 --- a/drivers/media/usb/dvb-usb-v2/ec168.c +++ b/drivers/media/usb/dvb-usb-v2/ec168.c @@ -115,6 +115,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], while (i < num) { if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = READ_DEMOD; req.value = 0; req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -131,6 +135,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], } } else { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_DEMOD; req.value = msg[i].buf[1]; /* val */ req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -139,6 +147,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = ec168_ctrl_msg(d, &req); i += 1; } else { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_I2C; req.value = msg[i].buf[0]; /* val */ req.index = 0x0100 + msg[i].addr; /* I2C addr */ From dff919090155fb22679869e8469168f270dcd97f Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Mon, 13 Mar 2023 09:27:51 +0000 Subject: [PATCH 137/358] media: dvb-usb-v2: ce6230: fix null-ptr-deref in ce6230_i2c_master_xfer() In ce6230_i2c_master_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach ce6230_i2c_master_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/20230313092751.209496-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb-v2/ce6230.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/ce6230.c b/drivers/media/usb/dvb-usb-v2/ce6230.c index 44540de1a206..d3b5cb4a24da 100644 --- a/drivers/media/usb/dvb-usb-v2/ce6230.c +++ b/drivers/media/usb/dvb-usb-v2/ce6230.c @@ -101,6 +101,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_READ; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; @@ -117,6 +121,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, } else { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_WRITE; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; From aa4a447b81b84f69c1a89ad899df157f386d7636 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sun, 7 May 2023 15:52:47 +0100 Subject: [PATCH 138/358] media: dvb-usb-v2: rtl28xxu: fix null-ptr-deref in rtl28xxu_i2c_xfer In rtl28xxu_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach rtl28xxu_i2c_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/tencent_3623572106754AC2F266B316798B0F6CCA05@qq.com Signed-off-by: Zhang Shurong Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index 795a012d4020..f7884bb56fcc 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -176,6 +176,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1 || msg[1].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { /* return demod page from driver cache */ @@ -189,6 +193,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if (msg[0].len < 2) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_RD; @@ -217,8 +225,16 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { + if (msg[0].len < 2) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* save demod page for later demod access */ dev->page = msg[0].buf[1]; ret = 0; @@ -231,6 +247,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if ((msg[0].len < 23) && (!dev->new_i2c_write)) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_WR; From 9ded5bd2a49ce3015b7c936743eec0a0e6e11f0c Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Mon, 13 Mar 2023 09:50:08 +0000 Subject: [PATCH 139/358] media: dvb-usb: digitv: fix null-ptr-deref in digitv_i2c_xfer() In digitv_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach digitv_i2c_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/20230313095008.1039689-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb/digitv.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c index 2756815a780b..32134be16914 100644 --- a/drivers/media/usb/dvb-usb/digitv.c +++ b/drivers/media/usb/dvb-usb/digitv.c @@ -63,6 +63,10 @@ static int digitv_i2c_xfer(struct i2c_adapter *adap,struct i2c_msg msg[],int num warn("more than 2 i2c messages at a time is not handled yet. TODO."); for (i = 0; i < num; i++) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } /* write/read request */ if (i+1 < num && (msg[i+1].flags & I2C_M_RD)) { if (digitv_ctrl_msg(d, USB_READ_COFDM, msg[i].buf[0], NULL, 0, From a3fd1ef27aa686d871cefe207bd6168c4b0cd29e Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Tue, 28 Mar 2023 13:44:16 +0100 Subject: [PATCH 140/358] media: dvb-usb: dw2102: fix uninit-value in su3000_read_mac_address In su3000_read_mac_address, if i2c_transfer fails to execute two messages, array mac address will not be initialized. Without handling such error, later in function dvb_usb_adapter_dvb_init, proposed_mac is accessed before initialization. Fix this error by returning a negative value if message execution fails. Link: https://lore.kernel.org/linux-media/20230328124416.560889-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb/dw2102.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index 0ca764282c76..8747960e6146 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -946,7 +946,7 @@ static int su3000_read_mac_address(struct dvb_usb_device *d, u8 mac[6]) for (i = 0; i < 6; i++) { obuf[1] = 0xf0 + i; if (i2c_transfer(&d->i2c_adap, msg, 2) != 2) - break; + return -1; else mac[i] = ibuf[0]; } From e6ad6233592593079db5c8fa592c298e51bc1356 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Wed, 15 Mar 2023 13:45:18 +0000 Subject: [PATCH 141/358] media: netup_unidvb: fix irq init by register it at the end of probe IRQ handler netup_spi_interrupt() takes spinlock spi->lock. The lock is initialized in netup_spi_init(). However, irq handler is registered before initializing the lock. Spinlock dma->lock and i2c->lock suffer from the same problem. Fix this by registering the irq at the end of probe. Link: https://lore.kernel.org/linux-media/20230315134518.1074497-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- .../media/pci/netup_unidvb/netup_unidvb_core.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index aaa1d2dedebd..d85bfbb77a25 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -887,12 +887,7 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, ndev->lmmio0, (u32)pci_resource_len(pci_dev, 0), ndev->lmmio1, (u32)pci_resource_len(pci_dev, 1), pci_dev->irq); - if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, - "netup_unidvb", pci_dev) < 0) { - dev_err(&pci_dev->dev, - "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); - goto irq_request_err; - } + ndev->dma_size = 2 * 188 * NETUP_DMA_BLOCKS_COUNT * NETUP_DMA_PACKETS_COUNT; ndev->dma_virt = dma_alloc_coherent(&pci_dev->dev, @@ -933,6 +928,14 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, dev_err(&pci_dev->dev, "netup_unidvb: DMA setup failed\n"); goto dma_setup_err; } + + if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, + "netup_unidvb", pci_dev) < 0) { + dev_err(&pci_dev->dev, + "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); + goto dma_setup_err; + } + dev_info(&pci_dev->dev, "netup_unidvb: device has been initialized\n"); return 0; @@ -951,8 +954,6 @@ spi_setup_err: dma_free_coherent(&pci_dev->dev, ndev->dma_size, ndev->dma_virt, ndev->dma_phys); dma_alloc_err: - free_irq(pci_dev->irq, pci_dev); -irq_request_err: iounmap(ndev->lmmio1); pci_bar1_error: iounmap(ndev->lmmio0); From a4315e5be7020aac9b24a8151caf4bb85224cd0e Mon Sep 17 00:00:00 2001 From: YongSu Yoo Date: Thu, 18 Aug 2022 13:50:27 +0100 Subject: [PATCH 142/358] media: dvb_ca_en50221: fix a size write bug The function of "dvb_ca_en50221_write_data" at source/drivers/media /dvb-core/dvb_ca_en50221.c is used for two cases. The first case is for writing APDU data in the function of "dvb_ca_en50221_io_write" at source/drivers/media/dvb-core/ dvb_ca_en50221.c. The second case is for writing the host link buf size on the Command Register in the function of "dvb_ca_en50221_link_init" at source/drivers/media/dvb-core/dvb_ca_en50221.c. In the second case, there exists a bug like following. In the function of the "dvb_ca_en50221_link_init", after a TV host calculates the host link buf_size, the TV host writes the calculated host link buf_size on the Size Register. Accroding to the en50221 Spec (the page 60 of https://dvb.org/wp-content/uploads/2020/02/En50221.V1.pdf), before this writing operation, the "SW(CMDREG_SW)" flag in the Command Register should be set. We can see this setting operation in the function of the "dvb_ca_en50221_link_init" like below. ... if ((ret = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN | CMDREG_SW)) != 0) return ret; ... But, after that, the real writing operation is implemented using the function of the "dvb_ca_en50221_write_data" in the function of "dvb_ca_en50221_link_init", and the "dvb_ca_en50221_write_data" includes the function of "ca->pub->write_cam_control", and the function of the "ca->pub->write_cam_control" in the function of the "dvb_ca_en50221_wrte_data" does not include "CMDREG_SW" flag like below. ... if ((status = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN | CMDREG_HC)) != 0) ... In the above source code, we can see only the "IRQEN | CMDREG_HC", but we cannot see the "CMDREG_SW". The "CMDREG_SW" flag which was set in the function of the "dvb_ca_en50221_link_init" was rollbacked by the follwoing function of the "dvb_ca_en50221_write_data". This is a bug. and this bug causes that the calculated host link buf_size is not properly written in the CI module. Through this patch, we fix this bug. Link: https://lore.kernel.org/linux-media/20220818125027.1131-1-yongsuyoo0215@gmail.com Signed-off-by: YongSu Yoo Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_ca_en50221.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index c2d2792227f8..b6ca29dfb184 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -187,7 +187,7 @@ static void dvb_ca_en50221_thread_wakeup(struct dvb_ca_private *ca); static int dvb_ca_en50221_read_data(struct dvb_ca_private *ca, int slot, u8 *ebuf, int ecount); static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *ebuf, int ecount); + u8 *ebuf, int ecount, int size_write_flag); /** * findstr - Safely find needle in haystack. @@ -370,7 +370,7 @@ static int dvb_ca_en50221_link_init(struct dvb_ca_private *ca, int slot) ret = dvb_ca_en50221_wait_if_status(ca, slot, STATUSREG_FR, HZ / 10); if (ret) return ret; - ret = dvb_ca_en50221_write_data(ca, slot, buf, 2); + ret = dvb_ca_en50221_write_data(ca, slot, buf, 2, CMDREG_SW); if (ret != 2) return -EIO; ret = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN); @@ -778,11 +778,13 @@ exit: * @buf: The data in this buffer is treated as a complete link-level packet to * be written. * @bytes_write: Size of ebuf. + * @size_write_flag: A flag on Command Register which says whether the link size + * information will be writen or not. * * return: Number of bytes written, or < 0 on error. */ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *buf, int bytes_write) + u8 *buf, int bytes_write, int size_write_flag) { struct dvb_ca_slot *sl = &ca->slot_info[slot]; int status; @@ -817,7 +819,7 @@ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, /* OK, set HC bit */ status = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, - IRQEN | CMDREG_HC); + IRQEN | CMDREG_HC | size_write_flag); if (status) goto exit; @@ -1508,7 +1510,7 @@ static ssize_t dvb_ca_en50221_io_write(struct file *file, mutex_lock(&sl->slot_lock); status = dvb_ca_en50221_write_data(ca, slot, fragbuf, - fraglen + 2); + fraglen + 2, 0); mutex_unlock(&sl->slot_lock); if (status == (fraglen + 2)) { written = 1; From 517a281338322ff8293f988771c98aaa7205e457 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:25 +0000 Subject: [PATCH 143/358] media: ttusb-dec: fix memory leak in ttusb_dec_exit_dvb() Since dvb_frontend_detach() is not called in ttusb_dec_exit_dvb(), which is called when the device is disconnected, dvb_frontend_free() is not finally called. This causes a memory leak just by repeatedly plugging and unplugging the device. Fix this issue by adding dvb_frontend_detach() to ttusb_dec_exit_dvb(). Link: https://lore.kernel.org/linux-media/20221117045925.14297-5-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/ttusb-dec/ttusb_dec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/usb/ttusb-dec/ttusb_dec.c b/drivers/media/usb/ttusb-dec/ttusb_dec.c index 38822cedd93a..c4474d4c44e2 100644 --- a/drivers/media/usb/ttusb-dec/ttusb_dec.c +++ b/drivers/media/usb/ttusb-dec/ttusb_dec.c @@ -1544,8 +1544,7 @@ static void ttusb_dec_exit_dvb(struct ttusb_dec *dec) dvb_dmx_release(&dec->demux); if (dec->fe) { dvb_unregister_frontend(dec->fe); - if (dec->fe->ops.release) - dec->fe->ops.release(dec->fe); + dvb_frontend_detach(dec->fe); } dvb_unregister_adapter(&dec->adapter); } From ae11c0efaec32fb45130ee9886689f467232eebc Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 13:13:18 +0000 Subject: [PATCH 144/358] media: mn88443x: fix !CONFIG_OF error by drop of_match_ptr from ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver will match mostly by DT table (even thought there is regular ID table) so there is little benefit in of_match_ptr (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/media/dvb-frontends/mn88443x.c:782:34: error: ‘mn88443x_of_match’ defined but not used [-Werror=unused-const-variable=] Link: https://lore.kernel.org/linux-media/20230312131318.351173-28-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-frontends/mn88443x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/dvb-frontends/mn88443x.c b/drivers/media/dvb-frontends/mn88443x.c index 1f1753f2ab1a..0782f8377eb2 100644 --- a/drivers/media/dvb-frontends/mn88443x.c +++ b/drivers/media/dvb-frontends/mn88443x.c @@ -798,7 +798,7 @@ MODULE_DEVICE_TABLE(i2c, mn88443x_i2c_id); static struct i2c_driver mn88443x_driver = { .driver = { .name = "mn88443x", - .of_match_table = of_match_ptr(mn88443x_of_match), + .of_match_table = mn88443x_of_match, }, .probe_new = mn88443x_probe, .remove = mn88443x_remove, From 6769a0b7ee0c3b31e1b22c3fadff2bfb642de23f Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:22 +0000 Subject: [PATCH 145/358] media: dvb-core: Fix use-after-free on race condition at dvb_frontend If the device node of dvb_frontend is open() and the device is disconnected, many kinds of UAFs may occur when calling close() on the device node. The root cause of this is that wake_up() for dvbdev->wait_queue is implemented in the dvb_frontend_release() function, but wait_event() is not implemented in the dvb_frontend_stop() function. So, implement wait_event() function in dvb_frontend_stop() and add 'remove_mutex' which prevents race condition for 'fe->exit'. [mchehab: fix a couple of checkpatch warnings and some mistakes at the error handling logic] Link: https://lore.kernel.org/linux-media/20221117045925.14297-2-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_frontend.c | 53 ++++++++++++++++++++++----- include/media/dvb_frontend.h | 6 ++- 2 files changed, 49 insertions(+), 10 deletions(-) diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index cc0a789f09ae..947b61959b2b 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -809,15 +809,26 @@ static void dvb_frontend_stop(struct dvb_frontend *fe) dev_dbg(fe->dvb->device, "%s:\n", __func__); + mutex_lock(&fe->remove_mutex); + if (fe->exit != DVB_FE_DEVICE_REMOVED) fe->exit = DVB_FE_NORMAL_EXIT; mb(); - if (!fepriv->thread) + if (!fepriv->thread) { + mutex_unlock(&fe->remove_mutex); return; + } kthread_stop(fepriv->thread); + mutex_unlock(&fe->remove_mutex); + + if (fepriv->dvbdev->users < -1) { + wait_event(fepriv->dvbdev->wait_queue, + fepriv->dvbdev->users == -1); + } + sema_init(&fepriv->sem, 1); fepriv->state = FESTATE_IDLE; @@ -2761,9 +2772,13 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) struct dvb_adapter *adapter = fe->dvb; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); - if (fe->exit == DVB_FE_DEVICE_REMOVED) - return -ENODEV; + if (fe->exit == DVB_FE_DEVICE_REMOVED) { + ret = -ENODEV; + goto err_remove_mutex; + } if (adapter->mfe_shared == 2) { mutex_lock(&adapter->mfe_lock); @@ -2771,7 +2786,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_dvbdev && !adapter->mfe_dvbdev->writers) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2794,8 +2810,10 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) while (mferetry-- && (mfedev->users != -1 || mfepriv->thread)) { if (msleep_interruptible(500)) { - if (signal_pending(current)) - return -EINTR; + if (signal_pending(current)) { + ret = -EINTR; + goto err_remove_mutex; + } } } @@ -2807,7 +2825,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (mfedev->users != -1 || mfepriv->thread) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2866,6 +2885,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + + mutex_unlock(&fe->remove_mutex); return ret; err3: @@ -2887,6 +2908,9 @@ err1: err0: if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + +err_remove_mutex: + mutex_unlock(&fe->remove_mutex); return ret; } @@ -2897,6 +2921,8 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) struct dvb_frontend_private *fepriv = fe->frontend_priv; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); if ((file->f_flags & O_ACCMODE) != O_RDONLY) { @@ -2918,10 +2944,18 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) } mutex_unlock(&fe->dvb->mdev_lock); #endif - if (fe->exit != DVB_FE_NO_EXIT) - wake_up(&dvbdev->wait_queue); if (fe->ops.ts_bus_ctrl) fe->ops.ts_bus_ctrl(fe, 0); + + if (fe->exit != DVB_FE_NO_EXIT) { + mutex_unlock(&fe->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&fe->remove_mutex); + } + + } else { + mutex_unlock(&fe->remove_mutex); } dvb_frontend_put(fe); @@ -3022,6 +3056,7 @@ int dvb_register_frontend(struct dvb_adapter *dvb, fepriv = fe->frontend_priv; kref_init(&fe->refcount); + mutex_init(&fe->remove_mutex); /* * After initialization, there need to be two references: one diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h index e7c44870f20d..367d5381217b 100644 --- a/include/media/dvb_frontend.h +++ b/include/media/dvb_frontend.h @@ -686,7 +686,10 @@ struct dtv_frontend_properties { * @id: Frontend ID * @exit: Used to inform the DVB core that the frontend * thread should exit (usually, means that the hardware - * got disconnected. + * got disconnected). + * @remove_mutex: mutex that avoids a race condition between a callback + * called when the hardware is disconnected and the + * file_operations of dvb_frontend. */ struct dvb_frontend { @@ -704,6 +707,7 @@ struct dvb_frontend { int (*callback)(void *adapter_priv, int component, int cmd, int arg); int id; unsigned int exit; + struct mutex remove_mutex; }; /** From 4172385b0c9ac366dcab78eda48c26814b87ed1a Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:23 +0000 Subject: [PATCH 146/358] media: dvb-core: Fix use-after-free due on race condition at dvb_net A race condition may occur between the .disconnect function, which is called when the device is disconnected, and the dvb_device_open() function, which is called when the device node is open()ed. This results in several types of UAFs. The root cause of this is that you use the dvb_device_open() function, which does not implement a conditional statement that checks 'dvbnet->exit'. So, add 'remove_mutex` to protect 'dvbnet->exit' and use locked_dvb_net_open() function to check 'dvbnet->exit'. [mchehab: fix a checkpatch warning] Link: https://lore.kernel.org/linux-media/20221117045925.14297-3-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_net.c | 38 +++++++++++++++++++++++++++++--- include/media/dvb_net.h | 4 ++++ 2 files changed, 39 insertions(+), 3 deletions(-) diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index 8a2febf33ce2..8bb8dd34c223 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -1564,15 +1564,43 @@ static long dvb_net_ioctl(struct file *file, return dvb_usercopy(file, cmd, arg, dvb_net_do_ioctl); } +static int locked_dvb_net_open(struct inode *inode, struct file *file) +{ + struct dvb_device *dvbdev = file->private_data; + struct dvb_net *dvbnet = dvbdev->priv; + int ret; + + if (mutex_lock_interruptible(&dvbnet->remove_mutex)) + return -ERESTARTSYS; + + if (dvbnet->exit) { + mutex_unlock(&dvbnet->remove_mutex); + return -ENODEV; + } + + ret = dvb_generic_open(inode, file); + + mutex_unlock(&dvbnet->remove_mutex); + + return ret; +} + static int dvb_net_close(struct inode *inode, struct file *file) { struct dvb_device *dvbdev = file->private_data; struct dvb_net *dvbnet = dvbdev->priv; + mutex_lock(&dvbnet->remove_mutex); + dvb_generic_release(inode, file); - if(dvbdev->users == 1 && dvbnet->exit == 1) + if (dvbdev->users == 1 && dvbnet->exit == 1) { + mutex_unlock(&dvbnet->remove_mutex); wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&dvbnet->remove_mutex); + } + return 0; } @@ -1580,7 +1608,7 @@ static int dvb_net_close(struct inode *inode, struct file *file) static const struct file_operations dvb_net_fops = { .owner = THIS_MODULE, .unlocked_ioctl = dvb_net_ioctl, - .open = dvb_generic_open, + .open = locked_dvb_net_open, .release = dvb_net_close, .llseek = noop_llseek, }; @@ -1599,10 +1627,13 @@ void dvb_net_release (struct dvb_net *dvbnet) { int i; + mutex_lock(&dvbnet->remove_mutex); dvbnet->exit = 1; + mutex_unlock(&dvbnet->remove_mutex); + if (dvbnet->dvbdev->users < 1) wait_event(dvbnet->dvbdev->wait_queue, - dvbnet->dvbdev->users==1); + dvbnet->dvbdev->users == 1); dvb_unregister_device(dvbnet->dvbdev); @@ -1621,6 +1652,7 @@ int dvb_net_init (struct dvb_adapter *adap, struct dvb_net *dvbnet, int i; mutex_init(&dvbnet->ioctl_mutex); + mutex_init(&dvbnet->remove_mutex); dvbnet->demux = dmx; for (i=0; i Date: Thu, 17 Nov 2022 04:59:24 +0000 Subject: [PATCH 147/358] media: dvb-core: Fix use-after-free due to race at dvb_register_device() dvb_register_device() dynamically allocates fops with kmemdup() to set the fops->owner. And these fops are registered in 'file->f_ops' using replace_fops() in the dvb_device_open() process, and kfree()d in dvb_free_device(). However, it is not common to use dynamically allocated fops instead of 'static const' fops as an argument of replace_fops(), and UAF may occur. These UAFs can occur on any dvb type using dvb_register_device(), such as dvb_dvr, dvb_demux, dvb_frontend, dvb_net, etc. So, instead of kfree() the fops dynamically allocated in dvb_register_device() in dvb_free_device() called during the .disconnect() process, kfree() it collectively in exit_dvbdev() called when the dvbdev.c module is removed. Link: https://lore.kernel.org/linux-media/20221117045925.14297-4-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvbdev.c | 84 ++++++++++++++++++++++++--------- include/media/dvbdev.h | 15 ++++++ 2 files changed, 78 insertions(+), 21 deletions(-) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index e9b3ce09e534..a4b05e366ccc 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -27,6 +27,7 @@ #include static DEFINE_MUTEX(dvbdev_mutex); +static LIST_HEAD(dvbdevfops_list); static int dvbdev_debug; module_param(dvbdev_debug, int, 0644); @@ -453,14 +454,15 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, enum dvb_device_type type, int demux_sink_pads) { struct dvb_device *dvbdev; - struct file_operations *dvbdevfops; + struct file_operations *dvbdevfops = NULL; + struct dvbdevfops_node *node = NULL, *new_node = NULL; struct device *clsdev; int minor; int id, ret; mutex_lock(&dvbdev_register_lock); - if ((id = dvbdev_get_free_id (adap, type)) < 0){ + if ((id = dvbdev_get_free_id (adap, type)) < 0) { mutex_unlock(&dvbdev_register_lock); *pdvbdev = NULL; pr_err("%s: couldn't find free device id\n", __func__); @@ -468,18 +470,45 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } *pdvbdev = dvbdev = kzalloc(sizeof(*dvbdev), GFP_KERNEL); - if (!dvbdev){ mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } - dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + /* + * When a device of the same type is probe()d more than once, + * the first allocated fops are used. This prevents memory leaks + * that can occur when the same device is probe()d repeatedly. + */ + list_for_each_entry(node, &dvbdevfops_list, list_head) { + if (node->fops->owner == adap->module && + node->type == type && + node->template == template) { + dvbdevfops = node->fops; + break; + } + } - if (!dvbdevfops){ - kfree (dvbdev); - mutex_unlock(&dvbdev_register_lock); - return -ENOMEM; + if (dvbdevfops == NULL) { + dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + if (!dvbdevfops) { + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node = kzalloc(sizeof(struct dvbdevfops_node), GFP_KERNEL); + if (!new_node) { + kfree(dvbdevfops); + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node->fops = dvbdevfops; + new_node->type = type; + new_node->template = template; + list_add_tail (&new_node->list_head, &dvbdevfops_list); } memcpy(dvbdev, template, sizeof(struct dvb_device)); @@ -490,20 +519,20 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvbdev->priv = priv; dvbdev->fops = dvbdevfops; init_waitqueue_head (&dvbdev->wait_queue); - dvbdevfops->owner = adap->module; - list_add_tail (&dvbdev->list_head, &adap->device_list); - down_write(&minor_rwsem); #ifdef CONFIG_DVB_DYNAMIC_MINORS for (minor = 0; minor < MAX_DVB_MINORS; minor++) if (dvb_minors[minor] == NULL) break; - if (minor == MAX_DVB_MINORS) { + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); @@ -512,41 +541,47 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, #else minor = nums2minor(adap->num, type, id); #endif - dvbdev->minor = minor; dvb_minors[minor] = dvb_device_get(dvbdev); up_write(&minor_rwsem); - ret = dvb_register_media_device(dvbdev, type, minor, demux_sink_pads); if (ret) { pr_err("%s: dvb_register_media_device failed to create the mediagraph\n", __func__); - + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); mutex_unlock(&dvbdev_register_lock); return ret; } - mutex_unlock(&dvbdev_register_lock); - clsdev = device_create(dvb_class, adap->device, MKDEV(DVB_MAJOR, minor), dvbdev, "dvb%d.%s%d", adap->num, dnames[type], id); if (IS_ERR(clsdev)) { pr_err("%s: failed to create device dvb%d.%s%d (%ld)\n", __func__, adap->num, dnames[type], id, PTR_ERR(clsdev)); + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); return PTR_ERR(clsdev); } + dprintk("DVB: register adapter%d/%s%d @ minor: %i (0x%02x)\n", adap->num, dnames[type], id, minor, minor); + mutex_unlock(&dvbdev_register_lock); return 0; } EXPORT_SYMBOL(dvb_register_device); @@ -575,7 +610,6 @@ static void dvb_free_device(struct kref *ref) { struct dvb_device *dvbdev = container_of(ref, struct dvb_device, ref); - kfree (dvbdev->fops); kfree (dvbdev); } @@ -1081,9 +1115,17 @@ error: static void __exit exit_dvbdev(void) { + struct dvbdevfops_node *node, *next; + class_destroy(dvb_class); cdev_del(&dvb_device_cdev); unregister_chrdev_region(MKDEV(DVB_MAJOR, 0), MAX_DVB_MINORS); + + list_for_each_entry_safe(node, next, &dvbdevfops_list, list_head) { + list_del (&node->list_head); + kfree(node->fops); + kfree(node); + } } subsys_initcall(init_dvbdev); diff --git a/include/media/dvbdev.h b/include/media/dvbdev.h index 29d25c8a6f13..8958e5e2fc5b 100644 --- a/include/media/dvbdev.h +++ b/include/media/dvbdev.h @@ -193,6 +193,21 @@ struct dvb_device { void *priv; }; +/** + * struct dvbdevfops_node - fops nodes registered in dvbdevfops_list + * + * @fops: Dynamically allocated fops for ->owner registration + * @type: type of dvb_device + * @template: dvb_device used for registration + * @list_head: list_head for dvbdevfops_list + */ +struct dvbdevfops_node { + struct file_operations *fops; + enum dvb_device_type type; + const struct dvb_device *template; + struct list_head list_head; +}; + /** * dvb_device_get - Increase dvb_device reference * From b8c75e4a1b325ea0a9433fa8834be97b5836b946 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 12 May 2023 16:18:00 +0100 Subject: [PATCH 148/358] media: dvb-core: Fix kernel WARNING for blocking operation in wait_event*() Using a semaphore in the wait_event*() condition is no good idea. It hits a kernel WARN_ON() at prepare_to_wait_event() like: do not call blocking ops when !TASK_RUNNING; state=1 set at prepare_to_wait_event+0x6d/0x690 For avoiding the potential deadlock, rewrite to an open-coded loop instead. Unlike the loop in wait_event*(), this uses wait_woken() after the condition check, hence the task state stays consistent. CVE-2023-31084 was assigned to this bug. Link: https://lore.kernel.org/r/CA+UBctCu7fXn4q41O_3=id1+OdyQ85tZY1x+TkT-6OVBL6KAUw@mail.gmail.com/ Link: https://lore.kernel.org/linux-media/20230512151800.1874-1-tiwai@suse.de Reported-by: Yu Hao Closes: https://nvd.nist.gov/vuln/detail/CVE-2023-31084 Signed-off-by: Takashi Iwai Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_frontend.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index 947b61959b2b..bc6950a5740f 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -293,14 +293,22 @@ static int dvb_frontend_get_event(struct dvb_frontend *fe, } if (events->eventw == events->eventr) { - int ret; + struct wait_queue_entry wait; + int ret = 0; if (flags & O_NONBLOCK) return -EWOULDBLOCK; - ret = wait_event_interruptible(events->wait_queue, - dvb_frontend_test_event(fepriv, events)); - + init_waitqueue_entry(&wait, current); + add_wait_queue(&events->wait_queue, &wait); + while (!dvb_frontend_test_event(fepriv, events)) { + wait_woken(&wait, TASK_INTERRUPTIBLE, 0); + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + } + remove_wait_queue(&events->wait_queue, &wait); if (ret < 0) return ret; } From 280a8ab81733da8bc442253c700a52c4c0886ffd Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Mon, 21 Nov 2022 06:33:08 +0000 Subject: [PATCH 149/358] media: dvb-core: Fix use-after-free due to race condition at dvb_ca_en50221 If the device node of dvb_ca_en50221 is open() and the device is disconnected, a UAF may occur when calling close() on the device node. The root cause is that wake_up() and wait_event() for dvbdev->wait_queue are not implemented. So implement wait_event() function in dvb_ca_en50221_release() and add 'remove_mutex' which prevents race condition for 'ca->exit'. [mchehab: fix a checkpatch warning] Link: https://lore.kernel.org/linux-media/20221121063308.GA33821@ubuntu Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_ca_en50221.c | 37 ++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index b6ca29dfb184..baf64540dc00 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -151,6 +151,12 @@ struct dvb_ca_private { /* mutex serializing ioctls */ struct mutex ioctl_mutex; + + /* A mutex used when a device is disconnected */ + struct mutex remove_mutex; + + /* Whether the device is disconnected */ + int exit; }; static void dvb_ca_private_free(struct dvb_ca_private *ca) @@ -1711,12 +1717,22 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dprintk("%s\n", __func__); - if (!try_module_get(ca->pub->owner)) + mutex_lock(&ca->remove_mutex); + + if (ca->exit) { + mutex_unlock(&ca->remove_mutex); + return -ENODEV; + } + + if (!try_module_get(ca->pub->owner)) { + mutex_unlock(&ca->remove_mutex); return -EIO; + } err = dvb_generic_open(inode, file); if (err < 0) { module_put(ca->pub->owner); + mutex_unlock(&ca->remove_mutex); return err; } @@ -1741,6 +1757,7 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dvb_ca_private_get(ca); + mutex_unlock(&ca->remove_mutex); return 0; } @@ -1760,6 +1777,8 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + /* mark the CA device as closed */ ca->open = 0; dvb_ca_en50221_thread_update_delay(ca); @@ -1770,6 +1789,13 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dvb_ca_private_put(ca); + if (dvbdev->users == 1 && ca->exit == 1) { + mutex_unlock(&ca->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&ca->remove_mutex); + } + return err; } @@ -1893,6 +1919,7 @@ int dvb_ca_en50221_init(struct dvb_adapter *dvb_adapter, } mutex_init(&ca->ioctl_mutex); + mutex_init(&ca->remove_mutex); if (signal_pending(current)) { ret = -EINTR; @@ -1935,6 +1962,14 @@ void dvb_ca_en50221_release(struct dvb_ca_en50221 *pubca) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + ca->exit = 1; + mutex_unlock(&ca->remove_mutex); + + if (ca->dvbdev->users < 1) + wait_event(ca->dvbdev->wait_queue, + ca->dvbdev->users == 1); + /* shutdown the thread if there was one */ kthread_stop(ca->thread); From eb8d3a2c809abd73ab0a060fe971d6b9019aa3c1 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 9 May 2023 09:41:49 +1000 Subject: [PATCH 150/358] SUNRPC: double free xprt_ctxt while still in use When an RPC request is deferred, the rq_xprt_ctxt pointer is moved out of the svc_rqst into the svc_deferred_req. When the deferred request is revisited, the pointer is copied into the new svc_rqst - and also remains in the svc_deferred_req. In the (rare?) case that the request is deferred a second time, the old svc_deferred_req is reused - it still has all the correct content. However in that case the rq_xprt_ctxt pointer is NOT cleared so that when xpo_release_xprt is called, the ctxt is freed (UDP) or possible added to a free list (RDMA). When the deferred request is revisited for a second time, it will reference this ctxt which may be invalid, and the free the object a second time which is likely to oops. So change svc_defer() to *always* clear rq_xprt_ctxt, and assert that the value is now stored in the svc_deferred_req. Fixes: 773f91b2cf3f ("SUNRPC: Fix NFSD's request deferral on RDMA transports") Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- net/sunrpc/svc_xprt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 84e5d7d31481..5fd94f6bdc75 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1223,13 +1223,14 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; dr->xprt_ctxt = rqstp->rq_xprt_ctxt; - rqstp->rq_xprt_ctxt = NULL; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip, dr->argslen << 2); } + WARN_ON_ONCE(rqstp->rq_xprt_ctxt != dr->xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; From 948f072ada23e0a504c5e4d7d71d4c83bd0785ec Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 9 May 2023 09:42:47 +1000 Subject: [PATCH 151/358] SUNRPC: always free ctxt when freeing deferred request Since the ->xprt_ctxt pointer was added to svc_deferred_req, it has not been sufficient to use kfree() to free a deferred request. We may need to free the ctxt as well. As freeing the ctxt is all that ->xpo_release_rqst() does, we repurpose it to explicit do that even when the ctxt is not stored in an rqst. So we now have ->xpo_release_ctxt() which is given an xprt and a ctxt, which may have been taken either from an rqst or from a dreq. The caller is now responsible for clearing that pointer after the call to ->xpo_release_ctxt. We also clear dr->xprt_ctxt when the ctxt is moved into a new rqst when revisiting a deferred request. This ensures there is only one pointer to the ctxt, so the risk of double freeing in future is reduced. The new code in svc_xprt_release which releases both the ctxt and any rq_deferred depends on this. Fixes: 773f91b2cf3f ("SUNRPC: Fix NFSD's request deferral on RDMA transports") Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 2 +- include/linux/sunrpc/svc_xprt.h | 2 +- net/sunrpc/svc_xprt.c | 23 +++++++++++++----- net/sunrpc/svcsock.c | 30 +++++++++++++----------- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 11 ++++----- net/sunrpc/xprtrdma/svc_rdma_transport.c | 2 +- 6 files changed, 41 insertions(+), 29 deletions(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24aa159d29a7..fbc4bd423b35 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -176,7 +176,7 @@ extern struct svc_rdma_recv_ctxt * extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt); extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); -extern void svc_rdma_release_rqst(struct svc_rqst *rqstp); +extern void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *ctxt); extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 867479204840..a6b12631db21 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -23,7 +23,7 @@ struct svc_xprt_ops { int (*xpo_sendto)(struct svc_rqst *); int (*xpo_result_payload)(struct svc_rqst *, unsigned int, unsigned int); - void (*xpo_release_rqst)(struct svc_rqst *); + void (*xpo_release_ctxt)(struct svc_xprt *xprt, void *ctxt); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 5fd94f6bdc75..13a14897bc17 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -532,13 +532,23 @@ void svc_reserve(struct svc_rqst *rqstp, int space) } EXPORT_SYMBOL_GPL(svc_reserve); +static void free_deferred(struct svc_xprt *xprt, struct svc_deferred_req *dr) +{ + if (!dr) + return; + + xprt->xpt_ops->xpo_release_ctxt(xprt, dr->xprt_ctxt); + kfree(dr); +} + static void svc_xprt_release(struct svc_rqst *rqstp) { struct svc_xprt *xprt = rqstp->rq_xprt; - xprt->xpt_ops->xpo_release_rqst(rqstp); + xprt->xpt_ops->xpo_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; - kfree(rqstp->rq_deferred); + free_deferred(xprt, rqstp->rq_deferred); rqstp->rq_deferred = NULL; svc_rqst_release_pages(rqstp); @@ -1054,7 +1064,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt) spin_unlock_bh(&serv->sv_lock); while ((dr = svc_deferred_dequeue(xprt)) != NULL) - kfree(dr); + free_deferred(xprt, dr); call_xpt_users(xprt); svc_xprt_put(xprt); @@ -1176,8 +1186,8 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) if (too_many || test_bit(XPT_DEAD, &xprt->xpt_flags)) { spin_unlock(&xprt->xpt_lock); trace_svc_defer_drop(dr); + free_deferred(xprt, dr); svc_xprt_put(xprt); - kfree(dr); return; } dr->xprt = NULL; @@ -1222,14 +1232,13 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->addrlen = rqstp->rq_addrlen; dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; - dr->xprt_ctxt = rqstp->rq_xprt_ctxt; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip, dr->argslen << 2); } - WARN_ON_ONCE(rqstp->rq_xprt_ctxt != dr->xprt_ctxt); + dr->xprt_ctxt = rqstp->rq_xprt_ctxt; rqstp->rq_xprt_ctxt = NULL; trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); @@ -1263,6 +1272,8 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp) rqstp->rq_daddr = dr->daddr; rqstp->rq_respages = rqstp->rq_pages; rqstp->rq_xprt_ctxt = dr->xprt_ctxt; + + dr->xprt_ctxt = NULL; svc_xprt_received(rqstp->rq_xprt); return dr->argslen << 2; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 9989194446a5..63fe7a338992 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -121,27 +121,27 @@ static void svc_reclassify_socket(struct socket *sock) #endif /** - * svc_tcp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_tcp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_tcp_release_rqst(struct svc_rqst *rqstp) +static void svc_tcp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { } /** - * svc_udp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_udp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_udp_release_rqst(struct svc_rqst *rqstp) +static void svc_udp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { - struct sk_buff *skb = rqstp->rq_xprt_ctxt; + struct sk_buff *skb = ctxt; - if (skb) { - rqstp->rq_xprt_ctxt = NULL; + if (skb) consume_skb(skb); - } } union svc_pktinfo_u { @@ -696,7 +696,8 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_udp_release_rqst(rqstp); + svc_udp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; svc_set_cmsg_data(rqstp, cmh); @@ -768,7 +769,7 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_recvfrom = svc_udp_recvfrom, .xpo_sendto = svc_udp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_udp_release_rqst, + .xpo_release_ctxt = svc_udp_release_ctxt, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_udp_has_wspace, @@ -1301,7 +1302,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_tcp_release_rqst(rqstp); + svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; atomic_inc(&svsk->sk_sendqlen); mutex_lock(&xprt->xpt_mutex); @@ -1346,7 +1348,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_recvfrom = svc_tcp_recvfrom, .xpo_sendto = svc_tcp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_tcp_release_rqst, + .xpo_release_ctxt = svc_tcp_release_ctxt, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_tcp_has_wspace, diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 1c658fa43063..a22fe7587fa6 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -239,21 +239,20 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, } /** - * svc_rdma_release_rqst - Release transport-specific per-rqst resources - * @rqstp: svc_rqst being released + * svc_rdma_release_ctxt - Release transport-specific per-rqst resources + * @xprt: the transport which owned the context + * @vctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * * Ensure that the recv_ctxt is released whether or not a Reply * was sent. For example, the client could close the connection, * or svc_process could drop an RPC, before the Reply is sent. */ -void svc_rdma_release_rqst(struct svc_rqst *rqstp) +void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *vctxt) { - struct svc_rdma_recv_ctxt *ctxt = rqstp->rq_xprt_ctxt; - struct svc_xprt *xprt = rqstp->rq_xprt; + struct svc_rdma_recv_ctxt *ctxt = vctxt; struct svcxprt_rdma *rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); - rqstp->rq_xprt_ctxt = NULL; if (ctxt) svc_rdma_recv_ctxt_put(rdma, ctxt); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 416b298f74dd..ca04f7a6a085 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -80,7 +80,7 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_recvfrom = svc_rdma_recvfrom, .xpo_sendto = svc_rdma_sendto, .xpo_result_payload = svc_rdma_result_payload, - .xpo_release_rqst = svc_rdma_release_rqst, + .xpo_release_ctxt = svc_rdma_release_ctxt, .xpo_detach = svc_rdma_detach, .xpo_free = svc_rdma_free, .xpo_has_wspace = svc_rdma_has_wspace, From 07a27305938559fb35f7a46fb90a5e37728bdee6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 14 May 2023 15:51:48 -0400 Subject: [PATCH 152/358] SUNRPC: Fix trace_svc_register() call site The trace event recorded incorrect values for the registered family, protocol, and port because the arguments are in the wrong order. Fixes: b4af59328c25 ("SUNRPC: Trace server-side rpcbind registration events") Signed-off-by: Chuck Lever --- net/sunrpc/svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 43e32129a583..79967b6925bd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1052,7 +1052,7 @@ static int __svc_register(struct net *net, const char *progname, #endif } - trace_svc_register(progname, version, protocol, port, family, error); + trace_svc_register(progname, version, family, protocol, port, error); return error; } From a7844528722619d2f97740ae5ec747afff18c4be Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Fri, 12 May 2023 13:52:04 +0200 Subject: [PATCH 153/358] dt-bindings: ata: ahci-ceva: Cover all 4 iommus entries Current only one entry is enabled but IP itself is using 4 different IDs which are already listed in zynqmp.dtsi. sata: ahci@fd0c0000 { compatible = "ceva,ahci-1v84"; ... iommus = <&smmu 0x4c0>, <&smmu 0x4c1>, <&smmu 0x4c2>, <&smmu 0x4c3>; }; Fixes: 8ac47837f0e0 ("arm64: dts: zynqmp: Add missing iommu IDs") Cc: stable@vger.kernel.org # v5.12+ Signed-off-by: Michal Simek Acked-by: Krzysztof Kozlowski Signed-off-by: Damien Le Moal --- Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml index 9b31f864e071..71364c6081ff 100644 --- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml +++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml @@ -32,7 +32,7 @@ properties: maxItems: 1 iommus: - maxItems: 1 + maxItems: 4 power-domains: maxItems: 1 From 7430dea49410de3d154fb87f931d079a0a643b1a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:06 -0500 Subject: [PATCH 154/358] ASoC: SOF: Intel: hda-mlink: fix sublink refcounting In hindsight it was a very bad idea to use the same refcount for Extended and 'legacy' HDaudio multi-links. The existing solution only powers-up the first sublink, which causes SoundWire and SSP tests to fail when more than one DAI is used concurrently. Solving this problem requires per-sublink refcounting, as suggested in this patch. The existing refcounting remains for 'legacy' HdAudio links, mainly to avoid changing the obscure programming sequence in snd_hdac_ext_bus_link_put(). Signed-off-by: Pierre-Louis Bossart eml_lock); - if (++hlink->ref_count > 1) - goto skip_init; + if (!alt) { + if (++hlink->ref_count > 1) + goto skip_init; + } else { + if (++h2link->sublink_ref_count[sublink] > 1) + goto skip_init; + } ret = hdaml_link_init(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); @@ -684,9 +694,13 @@ static int hdac_bus_eml_power_down_base(struct hdac_bus *bus, bool alt, int elid if (eml_lock) mutex_lock(&h2link->eml_lock); - if (--hlink->ref_count > 0) - goto skip_shutdown; - + if (!alt) { + if (--hlink->ref_count > 0) + goto skip_shutdown; + } else { + if (--h2link->sublink_ref_count[sublink] > 0) + goto skip_shutdown; + } ret = hdaml_link_shutdown(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); skip_shutdown: From dcb88fc47d0e79fd54a19a63a4c8a7594ba0838e Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:07 -0500 Subject: [PATCH 155/358] ASoC: SOF: Intel: hda-mlink: add helper to get SoundWire hlink Same functionality as for DMIC/SSP with different ID. Signed-off-by: Pierre-Louis Bossart hext_link; +} +EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_get_hlink, SND_SOC_SOF_HDA_MLINK); + int hdac_bus_eml_enable_offload(struct hdac_bus *bus, bool alt, int elid, bool enable) { struct hdac_ext2_link *h2link; From af8c32b1a3d55f9b42294aee7e7c7eca85ee3bd2 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:08 -0500 Subject: [PATCH 156/358] ASoC: SOF: Intel: hda-mlink: fix base_ptr computation The base_ptr value needs to be derived from the remap_addr pointer, not the ml_addr. This base_ptr was used only in debug logs that were so far not contributed upstream so the issue was not detected. It needs to be fixed for SoundWire support on LunarLake. Fixes: 17c9b6ec35c0 ("ASoC: SOF: Intel: hda-mlink: add structures to parse ALT links") Signed-off-by: Pierre-Louis Bossart hext_link; u32 base_offset; @@ -136,7 +136,7 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, h2link->elid = FIELD_GET(AZX_REG_ML_LEPTR_ID, h2link->leptr); base_offset = FIELD_GET(AZX_REG_ML_LEPTR_PTR, h2link->leptr); - h2link->base_ptr = hlink->ml_addr + base_offset; + h2link->base_ptr = remap_addr + base_offset; switch (h2link->elid) { case AZX_REG_ML_LEPTR_ID_SDW: @@ -369,7 +369,7 @@ static int hda_ml_alloc_h2link(struct hdac_bus *bus, int index) hlink->bus = bus; hlink->ml_addr = bus->mlcap + AZX_ML_BASE + (AZX_ML_INTERVAL * index); - ret = hdaml_lnk_enum(bus->dev, h2link, hlink->ml_addr, index); + ret = hdaml_lnk_enum(bus->dev, h2link, bus->remap_addr, hlink->ml_addr, index); if (ret < 0) { kfree(h2link); return ret; From 7dfd1ccdb71e5b819c2898b59c58b89f26038292 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:09 -0500 Subject: [PATCH 157/358] ASoC: SOF: Intel: hda-mlink: use 'ml_addr' parameter consistently We mix the use of hlink->ml_addr and the 'ml_addr' parameter. It's the same thing, let's align on using the parameter. Signed-off-by: Pierre-Louis Bossart slcount); /* find IP ID and offsets */ - h2link->leptr = readl(hlink->ml_addr + AZX_REG_ML_LEPTR); + h2link->leptr = readl(ml_addr + AZX_REG_ML_LEPTR); h2link->elid = FIELD_GET(AZX_REG_ML_LEPTR_ID, h2link->leptr); From 9643456ec3c48adfe535c56f659ab705365f4572 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:10 -0500 Subject: [PATCH 158/358] ASoC: SOF: Intel: hda-mlink: initialize instance_offset member We defined the values but never initialized it for SoundWire/SSP, fix this miss. A Fixes: tag is not provided as instance_offset was not used so far, so nothing was really broken. This patch is only required for the SoundWire support in the following patch. Signed-off-by: Pierre-Louis Bossart elid) { case AZX_REG_ML_LEPTR_ID_SDW: + h2link->instance_offset = AZX_REG_SDW_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_SDW_SHIM_OFFSET; h2link->ip_offset = AZX_REG_SDW_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_SDW_VS_SHIM_OFFSET; @@ -154,6 +155,7 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, link_idx, base_offset); break; case AZX_REG_ML_LEPTR_ID_INTEL_SSP: + h2link->instance_offset = AZX_REG_INTEL_SSP_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_INTEL_SSP_SHIM_OFFSET; h2link->ip_offset = AZX_REG_INTEL_SSP_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_INTEL_SSP_VS_SHIM_OFFSET; From ccc2f0c1b6b613cd0014c3dcd465a4b57856b0fe Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:11 -0500 Subject: [PATCH 159/358] ASoC: SOF: Intel: hda-mlink: add helper to program SoundWire PCMSyCM registers These registers enable the HDaudio DMA hardware to split/merge data from different PDIs, possibly on different links. This capability exists for all types of HDaudio extended links, but for now is only required for SoundWire. In the SSP/DMIC case, the IP is programmed by the DSP firmware. Signed-off-by: Pierre-Louis Bossart base_ptr + h2link->shim_offset + + h2link->instance_offset * sublink + + AZX_REG_SDW_SHIM_PCMSyCM(y); + + mutex_lock(&h2link->eml_lock); + + hdaml_shim_map_stream_ch(pcmsycm, 0, hweight32(channel_mask), + stream_id, dir); + + mutex_unlock(&h2link->eml_lock); + + val = readw(pcmsycm); + + dev_dbg(bus->dev, "channel_mask %#x stream_id %d dir %d pcmscm %#x\n", + channel_mask, stream_id, dir, val); + + return 0; +} EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_map_stream_ch, SND_SOC_SOF_HDA_MLINK); + void hda_bus_ml_put_all(struct hdac_bus *bus) { struct hdac_ext_link *hlink; From 3de975862f985f1c9e225a0d13aa3d501373f7c3 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 13:33:13 +0300 Subject: [PATCH 160/358] ASoC: SOF: debug: conditionally bump runtime_pm counter on exceptions When a firmware IPC error happens during a pm_runtime suspend, we ignore the error and suspend anyways. However, the code unconditionally increases the runtime_pm counter. This results in a confusing configuration where the code will suspend, resume but never suspend again due to the use of pm_runtime_get_noresume(). The intent of the counter increase was to prevent entry in D3, but if that transition to D3 is already started it cannot be stopped. In addition, there's no point in that case in trying to prevent anything, the firmware error is handled and the next resume will re-initialize the firmware completely. This patch changes the logic to prevent suspend when the device is pm_runtime active and has a use_count > 0. Signed-off-by: Pierre-Louis Bossart ipc_dump_printed) dev_info(sdev->dev, - "preventing DSP entering D3 state to preserve context\n"); - pm_runtime_get_noresume(sdev->dev); + "Attempting to prevent DSP from entering D3 state to preserve context\n"); + pm_runtime_get_if_in_use(sdev->dev); } /* dump vital information to the logs */ From da0fe8fd515a471d373acc3682bfb5522cca4d55 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 13:33:14 +0300 Subject: [PATCH 161/358] ASoC: SOF: pcm: fix pm_runtime imbalance in error handling When an error occurs, we need to make sure the device can pm_runtime suspend instead of keeping it active. Signed-off-by: Pierre-Louis Bossart tplg_filename_prefix, plat_data->tplg_filename); - if (!tplg_filename) - return -ENOMEM; - - ret = snd_sof_load_topology(component, tplg_filename); - if (ret < 0) { - dev_err(component->dev, "error: failed to load DSP topology %d\n", - ret); - return ret; + if (!tplg_filename) { + ret = -ENOMEM; + goto pm_error; } + ret = snd_sof_load_topology(component, tplg_filename); + if (ret < 0) + dev_err(component->dev, "error: failed to load DSP topology %d\n", + ret); + +pm_error: pm_runtime_mark_last_busy(component->dev); pm_runtime_put_autosuspend(component->dev); From bc424273c74c1565c459c8f2a6ed95caee368d0a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 13:33:15 +0300 Subject: [PATCH 162/358] ASoC: SOF: sof-client-probes: fix pm_runtime imbalance in error handling When an error occurs, we need to make sure the device can pm_runtime suspend instead of keeping it active. Signed-off-by: Pierre-Louis Bossart points_info(cdev, &desc, &num_desc); if (ret < 0) - goto exit; - - pm_runtime_mark_last_busy(dev); - err = pm_runtime_put_autosuspend(dev); - if (err < 0) - dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + goto pm_error; for (i = 0; i < num_desc; i++) { offset = strlen(buf); @@ -241,6 +236,13 @@ static ssize_t sof_probes_dfs_points_read(struct file *file, char __user *to, ret = simple_read_from_buffer(to, count, ppos, buf, strlen(buf)); kfree(desc); + +pm_error: + pm_runtime_mark_last_busy(dev); + err = pm_runtime_put_autosuspend(dev); + if (err < 0) + dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + exit: kfree(buf); return ret; From 4708449eafe60742334606168926985798c9c9b8 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 12 May 2023 14:03:17 +0300 Subject: [PATCH 163/358] ASoC: SOF: ipc3-topology: Make sure that only one cmd is sent in dai_config The commands in sof_ipc_dai_config.flags are encoded as bits: 1 (bit0) - hw_params 2 (bit1) - hw_free 4 (bit2) - pause These are commands, they cannot be combined as one would assume, for example 3 (bit0 | bit1) is invalid. This can happen right at the second start of a stream as at the end of the first stream we set the hw_free command (bit1) and on the second start we would OR on top of it the hw_params (bit0). Fixes: b66bfc3a9810 ("ASoC: SOF: sof-audio: Fix broken early bclk feature for SSP") Signed-off-by: Peter Ujfalusi flags &= ~SOF_DAI_CONFIG_FLAGS_CMD_MASK; config->flags |= flags; - else + } else { config->flags = flags; + } /* only send the IPC if the widget is set up in the DSP */ if (swidget->use_count > 0) { From a93d2afd3f77a7331271a0f25c6a11003db69b3c Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Thu, 11 May 2023 09:25:12 -0700 Subject: [PATCH 164/358] ASoC: mediatek: mt8186: Fix use-after-free in driver remove path When devm runs function in the "remove" path for a device it runs them in the reverse order. That means that if you have parts of your driver that aren't using devm or are using "roll your own" devm w/ devm_add_action_or_reset() you need to keep that in mind. The mt8186 audio driver didn't quite get this right. Specifically, in mt8186_init_clock() it called mt8186_audsys_clk_register() and then went on to call a bunch of other devm function. The caller of mt8186_init_clock() used devm_add_action_or_reset() to call mt8186_deinit_clock() but, because of the intervening devm functions, the order was wrong. Specifically at probe time, the order was: 1. mt8186_audsys_clk_register() 2. afe_priv->clk = devm_kcalloc(...) 3. afe_priv->clk[i] = devm_clk_get(...) At remove time, the order (which should have been 3, 2, 1) was: 1. mt8186_audsys_clk_unregister() 3. Free all of afe_priv->clk[i] 2. Free afe_priv->clk The above seemed to be causing a use-after-free. Luckily, it's easy to fix this by simply using devm more correctly. Let's move the devm_add_action_or_reset() to the right place. In addition to fixing the use-after-free, code inspection shows that this fixes a leak (missing call to mt8186_audsys_clk_unregister()) that would have happened if any of the syscon_regmap_lookup_by_phandle() calls in mt8186_init_clock() had failed. Fixes: 55b423d5623c ("ASoC: mediatek: mt8186: support audio clock control in platform driver") Signed-off-by: Douglas Anderson memif_32bit_supported = 0; afe->memif_size = MT8186_MEMIF_NUM; diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c index 578969ca91c8..5666be6b1bd2 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c @@ -84,6 +84,29 @@ static const struct afe_gate aud_clks[CLK_AUD_NR_CLK] = { GATE_AUD2(CLK_AUD_ETDM_OUT1_BCLK, "aud_etdm_out1_bclk", "top_audio", 24), }; +static void mt8186_audsys_clk_unregister(void *data) +{ + struct mtk_base_afe *afe = data; + struct mt8186_afe_private *afe_priv = afe->platform_priv; + struct clk *clk; + struct clk_lookup *cl; + int i; + + if (!afe_priv) + return; + + for (i = 0; i < CLK_AUD_NR_CLK; i++) { + cl = afe_priv->lookup[i]; + if (!cl) + continue; + + clk = cl->clk; + clk_unregister_gate(clk); + + clkdev_drop(cl); + } +} + int mt8186_audsys_clk_register(struct mtk_base_afe *afe) { struct mt8186_afe_private *afe_priv = afe->platform_priv; @@ -124,27 +147,6 @@ int mt8186_audsys_clk_register(struct mtk_base_afe *afe) afe_priv->lookup[i] = cl; } - return 0; + return devm_add_action_or_reset(afe->dev, mt8186_audsys_clk_unregister, afe); } -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe) -{ - struct mt8186_afe_private *afe_priv = afe->platform_priv; - struct clk *clk; - struct clk_lookup *cl; - int i; - - if (!afe_priv) - return; - - for (i = 0; i < CLK_AUD_NR_CLK; i++) { - cl = afe_priv->lookup[i]; - if (!cl) - continue; - - clk = cl->clk; - clk_unregister_gate(clk); - - clkdev_drop(cl); - } -} diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h index b8d6a06e11e8..897a2914dc19 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h @@ -10,6 +10,5 @@ #define _MT8186_AUDSYS_CLK_H_ int mt8186_audsys_clk_register(struct mtk_base_afe *afe); -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe); #endif From 647b5f5fdcbaba6f6fd8db69508fcbeb1fdfc2a6 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 13 May 2023 11:02:28 +0200 Subject: [PATCH 165/358] ASoC: MAINTAINERS: drop Krzysztof Kozlowski from Samsung audio Remove Krzysztof Kozlowski from maintainer of Samsung SoC Audio drivers and change the status to maintenance (no one is reality being paid for looking at this). Signed-off-by: Krzysztof Kozlowski M: Sylwester Nawrocki L: alsa-devel@alsa-project.org (moderated for non-subscribers) -S: Supported +S: Maintained B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ From 171b53be635ac15d4feafeb33946035649b1ca14 Mon Sep 17 00:00:00 2001 From: Kai Vehmanen Date: Fri, 12 May 2023 13:46:38 +0300 Subject: [PATCH 166/358] ASoC: SOF: pm: save io region state in case of errors in resume MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If there are failures in DSP runtime resume, the device state will not reach active and this makes it impossible e.g. to retrieve a possible DSP panic dump via "exception" debugfs node. If CONFIG_SND_SOC_SOF_DEBUG_ENABLE_DEBUGFS_CACHE=y is set, the data in cache is stale. If debugfs cache is not used, the region simply cannot be read. To allow debugging these scenarios, update the debugfs cache contents in resume error handler. User-space can then later retrieve DSP panic and other state via debugfs (requires SOF debugfs cache to be enabled in build). Reported-by: Curtis Malainey set_up_all_pipelines(sdev, false); if (ret < 0) { dev_err(sdev->dev, "Failed to restore pipeline after resume %d\n", ret); - return ret; + goto setup_fail; } } @@ -178,6 +178,18 @@ static int sof_resume(struct device *dev, bool runtime_resume) dev_err(sdev->dev, "ctx_restore IPC error during resume: %d\n", ret); } +setup_fail: +#if IS_ENABLED(CONFIG_SND_SOC_SOF_DEBUG_ENABLE_DEBUGFS_CACHE) + if (ret < 0) { + /* + * Debugfs cannot be read in runtime suspend, so cache + * the contents upon failure. This allows to capture + * possible DSP coredump information. + */ + sof_cache_debugfs(sdev); + } +#endif + return ret; } From 41c5305cc3d827d2ea686533777a285176ae01a0 Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Fri, 12 May 2023 14:46:30 +0300 Subject: [PATCH 167/358] ASoC: SOF: topology: Fix logic for copying tuples MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Topology could have more instances of the tokens being searched for than the number of sets that need to be copied. Stop copying token after the limit of number of token instances has been reached. This worked before only by chance as we had allocated more size for the tuples array than the number of actual tokens being parsed. Fixes: 7006d20e5e9d ("ASoC: SOF: Introduce IPC3 ops") Signed-off-by: Ranjani Sridharan Date: Fri, 12 May 2023 15:42:37 +0100 Subject: [PATCH 168/358] ASoC: cs35l56: Prevent unbalanced pm_runtime in dsp_work() on SoundWire Flush the SoundWire interrupt handler work instead of cancelling it. When a SoundWire interrupt is triggered the pm_runtime is held until the work has completed. It's therefore unsafe to cancel the work, it must be flushed. Signed-off-by: Simon Trimmer sdw_peripheral) { cs35l56->sdw_irq_no_unmask = true; - cancel_work_sync(&cs35l56->sdw_irq_work); + flush_work(&cs35l56->sdw_irq_work); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_MASK_1, 0); sdw_read_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1, 0xFF); + flush_work(&cs35l56->sdw_irq_work); } ret = cs35l56_mbox_send(cs35l56, CS35L56_MBOX_CMD_SHUTDOWN); From dc60b67d259ea63196dcd0400dd43ba062e2e097 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Fri, 12 May 2023 16:45:03 +0100 Subject: [PATCH 169/358] MAINTAINERS: Remove self from Cirrus Codec drivers I'm leaving Cirrus Logic, and will no longer have access to hardware and documentation necessary to be effective in a maintainership role. Signed-off-by: Lucas Tanure M: David Rhodes -M: Lucas Tanure M: Richard Fitzgerald L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: patches@opensource.cirrus.com From 2ef0785b30bd6549ddbc124979f1b6596e065ae2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 17 Apr 2023 23:04:11 +0200 Subject: [PATCH 170/358] drm/exynos: fix g2d_open/close helper function definitions The empty stub functions are defined as global functions, which causes a warning because of missing prototypes: drivers/gpu/drm/exynos/exynos_drm_g2d.h:37:5: error: no previous prototype for 'g2d_open' drivers/gpu/drm/exynos/exynos_drm_g2d.h:42:5: error: no previous prototype for 'g2d_close' Mark them as 'static inline' to avoid the warning and to make them behave as intended. Fixes: eb4d9796fa34 ("drm/exynos: g2d: Convert to driver component API") Signed-off-by: Arnd Bergmann Reviewed-by: Andi Shyti Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_g2d.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.h b/drivers/gpu/drm/exynos/exynos_drm_g2d.h index 74ea3c26dead..1a5ae781b56c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.h +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.h @@ -34,11 +34,11 @@ static inline int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data, return -ENODEV; } -int g2d_open(struct drm_device *drm_dev, struct drm_file *file) +static inline int g2d_open(struct drm_device *drm_dev, struct drm_file *file) { return 0; } -void g2d_close(struct drm_device *drm_dev, struct drm_file *file) +static inline void g2d_close(struct drm_device *drm_dev, struct drm_file *file) { } #endif From 35a4b8ce4ac00e940b46b1034916ccb22ce9bdef Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 25 Apr 2023 12:28:29 +0530 Subject: [PATCH 171/358] powerpc/bpf: populate extable entries only during the last pass Since commit 85e031154c7c ("powerpc/bpf: Perform complete extra passes to update addresses"), two additional passes are performed to avoid space and CPU time wastage on powerpc. But these extra passes led to WARN_ON_ONCE() hits in bpf_add_extable_entry() as extable entries are populated again, during the extra pass, without resetting the index. Fix it by resetting entry index before repopulating extable entries, if and when there is an additional pass. Fixes: 85e031154c7c ("powerpc/bpf: Perform complete extra passes to update addresses") Cc: stable@vger.kernel.org # v6.3+ Signed-off-by: Hari Bathini Reviewed-by: Naveen N. Rao Signed-off-by: Michael Ellerman Link: https://msgid.link/20230425065829.18189-1-hbathini@linux.ibm.com --- arch/powerpc/net/bpf_jit_comp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index e93aefcfb83f..37043dfc1add 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) bpf_hdr = jit_data->header; proglen = jit_data->proglen; extra_pass = true; + /* During extra pass, ensure index is reset before repopulating extable entries */ + cgctx.exentry_idx = 0; goto skip_init_ctx; } From c83b49383b595be50647f0c764a48c78b5f3c4f8 Mon Sep 17 00:00:00 2001 From: Dong Chenchen Date: Thu, 11 May 2023 20:54:40 +0800 Subject: [PATCH 172/358] net: nsh: Use correct mac_offset to unwind gso skb in nsh_gso_segment() As the call trace shows, skb_panic was caused by wrong skb->mac_header in nsh_gso_segment(): invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 3 PID: 2737 Comm: syz Not tainted 6.3.0-next-20230505 #1 RIP: 0010:skb_panic+0xda/0xe0 call Trace: skb_push+0x91/0xa0 nsh_gso_segment+0x4f3/0x570 skb_mac_gso_segment+0x19e/0x270 __skb_gso_segment+0x1e8/0x3c0 validate_xmit_skb+0x452/0x890 validate_xmit_skb_list+0x99/0xd0 sch_direct_xmit+0x294/0x7c0 __dev_queue_xmit+0x16f0/0x1d70 packet_xmit+0x185/0x210 packet_snd+0xc15/0x1170 packet_sendmsg+0x7b/0xa0 sock_sendmsg+0x14f/0x160 The root cause is: nsh_gso_segment() use skb->network_header - nhoff to reset mac_header in skb_gso_error_unwind() if inner-layer protocol gso fails. However, skb->network_header may be reset by inner-layer protocol gso function e.g. mpls_gso_segment. skb->mac_header reset by the inaccurate network_header will be larger than skb headroom. nsh_gso_segment nhoff = skb->network_header - skb->mac_header; __skb_pull(skb,nsh_len) skb_mac_gso_segment mpls_gso_segment skb_reset_network_header(skb);//skb->network_header+=nsh_len return -EINVAL; skb_gso_error_unwind skb_push(skb, nsh_len); skb->mac_header = skb->network_header - nhoff; // skb->mac_header > skb->headroom, cause skb_push panic Use correct mac_offset to restore mac_header and get rid of nhoff. Fixes: c411ed854584 ("nsh: add GSO support") Reported-by: syzbot+632b5d9964208bfef8c0@syzkaller.appspotmail.com Suggested-by: Eric Dumazet Signed-off-by: Dong Chenchen Signed-off-by: David S. Miller --- net/nsh/nsh.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index e9ca007718b7..0f23e5e8e03e 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -77,13 +77,12 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; unsigned int nsh_len, mac_len; __be16 proto; - int nhoff; skb_reset_network_header(skb); - nhoff = skb->network_header - skb->mac_header; mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -108,15 +107,14 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, segs = skb_mac_gso_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, htons(ETH_P_NSH), nsh_len, - skb->network_header - nhoff, - mac_len); + mac_offset, mac_len); goto out; } for (skb = segs; skb; skb = skb->next) { skb->protocol = htons(ETH_P_NSH); __skb_push(skb, nsh_len); - skb_set_mac_header(skb, -nhoff); + skb->mac_header = mac_offset; skb->network_header = skb->mac_header + mac_len; skb->mac_len = mac_len; } From 5896f2d363d5cfb7510856c90d5e0ed934a1d340 Mon Sep 17 00:00:00 2001 From: Suraj Kandpal Date: Fri, 5 May 2023 09:45:12 +0530 Subject: [PATCH 173/358] drm/i915/hdcp: Check if media_gt exists Check if media_gt exists if we are using gsc cs --v2 -correct typo [Ankit] -assign gsc variable if gt exists [Ankit] --v3 -declare gsc and gt variables in if block [Ankit] --v4 -add fixes tag [Ankit] Fixes: 883631771038 ("drm/i915/mtl: Add HDCP GSC interface") Cc: Tomas Winkler Cc: Rodrigo Vivi Cc: Uma Shankar Cc: Anshuman Gupta Cc: Ankit Nautiyal Signed-off-by: Suraj Kandpal Reviewed-by: Gustavo Sousa Reviewed-by: Ankit Nautiyal Signed-off-by: Animesh Manna Link: https://patchwork.freedesktop.org/patch/msgid/20230505041512.585486-1-suraj.kandpal@intel.com (cherry picked from commit 6986f05b557bf1efea5bac8dbdffb7ee89d0cf77) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/display/intel_hdcp.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 650232c4892b..b183efab04a1 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -204,8 +204,6 @@ bool intel_hdcp2_capable(struct intel_connector *connector) struct intel_digital_port *dig_port = intel_attached_dig_port(connector); struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_hdcp *hdcp = &connector->hdcp; - struct intel_gt *gt = dev_priv->media_gt; - struct intel_gsc_uc *gsc = >->uc.gsc; bool capable = false; /* I915 support for HDCP2.2 */ @@ -213,9 +211,13 @@ bool intel_hdcp2_capable(struct intel_connector *connector) return false; /* If MTL+ make sure gsc is loaded and proxy is setup */ - if (intel_hdcp_gsc_cs_required(dev_priv)) - if (!intel_uc_fw_is_running(&gsc->fw)) + if (intel_hdcp_gsc_cs_required(dev_priv)) { + struct intel_gt *gt = dev_priv->media_gt; + struct intel_gsc_uc *gsc = gt ? >->uc.gsc : NULL; + + if (!gsc || !intel_uc_fw_is_running(&gsc->fw)) return false; + } /* MEI/GSC interface is solid depending on which is used */ mutex_lock(&dev_priv->display.hdcp.comp_mutex); From 6ead9c98cafcbc6992cf35f0ca393df2c03e3316 Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Fri, 12 May 2023 08:38:43 -0500 Subject: [PATCH 174/358] net: fec: remove the xdp_return_frame when lack of tx BDs In the implementation, the sent_frame count does not increment when transmit errors occur. Therefore, bq_xmit_all() will take care of returning the XDP frames. Fixes: 26312c685ae0 ("net: fec: correct the counting of XDP sent frames") Signed-off-by: Shenwei Wang Reviewed-by: Horatiu Vultur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 241df41d500f..577d94821b3e 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3798,7 +3798,6 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free < MAX_SKB_FRAGS + 1) { netdev_err(fep->netdev, "NOT enough BD for SG!\n"); - xdp_return_frame(frame); return NETDEV_TX_BUSY; } From 5306623a9826aa7d63b32c6a3803c798a765474d Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Fri, 12 May 2023 11:18:12 -0400 Subject: [PATCH 175/358] virtio_net: Fix error unwinding of XDP initialization When initializing XDP in virtnet_open(), some rq xdp initialization may hit an error causing net device open failed. However, previous rqs have already initialized XDP and enabled NAPI, which is not the expected behavior. Need to roll back the previous rq initialization to avoid leaks in error unwinding of init code. Also extract helper functions of disable and enable queue pairs. Use newly introduced disable helper function in error unwinding and virtnet_close. Use enable helper function in virtnet_open. Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info") Signed-off-by: Feng Liu Reviewed-by: Jiri Pirko Reviewed-by: William Tu Acked-by: Michael S. Tsirkin Acked-by: Jason Wang Reviewed-by: Xuan Zhuo Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 61 +++++++++++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 17 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a12ae26db0e2..56ca1d270304 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1868,6 +1868,38 @@ static int virtnet_poll(struct napi_struct *napi, int budget) return received; } +static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + virtnet_napi_tx_disable(&vi->sq[qp_index].napi); + napi_disable(&vi->rq[qp_index].napi); + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); +} + +static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + struct net_device *dev = vi->dev; + int err; + + err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index, + vi->rq[qp_index].napi.napi_id); + if (err < 0) + return err; + + err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err < 0) + goto err_xdp_reg_mem_model; + + virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); + virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); + + return 0; + +err_xdp_reg_mem_model: + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); + return err; +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -1881,22 +1913,20 @@ static int virtnet_open(struct net_device *dev) if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); - err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id); + err = virtnet_enable_queue_pair(vi, i); if (err < 0) - return err; - - err = xdp_rxq_info_reg_mem_model(&vi->rq[i].xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL); - if (err < 0) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - return err; - } - - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); - virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi); + goto err_enable_qp; } return 0; + +err_enable_qp: + disable_delayed_refill(vi); + cancel_delayed_work_sync(&vi->refill); + + for (i--; i >= 0; i--) + virtnet_disable_queue_pair(vi, i); + return err; } static int virtnet_poll_tx(struct napi_struct *napi, int budget) @@ -2305,11 +2335,8 @@ static int virtnet_close(struct net_device *dev) /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill); - for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_tx_disable(&vi->sq[i].napi); - napi_disable(&vi->rq[i].napi); - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - } + for (i = 0; i < vi->max_queue_pairs; i++) + virtnet_disable_queue_pair(vi, i); return 0; } From b48a18644046c9bc0667493a147dfa01e8241eab Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Sat, 13 May 2023 09:57:27 +0100 Subject: [PATCH 176/358] net: mdio: i2c: fix rollball accessors Commit 87e3bee0f247 ("net: mdio: i2c: Separate C22 and C45 transactions") separated the non-rollball bus accessors, but left the rollball accessors as is. As rollball accessors are clause 45, this results in the rollball protocol being completely non-functional. Fix this. Fixes: 87e3bee0f247 ("net: mdio: i2c: Separate C22 and C45 transactions") Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/mdio/mdio-i2c.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/net/mdio/mdio-i2c.c b/drivers/net/mdio/mdio-i2c.c index 1e0c206d0f2e..da2001ea1f99 100644 --- a/drivers/net/mdio/mdio-i2c.c +++ b/drivers/net/mdio/mdio-i2c.c @@ -291,7 +291,8 @@ static int i2c_rollball_mii_cmd(struct mii_bus *bus, int bus_addr, u8 cmd, return i2c_transfer_rollball(i2c, msgs, ARRAY_SIZE(msgs)); } -static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) +static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int devad, + int reg) { u8 buf[4], res[6]; int bus_addr, ret; @@ -302,7 +303,7 @@ static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) return 0xffff; buf[0] = ROLLBALL_DATA_ADDR; - buf[1] = (reg >> 16) & 0x1f; + buf[1] = devad; buf[2] = (reg >> 8) & 0xff; buf[3] = reg & 0xff; @@ -322,8 +323,8 @@ static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) return val; } -static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int reg, - u16 val) +static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int devad, + int reg, u16 val) { int bus_addr, ret; u8 buf[6]; @@ -333,7 +334,7 @@ static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int reg, return 0; buf[0] = ROLLBALL_DATA_ADDR; - buf[1] = (reg >> 16) & 0x1f; + buf[1] = devad; buf[2] = (reg >> 8) & 0xff; buf[3] = reg & 0xff; buf[4] = val >> 8; @@ -405,8 +406,8 @@ struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c, return ERR_PTR(ret); } - mii->read = i2c_mii_read_rollball; - mii->write = i2c_mii_write_rollball; + mii->read_c45 = i2c_mii_read_rollball; + mii->write_c45 = i2c_mii_write_rollball; break; default: mii->read = i2c_mii_read_default_c22; From 3ae6d66b605be604644d4bb5708a7ffd9cf1abe8 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 14 May 2023 15:52:27 -0400 Subject: [PATCH 177/358] tipc: add tipc_bearer_min_mtu to calculate min mtu As different media may requires different min mtu, and even the same media with different net family requires different min mtu, add tipc_bearer_min_mtu() to calculate min mtu accordingly. This API will be used to check the new mtu when doing the link mtu negotiation in the next patch. Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/bearer.c | 13 +++++++++++++ net/tipc/bearer.h | 3 +++ net/tipc/udp_media.c | 5 +++-- 3 files changed, 19 insertions(+), 2 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 35cac7733fd3..0e9a29e1536b 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -541,6 +541,19 @@ int tipc_bearer_mtu(struct net *net, u32 bearer_id) return mtu; } +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id) +{ + int mtu = TIPC_MIN_BEARER_MTU; + struct tipc_bearer *b; + + rcu_read_lock(); + b = bearer_get(net, bearer_id); + if (b) + mtu += b->encap_hlen; + rcu_read_unlock(); + return mtu; +} + /* tipc_bearer_xmit_skb - sends buffer to destination over bearer */ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 490ad6e5f7a3..bd0cc5c287ef 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -146,6 +146,7 @@ struct tipc_media { * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer + * @encap_hlen: encap headers length * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * @@ -170,6 +171,7 @@ struct tipc_bearer { u32 identity; struct tipc_discoverer *disc; char net_plane; + u16 encap_hlen; unsigned long up; refcount_t refcnt; }; @@ -232,6 +234,7 @@ int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index c2bb818704c8..0a85244fd618 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -738,8 +738,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = local.ipv4.s_addr; udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; - if (tipc_mtu_bad(dev, sizeof(struct iphdr) + - sizeof(struct udphdr))) { + b->encap_hlen = sizeof(struct iphdr) + sizeof(struct udphdr); + if (tipc_mtu_bad(dev, b->encap_hlen)) { err = -EINVAL; goto err; } @@ -760,6 +760,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, else udp_conf.local_ip6 = local.ipv6; ub->ifindex = dev->ifindex; + b->encap_hlen = sizeof(struct ipv6hdr) + sizeof(struct udphdr); b->mtu = 1280; #endif } else { From 56077b56cd3fb78e1c8619e29581ba25a5c55e86 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 14 May 2023 15:52:28 -0400 Subject: [PATCH 178/358] tipc: do not update mtu if msg_max is too small in mtu negotiation When doing link mtu negotiation, a malicious peer may send Activate msg with a very small mtu, e.g. 4 in Shuang's testing, without checking for the minimum mtu, l->mtu will be set to 4 in tipc_link_proto_rcv(), then n->links[bearer_id].mtu is set to 4294967228, which is a overflow of '4 - INT_H_SIZE - EMSG_OVERHEAD' in tipc_link_mss(). With tipc_link.mtu = 4, tipc_link_xmit() kept printing the warning: tipc: Too large msg, purging xmit list 1 5 0 40 4! tipc: Too large msg, purging xmit list 1 15 0 60 4! And with tipc_link_entry.mtu 4294967228, a huge skb was allocated in named_distribute(), and when purging it in tipc_link_xmit(), a crash was even caused: general protection fault, probably for non-canonical address 0x2100001011000dd: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 0 Comm: swapper/0 Kdump: loaded Not tainted 6.3.0.neta #19 RIP: 0010:kfree_skb_list_reason+0x7e/0x1f0 Call Trace: skb_release_data+0xf9/0x1d0 kfree_skb_reason+0x40/0x100 tipc_link_xmit+0x57a/0x740 [tipc] tipc_node_xmit+0x16c/0x5c0 [tipc] tipc_named_node_up+0x27f/0x2c0 [tipc] tipc_node_write_unlock+0x149/0x170 [tipc] tipc_rcv+0x608/0x740 [tipc] tipc_udp_recv+0xdc/0x1f0 [tipc] udp_queue_rcv_one_skb+0x33e/0x620 udp_unicast_rcv_skb.isra.72+0x75/0x90 __udp4_lib_rcv+0x56d/0xc20 ip_protocol_deliver_rcu+0x100/0x2d0 This patch fixes it by checking the new mtu against tipc_bearer_min_mtu(), and not updating mtu if it is too small. Fixes: ed193ece2649 ("tipc: simplify link mtu negotiation") Reported-by: Shuang Li Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index b3ce24823f50..2eff1c7949cb 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2200,7 +2200,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; - u32 dlen = msg_data_sz(hdr), glen = 0; + u32 dlen = msg_data_sz(hdr), glen = 0, msg_max; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); @@ -2239,6 +2239,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG: + msg_max = msg_max_pkt(hdr); + if (msg_max < tipc_bearer_min_mtu(l->net, l->bearer_id)) + break; /* Complete own link name with peer's interface name */ if_name = strrchr(l->name, ':') + 1; if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) @@ -2283,8 +2286,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, l->peer_session = msg_session(hdr); l->in_session = true; l->peer_bearer_id = msg_bearer_id(hdr); - if (l->mtu > msg_max_pkt(hdr)) - l->mtu = msg_max_pkt(hdr); + if (l->mtu > msg_max) + l->mtu = msg_max; break; case STATE_MSG: From 35a089b5d793d2bfd2cc7cfa6104545184de2ce7 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 14 May 2023 15:52:29 -0400 Subject: [PATCH 179/358] tipc: check the bearer min mtu properly when setting it by netlink Checking the bearer min mtu with tipc_udp_mtu_bad() only works for IPv4 UDP bearer, and IPv6 UDP bearer has a different value for the min mtu. This patch checks with encap_hlen + TIPC_MIN_BEARER_MTU for min mtu, which works for both IPv4 and IPv6 UDP bearer. Note that tipc_udp_mtu_bad() is still used to check media min mtu in __tipc_nl_media_set(), as m->mtu currently is only used by the IPv4 UDP bearer as its default mtu value. Fixes: 682cd3cf946b ("tipc: confgiure and apply UDP bearer MTU on running links") Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/bearer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 0e9a29e1536b..53881406e200 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1151,8 +1151,8 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP - if (tipc_udp_mtu_bad(nla_get_u32 - (props[TIPC_NLA_PROP_MTU]))) { + if (nla_get_u32(props[TIPC_NLA_PROP_MTU]) < + b->encap_hlen + TIPC_MIN_BEARER_MTU) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; From df0acdc59b094cdaef19b1c8d83c9721082bab7b Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Sat, 13 May 2023 22:03:45 +0100 Subject: [PATCH 180/358] net: phylink: fix ksettings_set() ethtool call While testing a Fiberstore SFP-10G-T module (which uses 10GBASE-R with rate adaption) in a Clearfog platform (which can't do that) it was found that the PHYs advertisement was not limited according to the hosts capabilities when using ethtool to change it. Fix this by ensuring that we mask the advertisement with the computed support mask as the very first thing we do. Fixes: cbc1bb1e4689 ("net: phylink: simplify phy case for ksettings_set method") Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a4111f1be375..e237949deee6 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -2225,6 +2225,10 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, ASSERT_RTNL(); + /* Mask out unsupported advertisements */ + linkmode_and(config.advertising, kset->link_modes.advertising, + pl->supported); + if (pl->phydev) { /* We can rely on phylib for this update; we also do not need * to update the pl->link_config settings: @@ -2249,10 +2253,6 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, config = pl->link_config; - /* Mask out unsupported advertisements */ - linkmode_and(config.advertising, kset->link_modes.advertising, - pl->supported); - /* FIXME: should we reject autoneg if phy/mac does not support it? */ switch (kset->base.autoneg) { case AUTONEG_DISABLE: From be3c215342956313845308e0e631341e62370a2b Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Mon, 15 May 2023 13:44:03 +0300 Subject: [PATCH 181/358] ASoC: SOF: Separate the tokens for input and output pin index MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using the same token ID for both input and output format pin index results in collisions and incorrect pin index getting parsed from topology. Signed-off-by: Ranjani Sridharan Date: Mon, 15 May 2023 11:52:00 +0300 Subject: [PATCH 182/358] ASoC: SOF: topology: Fix tuples array allocation The memory allocated for the tuples array assumes that there's 1 instance of all tokens already. So for those tokens that have multiple instances in topology, we need to exclude the initial instance that has already been accounted for. Fixes: 4fdef47a44d6 ("ASoC: SOF: ipc4-topology: Add new tokens for input/output pin format count") Signed-off-by: Ranjani Sridharan 1) { struct snd_sof_tuple *new_tuples; - num_tuples += token_list[object_token_list[i]].count * num_sets; + num_tuples += token_list[object_token_list[i]].count * (num_sets - 1); new_tuples = krealloc(swidget->tuples, sizeof(*new_tuples) * num_tuples, GFP_KERNEL); if (!new_tuples) { From 21a3f3328972bdb774c62b301a715b5cebf03fa2 Mon Sep 17 00:00:00 2001 From: Azeem Shaikh Date: Mon, 15 May 2023 02:40:44 +0000 Subject: [PATCH 183/358] NFSD: Remove open coding of string copy Instead of open coding a __dynamic_array(), use the __string() and __assign_str() helper macros that exist for this kind of use case. Part of an effort to remove deprecated strlcpy() [1] completely from the kernel[2]. [1] https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy [2] https://github.com/KSPP/linux/issues/89 Fixes: 3c92fba557c6 ("NFSD: Enhance the nfsd_cb_setup tracepoint") Signed-off-by: Azeem Shaikh Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/trace.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 4183819ea082..72a906a053dc 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -1365,19 +1365,19 @@ TRACE_EVENT(nfsd_cb_setup, __field(u32, cl_id) __field(unsigned long, authflavor) __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) - __array(unsigned char, netid, 8) + __string(netid, netid) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; - strlcpy(__entry->netid, netid, sizeof(__entry->netid)); + __assign_str(netid, netid); __entry->authflavor = authflavor; __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x proto=%s flavor=%s", __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, - __entry->netid, show_nfsd_authflavor(__entry->authflavor)) + __get_str(netid), show_nfsd_authflavor(__entry->authflavor)) ); TRACE_EVENT(nfsd_cb_setup_err, From 8703dd6b238da0ec6c276e53836f8200983d3d9b Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 20 Apr 2023 13:31:29 +0200 Subject: [PATCH 184/358] s390/crypto: use vector instructions only if available for ChaCha20 Commit 349d03ffd5f6 ("crypto: s390 - add crypto library interface for ChaCha20") added a library interface to the s390 specific ChaCha20 implementation. However no check was added to verify if the required facilities are installed before branching into the assembler code. If compiled into the kernel, this will lead to the following crash, if vector instructions are not available: data exception: 0007 ilc:3 [#1] SMP Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc7+ #11 Hardware name: IBM 3931 A01 704 (KVM/Linux) Krnl PSW : 0704e00180000000 000000001857277a (chacha20_vx+0x32/0x818) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 RI:0 EA:3 Krnl GPRS: 0000037f0000000a ffffffffffffff60 000000008184b000 0000000019f5c8e6 0000000000000109 0000037fffb13c58 0000037fffb13c78 0000000019bb1780 0000037fffb13c58 0000000019f5c8e6 000000008184b000 0000000000000109 00000000802d8000 0000000000000109 0000000018571ebc 0000037fffb13718 Krnl Code: 000000001857276a: c07000b1f80b larl %r7,0000000019bb1780 0000000018572770: a708000a lhi %r0,10 #0000000018572774: e78950000c36 vlm %v24,%v25,0(%r5),0 >000000001857277a: e7a060000806 vl %v26,0(%r6),0 0000000018572780: e7bf70004c36 vlm %v27,%v31,0(%r7),4 0000000018572786: e70b00000456 vlr %v0,%v27 000000001857278c: e71800000456 vlr %v1,%v24 0000000018572792: e74b00000456 vlr %v4,%v27 Call Trace: [<000000001857277a>] chacha20_vx+0x32/0x818 Last Breaking-Event-Address: [<0000000018571eb6>] chacha20_crypt_s390.constprop.0+0x6e/0xd8 ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b Fix this by adding a missing MACHINE_HAS_VX check. Fixes: 349d03ffd5f6 ("crypto: s390 - add crypto library interface for ChaCha20") Reported-by: Marc Hartmayer Cc: # 5.19+ Reviewed-by: Harald Freudenberger [agordeev@linux.ibm.com: remove duplicates in commit message] Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- arch/s390/crypto/chacha-glue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c index 7752bd314558..5fae187f947a 100644 --- a/arch/s390/crypto/chacha-glue.c +++ b/arch/s390/crypto/chacha-glue.c @@ -82,7 +82,7 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, * it cannot handle a block of data or less, but otherwise * it can handle data of arbitrary size */ - if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20) + if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !MACHINE_HAS_VX) chacha_crypt_generic(state, dst, src, bytes, nrounds); else chacha20_crypt_s390(state, dst, src, bytes, From 844cf829e5f33e00b279230470c8c93b58b8c16f Mon Sep 17 00:00:00 2001 From: Holger Dengler Date: Thu, 20 Apr 2023 14:34:10 +0200 Subject: [PATCH 185/358] s390/pkey: zeroize key blobs Key blobs for the IOCTLs PKEY_KBLOB2PROTK[23] may contain clear key material. Zeroize the copies of these keys in kernel memory after creating the protected key. Reviewed-by: Harald Freudenberger Signed-off-by: Holger Dengler Signed-off-by: Alexander Gordeev --- drivers/s390/crypto/pkey_api.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 5a05d1cdfec2..a8def50c149b 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -1293,6 +1293,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return PTR_ERR(kkey); rc = pkey_keyblob2pkey(kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey()=%d\n", __func__, rc); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1426,6 +1427,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1552,6 +1554,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, protkey, &protkeylen); DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) { kfree(protkey); From 124acbe275040809abfa5fbe6e25790a53d5a161 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 4 May 2023 13:40:46 +0200 Subject: [PATCH 186/358] s390/defconfigs: set CONFIG_INIT_STACK_NONE=y Set CONFIG_INIT_STACK_NONE=y in defconfigs to avoid the extra overhead of initializing all stack variables by default. Users who want to have that must change the configuration on their own. Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- arch/s390/configs/debug_defconfig | 1 + arch/s390/configs/defconfig | 1 + arch/s390/configs/zfcpdump_defconfig | 1 + 3 files changed, 3 insertions(+) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 4ccf66d29fc2..1b68156f2040 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -703,6 +703,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 693297a2e897..b0643283bbdd 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -686,6 +686,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 33a232bb68af..6f68b39817ef 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -67,6 +67,7 @@ CONFIG_ZFCP=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" +CONFIG_INIT_STACK_NONE=y # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y From b1b0d5aec1cf9f9a900a14964f869c68688d923e Mon Sep 17 00:00:00 2001 From: Vineeth Vijayan Date: Tue, 2 May 2023 11:12:42 +0200 Subject: [PATCH 187/358] s390/cio: include subchannels without devices also for evaluation Currently when the new channel-path is enabled, we do evaluation only on the subchannels with a device connected on it. This is because, in the past, if the device in the subchannel is not working or not available, we used to unregister the subchannels. But, from the 'commit 2297791c92d0 ("s390/cio: dont unregister subchannel from child-drivers")' we allow subchannels with or without an active device connected on it. So, when we do the io_subchannel_verify, make sure that, we are evaluating the subchannels without any device too. Fixes: 2297791c92d0 ("s390/cio: dont unregister subchannel from child-drivers") Reported-by: Boris Fiuczynski Signed-off-by: Vineeth Vijayan Reviewed-by: Peter Oberparleiter Signed-off-by: Alexander Gordeev --- drivers/s390/cio/device.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 8eb089b99cde..d5c43e9b5128 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1111,6 +1111,8 @@ static void io_subchannel_verify(struct subchannel *sch) cdev = sch_get_cdev(sch); if (cdev) dev_fsm_event(cdev, DEV_EVENT_VERIFY); + else + css_schedule_eval(sch->schid); } static void io_subchannel_terminate_path(struct subchannel *sch, u8 mask) From a33239be2d38ff5a44427db1707c08787508d34a Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Thu, 4 May 2023 16:21:48 +0200 Subject: [PATCH 188/358] s390/topology: honour nr_cpu_ids when adding CPUs When SMT thread CPUs are added to CPU masks the nr_cpu_ids limit is not checked and could be exceeded. This leads to a warning for example if CONFIG_DEBUG_PER_CPU_MAPS is set and the command line parameter nr_cpus is set to 1. Reviewed-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- arch/s390/kernel/topology.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 9fd19530c9a5..68adf1de8888 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -95,7 +95,7 @@ out: static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) { static cpumask_t mask; - int i; + unsigned int max_cpu; cpumask_clear(&mask); if (!cpumask_test_cpu(cpu, &cpu_setup_mask)) @@ -104,9 +104,10 @@ static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) if (topology_mode != TOPOLOGY_MODE_HW) goto out; cpu -= cpu % (smp_cpu_mtid + 1); - for (i = 0; i <= smp_cpu_mtid; i++) { - if (cpumask_test_cpu(cpu + i, &cpu_setup_mask)) - cpumask_set_cpu(cpu + i, &mask); + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + if (cpumask_test_cpu(cpu, &cpu_setup_mask)) + cpumask_set_cpu(cpu, &mask); } out: cpumask_copy(dst, &mask); @@ -123,25 +124,26 @@ static void add_cpus_to_mask(struct topology_core *tl_core, unsigned int core; for_each_set_bit(core, &tl_core->mask, TOPOLOGY_CORE_BITS) { - unsigned int rcore; - int lcpu, i; + unsigned int max_cpu, rcore; + int cpu; rcore = TOPOLOGY_CORE_BITS - 1 - core + tl_core->origin; - lcpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); - if (lcpu < 0) + cpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); + if (cpu < 0) continue; - for (i = 0; i <= smp_cpu_mtid; i++) { - topo = &cpu_topology[lcpu + i]; + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + topo = &cpu_topology[cpu]; topo->drawer_id = drawer->id; topo->book_id = book->id; topo->socket_id = socket->id; topo->core_id = rcore; - topo->thread_id = lcpu + i; + topo->thread_id = cpu; topo->dedicated = tl_core->d; - cpumask_set_cpu(lcpu + i, &drawer->mask); - cpumask_set_cpu(lcpu + i, &book->mask); - cpumask_set_cpu(lcpu + i, &socket->mask); - smp_cpu_set_polarization(lcpu + i, tl_core->pp); + cpumask_set_cpu(cpu, &drawer->mask); + cpumask_set_cpu(cpu, &book->mask); + cpumask_set_cpu(cpu, &socket->mask); + smp_cpu_set_polarization(cpu, tl_core->pp); } } } From 2facd5d3980f3a26c04fe6ec8689a1d019a5812c Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Sun, 7 May 2023 18:09:02 +0200 Subject: [PATCH 189/358] s390/ipl: fix IPIB virtual vs physical address confusion The pointer to IPL Parameter Information Block is stored in the absolute lowcore for later use by dump tools. That pointer is a virtual address, though it should be physical instead. Note, this does not fix a real issue, since virtual and physical addresses are currently the same. Suggested-by: Heiko Carstens Reviewed-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- arch/s390/kernel/ipl.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 43de939b7af1..f44f70de9661 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1935,14 +1935,13 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { - unsigned long ipib = (unsigned long) reipl_block_actual; struct lowcore *abs_lc; unsigned int csum; csum = (__force unsigned int) csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); abs_lc = get_abs_lowcore(); - abs_lc->ipib = ipib; + abs_lc->ipib = __pa(reipl_block_actual); abs_lc->ipib_checksum = csum; put_abs_lowcore(abs_lc); dump_run(trigger); From 71a485624c4cbb144169852d7bb8ca8c0667d7a3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rub=C3=A9n=20G=C3=B3mez?= Date: Mon, 8 May 2023 18:03:07 +0000 Subject: [PATCH 190/358] ACPI: resource: Add IRQ override quirk for LG UltraPC 17U70P MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add an ACPI IRQ override quirk for LG UltraPC 17U70P to address the internal keyboard problem on it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=213031 Link: https://bugzilla.kernel.org/show_bug.cgi?id=216983 Signed-off-by: Rubén Gómez Agudo [ rjw: Subject, changelog, white space damage fixes ] Signed-off-by: Rafael J. Wysocki --- drivers/acpi/resource.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index e8492b3a393a..0800a9d77558 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -516,6 +516,17 @@ static const struct dmi_system_id maingear_laptop[] = { { } }; +static const struct dmi_system_id lg_laptop[] = { + { + .ident = "LG Electronics 17U70P", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), + DMI_MATCH(DMI_BOARD_NAME, "17U70P"), + }, + }, + { } +}; + struct irq_override_cmp { const struct dmi_system_id *system; unsigned char irq; @@ -532,6 +543,7 @@ static const struct irq_override_cmp override_table[] = { { lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, { tongfang_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, { maingear_laptop, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, + { lg_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, }; static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, From 8133a3f0aa66ed3d7d974c89ac6aca6fe6cec837 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 15 May 2023 22:40:08 +1000 Subject: [PATCH 191/358] powerpc/crypto: Fix aes-gcm-p10 build when VSX=n MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When VSX is disabled, eg. microwatt_defconfig, the build fails with: In function ‘enable_kernel_vsx’, inlined from ‘vsx_begin’ at arch/powerpc/crypto/aes-gcm-p10-glue.c:68:2, inlined from ‘p10_aes_gcm_crypt.constprop’ at arch/powerpc/crypto/aes-gcm-p10-glue.c:244:2: ... arch/powerpc/include/asm/switch_to.h:86:9: note: in expansion of macro ‘BUILD_BUG’ 86 | BUILD_BUG(); | ^~~~~~~~~ Fix it by making the p10-aes-gcm code depend on VSX. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230515124731.122962-1-mpe%40ellerman.id.au --- arch/powerpc/crypto/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig index 7113f9355165..ad1872518992 100644 --- a/arch/powerpc/crypto/Kconfig +++ b/arch/powerpc/crypto/Kconfig @@ -96,7 +96,7 @@ config CRYPTO_AES_PPC_SPE config CRYPTO_AES_GCM_P10 tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)" - depends on PPC64 && CPU_LITTLE_ENDIAN + depends on PPC64 && CPU_LITTLE_ENDIAN && VSX select CRYPTO_LIB_AES select CRYPTO_ALGAPI select CRYPTO_AEAD From 73c7f8246539da12c76bb731a2fe7389ae55eae8 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Thu, 11 May 2023 14:53:12 +0200 Subject: [PATCH 192/358] cpufreq: ACPI: Prevent a warning when another frequency driver is loaded The recent change to use platform devices to load ACPI PPC and PCC drivers caused that a misleading warning is reported when a respective module cannot be loaded because another CPU frequency driver is already registered: kernel: acpi-cpufreq: probe of acpi-cpufreq failed with error -17 Address it by changing the return code in acpi-cpufreq and pcc-cpufreq for this case from -EEXIST to -ENODEV which silences the warning in call_driver_probe(). The change has also a benefit for users of init_module() as this return code is propagated out from the syscall. The previous -EEXIST code made the callers, such as kmod, wrongly believe that the module was already loaded instead of that it failed to load. Fixes: 691a63712347 ("ACPI: cpufreq: Use platform devices to load ACPI PPC and PCC drivers") Reported-by: Kevin Locke Link: https://lore.kernel.org/lkml/ZFreh8SDMX67EaB6@kevinlocke.name/ Signed-off-by: Petr Pavlu Tested-by: Kevin Locke Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/acpi-cpufreq.c | 2 +- drivers/cpufreq/pcc-cpufreq.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 29904395e95f..b2f05d27167e 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -975,7 +975,7 @@ static int __init acpi_cpufreq_probe(struct platform_device *pdev) /* don't keep reloading if cpufreq_driver exists */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; pr_debug("%s\n", __func__); diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 1d2cfea9858a..73efbcf5513b 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -583,7 +583,7 @@ static int __init pcc_cpufreq_probe(struct platform_device *pdev) /* Skip initialization if another cpufreq driver is there. */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; if (acpi_disabled) return -ENODEV; From 8e4942db5f5ed7b7d9690d93235b3ca49c5c59ce Mon Sep 17 00:00:00 2001 From: Ping-Ke Shih Date: Mon, 8 May 2023 16:55:39 +0800 Subject: [PATCH 193/358] wifi: rtw88: correct qsel_to_ep[] type as int qsel_to_ep[] can be assigned negative value, so change type from 'u8' to 'int'. Otherwise, Smatch static checker warns: drivers/net/wireless/realtek/rtw88/usb.c:219 rtw_usb_parse() warn: assigning (-22) to unsigned variable 'rtwusb->qsel_to_ep[8]' Cc: stable@vger.kernel.org Fixes: a6f187f92bcc ("wifi: rtw88: usb: fix priority queue to endpoint mapping") Reported-by: Dan Carpenter Link: https://lore.kernel.org/linux-wireless/c3f70197-829d-48ed-ae15-66a9de80fa90@kili.mountain/ Cc: Sascha Hauer Signed-off-by: Ping-Ke Shih Acked-by: Sascha Hauer Tested-by: Larry Finger Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230508085539.46795-1-pkshih@realtek.com --- drivers/net/wireless/realtek/rtw88/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtw88/usb.h b/drivers/net/wireless/realtek/rtw88/usb.h index 30647f0dd61c..ad1d7955c6a5 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.h +++ b/drivers/net/wireless/realtek/rtw88/usb.h @@ -78,7 +78,7 @@ struct rtw_usb { u8 pipe_interrupt; u8 pipe_in; u8 out_ep[RTW_USB_EP_MAX]; - u8 qsel_to_ep[TX_DESC_QSEL_MAX]; + int qsel_to_ep[TX_DESC_QSEL_MAX]; u8 usb_txagg_num; struct workqueue_struct *txwq, *rxwq; From 60fc756fc8e6954a5618eecac73b255d651602e4 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 10 May 2023 16:18:56 +0200 Subject: [PATCH 194/358] wifi: brcmfmac: Check for probe() id argument being NULL The probe() id argument may be NULL in 2 scenarios: 1. brcmf_pcie_pm_leave_D3() calling brcmf_pcie_probe() to reprobe the device. 2. If a user tries to manually bind the driver from sysfs then the sdio / pcie / usb probe() function gets called with NULL as id argument. 1. Is being hit by users causing the following oops on resume and causing wifi to stop working: BUG: kernel NULL pointer dereference, address: 0000000000000018 Hardware name: Dell Inc. XPS 13 9350/0PWNCR, BIDS 1.13.0 02/10/2020 Workgueue: events_unbound async_run_entry_fn RIP: 0010:brcmf_pcie_probe+Ox16b/0x7a0 [brcmfmac] Call Trace: brcmf_pcie_pm_leave_D3+0xc5/8x1a0 [brcmfmac be3b4cefca451e190fa35be8f00db1bbec293887] ? pci_pm_resume+0x5b/0xf0 ? pci_legacy_resume+0x80/0x80 dpm_run_callback+0x47/0x150 device_resume+0xa2/0x1f0 async_resume+0x1d/0x30 Fix this by checking for id being NULL. In the PCI and USB cases try a manual lookup of the id so that manually binding the driver through sysfs and more importantly brcmf_pcie_probe() on resume will work. For the SDIO case there is no helper to do a manual sdio_device_id lookup, so just directly error out on a NULL id there. Fixes: da6d9c8ecd00 ("wifi: brcmfmac: add firmware vendor info in driver info") Reported-by: Felix Link: https://lore.kernel.org/regressions/4ef3f252ff530cbfa336f5a0d80710020fc5cb1e.camel@gmail.com/ Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Reviewed-by: Arend van Spriel Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230510141856.46532-1-hdegoede@redhat.com --- .../net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 5 +++++ .../net/wireless/broadcom/brcm80211/brcmfmac/pcie.c | 11 +++++++++++ .../net/wireless/broadcom/brcm80211/brcmfmac/usb.c | 11 +++++++++++ 3 files changed, 27 insertions(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index ff710b0b5071..00679a990e3d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -1039,6 +1039,11 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func, struct brcmf_sdio_dev *sdiodev; struct brcmf_bus *bus_if; + if (!id) { + dev_err(&func->dev, "Error no sdio_device_id passed for %x:%x\n", func->vendor, func->device); + return -ENODEV; + } + brcmf_dbg(SDIO, "Enter\n"); brcmf_dbg(SDIO, "Class=%x\n", func->class); brcmf_dbg(SDIO, "sdio vendor ID: 0x%04x\n", func->vendor); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 59f3e9c5e139..80220685f5e4 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -2394,6 +2394,9 @@ static void brcmf_pcie_debugfs_create(struct device *dev) } #endif +/* Forward declaration for pci_match_id() call */ +static const struct pci_device_id brcmf_pcie_devid_table[]; + static int brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -2404,6 +2407,14 @@ brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct brcmf_core *core; struct brcmf_bus *bus; + if (!id) { + id = pci_match_id(brcmf_pcie_devid_table, pdev); + if (!id) { + pci_err(pdev, "Error could not find pci_device_id for %x:%x\n", pdev->vendor, pdev->device); + return -ENODEV; + } + } + brcmf_dbg(PCIE, "Enter %x:%x\n", pdev->vendor, pdev->device); ret = -ENOMEM; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c index 246843aeb696..2178675ae1a4 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c @@ -1331,6 +1331,9 @@ brcmf_usb_disconnect_cb(struct brcmf_usbdev_info *devinfo) brcmf_usb_detach(devinfo); } +/* Forward declaration for usb_match_id() call */ +static const struct usb_device_id brcmf_usb_devid_table[]; + static int brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { @@ -1342,6 +1345,14 @@ brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) u32 num_of_eps; u8 endpoint_num, ep; + if (!id) { + id = usb_match_id(intf, brcmf_usb_devid_table); + if (!id) { + dev_err(&intf->dev, "Error could not find matching usb_device_id\n"); + return -ENODEV; + } + } + brcmf_dbg(USB, "Enter 0x%04x:0x%04x\n", id->idVendor, id->idProduct); devinfo = kzalloc(sizeof(*devinfo), GFP_ATOMIC); From 20429444e653ee8242dfbf815c0c37866beb371b Mon Sep 17 00:00:00 2001 From: Yun Lu Date: Fri, 12 May 2023 09:20:55 +0800 Subject: [PATCH 195/358] wifi: rtl8xxxu: fix authentication timeout due to incorrect RCR value When using rtl8192cu with rtl8xxxu driver to connect wifi, there is a probability of failure, which shows "authentication with ... timed out". Through debugging, it was found that the RCR register has been inexplicably modified to an incorrect value, resulting in the nic not being able to receive authenticated frames. To fix this problem, add regrcr in rtl8xxxu_priv struct, and store the RCR value every time the register is written, and use it the next time the register need to be modified. Signed-off-by: Yun Lu Link: https://lore.kernel.org/all/20230427020512.1221062-1-luyun_611@163.com Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230512012055.2990472-1-luyun_611@163.com --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h | 1 + drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h index 8eafbf1cee71..808c1c895113 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h @@ -1803,6 +1803,7 @@ struct rtl8xxxu_priv { u32 rege9c; u32 regeb4; u32 regebc; + u32 regrcr; int next_mbox; int nr_out_eps; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index fd8c8c6d53d6..831639d73657 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -4171,6 +4171,7 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw) RCR_ACCEPT_MGMT_FRAME | RCR_HTC_LOC_CTRL | RCR_APPEND_PHYSTAT | RCR_APPEND_ICV | RCR_APPEND_MIC; rtl8xxxu_write32(priv, REG_RCR, val32); + priv->regrcr = val32; if (fops->init_reg_rxfltmap) { /* Accept all data frames */ @@ -6501,7 +6502,7 @@ static void rtl8xxxu_configure_filter(struct ieee80211_hw *hw, unsigned int *total_flags, u64 multicast) { struct rtl8xxxu_priv *priv = hw->priv; - u32 rcr = rtl8xxxu_read32(priv, REG_RCR); + u32 rcr = priv->regrcr; dev_dbg(&priv->udev->dev, "%s: changed_flags %08x, total_flags %08x\n", __func__, changed_flags, *total_flags); @@ -6547,6 +6548,7 @@ static void rtl8xxxu_configure_filter(struct ieee80211_hw *hw, */ rtl8xxxu_write32(priv, REG_RCR, rcr); + priv->regrcr = rcr; *total_flags &= (FIF_ALLMULTI | FIF_FCSFAIL | FIF_BCN_PRBRESP_PROMISC | FIF_CONTROL | FIF_OTHER_BSS | FIF_PSPOLL | From db2773d65b02aed319a93efdfb958087771d4e19 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 6 Apr 2023 13:08:45 +0200 Subject: [PATCH 196/358] can: isotp: recvmsg(): allow MSG_CMSG_COMPAT flag The control message provided by isotp support MSG_CMSG_COMPAT but blocked recvmsg() syscalls that have set this flag, i.e. on 32bit user space on 64 bit kernels. Link: https://github.com/hartkopp/can-isotp/issues/59 Cc: Oleksij Rempel Suggested-by: Marc Kleine-Budde Signed-off-by: Oliver Hartkopp Fixes: 42bf50a1795a ("can: isotp: support MSG_TRUNC flag when reading from socket") Link: https://lore.kernel.org/20230505110308.81087-2-mkl@pengutronix.de Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- net/can/isotp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/can/isotp.c b/net/can/isotp.c index a750259cb79c..84f9aba02901 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1139,7 +1139,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, struct isotp_sock *so = isotp_sk(sk); int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK)) + if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK | MSG_CMSG_COMPAT)) return -EINVAL; if (!so->bound) From 1db080cbdbab28752bbb1c86d64daf96253a5da1 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 6 Apr 2023 13:08:45 +0200 Subject: [PATCH 197/358] can: j1939: recvmsg(): allow MSG_CMSG_COMPAT flag The control message provided by J1939 support MSG_CMSG_COMPAT but blocked recvmsg() syscalls that have set this flag, i.e. on 32bit user space on 64 bit kernels. Link: https://github.com/hartkopp/can-isotp/issues/59 Cc: Oleksij Rempel Suggested-by: Marc Kleine-Budde Signed-off-by: Oliver Hartkopp Tested-by: Oleksij Rempel Acked-by: Oleksij Rempel Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Link: https://lore.kernel.org/20230505110308.81087-3-mkl@pengutronix.de Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- net/can/j1939/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 7e90f9e61d9b..1790469b2580 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -798,7 +798,7 @@ static int j1939_sk_recvmsg(struct socket *sock, struct msghdr *msg, struct j1939_sk_buff_cb *skcb; int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE)) + if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE | MSG_CMSG_COMPAT)) return -EINVAL; if (flags & MSG_ERRQUEUE) From 6bffdc38f9935bae49f980448f3f6be2dada0564 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sat, 6 May 2023 20:45:15 +0200 Subject: [PATCH 198/358] can: dev: fix missing CAN XL support in can_put_echo_skb() can_put_echo_skb() checks for the enabled IFF_ECHO flag and the correct ETH_P type of the given skbuff. When implementing the CAN XL support the new check for ETH_P_CANXL has been forgotten. Fixes: fb08cba12b52 ("can: canxl: update CAN infrastructure for CAN XL frames") Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20230506184515.39241-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/skb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/dev/skb.c b/drivers/net/can/dev/skb.c index 241ec636e91f..f6d05b3ef59a 100644 --- a/drivers/net/can/dev/skb.c +++ b/drivers/net/can/dev/skb.c @@ -54,7 +54,8 @@ int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, /* check flag whether this packet has to be looped back */ if (!(dev->flags & IFF_ECHO) || (skb->protocol != htons(ETH_P_CAN) && - skb->protocol != htons(ETH_P_CANFD))) { + skb->protocol != htons(ETH_P_CANFD) && + skb->protocol != htons(ETH_P_CANXL))) { kfree_skb(skb); return 0; } From 4920bded3ee077c99cd52666519cb50f9ee35b26 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 4 Apr 2023 13:59:00 +0200 Subject: [PATCH 199/358] can: CAN_BXCAN should depend on ARCH_STM32 The STMicroelectronics STM32 basic extended CAN Controller (bxCAN) is only present on STM32 SoCs. Hence drop the "|| OF" part from its dependency rule, to prevent asking the user about this driver when configuring a kernel without STM32 SoC support. Fixes: f00647d8127be4d3 ("can: bxcan: add support for ST bxCAN controller") Signed-off-by: Geert Uytterhoeven Reviewed-by: Simon Horman Link: https://lore.kernel.org/all/40095112efd1b2214e4223109fd9f0c6d0158a2d.1680609318.git.geert+renesas@glider.be Signed-off-by: Marc Kleine-Budde --- drivers/net/can/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 3ceccafd701b..b190007c01be 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -95,7 +95,7 @@ config CAN_AT91 config CAN_BXCAN tristate "STM32 Basic Extended CAN (bxCAN) devices" - depends on OF || ARCH_STM32 || COMPILE_TEST + depends on ARCH_STM32 || COMPILE_TEST depends on HAS_IOMEM select CAN_RX_OFFLOAD help From caf78f0f491981893b6a5a71c9dabd2734909c4a Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:36 +0200 Subject: [PATCH 200/358] dt-bindings: net: can: add "st,can-secondary" property On the stm32f7 Socs the can peripheral can be in single or dual configuration. In the dual configuration, in turn, it can be in primary or secondary mode. The addition of the 'st,can-secondary' property allows you to specify this mode in the dual configuration. CAN peripheral nodes in single configuration contain neither "st,can-primary" nor "st,can-secondary". Signed-off-by: Dario Binacchi Reviewed-by: Rob Herring Link: https://lore.kernel.org/all/20230427204540.3126234-2-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- .../bindings/net/can/st,stm32-bxcan.yaml | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml index 769fa5c27b76..de1d4298893b 100644 --- a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml +++ b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml @@ -21,11 +21,22 @@ properties: st,can-primary: description: - Primary and secondary mode of the bxCAN peripheral is only relevant - if the chip has two CAN peripherals. In that case they share some - of the required logic. + Primary mode of the bxCAN peripheral is only relevant if the chip has + two CAN peripherals in dual CAN configuration. In that case they share + some of the required logic. + Not to be used if the peripheral is in single CAN configuration. To avoid misunderstandings, it should be noted that ST documentation - uses the terms master/slave instead of primary/secondary. + uses the terms master instead of primary. + type: boolean + + st,can-secondary: + description: + Secondary mode of the bxCAN peripheral is only relevant if the chip + has two CAN peripherals in dual CAN configuration. In that case they + share some of the required logic. + Not to be used if the peripheral is in single CAN configuration. + To avoid misunderstandings, it should be noted that ST documentation + uses the terms slave instead of secondary. type: boolean reg: From 6b443faa313c519db755ff90be32758fd9c66453 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:37 +0200 Subject: [PATCH 201/358] ARM: dts: stm32f429: put can2 in secondary mode This is a preparation patch for the upcoming support to manage CAN peripherals in single configuration. The addition ensures backwards compatibility. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/all/20230427204540.3126234-3-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- arch/arm/boot/dts/stm32f429.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi index c9e05e3540d6..00bf53f99c29 100644 --- a/arch/arm/boot/dts/stm32f429.dtsi +++ b/arch/arm/boot/dts/stm32f429.dtsi @@ -387,6 +387,7 @@ interrupt-names = "tx", "rx0", "rx1", "sce"; resets = <&rcc STM32F4_APB1_RESET(CAN2)>; clocks = <&rcc 0 STM32F4_APB1_CLOCK(CAN2)>; + st,can-secondary; st,gcan = <&gcan>; status = "disabled"; }; From 011644249686f2675e142519cd59e81e04cfc231 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:38 +0200 Subject: [PATCH 202/358] ARM: dts: stm32: add pin map for CAN controller on stm32f7 Add pin configurations for using CAN controller on stm32f7. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/all/20230427204540.3126234-4-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- arch/arm/boot/dts/stm32f7-pinctrl.dtsi | 82 ++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) diff --git a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi index c8e6c52fb248..9f65403295ca 100644 --- a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi +++ b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi @@ -283,6 +283,88 @@ slew-rate = <2>; }; }; + + can1_pins_a: can1-0 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_b: can1-1 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_c: can1-2 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can1_pins_d: can1-3 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can2_pins_a: can2-0 { + pins1 { + pinmux = ; /* CAN2_TX */ + }; + pins2 { + pinmux = ; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can2_pins_b: can2-1 { + pins1 { + pinmux = ; /* CAN2_TX */ + }; + pins2 { + pinmux = ; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can3_pins_a: can3-0 { + pins1 { + pinmux = ; /* CAN3_TX */ + }; + pins2 { + pinmux = ; /* CAN3_RX */ + bias-pull-up; + }; + }; + + can3_pins_b: can3-1 { + pins1 { + pinmux = ; /* CAN3_TX */ + }; + pins2 { + pinmux = ; /* CAN3_RX */ + bias-pull-up; + }; + }; }; }; }; From 85a79b971164c4636b2db7f4aef9788142e3f885 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:39 +0200 Subject: [PATCH 203/358] can: bxcan: add support for single peripheral configuration Add support for bxCAN controller in single peripheral configuration: - primary bxCAN - dedicated Memory Access Controller unit - 512-byte SRAM memory - 14 filter banks Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/all/20230427204540.3126234-5-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/bxcan.c | 34 +++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/drivers/net/can/bxcan.c b/drivers/net/can/bxcan.c index e26ccd41e3cb..027a8a162fe4 100644 --- a/drivers/net/can/bxcan.c +++ b/drivers/net/can/bxcan.c @@ -118,7 +118,7 @@ #define BXCAN_FiR1_REG(b) (0x40 + (b) * 8) #define BXCAN_FiR2_REG(b) (0x44 + (b) * 8) -#define BXCAN_FILTER_ID(primary) (primary ? 0 : 14) +#define BXCAN_FILTER_ID(cfg) ((cfg) == BXCAN_CFG_DUAL_SECONDARY ? 14 : 0) /* Filter primary register (FMR) bits */ #define BXCAN_FMR_CANSB_MASK GENMASK(13, 8) @@ -135,6 +135,12 @@ enum bxcan_lec_code { BXCAN_LEC_UNUSED }; +enum bxcan_cfg { + BXCAN_CFG_SINGLE = 0, + BXCAN_CFG_DUAL_PRIMARY, + BXCAN_CFG_DUAL_SECONDARY +}; + /* Structure of the message buffer */ struct bxcan_mb { u32 id; /* can identifier */ @@ -167,7 +173,7 @@ struct bxcan_priv { struct regmap *gcan; int tx_irq; int sce_irq; - bool primary; + enum bxcan_cfg cfg; struct clk *clk; spinlock_t rmw_lock; /* lock for read-modify-write operations */ unsigned int tx_head; @@ -202,17 +208,17 @@ static inline void bxcan_rmw(struct bxcan_priv *priv, void __iomem *addr, spin_unlock_irqrestore(&priv->rmw_lock, flags); } -static void bxcan_disable_filters(struct bxcan_priv *priv, bool primary) +static void bxcan_disable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg) { - unsigned int fid = BXCAN_FILTER_ID(primary); + unsigned int fid = BXCAN_FILTER_ID(cfg); u32 fmask = BIT(fid); regmap_update_bits(priv->gcan, BXCAN_FA1R_REG, fmask, 0); } -static void bxcan_enable_filters(struct bxcan_priv *priv, bool primary) +static void bxcan_enable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg) { - unsigned int fid = BXCAN_FILTER_ID(primary); + unsigned int fid = BXCAN_FILTER_ID(cfg); u32 fmask = BIT(fid); /* Filter settings: @@ -680,7 +686,7 @@ static int bxcan_chip_start(struct net_device *ndev) BXCAN_BTR_BRP_MASK | BXCAN_BTR_TS1_MASK | BXCAN_BTR_TS2_MASK | BXCAN_BTR_SJW_MASK, set); - bxcan_enable_filters(priv, priv->primary); + bxcan_enable_filters(priv, priv->cfg); /* Clear all internal status */ priv->tx_head = 0; @@ -806,7 +812,7 @@ static void bxcan_chip_stop(struct net_device *ndev) BXCAN_IER_EPVIE | BXCAN_IER_EWGIE | BXCAN_IER_FOVIE1 | BXCAN_IER_FFIE1 | BXCAN_IER_FMPIE1 | BXCAN_IER_FOVIE0 | BXCAN_IER_FFIE0 | BXCAN_IER_FMPIE0 | BXCAN_IER_TMEIE, 0); - bxcan_disable_filters(priv, priv->primary); + bxcan_disable_filters(priv, priv->cfg); bxcan_enter_sleep_mode(priv); priv->can.state = CAN_STATE_STOPPED; } @@ -931,7 +937,7 @@ static int bxcan_probe(struct platform_device *pdev) struct clk *clk = NULL; void __iomem *regs; struct regmap *gcan; - bool primary; + enum bxcan_cfg cfg; int err, rx_irq, tx_irq, sce_irq; regs = devm_platform_ioremap_resource(pdev, 0); @@ -946,7 +952,13 @@ static int bxcan_probe(struct platform_device *pdev) return PTR_ERR(gcan); } - primary = of_property_read_bool(np, "st,can-primary"); + if (of_property_read_bool(np, "st,can-primary")) + cfg = BXCAN_CFG_DUAL_PRIMARY; + else if (of_property_read_bool(np, "st,can-secondary")) + cfg = BXCAN_CFG_DUAL_SECONDARY; + else + cfg = BXCAN_CFG_SINGLE; + clk = devm_clk_get(dev, NULL); if (IS_ERR(clk)) { dev_err(dev, "failed to get clock\n"); @@ -992,7 +1004,7 @@ static int bxcan_probe(struct platform_device *pdev) priv->clk = clk; priv->tx_irq = tx_irq; priv->sce_irq = sce_irq; - priv->primary = primary; + priv->cfg = cfg; priv->can.clock.freq = clk_get_rate(clk); spin_lock_init(&priv->rmw_lock); priv->tx_head = 0; From 0920ccdf41e3078a4dd2567eb905ea154bc826e6 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:40 +0200 Subject: [PATCH 204/358] ARM: dts: stm32: add CAN support on stm32f746 Add support for bxcan (Basic eXtended CAN controller) to STM32F746. The chip contains three CAN peripherals, CAN1 and CAN2 in dual peripheral configuration and CAN3 in single peripheral configuration: - Dual CAN peripheral configuration: * CAN1: Primary bxCAN for managing the communication between a secondary bxCAN and the 512-byte SRAM memory. * CAN2: Secondary bxCAN with no direct access to the SRAM memory. This means that the two bxCAN cells share the 512-byte SRAM memory and CAN2 can't be used without enabling CAN1. - Single CAN peripheral configuration: * CAN3: Primary bxCAN with dedicated Memory Access Controller unit and 512-byte SRAM memory. ------------------------------------------------------------------------- | features | CAN1 | CAN2 | CAN 3 | ------------------------------------------------------------------------- | SRAM | 512-byte shared between CAN1 & CAN2 | 512-byte | ------------------------------------------------------------------------- | Filters | 26 filters shared between CAN1 & CAN2 | 14 filters | ------------------------------------------------------------------------- Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/all/20230427204540.3126234-6-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- arch/arm/boot/dts/stm32f746.dtsi | 47 ++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/arch/arm/boot/dts/stm32f746.dtsi b/arch/arm/boot/dts/stm32f746.dtsi index dc868e6da40e..973698bc9ef4 100644 --- a/arch/arm/boot/dts/stm32f746.dtsi +++ b/arch/arm/boot/dts/stm32f746.dtsi @@ -257,6 +257,23 @@ status = "disabled"; }; + can3: can@40003400 { + compatible = "st,stm32f4-bxcan"; + reg = <0x40003400 0x200>; + interrupts = <104>, <105>, <106>, <107>; + interrupt-names = "tx", "rx0", "rx1", "sce"; + resets = <&rcc STM32F7_APB1_RESET(CAN3)>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN3)>; + st,gcan = <&gcan3>; + status = "disabled"; + }; + + gcan3: gcan@40003600 { + compatible = "st,stm32f4-gcan", "syscon"; + reg = <0x40003600 0x200>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN3)>; + }; + usart2: serial@40004400 { compatible = "st,stm32f7-uart"; reg = <0x40004400 0x400>; @@ -337,6 +354,36 @@ status = "disabled"; }; + can1: can@40006400 { + compatible = "st,stm32f4-bxcan"; + reg = <0x40006400 0x200>; + interrupts = <19>, <20>, <21>, <22>; + interrupt-names = "tx", "rx0", "rx1", "sce"; + resets = <&rcc STM32F7_APB1_RESET(CAN1)>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN1)>; + st,can-primary; + st,gcan = <&gcan1>; + status = "disabled"; + }; + + gcan1: gcan@40006600 { + compatible = "st,stm32f4-gcan", "syscon"; + reg = <0x40006600 0x200>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN1)>; + }; + + can2: can@40006800 { + compatible = "st,stm32f4-bxcan"; + reg = <0x40006800 0x200>; + interrupts = <63>, <64>, <65>, <66>; + interrupt-names = "tx", "rx0", "rx1", "sce"; + resets = <&rcc STM32F7_APB1_RESET(CAN2)>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN2)>; + st,can-secondary; + st,gcan = <&gcan1>; + status = "disabled"; + }; + cec: cec@40006c00 { compatible = "st,stm32-cec"; reg = <0x40006C00 0x400>; From 1398aa803f198b7a386fdd8404666043e95f4c16 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Wed, 26 Apr 2023 20:29:27 +0300 Subject: [PATCH 205/358] tpm_tis: Use tpm_chip_{start,stop} decoration inside tpm_tis_resume Before sending a TPM command, CLKRUN protocol must be disabled. This is not done in the case of tpm1_do_selftest() call site inside tpm_tis_resume(). Address this by decorating the calls with tpm_chip_{start,stop}, which should be always used to arm and disarm the TPM chip for transmission. Finally, move the call to the main TPM driver callback as the last step because it should arm the chip by itself, if it needs that type of functionality. Cc: stable@vger.kernel.org Reported-by: Jason A. Donenfeld Closes: https://lore.kernel.org/linux-integrity/CS68AWILHXS4.3M36M1EKZLUMS@suppilovahvero/ Fixes: a3fbfae82b4c ("tpm: take TPM chip power gating out of tpm_transmit()") Reviewed-by: Jerry Snitselaar Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm_tis_core.c | 43 +++++++++++++++------------------ 1 file changed, 19 insertions(+), 24 deletions(-) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 02945d53fcef..558144fa707a 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1209,25 +1209,20 @@ static void tpm_tis_reenable_interrupts(struct tpm_chip *chip) u32 intmask; int rc; - if (chip->ops->clk_enable != NULL) - chip->ops->clk_enable(chip, true); - - /* reenable interrupts that device may have lost or - * BIOS/firmware may have disabled + /* + * Re-enable interrupts that device may have lost or BIOS/firmware may + * have disabled. */ rc = tpm_tis_write8(priv, TPM_INT_VECTOR(priv->locality), priv->irq); - if (rc < 0) - goto out; + if (rc < 0) { + dev_err(&chip->dev, "Setting IRQ failed.\n"); + return; + } intmask = priv->int_mask | TPM_GLOBAL_INT_ENABLE; - - tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); - -out: - if (chip->ops->clk_enable != NULL) - chip->ops->clk_enable(chip, false); - - return; + rc = tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); + if (rc < 0) + dev_err(&chip->dev, "Enabling interrupts failed.\n"); } int tpm_tis_resume(struct device *dev) @@ -1235,27 +1230,27 @@ int tpm_tis_resume(struct device *dev) struct tpm_chip *chip = dev_get_drvdata(dev); int ret; - ret = tpm_tis_request_locality(chip, 0); - if (ret < 0) + ret = tpm_chip_start(chip); + if (ret) return ret; if (chip->flags & TPM_CHIP_FLAG_IRQ) tpm_tis_reenable_interrupts(chip); - ret = tpm_pm_resume(dev); - if (ret) - goto out; - /* * TPM 1.2 requires self-test on resume. This function actually returns * an error code but for unknown reason it isn't handled. */ if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) tpm1_do_selftest(chip); -out: - tpm_tis_relinquish_locality(chip, 0); - return ret; + tpm_chip_stop(chip); + + ret = tpm_pm_resume(dev); + if (ret) + return ret; + + return 0; } EXPORT_SYMBOL_GPL(tpm_tis_resume); #endif From 99d46450625590d410f86fe4660a5eff7d3b8343 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Wed, 26 Apr 2023 20:29:28 +0300 Subject: [PATCH 206/358] tpm: Prevent hwrng from activating during resume Set TPM_CHIP_FLAG_SUSPENDED in tpm_pm_suspend() and reset in tpm_pm_resume(). While the flag is set, tpm_hwrng() gives back zero bytes. This prevents hwrng from racing during resume. Cc: stable@vger.kernel.org Fixes: 6e592a065d51 ("tpm: Move Linux RNG connection to hwrng") Reviewed-by: Jerry Snitselaar Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-chip.c | 4 ++++ drivers/char/tpm/tpm-interface.c | 10 ++++++++++ include/linux/tpm.h | 1 + 3 files changed, 15 insertions(+) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index c10a4aa97373..cd48033b804a 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -571,6 +571,10 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng); + /* Give back zero bytes, as TPM chip has not yet fully resumed: */ + if (chip->flags & TPM_CHIP_FLAG_SUSPENDED) + return 0; + return tpm_get_random(chip, data, max); } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 4463d0018290..586ca10b0d72 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -412,6 +412,8 @@ int tpm_pm_suspend(struct device *dev) } suspended: + chip->flags |= TPM_CHIP_FLAG_SUSPENDED; + if (rc) dev_err(dev, "Ignoring error %d while suspending\n", rc); return 0; @@ -429,6 +431,14 @@ int tpm_pm_resume(struct device *dev) if (chip == NULL) return -ENODEV; + chip->flags &= ~TPM_CHIP_FLAG_SUSPENDED; + + /* + * Guarantee that SUSPENDED is written last, so that hwrng does not + * activate before the chip has been fully resumed. + */ + wmb(); + return 0; } EXPORT_SYMBOL_GPL(tpm_pm_resume); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 77693389c3f9..6a1e8f157255 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -282,6 +282,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), + TPM_CHIP_FLAG_SUSPENDED = BIT(8), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) From e7d3e5c4b1dd50a70b31524c3228c62bb41bbab2 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Wed, 10 May 2023 17:54:03 -0700 Subject: [PATCH 207/358] tpm/tpm_tis: Disable interrupts for more Lenovo devices The P360 Tiny suffers from an irq storm issue like the T490s, so add an entry for it to tpm_tis_dmi_table, and force polling. There also previously was a report from the previous attempt to enable interrupts that involved a ThinkPad L490. So an entry is added for it as well. Cc: stable@vger.kernel.org Reported-by: Peter Zijlstra # P360 Tiny Closes: https://lore.kernel.org/linux-integrity/20230505130731.GO83892@hirez.programming.kicks-ass.net/ Signed-off-by: Jerry Snitselaar Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm_tis.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 7af389806643..709b4e13bd6e 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -122,6 +122,22 @@ static const struct dmi_system_id tpm_tis_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"), }, }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkStation P360 Tiny", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkStation P360 Tiny"), + }, + }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkPad L490", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L490"), + }, + }, {} }; From 225c657945c4a6307741cb3cc89467eadcc26e9b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sun, 14 May 2023 19:56:07 -0700 Subject: [PATCH 208/358] net: bcmgenet: Restore phy_stop() depending upon suspend/close Removing the phy_stop() from bcmgenet_netif_stop() ended up causing warnings from the PHY library that phy_start() is called from the RUNNING state since we are no longer stopping the PHY state machine during bcmgenet_suspend(). Restore the call to phy_stop() but make it conditional on being called from the close or suspend path. Fixes: c96e731c93ff ("net: bcmgenet: connect and disconnect from the PHY state machine") Fixes: 93e0401e0fc0 ("net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop()") Signed-off-by: Florian Fainelli Reviewed-by: Pavan Chebbi Link: https://lore.kernel.org/r/20230515025608.2587012-1-f.fainelli@gmail.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index f28ffc31df22..eca0c92c0c84 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3450,7 +3450,7 @@ err_clk_disable: return ret; } -static void bcmgenet_netif_stop(struct net_device *dev) +static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -3465,6 +3465,8 @@ static void bcmgenet_netif_stop(struct net_device *dev) /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); + if (stop_phy) + phy_stop(dev->phydev); bcmgenet_disable_rx_napi(priv); bcmgenet_intr_disable(priv); @@ -3485,7 +3487,7 @@ static int bcmgenet_close(struct net_device *dev) netif_dbg(priv, ifdown, dev, "bcmgenet_close\n"); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, false); /* Really kill the PHY state machine and disconnect from it */ phy_disconnect(dev->phydev); @@ -4303,7 +4305,7 @@ static int bcmgenet_suspend(struct device *d) netif_device_detach(dev); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, true); if (!device_may_wakeup(d)) phy_suspend(dev->phydev); From d91d580878064b880f3574ac35b98d8b70ee8620 Mon Sep 17 00:00:00 2001 From: Min-Hua Chen Date: Tue, 2 May 2023 23:19:06 +0800 Subject: [PATCH 209/358] arm64/mm: mark private VM_FAULT_X defines as vm_fault_t This patch fixes several sparse warnings for fault.c: arch/arm64/mm/fault.c:493:24: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:493:24: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:493:24: sparse: got int arch/arm64/mm/fault.c:501:32: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:501:32: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:501:32: sparse: got int arch/arm64/mm/fault.c:503:32: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:503:32: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:503:32: sparse: got int arch/arm64/mm/fault.c:511:24: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:511:24: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:511:24: sparse: got int arch/arm64/mm/fault.c:670:13: sparse: warning: restricted vm_fault_t degrades to integer arch/arm64/mm/fault.c:670:13: sparse: warning: restricted vm_fault_t degrades to integer arch/arm64/mm/fault.c:713:39: sparse: warning: restricted vm_fault_t degrades to integer Reported-by: kernel test robot Signed-off-by: Min-Hua Chen Link: https://lore.kernel.org/r/20230502151909.128810-1-minhuadotchen@gmail.com Signed-off-by: Will Deacon --- arch/arm64/mm/fault.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9e0db5c387e3..cb21ccd7940d 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -480,8 +480,8 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -#define VM_FAULT_BADMAP 0x010000 -#define VM_FAULT_BADACCESS 0x020000 +#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) +#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags, From b0abde80620f42d1ceb3de5e4c1a49cdd5628229 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 10 May 2023 08:48:11 +0200 Subject: [PATCH 210/358] arm64: vdso: Pass (void *) to virt_to_page() Like the other calls in this function virt_to_page() expects a pointer, not an integer. However since many architectures implement virt_to_pfn() as a macro, this function becomes polymorphic and accepts both a (unsigned long) and a (void *). Fix this up with an explicit cast. Signed-off-by: Linus Walleij Link: http://lists.infradead.org/pipermail/linux-arm-kernel/2023-May/832583.html Signed-off-by: Will Deacon --- arch/arm64/kernel/vdso.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 0119dc91abb5..d9e1355730ef 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -288,7 +288,7 @@ static int aarch32_alloc_kuser_vdso_page(void) memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start, kuser_sz); - aarch32_vectors_page = virt_to_page(vdso_page); + aarch32_vectors_page = virt_to_page((void *)vdso_page); return 0; } From 68e3f61eb9f58798e28b18152cd38cb269eebc34 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 8 May 2023 18:05:18 +0200 Subject: [PATCH 211/358] ARM: perf: Mark all accessor functions inline MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When just including : arch/arm/include/asm/arm_pmuv3.h:110:13: error: ‘write_pmevtypern’ defined but not used [-Werror=unused-function] 110 | static void write_pmevtypern(int n, unsigned long val) | ^~~~~~~~~~~~~~~~ arch/arm/include/asm/arm_pmuv3.h:103:13: error: ‘write_pmevcntrn’ defined but not used [-Werror=unused-function] 103 | static void write_pmevcntrn(int n, unsigned long val) | ^~~~~~~~~~~~~~~ arch/arm/include/asm/arm_pmuv3.h:95:22: error: ‘read_pmevcntrn’ defined but not used [-Werror=unused-function] 95 | static unsigned long read_pmevcntrn(int n) | ^~~~~~~~~~~~~~ Fix this by adding the missing "inline" keywords to the three accessor functions that lack them. Fixes: 009d6dc87a56 ("ARM: perf: Allow the use of the PMUv3 driver on 32bit ARM") Signed-off-by: Geert Uytterhoeven Acked-by: Mark Rutland Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/3a7d9bc7470aa2d85696ee9765c74f8c03fb5454.1683561482.git.geert+renesas@glider.be Signed-off-by: Will Deacon --- arch/arm/include/asm/arm_pmuv3.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h index 78d3d4b82c6c..f4db3e75d75f 100644 --- a/arch/arm/include/asm/arm_pmuv3.h +++ b/arch/arm/include/asm/arm_pmuv3.h @@ -92,7 +92,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(PMEVCNTR##n) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -100,14 +100,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, PMEVCNTR##n) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, PMEVTYPER##n) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } From 3bc879e355da4ff925e9d82278a829547d9d54bf Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 8 May 2023 18:05:19 +0200 Subject: [PATCH 212/358] arm64: perf: Mark all accessor functions inline MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When just including : arch/arm64/include/asm/arm_pmuv3.h:31:13: error: ‘write_pmevtypern’ defined but not used [-Werror=unused-function] 31 | static void write_pmevtypern(int n, unsigned long val) | ^~~~~~~~~~~~~~~~ arch/arm64/include/asm/arm_pmuv3.h:24:13: error: ‘write_pmevcntrn’ defined but not used [-Werror=unused-function] 24 | static void write_pmevcntrn(int n, unsigned long val) | ^~~~~~~~~~~~~~~ arch/arm64/include/asm/arm_pmuv3.h:16:22: error: ‘read_pmevcntrn’ defined but not used [-Werror=unused-function] 16 | static unsigned long read_pmevcntrn(int n) | ^~~~~~~~~~~~~~ Fix this by adding the missing "inline" keywords to the three accessor functions that lack them. Fixes: df29ddf4f04b ("arm64: perf: Abstract system register accesses away") Signed-off-by: Geert Uytterhoeven Reviewed-by: Marc Zyngier Acked-by: Mark Rutland Link: https://lore.kernel.org/r/d53a19043c0c3bd25f6c203e73a2fb08a9661824.1683561482.git.geert+renesas@glider.be Signed-off-by: Will Deacon --- arch/arm64/include/asm/arm_pmuv3.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h index d6b51deb7bf0..18dc2fb3d7b7 100644 --- a/arch/arm64/include/asm/arm_pmuv3.h +++ b/arch/arm64/include/asm/arm_pmuv3.h @@ -13,7 +13,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(pmevcntr##n##_el0) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -21,14 +21,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, pmevcntr##n##_el0) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, pmevtyper##n##_el0) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } From 2efbafb91e12ff5a16cbafb0085e4c10c3fca493 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 20 Apr 2023 14:09:45 -0700 Subject: [PATCH 213/358] arm64: Also reset KASAN tag if page is not PG_mte_tagged Consider the following sequence of events: 1) A page in a PROT_READ|PROT_WRITE VMA is faulted. 2) Page migration allocates a page with the KASAN allocator, causing it to receive a non-match-all tag, and uses it to replace the page faulted in 1. 3) The program uses mprotect() to enable PROT_MTE on the page faulted in 1. As a result of step 3, we are left with a non-match-all tag for a page with tags accessible to userspace, which can lead to the same kind of tag check faults that commit e74a68468062 ("arm64: Reset KASAN tag in copy_highpage with HW tags only") intended to fix. The general invariant that we have for pages in a VMA with VM_MTE_ALLOWED is that they cannot have a non-match-all tag. As a result of step 2, the invariant is broken. This means that the fix in the referenced commit was incomplete and we also need to reset the tag for pages without PG_mte_tagged. Fixes: e5b8d9218951 ("arm64: mte: reset the page tag in page->flags") Cc: # 5.15 Link: https://linux-review.googlesource.com/id/I7409cdd41acbcb215c2a7417c1e50d37b875beff Signed-off-by: Peter Collingbourne Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20230420210945.2313627-1-pcc@google.com Signed-off-by: Will Deacon --- arch/arm64/mm/copypage.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 4aadcfb01754..a7bb20055ce0 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -21,9 +21,10 @@ void copy_highpage(struct page *to, struct page *from) copy_page(kto, kfrom); + if (kasan_hw_tags_enabled()) + page_kasan_tag_reset(to); + if (system_supports_mte() && page_mte_tagged(from)) { - if (kasan_hw_tags_enabled()) - page_kasan_tag_reset(to); /* It's a new page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(to)); mte_copy_page_tags(kto, kfrom); From c4c597f1b367433c52c531dccd6859a39b4580fb Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 20 Apr 2023 14:43:27 -0700 Subject: [PATCH 214/358] arm64: mte: Do not set PG_mte_tagged if tags were not initialized The mte_sync_page_tags() function sets PG_mte_tagged if it initializes page tags. Then we return to mte_sync_tags(), which sets PG_mte_tagged again. At best, this is redundant. However, it is possible for mte_sync_page_tags() to return without having initialized tags for the page, i.e. in the case where check_swap is true (non-compound page), is_swap_pte(old_pte) is false and pte_is_tagged is false. So at worst, we set PG_mte_tagged on a page with uninitialized tags. This can happen if, for example, page migration causes a PTE for an untagged page to be replaced. If the userspace program subsequently uses mprotect() to enable PROT_MTE for that page, the uninitialized tags will be exposed to userspace. Fix it by removing the redundant call to set_page_mte_tagged(). Fixes: e059853d14ca ("arm64: mte: Fix/clarify the PG_mte_tagged semantics") Signed-off-by: Peter Collingbourne Cc: # 6.1 Link: https://linux-review.googlesource.com/id/Ib02d004d435b2ed87603b858ef7480f7b1463052 Reviewed-by: Catalin Marinas Reviewed-by: Alexandru Elisei Link: https://lore.kernel.org/r/20230420214327.2357985-1-pcc@google.com Signed-off-by: Will Deacon --- arch/arm64/kernel/mte.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index f5bcb0dc6267..7e89968bd282 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -66,13 +66,10 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) return; /* if PG_mte_tagged is set, tags have already been initialised */ - for (i = 0; i < nr_pages; i++, page++) { - if (!page_mte_tagged(page)) { + for (i = 0; i < nr_pages; i++, page++) + if (!page_mte_tagged(page)) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); - set_page_mte_tagged(page); - } - } /* ensure the tags are visible before the PTE is set */ smp_wmb(); From ad593827db9b73f15eb65416ec975ec0311f773a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 15 May 2023 21:12:31 -0300 Subject: [PATCH 215/358] powerpc/iommu: Remove iommu_del_device() Now that power calls iommu_device_register() and populates its groups using iommu_ops->device_group it should not be calling iommu_group_remove_device(). The core code owns the groups and all the other related iommu data, it will clean it up automatically. Remove the bus notifiers and explicit calls to iommu_group_remove_device(). Fixes: a940904443e4 ("powerpc/iommu: Add iommu_ops to report capabilities and allow blocking domains") Signed-off-by: Jason Gunthorpe Signed-off-by: Michael Ellerman Link: https://msgid.link/0-v1-1421774b874b+167-ppc_device_group_jgg@nvidia.com --- arch/powerpc/include/asm/iommu.h | 5 ----- arch/powerpc/kernel/iommu.c | 17 ----------------- arch/powerpc/platforms/powernv/pci.c | 25 ------------------------- arch/powerpc/platforms/pseries/iommu.c | 25 ------------------------- 4 files changed, 72 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 678b5bdc79b1..34e14dfd8e04 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -205,7 +205,6 @@ extern void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, unsigned long pe_num); extern int iommu_add_device(struct iommu_table_group *table_group, struct device *dev); -extern void iommu_del_device(struct device *dev); extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); @@ -229,10 +228,6 @@ static inline int iommu_add_device(struct iommu_table_group *table_group, { return 0; } - -static inline void iommu_del_device(struct device *dev) -{ -} #endif /* !CONFIG_IOMMU_API */ u64 dma_iommu_get_required_mask(struct device *dev); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0089dd49b4cb..8fce2da109eb 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1168,23 +1168,6 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_add_device); -void iommu_del_device(struct device *dev) -{ - /* - * Some devices might not have IOMMU table and group - * and we needn't detach them from the associated - * IOMMU groups - */ - if (!device_iommu_mapped(dev)) { - pr_debug("iommu_tce: skipping device %s with no tbl\n", - dev_name(dev)); - return; - } - - iommu_group_remove_device(dev); -} -EXPORT_SYMBOL_GPL(iommu_del_device); - /* * A simple iommu_table_group_ops which only allows reusing the existing * iommu_table. This handles VFIO for POWER7 or the nested KVM. diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 233a50e65fce..7725492097b6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -865,28 +865,3 @@ void __init pnv_pci_init(void) /* Configure IOMMU DMA hooks */ set_pci_dma_ops(&dma_iommu_ops); } - -static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block pnv_tce_iommu_bus_nb = { - .notifier_call = pnv_tce_iommu_bus_notifier, -}; - -static int __init pnv_tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 7464fa6e4145..e44d3c4a0781 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1695,31 +1695,6 @@ static int __init disable_multitce(char *str) __setup("multitce=", disable_multitce); -static int tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = tce_iommu_bus_notifier, -}; - -static int __init tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init); - #ifdef CONFIG_SPAPR_TCE_IOMMU struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose, struct pci_dev *pdev) From 096339ab84f36beae0b1db25e0ce63fb3873e8b2 Mon Sep 17 00:00:00 2001 From: Gaurav Batra Date: Thu, 4 May 2023 12:59:13 -0500 Subject: [PATCH 216/358] powerpc/iommu: DMA address offset is incorrectly calculated with 2MB TCEs When DMA window is backed by 2MB TCEs, the DMA address for the mapped page should be the offset of the page relative to the 2MB TCE. The code was incorrectly setting the DMA address to the beginning of the TCE range. Mellanox driver is reporting timeout trying to ENABLE_HCA for an SR-IOV ethernet port, when DMA window is backed by 2MB TCEs. Fixes: 387273118714 ("powerps/pseries/dma: Add support for 2M IOMMU page size") Cc: stable@vger.kernel.org # v5.16+ Signed-off-by: Gaurav Batra Reviewed-by: Greg Joyce Reviewed-by: Brian King Signed-off-by: Michael Ellerman Link: https://msgid.link/20230504175913.83844-1-gbatra@linux.vnet.ibm.com --- arch/powerpc/kernel/iommu.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 8fce2da109eb..67f0b01e6ff5 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -518,7 +518,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Convert entry to a dma_addr_t */ entry += tbl->it_offset; dma_addr = entry << tbl->it_page_shift; - dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl)); + dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl)); DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n", npages, entry, dma_addr); @@ -905,6 +905,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, unsigned int order; unsigned int nio_pages, io_order; struct page *page; + int tcesize = (1 << tbl->it_page_shift); size = PAGE_ALIGN(size); order = get_order(size); @@ -931,7 +932,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; + io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, mask >> tbl->it_page_shift, io_order, 0); @@ -939,7 +941,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, free_pages((unsigned long)ret, order); return NULL; } - *dma_handle = mapping; + + *dma_handle = mapping | ((u64)ret & (tcesize - 1)); return ret; } @@ -950,7 +953,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, unsigned int nio_pages; size = PAGE_ALIGN(size); - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); From 1f7aacc5eb9ed2cc17be7a90da5cd559effb9d59 Mon Sep 17 00:00:00 2001 From: Gaurav Batra Date: Fri, 5 May 2023 13:47:01 -0500 Subject: [PATCH 217/358] powerpc/iommu: Incorrect DDW Table is referenced for SR-IOV device For an SR-IOV device, while enabling DDW, a new table is created and added at index 1 in the group. In the below 2 scenarios, the table is incorrectly referenced at index 0 (which is where the table is for default DMA window). 1. When adding DDW This issue is exposed with "slub_debug". Error thrown out from dma_iommu_dma_supported() Warning: IOMMU offset too big for device mask mask: 0xffffffff, table offset: 0x800000000000000 2. During Dynamic removal of the PCI device. Error is from iommu_tce_table_put() since a NULL table pointer is passed in. Fixes: 381ceda88c4c ("powerpc/pseries/iommu: Make use of DDW for indirect mapping") Cc: stable@vger.kernel.org # v5.15+ Signed-off-by: Gaurav Batra Reviewed-by: Brian King Signed-off-by: Michael Ellerman Link: https://msgid.link/20230505184701.91613-1-gbatra@linux.vnet.ibm.com --- arch/powerpc/kernel/dma-iommu.c | 4 +++- arch/powerpc/platforms/pseries/iommu.c | 13 +++++++++---- 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 038ce8d9061d..8920862ffd79 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -144,7 +144,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask) /* We support DMA to/from any memory page via the iommu */ int dma_iommu_dma_supported(struct device *dev, u64 mask) { - struct iommu_table *tbl = get_iommu_table_base(dev); + struct iommu_table *tbl; if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) { /* @@ -162,6 +162,8 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask) return 1; } + tbl = get_iommu_table_base(dev); + if (!tbl) { dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask); return 0; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index e44d3c4a0781..918f511837db 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -91,19 +91,24 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) static void iommu_pseries_free_group(struct iommu_table_group *table_group, const char *node_name) { - struct iommu_table *tbl; - if (!table_group) return; - tbl = table_group->tables[0]; #ifdef CONFIG_IOMMU_API if (table_group->group) { iommu_group_put(table_group->group); BUG_ON(table_group->group); } #endif - iommu_tce_table_put(tbl); + + /* Default DMA window table is at index 0, while DDW at 1. SR-IOV + * adapters only have table on index 1. + */ + if (table_group->tables[0]) + iommu_tce_table_put(table_group->tables[0]); + + if (table_group->tables[1]) + iommu_tce_table_put(table_group->tables[1]); kfree(table_group); } From 2a821fc3136d5d99dcb9de152be8a052ca27d870 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 15 May 2023 16:40:58 +0300 Subject: [PATCH 218/358] xhci-pci: Only run d3cold avoidance quirk for s2idle Donghun reports that a notebook that has an AMD Ryzen 5700U but supports S3 has problems with USB after resuming from suspend. The issue was bisected down to commit d1658268e439 ("usb: pci-quirks: disable D3cold on xhci suspend for s2idle on AMD Renoir"). As this issue only happens on S3, narrow the broken D3cold quirk to only run in s2idle. Fixes: d1658268e439 ("usb: pci-quirks: disable D3cold on xhci suspend for s2idle on AMD Renoir") Reported-and-tested-by: Donghun Yoon Cc: stable@vger.kernel.org Signed-off-by: Mario Limonciello Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230515134059.161110-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 12 ++++++++++-- drivers/usb/host/xhci.h | 2 +- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ddb79f23fb3b..79b3691f373f 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "xhci.h" #include "xhci-trace.h" @@ -387,7 +388,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == PCI_DEVICE_ID_AMD_RENOIR_XHCI) - xhci->quirks |= XHCI_BROKEN_D3COLD; + xhci->quirks |= XHCI_BROKEN_D3COLD_S2I; if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; @@ -801,9 +802,16 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) * Systems with the TI redriver that loses port status change events * need to have the registers polled during D3, so avoid D3cold. */ - if (xhci->quirks & (XHCI_COMP_MODE_QUIRK | XHCI_BROKEN_D3COLD)) + if (xhci->quirks & XHCI_COMP_MODE_QUIRK) pci_d3cold_disable(pdev); +#ifdef CONFIG_SUSPEND + /* d3cold is broken, but only when s2idle is used */ + if (pm_suspend_target_state == PM_SUSPEND_TO_IDLE && + xhci->quirks & (XHCI_BROKEN_D3COLD_S2I)) + pci_d3cold_disable(pdev); +#endif + if (xhci->quirks & XHCI_PME_STUCK_QUIRK) xhci_pme_quirk(hcd); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 08d721921b7b..6b690ec91ff3 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1901,7 +1901,7 @@ struct xhci_hcd { #define XHCI_DISABLE_SPARSE BIT_ULL(38) #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) -#define XHCI_BROKEN_D3COLD BIT_ULL(41) +#define XHCI_BROKEN_D3COLD_S2I BIT_ULL(41) #define XHCI_EP_CTX_BROKEN_DCS BIT_ULL(42) #define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43) #define XHCI_RESET_TO_DEFAULT BIT_ULL(44) From fe82f16aafdaf8002281d3b9524291d4a4a28460 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 15 May 2023 16:40:59 +0300 Subject: [PATCH 219/358] xhci: Fix incorrect tracking of free space on transfer rings This incorrect tracking caused unnecessary ring expansion in some usecases which over days of use consume a lot of memory. xhci driver tries to keep track of free transfer blocks (TRBs) on the ring buffer, but failed to add back some cancelled transfers that were turned into no-op operations instead of just moving past them. This can happen if there are several queued pending transfers which then are cancelled in reverse order. Solve this by counting the numer of steps we move the dequeue pointer once we complete a transfer, and add it to the number of free trbs instead of just adding the trb number of the current transfer. This way we ensure we count the no-op trbs on the way as well. Fixes: 55f6153d8cc8 ("xhci: remove extra loop in interrupt context") Cc: stable@vger.kernel.org Reported-by: Miller Hunter Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217242 Tested-by: Miller Hunter Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230515134059.161110-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-ring.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 1ad12d5a4857..2bc82b3a2f98 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -276,6 +276,26 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring, trace_xhci_inc_enq(ring); } +static int xhci_num_trbs_to(struct xhci_segment *start_seg, union xhci_trb *start, + struct xhci_segment *end_seg, union xhci_trb *end, + unsigned int num_segs) +{ + union xhci_trb *last_on_seg; + int num = 0; + int i = 0; + + do { + if (start_seg == end_seg && end >= start) + return num + (end - start); + last_on_seg = &start_seg->trbs[TRBS_PER_SEGMENT - 1]; + num += last_on_seg - start; + start_seg = start_seg->next; + start = start_seg->trbs; + } while (i++ <= num_segs); + + return -EINVAL; +} + /* * Check to see if there's room to enqueue num_trbs on the ring and make sure * enqueue pointer will not advance into dequeue segment. See rules above. @@ -2140,6 +2160,7 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, u32 trb_comp_code) { struct xhci_ep_ctx *ep_ctx; + int trbs_freed; ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); @@ -2209,9 +2230,15 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, } /* Update ring dequeue pointer */ + trbs_freed = xhci_num_trbs_to(ep_ring->deq_seg, ep_ring->dequeue, + td->last_trb_seg, td->last_trb, + ep_ring->num_segs); + if (trbs_freed < 0) + xhci_dbg(xhci, "Failed to count freed trbs at TD finish\n"); + else + ep_ring->num_trbs_free += trbs_freed; ep_ring->dequeue = td->last_trb; ep_ring->deq_seg = td->last_trb_seg; - ep_ring->num_trbs_free += td->num_trbs - 1; inc_deq(xhci, ep_ring); return xhci_td_cleanup(xhci, td, ep_ring, td->status); From 02f76c401d17e409ed45bf7887148fcc22c93c85 Mon Sep 17 00:00:00 2001 From: Chih-Yen Chang Date: Sun, 14 May 2023 12:05:05 +0900 Subject: [PATCH 220/358] ksmbd: fix global-out-of-bounds in smb2_find_context_vals Add tag_len argument in smb2_find_context_vals() to avoid out-of-bound read when create_context's name_len is larger than tag length. [ 7.995411] ================================================================== [ 7.995866] BUG: KASAN: global-out-of-bounds in memcmp+0x83/0xa0 [ 7.996248] Read of size 8 at addr ffffffff8258d940 by task kworker/0:0/7 ... [ 7.998191] Call Trace: [ 7.998358] [ 7.998503] dump_stack_lvl+0x33/0x50 [ 7.998743] print_report+0xcc/0x620 [ 7.999458] kasan_report+0xae/0xe0 [ 7.999895] kasan_check_range+0x35/0x1b0 [ 8.000152] memcmp+0x83/0xa0 [ 8.000347] smb2_find_context_vals+0xf7/0x1e0 [ 8.000635] smb2_open+0x1df2/0x43a0 [ 8.006398] handle_ksmbd_work+0x274/0x810 [ 8.006666] process_one_work+0x419/0x760 [ 8.006922] worker_thread+0x2a2/0x6f0 [ 8.007429] kthread+0x160/0x190 [ 8.007946] ret_from_fork+0x1f/0x30 [ 8.008181] Cc: stable@vger.kernel.org Signed-off-by: Chih-Yen Chang Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/oplock.c | 5 +++-- fs/ksmbd/oplock.h | 2 +- fs/ksmbd/smb2pdu.c | 14 +++++++------- 3 files changed, 11 insertions(+), 10 deletions(-) diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 2e54ded4d92c..6d1ccb999893 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1449,11 +1449,12 @@ struct lease_ctx_info *parse_lease_state(void *open_req) * smb2_find_context_vals() - find a particular context info in open request * @open_req: buffer containing smb2 file open(create) request * @tag: context name to search for + * @tag_len: the length of tag * * Return: pointer to requested context, NULL if @str context not found * or error pointer if name length is invalid. */ -struct create_context *smb2_find_context_vals(void *open_req, const char *tag) +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len) { struct create_context *cc; unsigned int next = 0; @@ -1492,7 +1493,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) return ERR_PTR(-EINVAL); name = (char *)cc + name_off; - if (memcmp(name, tag, name_len) == 0) + if (name_len == tag_len && !memcmp(name, tag, name_len)) return cc; remain_len -= next; diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h index 09753448f779..4b0fe6da7694 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/ksmbd/oplock.h @@ -118,7 +118,7 @@ void create_durable_v2_rsp_buf(char *cc, struct ksmbd_file *fp); void create_mxac_rsp_buf(char *cc, int maximal_access); void create_disk_id_rsp_buf(char *cc, __u64 file_id, __u64 vol_id); void create_posix_rsp_buf(char *cc, struct ksmbd_file *fp); -struct create_context *smb2_find_context_vals(void *open_req, const char *str); +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len); struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, char *lease_key); int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index cb93fd231f4e..f317ce2461ee 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2464,7 +2464,7 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, return -ENOENT; /* Parse SD BUFFER create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER, 4); if (!context) return -ENOENT; else if (IS_ERR(context)) @@ -2666,7 +2666,7 @@ int smb2_open(struct ksmbd_work *work) if (req->CreateContextsOffset) { /* Parse non-durable handle create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2686,7 +2686,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST); + SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2697,7 +2697,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_TIMEWARP_REQUEST); + SMB2_CREATE_TIMEWARP_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2709,7 +2709,7 @@ int smb2_open(struct ksmbd_work *work) if (tcon->posix_extensions) { context = smb2_find_context_vals(req, - SMB2_CREATE_TAG_POSIX); + SMB2_CREATE_TAG_POSIX, 16); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -3107,7 +3107,7 @@ int smb2_open(struct ksmbd_work *work) struct create_alloc_size_req *az_req; az_req = (struct create_alloc_size_req *)smb2_find_context_vals(req, - SMB2_CREATE_ALLOCATION_SIZE); + SMB2_CREATE_ALLOCATION_SIZE, 4); if (IS_ERR(az_req)) { rc = PTR_ERR(az_req); goto err_out; @@ -3134,7 +3134,7 @@ int smb2_open(struct ksmbd_work *work) err); } - context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID); + context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out; From f0a96d1aafd8964e1f9955c830a3e5cb3c60a90f Mon Sep 17 00:00:00 2001 From: Chih-Yen Chang Date: Sat, 6 May 2023 00:01:54 +0900 Subject: [PATCH 221/358] ksmbd: fix wrong UserName check in session_user The offset of UserName is related to the address of security buffer. To ensure the validaty of UserName, we need to compare name_off + name_len with secbuf_len instead of auth_msg_len. [ 27.096243] ================================================================== [ 27.096890] BUG: KASAN: slab-out-of-bounds in smb_strndup_from_utf16+0x188/0x350 [ 27.097609] Read of size 2 at addr ffff888005e3b542 by task kworker/0:0/7 ... [ 27.099950] Call Trace: [ 27.100194] [ 27.100397] dump_stack_lvl+0x33/0x50 [ 27.100752] print_report+0xcc/0x620 [ 27.102305] kasan_report+0xae/0xe0 [ 27.103072] kasan_check_range+0x35/0x1b0 [ 27.103757] smb_strndup_from_utf16+0x188/0x350 [ 27.105474] smb2_sess_setup+0xaf8/0x19c0 [ 27.107935] handle_ksmbd_work+0x274/0x810 [ 27.108315] process_one_work+0x419/0x760 [ 27.108689] worker_thread+0x2a2/0x6f0 [ 27.109385] kthread+0x160/0x190 [ 27.110129] ret_from_fork+0x1f/0x30 [ 27.110454] Cc: stable@vger.kernel.org Signed-off-by: Chih-Yen Chang Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index f317ce2461ee..717bcd20545b 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1356,7 +1356,7 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, struct authenticate_message *authblob; struct ksmbd_user *user; char *name; - unsigned int auth_msg_len, name_off, name_len, secbuf_len; + unsigned int name_off, name_len, secbuf_len; secbuf_len = le16_to_cpu(req->SecurityBufferLength); if (secbuf_len < sizeof(struct authenticate_message)) { @@ -1366,9 +1366,8 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, authblob = user_authblob(conn, req); name_off = le32_to_cpu(authblob->UserName.BufferOffset); name_len = le16_to_cpu(authblob->UserName.Length); - auth_msg_len = le16_to_cpu(req->SecurityBufferOffset) + secbuf_len; - if (auth_msg_len < (u64)name_off + name_len) + if (secbuf_len < (u64)name_off + name_len) return NULL; name = smb_strndup_from_utf16((const char *)authblob + name_off, From 443d61d1fa9faa60ef925513d83742902390100f Mon Sep 17 00:00:00 2001 From: Chih-Yen Chang Date: Sat, 6 May 2023 00:03:54 +0900 Subject: [PATCH 222/358] ksmbd: allocate one more byte for implied bcc[0] ksmbd_smb2_check_message allows client to return one byte more, so we need to allocate additional memory in ksmbd_conn_handler_loop to avoid out-of-bound access. Cc: stable@vger.kernel.org Signed-off-by: Chih-Yen Chang Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/connection.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 4ed379f9b1aa..4882a812ea86 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -351,7 +351,8 @@ int ksmbd_conn_handler_loop(void *p) break; /* 4 for rfc1002 length field */ - size = pdu_size + 4; + /* 1 for implied bcc[0] */ + size = pdu_size + 4 + 1; conn->request_buf = kvmalloc(size, GFP_KERNEL); if (!conn->request_buf) break; From e7b8b8ed9960bf699bf4029f482d9e869c094ed6 Mon Sep 17 00:00:00 2001 From: Gustav Johansson Date: Sat, 6 May 2023 00:05:07 +0900 Subject: [PATCH 223/358] ksmbd: smb2: Allow messages padded to 8byte boundary clc length is now accepted to <= 8 less than length, rather than < 8. Solve issues on some of Axis's smb clients which send messages where clc length is 8 bytes less than length. The specific client was running kernel 4.19.217 with smb dialect 3.0.2 on armv7l. Cc: stable@vger.kernel.org Signed-off-by: Gustav Johansson Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2misc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c index fbdde426dd01..0ffe663b7590 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/ksmbd/smb2misc.c @@ -416,8 +416,11 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) /* * Allow a message that padded to 8byte boundary. + * Linux 4.19.217 with smb 3.0.2 are sometimes + * sending messages where the cls_len is exactly + * 8 bytes less than len. */ - if (clc_len < len && (len - clc_len) < 8) + if (clc_len < len && (len - clc_len) <= 8) goto validate_credit; pr_err_ratelimited( From ab7470bc6d8fb5f3004ccc8e4dfd49aab0f27561 Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Mon, 17 Apr 2023 17:44:45 -0600 Subject: [PATCH 224/358] ice: Fix stats after PF reset After a core PF reset, the VFs were showing wrong Rx/Tx stats. This is a regression in commit 6624e780a577 ("ice: split ice_vsi_setup into smaller functions") caused by missing to set "stat_offsets_loaded = false" in the ice_vsi_rebuild() path. Fixes: 6624e780a577 ("ice: split ice_vsi_setup into smaller functions") Signed-off-by: Ahmed Zaki Reviewed-by: Alexander Lobakin Tested-by: Rafal Romanowski Reviewed-by: Leon Romanovsky Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 450317dfcca7..11ae0e41f518 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2745,6 +2745,8 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) goto unroll_vector_base; ice_vsi_map_rings_to_vectors(vsi); + vsi->stat_offsets_loaded = false; + if (ice_is_xdp_ena_vsi(vsi)) { ret = ice_vsi_determine_xdp_res(vsi); if (ret) @@ -2793,6 +2795,9 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) ret = ice_vsi_alloc_ring_stats(vsi); if (ret) goto unroll_vector_base; + + vsi->stat_offsets_loaded = false; + /* Do not exit if configuring RSS had an issue, at least * receive traffic on first queue. Hence no need to capture * return value From 7255355a0636b4eff08d5e8139c77d98f151c4fc Mon Sep 17 00:00:00 2001 From: Dawid Wesierski Date: Tue, 18 Apr 2023 11:52:55 +0200 Subject: [PATCH 225/358] ice: Fix ice VF reset during iavf initialization Fix the current implementation that causes ice_trigger_vf_reset() to start resetting the VF even when the VF-NIC is still initializing. When we reset NIC with ice driver it can interfere with iavf-vf initialization e.g. during consecutive resets induced by ice iavf ice | | |<-----------------| | ice resets vf iavf | reset | start | |<-----------------| | ice resets vf | causing iavf | initialization | error | | iavf reset end This leads to a series of -53 errors (failed to init adminq) from the IAVF. Change the state of the vf_state field to be not active when the IAVF is still initializing. Make sure to wait until receiving the message on the message box to ensure that the vf is ready and initializded. In simple terms we use the ACTIVE flag to make sure that the ice driver knows if the iavf is ready for another reset iavf ice | | | | |<------------- ice resets vf iavf vf_state != ACTIVE reset | start | | | | | iavf | reset-------> vf_state == ACTIVE end ice resets vf | | | | Fixes: c54d209c78b8 ("ice: Wait for VF to be reset/ready before configuration") Signed-off-by: Dawid Wesierski Signed-off-by: Kamil Maziarz Acked-by: Jacob Keller Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_sriov.c | 8 ++++---- drivers/net/ethernet/intel/ice/ice_vf_lib.c | 19 +++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_vf_lib.h | 1 + drivers/net/ethernet/intel/ice/ice_virtchnl.c | 1 + 4 files changed, 25 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index f1dca59bd844..588ad8696756 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1171,7 +1171,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1286,7 +1286,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto out_put_vf; } - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1340,7 +1340,7 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) return -EOPNOTSUPP; } - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1653,7 +1653,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 89fd6982df09..bf74a2f3a4f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -185,6 +185,25 @@ int ice_check_vf_ready_for_cfg(struct ice_vf *vf) return 0; } +/** + * ice_check_vf_ready_for_reset - check if VF is ready to be reset + * @vf: VF to check if it's ready to be reset + * + * The purpose of this function is to ensure that the VF is not in reset, + * disabled, and is both initialized and active, thus enabling us to safely + * initialize another reset. + */ +int ice_check_vf_ready_for_reset(struct ice_vf *vf) +{ + int ret; + + ret = ice_check_vf_ready_for_cfg(vf); + if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + ret = -EAGAIN; + + return ret; +} + /** * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index e3cda6fb71ab..a38ef00a3679 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -215,6 +215,7 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); +int ice_check_vf_ready_for_reset(struct ice_vf *vf); void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 97243c616d5d..f4a524f80b11 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3955,6 +3955,7 @@ error_handler: ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: + clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: From 7dcbdf29282fbcdb646dc785e8a57ed2c2fec8ba Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Mon, 17 Apr 2023 12:09:39 -0600 Subject: [PATCH 226/358] iavf: send VLAN offloading caps once after VFR When the user disables rxvlan offloading and then changes the number of channels, all VLAN ports are unable to receive traffic. Changing the number of channels triggers a VFR reset. During re-init, when VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS is received, we do: 1 - set the IAVF_FLAG_SETUP_NETDEV_FEATURES flag 2 - call iavf_set_vlan_offload_features(adapter, 0, netdev->features); The second step sends to the PF the __default__ features, in this case aq_required |= IAVF_FLAG_AQ_ENABLE_CTAG_VLAN_STRIPPING While the first step forces the watchdog task to call netdev_update_features() -> iavf_set_features() -> iavf_set_vlan_offload_features(adapter, netdev->features, features). Since the user disabled the "rxvlan", this sets: aq_required |= IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_STRIPPING When we start processing the AQ commands, both flags are enabled. Since we process DISABLE_XTAG first then ENABLE_XTAG, this results in the PF enabling the rxvlan offload. This breaks all communications on the VLAN net devices. Fix by removing the call to iavf_set_vlan_offload_features() (second step). Calling netdev_update_features() from watchdog task is enough for both init and reset paths. Fixes: 7598f4b40bd6 ("iavf: Move netdev_update_features() into watchdog task") Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Leon Romanovsky Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 9afbbdac3590..7c0578b5457b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2238,11 +2238,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; - /* Request VLAN offload settings */ - if (VLAN_V2_ALLOWED(adapter)) - iavf_set_vlan_offload_features(adapter, 0, - netdev->features); - iavf_set_queue_vlan_tag_loc(adapter); was_mac_changed = !ether_addr_equal(netdev->dev_addr, From 1b6b4ed01493b7ea2205ab83c49198f7d13ca9d2 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 24 Apr 2023 10:32:24 +0300 Subject: [PATCH 227/358] wifi: cfg80211: Drop entries with invalid BSSIDs in RNR Ignore AP information for entries that include an invalid BSSID in the TBTT information field, e.g., all zeros BSSIDs. Fixes: c8cb5b854b40 ("nl80211/cfg80211: support 6 GHz scanning") Signed-off-by: Ilan Peer Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230424103224.5e65d04d1448.Ic10c8577ae4a85272c407106c9d0a2ecb5372743@changeid Signed-off-by: Johannes Berg --- net/wireless/scan.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index a1382255fab3..c501db7bbdb3 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -5,7 +5,7 @@ * Copyright 2008 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2023 Intel Corporation */ #include #include @@ -540,6 +540,10 @@ static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry, /* skip the TBTT offset */ pos++; + /* ignore entries with invalid BSSID */ + if (!is_valid_ether_addr(pos)) + return -EINVAL; + memcpy(entry->bssid, pos, ETH_ALEN); pos += ETH_ALEN; From ef6e1997da63ad0ac3fe33153fec9524c9ae56c9 Mon Sep 17 00:00:00 2001 From: Mirsad Goran Todorovac Date: Tue, 25 Apr 2023 18:40:08 +0200 Subject: [PATCH 228/358] wifi: mac80211: fortify the spinlock against deadlock by interrupt In the function ieee80211_tx_dequeue() there is a particular locking sequence: begin: spin_lock(&local->queue_stop_reason_lock); q_stopped = local->queue_stop_reasons[q]; spin_unlock(&local->queue_stop_reason_lock); However small the chance (increased by ftracetest), an asynchronous interrupt can occur in between of spin_lock() and spin_unlock(), and the interrupt routine will attempt to lock the same &local->queue_stop_reason_lock again. This will cause a costly reset of the CPU and the wifi device or an altogether hang in the single CPU and single core scenario. The only remaining spin_lock(&local->queue_stop_reason_lock) that did not disable interrupts was patched, which should prevent any deadlocks on the same CPU/core and the same wifi device. This is the probable trace of the deadlock: kernel: ================================ kernel: WARNING: inconsistent lock state kernel: 6.3.0-rc6-mt-20230401-00001-gf86822a1170f #4 Tainted: G W kernel: -------------------------------- kernel: inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. kernel: kworker/5:0/25656 [HC0[0]:SC0[0]:HE1:SE1] takes: kernel: ffff9d6190779478 (&local->queue_stop_reason_lock){+.?.}-{2:2}, at: return_to_handler+0x0/0x40 kernel: {IN-SOFTIRQ-W} state was registered at: kernel: lock_acquire+0xc7/0x2d0 kernel: _raw_spin_lock+0x36/0x50 kernel: ieee80211_tx_dequeue+0xb4/0x1330 [mac80211] kernel: iwl_mvm_mac_itxq_xmit+0xae/0x210 [iwlmvm] kernel: iwl_mvm_mac_wake_tx_queue+0x2d/0xd0 [iwlmvm] kernel: ieee80211_queue_skb+0x450/0x730 [mac80211] kernel: __ieee80211_xmit_fast.constprop.66+0x834/0xa50 [mac80211] kernel: __ieee80211_subif_start_xmit+0x217/0x530 [mac80211] kernel: ieee80211_subif_start_xmit+0x60/0x580 [mac80211] kernel: dev_hard_start_xmit+0xb5/0x260 kernel: __dev_queue_xmit+0xdbe/0x1200 kernel: neigh_resolve_output+0x166/0x260 kernel: ip_finish_output2+0x216/0xb80 kernel: __ip_finish_output+0x2a4/0x4d0 kernel: ip_finish_output+0x2d/0xd0 kernel: ip_output+0x82/0x2b0 kernel: ip_local_out+0xec/0x110 kernel: igmpv3_sendpack+0x5c/0x90 kernel: igmp_ifc_timer_expire+0x26e/0x4e0 kernel: call_timer_fn+0xa5/0x230 kernel: run_timer_softirq+0x27f/0x550 kernel: __do_softirq+0xb4/0x3a4 kernel: irq_exit_rcu+0x9b/0xc0 kernel: sysvec_apic_timer_interrupt+0x80/0xa0 kernel: asm_sysvec_apic_timer_interrupt+0x1f/0x30 kernel: _raw_spin_unlock_irqrestore+0x3f/0x70 kernel: free_to_partial_list+0x3d6/0x590 kernel: __slab_free+0x1b7/0x310 kernel: kmem_cache_free+0x52d/0x550 kernel: putname+0x5d/0x70 kernel: do_sys_openat2+0x1d7/0x310 kernel: do_sys_open+0x51/0x80 kernel: __x64_sys_openat+0x24/0x30 kernel: do_syscall_64+0x5c/0x90 kernel: entry_SYSCALL_64_after_hwframe+0x72/0xdc kernel: irq event stamp: 5120729 kernel: hardirqs last enabled at (5120729): [] trace_graph_return+0xd6/0x120 kernel: hardirqs last disabled at (5120728): [] trace_graph_return+0xf0/0x120 kernel: softirqs last enabled at (5069900): [] return_to_handler+0x0/0x40 kernel: softirqs last disabled at (5067555): [] return_to_handler+0x0/0x40 kernel: other info that might help us debug this: kernel: Possible unsafe locking scenario: kernel: CPU0 kernel: ---- kernel: lock(&local->queue_stop_reason_lock); kernel: kernel: lock(&local->queue_stop_reason_lock); kernel: *** DEADLOCK *** kernel: 8 locks held by kworker/5:0/25656: kernel: #0: ffff9d618009d138 ((wq_completion)events_freezable){+.+.}-{0:0}, at: process_one_work+0x1ca/0x530 kernel: #1: ffffb1ef4637fe68 ((work_completion)(&local->restart_work)){+.+.}-{0:0}, at: process_one_work+0x1ce/0x530 kernel: #2: ffffffff9f166548 (rtnl_mutex){+.+.}-{3:3}, at: return_to_handler+0x0/0x40 kernel: #3: ffff9d6190778728 (&rdev->wiphy.mtx){+.+.}-{3:3}, at: return_to_handler+0x0/0x40 kernel: #4: ffff9d619077b480 (&mvm->mutex){+.+.}-{3:3}, at: return_to_handler+0x0/0x40 kernel: #5: ffff9d61907bacd8 (&trans_pcie->mutex){+.+.}-{3:3}, at: return_to_handler+0x0/0x40 kernel: #6: ffffffff9ef9cda0 (rcu_read_lock){....}-{1:2}, at: iwl_mvm_queue_state_change+0x59/0x3a0 [iwlmvm] kernel: #7: ffffffff9ef9cda0 (rcu_read_lock){....}-{1:2}, at: iwl_mvm_mac_itxq_xmit+0x42/0x210 [iwlmvm] kernel: stack backtrace: kernel: CPU: 5 PID: 25656 Comm: kworker/5:0 Tainted: G W 6.3.0-rc6-mt-20230401-00001-gf86822a1170f #4 kernel: Hardware name: LENOVO 82H8/LNVNB161216, BIOS GGCN51WW 11/16/2022 kernel: Workqueue: events_freezable ieee80211_restart_work [mac80211] kernel: Call Trace: kernel: kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: dump_stack_lvl+0x5f/0xa0 kernel: dump_stack+0x14/0x20 kernel: print_usage_bug.part.46+0x208/0x2a0 kernel: mark_lock.part.47+0x605/0x630 kernel: ? sched_clock+0xd/0x20 kernel: ? trace_clock_local+0x14/0x30 kernel: ? __rb_reserve_next+0x5f/0x490 kernel: ? _raw_spin_lock+0x1b/0x50 kernel: __lock_acquire+0x464/0x1990 kernel: ? mark_held_locks+0x4e/0x80 kernel: lock_acquire+0xc7/0x2d0 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ? ftrace_return_to_handler+0x8b/0x100 kernel: ? preempt_count_add+0x4/0x70 kernel: _raw_spin_lock+0x36/0x50 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ieee80211_tx_dequeue+0xb4/0x1330 [mac80211] kernel: ? prepare_ftrace_return+0xc5/0x190 kernel: ? ftrace_graph_func+0x16/0x20 kernel: ? 0xffffffffc02ab0b1 kernel: ? lock_acquire+0xc7/0x2d0 kernel: ? iwl_mvm_mac_itxq_xmit+0x42/0x210 [iwlmvm] kernel: ? ieee80211_tx_dequeue+0x9/0x1330 [mac80211] kernel: ? __rcu_read_lock+0x4/0x40 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_mac_itxq_xmit+0xae/0x210 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_queue_state_change+0x311/0x3a0 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_wake_sw_queue+0x17/0x20 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_txq_gen2_unmap+0x1c9/0x1f0 [iwlwifi] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_txq_gen2_free+0x55/0x130 [iwlwifi] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_txq_gen2_tx_free+0x63/0x80 [iwlwifi] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: _iwl_trans_pcie_gen2_stop_device+0x3f3/0x5b0 [iwlwifi] kernel: ? _iwl_trans_pcie_gen2_stop_device+0x9/0x5b0 [iwlwifi] kernel: ? mutex_lock_nested+0x4/0x30 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_trans_pcie_gen2_stop_device+0x5f/0x90 [iwlwifi] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_stop_device+0x78/0xd0 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: __iwl_mvm_mac_start+0x114/0x210 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_mac_start+0x76/0x150 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: drv_start+0x79/0x180 [mac80211] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ieee80211_reconfig+0x1523/0x1ce0 [mac80211] kernel: ? synchronize_net+0x4/0x50 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ieee80211_restart_work+0x108/0x170 [mac80211] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: process_one_work+0x250/0x530 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: worker_thread+0x48/0x3a0 kernel: ? __pfx_worker_thread+0x10/0x10 kernel: kthread+0x10f/0x140 kernel: ? __pfx_kthread+0x10/0x10 kernel: ret_from_fork+0x29/0x50 kernel: Fixes: 4444bc2116ae ("wifi: mac80211: Proper mark iTXQs for resumption") Link: https://lore.kernel.org/all/1f58a0d1-d2b9-d851-73c3-93fcc607501c@alu.unizg.hr/ Reported-by: Mirsad Goran Todorovac Cc: Gregory Greenman Cc: Johannes Berg Link: https://lore.kernel.org/all/cdc80531-f25f-6f9d-b15f-25e16130b53a@alu.unizg.hr/ Cc: David S. Miller Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Leon Romanovsky Cc: Alexander Wetzel Signed-off-by: Mirsad Goran Todorovac Reviewed-by: Leon Romanovsky Reviewed-by: tag, or it goes automatically? Link: https://lore.kernel.org/r/20230425164005.25272-1-mirsad.todorovac@alu.unizg.hr Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1a3327407552..0d9fbc8458fd 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3791,6 +3791,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, ieee80211_tx_result r; struct ieee80211_vif *vif = txq->vif; int q = vif->hw_queue[txq->ac]; + unsigned long flags; bool q_stopped; WARN_ON_ONCE(softirq_count() == 0); @@ -3799,9 +3800,9 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, return NULL; begin: - spin_lock(&local->queue_stop_reason_lock); + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); q_stopped = local->queue_stop_reasons[q]; - spin_unlock(&local->queue_stop_reason_lock); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); if (unlikely(q_stopped)) { /* mark for waking later */ From 13ad2b1eeacd48ec0f31f55964e6dc7dfc2c0299 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 24 Apr 2023 19:42:04 +0200 Subject: [PATCH 229/358] wifi: mac80211: Fix puncturing bitmap handling in __ieee80211_csa_finalize() 'changed' can be OR'ed with BSS_CHANGED_EHT_PUNCTURING which is larger than an u32. So, turn 'changed' into an u64 and update ieee80211_set_after_csa_beacon() accordingly. In the commit in Fixes, only ieee80211_start_ap() was updated. Fixes: 2cc25e4b2a04 ("wifi: mac80211: configure puncturing bitmap") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/e84a3f80fe536787f7a2c7180507efc36cd14f95.1682358088.git.christophe.jaillet@wanadoo.fr Signed-off-by: Johannes Berg --- net/mac80211/cfg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 7317e4a5d1ff..c5e5f783f137 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3589,7 +3589,7 @@ void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, bool block_t EXPORT_SYMBOL(ieee80211_channel_switch_disconnect); static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, - u32 *changed) + u64 *changed) { int err; @@ -3632,7 +3632,7 @@ static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; - u32 changed = 0; + u64 changed = 0; int err; sdata_assert_lock(sdata); From 9e26f098a2a5a4c4cd327ad911ed2eb9a067a7b8 Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Sun, 30 Apr 2023 20:18:30 +0300 Subject: [PATCH 230/358] wifi: iwlwifi: mvm: rfi: disable RFI feature This feature depends on a platform bugfix. Until we have a mechanism that can verify a platform has the required bugfix, disable RFI. Fixes: ef3ed33dfc8f ("wifi: iwlwifi: bump FW API to 77 for AX devices") Reported-by: Jeff Chua Link: https://lore.kernel.org/linux-wireless/CAAJw_ZvZdFpw9W2Hisc9c2BAFbYAnQuaFFaFG6N7qPUP2fOL_w@mail.gmail.com/ Signed-off-by: Gregory Greenman Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 3 +-- drivers/net/wireless/intel/iwlwifi/mvm/mvm.h | 1 + drivers/net/wireless/intel/iwlwifi/mvm/rfi.c | 16 +++++++++++++--- 3 files changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index b35c96cf7ad2..e2573a9d6f27 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1727,8 +1727,7 @@ int iwl_mvm_up(struct iwl_mvm *mvm) iwl_mvm_tas_init(mvm); iwl_mvm_leds_sync(mvm); - if (fw_has_capa(&mvm->fw->ucode_capa, - IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) { + if (iwl_rfi_supported(mvm)) { if (iwl_mvm_eval_dsm_rfi(mvm) == DSM_VALUE_RFI_ENABLE) iwl_rfi_send_config_cmd(mvm, NULL); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 6e7470d3a826..9e5008e0e47f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -2347,6 +2347,7 @@ int iwl_mvm_mld_update_sta_keys(struct iwl_mvm *mvm, u32 old_sta_mask, u32 new_sta_mask); +bool iwl_rfi_supported(struct iwl_mvm *mvm); int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_table); struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c index bb77bc9aa821..2ecd32bed752 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2020 - 2021 Intel Corporation + * Copyright (C) 2020 - 2022 Intel Corporation */ #include "mvm.h" @@ -70,6 +70,16 @@ static const struct iwl_rfi_lut_entry iwl_rfi_table[IWL_RFI_LUT_SIZE] = { PHY_BAND_6, PHY_BAND_6,}}, }; +bool iwl_rfi_supported(struct iwl_mvm *mvm) +{ + /* The feature depends on a platform bugfix, so for now + * it's always disabled. + * When the platform support detection is implemented we should + * check FW TLV and platform support instead. + */ + return false; +} + int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_table) { int ret; @@ -81,7 +91,7 @@ int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_t .len[0] = sizeof(cmd), }; - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) + if (!iwl_rfi_supported(mvm)) return -EOPNOTSUPP; lockdep_assert_held(&mvm->mutex); @@ -113,7 +123,7 @@ struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm) .flags = CMD_WANT_SKB, }; - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) + if (!iwl_rfi_supported(mvm)) return ERR_PTR(-EOPNOTSUPP); mutex_lock(&mvm->mutex); From 248e4776514bf70236e6b1a54c65aa5324c8b1eb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 May 2023 16:45:01 +0300 Subject: [PATCH 231/358] wifi: mac80211: fix min center freq offset tracing We need to set the correct trace variable, otherwise we're overwriting something else instead and the right one that we print later is not initialized. Fixes: b6011960f392 ("mac80211: handle channel frequency offset") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230504134511.828474-2-gregory.greenman@intel.com Signed-off-by: Johannes Berg --- net/mac80211/trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index de5d69f21306..db0d0132c58c 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -67,7 +67,7 @@ __entry->min_freq_offset = (c)->chan ? (c)->chan->freq_offset : 0; \ __entry->min_chan_width = (c)->width; \ __entry->min_center_freq1 = (c)->center_freq1; \ - __entry->freq1_offset = (c)->freq1_offset; \ + __entry->min_freq1_offset = (c)->freq1_offset; \ __entry->min_center_freq2 = (c)->center_freq2; #define MIN_CHANDEF_PR_FMT " min_control:%d.%03d MHz min_width:%d min_center: %d.%03d/%d MHz" #define MIN_CHANDEF_PR_ARG __entry->min_control_freq, __entry->min_freq_offset, \ From a23d7f5b2fbda114de60c4b53311e052281d7533 Mon Sep 17 00:00:00 2001 From: Michael Lee Date: Thu, 4 May 2023 16:04:41 +0800 Subject: [PATCH 232/358] wifi: mac80211: Abort running color change when stopping the AP When stopping the AP, there might be a color change in progress. It should be deactivated here, or the driver might later finalize a color change on a stopped AP. Fixes: 5f9404abdf2a (mac80211: add support for BSS color change) Signed-off-by: Michael Lee Link: https://lore.kernel.org/r/20230504080441.22958-1-michael-cy.lee@mediatek.com Signed-off-by: Johannes Berg --- net/mac80211/cfg.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c5e5f783f137..86b2036d73ff 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1578,9 +1578,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); - /* abort any running channel switch */ + /* abort any running channel switch or color change */ mutex_lock(&local->mtx); link_conf->csa_active = false; + link_conf->color_change_active = false; if (link->csa_block_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); From 860e1b43da94551cd1e73adc36b3c64cc3e5dc01 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 May 2023 16:45:02 +0300 Subject: [PATCH 233/358] wifi: mac80211: simplify chanctx allocation There's no need to call ieee80211_recalc_chanctx_min_def() since it cannot and won't call the driver anyway; just use _ieee80211_recalc_chanctx_min_def() instead. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230504134511.828474-3-gregory.greenman@intel.com Signed-off-by: Johannes Berg --- net/mac80211/chan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index dbc34fbe7c8f..d23d1a7b4cc3 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -638,7 +638,7 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; ctx->conf.radar_enabled = false; - ieee80211_recalc_chanctx_min_def(local, ctx); + _ieee80211_recalc_chanctx_min_def(local, ctx); return ctx; } From b72a455a2409fd94d6d9b4eb51d659a88213243b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 May 2023 16:45:03 +0300 Subject: [PATCH 234/358] wifi: mac80211: consider reserved chanctx for mindef When a chanctx is reserved for a new vif and we recalculate the minimal definition for it, we need to consider the new interface it's being reserved for before we assign it, so it can be used directly with the correct min channel width. Fix the code to - optionally - consider that, and use that option just before doing the reassignment. Also, when considering channel context reservations, we should only consider the one link we're currently working with. Change the boolean argument to a link pointer to do that. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230504134511.828474-4-gregory.greenman@intel.com Signed-off-by: Johannes Berg --- net/mac80211/chan.c | 72 +++++++++++++++++++++++--------------- net/mac80211/ieee80211_i.h | 3 +- net/mac80211/util.c | 2 +- 3 files changed, 47 insertions(+), 30 deletions(-) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index d23d1a7b4cc3..1b182cf9d661 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -258,7 +258,8 @@ ieee80211_get_max_required_bw(struct ieee80211_sub_if_data *sdata, static enum nl80211_chan_width ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, - struct ieee80211_chanctx_conf *conf) + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; struct ieee80211_vif *vif = &sdata->vif; @@ -267,13 +268,14 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { enum nl80211_chan_width width = NL80211_CHAN_WIDTH_20_NOHT; - struct ieee80211_bss_conf *link_conf = - rcu_dereference(sdata->vif.link_conf[link_id]); + struct ieee80211_link_data *link = + rcu_dereference(sdata->link[link_id]); - if (!link_conf) + if (!link) continue; - if (rcu_access_pointer(link_conf->chanctx_conf) != conf) + if (link != rsvd_for && + rcu_access_pointer(link->conf->chanctx_conf) != &ctx->conf) continue; switch (vif->type) { @@ -287,7 +289,7 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, * point, so take the width from the chandef, but * account also for TDLS peers */ - width = max(link_conf->chandef.width, + width = max(link->conf->chandef.width, ieee80211_get_max_required_bw(sdata, link_id)); break; case NL80211_IFTYPE_P2P_DEVICE: @@ -296,7 +298,7 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_OCB: - width = link_conf->chandef.width; + width = link->conf->chandef.width; break; case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_UNSPECIFIED: @@ -316,7 +318,8 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, static enum nl80211_chan_width ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, - struct ieee80211_chanctx_conf *conf) + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { struct ieee80211_sub_if_data *sdata; enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; @@ -328,7 +331,8 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, if (!ieee80211_sdata_running(sdata)) continue; - width = ieee80211_get_chanctx_vif_max_required_bw(sdata, conf); + width = ieee80211_get_chanctx_vif_max_required_bw(sdata, ctx, + rsvd_for); max_bw = max(max_bw, width); } @@ -336,8 +340,8 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, /* use the configured bandwidth in case of monitor interface */ sdata = rcu_dereference(local->monitor_sdata); if (sdata && - rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) == conf) - max_bw = max(max_bw, conf->def.width); + rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) == &ctx->conf) + max_bw = max(max_bw, ctx->conf.def.width); rcu_read_unlock(); @@ -349,8 +353,10 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, * the max of min required widths of all the interfaces bound to this * channel context. */ -static u32 _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) +static u32 +_ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { enum nl80211_chan_width max_bw; struct cfg80211_chan_def min_def; @@ -370,7 +376,7 @@ static u32 _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, return 0; } - max_bw = ieee80211_get_chanctx_max_required_bw(local, &ctx->conf); + max_bw = ieee80211_get_chanctx_max_required_bw(local, ctx, rsvd_for); /* downgrade chandef up to max_bw */ min_def = ctx->conf.def; @@ -448,9 +454,10 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, * channel context. */ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { - u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx); + u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); if (!changed) return; @@ -464,10 +471,11 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, ieee80211_chan_bw_change(local, ctx, false); } -static void ieee80211_change_chanctx(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - struct ieee80211_chanctx *old_ctx, - const struct cfg80211_chan_def *chandef) +static void _ieee80211_change_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_chanctx *old_ctx, + const struct cfg80211_chan_def *chandef, + struct ieee80211_link_data *rsvd_for) { u32 changed; @@ -492,7 +500,7 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, ieee80211_chan_bw_change(local, old_ctx, true); if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) { - ieee80211_recalc_chanctx_min_def(local, ctx); + ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); return; } @@ -502,7 +510,7 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, /* check if min chanctx also changed */ changed = IEEE80211_CHANCTX_CHANGE_WIDTH | - _ieee80211_recalc_chanctx_min_def(local, ctx); + _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); drv_change_chanctx(local, ctx, changed); if (!local->use_chanctx) { @@ -514,6 +522,14 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, ieee80211_chan_bw_change(local, old_ctx, false); } +static void ieee80211_change_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_chanctx *old_ctx, + const struct cfg80211_chan_def *chandef) +{ + _ieee80211_change_chanctx(local, ctx, old_ctx, chandef, NULL); +} + static struct ieee80211_chanctx * ieee80211_find_chanctx(struct ieee80211_local *local, const struct cfg80211_chan_def *chandef, @@ -638,7 +654,7 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; ctx->conf.radar_enabled = false; - _ieee80211_recalc_chanctx_min_def(local, ctx); + _ieee80211_recalc_chanctx_min_def(local, ctx, NULL); return ctx; } @@ -873,12 +889,12 @@ out: ieee80211_recalc_chanctx_chantype(local, curr_ctx); ieee80211_recalc_smps_chanctx(local, curr_ctx); ieee80211_recalc_radar_chanctx(local, curr_ctx); - ieee80211_recalc_chanctx_min_def(local, curr_ctx); + ieee80211_recalc_chanctx_min_def(local, curr_ctx, NULL); } if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) { ieee80211_recalc_txpower(sdata, false); - ieee80211_recalc_chanctx_min_def(local, new_ctx); + ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL); } if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && @@ -1270,7 +1286,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) ieee80211_link_update_chandef(link, &link->reserved_chandef); - ieee80211_change_chanctx(local, new_ctx, old_ctx, chandef); + _ieee80211_change_chanctx(local, new_ctx, old_ctx, chandef, link); vif_chsw[0].vif = &sdata->vif; vif_chsw[0].old_ctx = &old_ctx->conf; @@ -1300,7 +1316,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) if (ieee80211_chanctx_refcount(local, old_ctx) == 0) ieee80211_free_chanctx(local, old_ctx); - ieee80211_recalc_chanctx_min_def(local, new_ctx); + ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL); ieee80211_recalc_smps_chanctx(local, new_ctx); ieee80211_recalc_radar_chanctx(local, new_ctx); @@ -1665,7 +1681,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) ieee80211_recalc_chanctx_chantype(local, ctx); ieee80211_recalc_smps_chanctx(local, ctx); ieee80211_recalc_radar_chanctx(local, ctx); - ieee80211_recalc_chanctx_min_def(local, ctx); + ieee80211_recalc_chanctx_min_def(local, ctx, NULL); list_for_each_entry_safe(link, link_tmp, &ctx->reserved_links, reserved_chanctx_list) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a0a7839cb961..b0372e76f373 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2537,7 +2537,8 @@ int ieee80211_chanctx_refcount(struct ieee80211_local *local, void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *chanctx); void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx); + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for); bool ieee80211_is_radar_required(struct ieee80211_local *local); void ieee80211_dfs_cac_timer(unsigned long data); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1527d6aafc14..4bf76150925d 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3015,7 +3015,7 @@ void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata, chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); - ieee80211_recalc_chanctx_min_def(local, chanctx); + ieee80211_recalc_chanctx_min_def(local, chanctx, NULL); } unlock: mutex_unlock(&local->chanctx_mtx); From 04312de4ced4b152749614e8179f3978a20a992f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 May 2023 16:45:04 +0300 Subject: [PATCH 235/358] wifi: mac80211: recalc chanctx mindef before assigning When we allocate a new channel context, or find an existing one that is compatible, we currently assign it to a link before its mindef is updated. This leads to strange situations, especially in link switching where you switch to an 80 MHz link and expect it to be active immediately, but the mindef is still configured to 20 MHz while assigning. Also, it's strange that the chandef passed to the assign method's argument is wider than the one in the context. Fix this by calculating the mindef with the new link considered before calling the driver. In particular, this fixes an iwlwifi problem during link switch where the firmware would assert because the (link) station that was added for the AP is configured to transmit at a bandwidth that's wider than the channel context that it's configured on. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230504134511.828474-5-gregory.greenman@intel.com Signed-off-by: Johannes Berg --- net/mac80211/chan.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 1b182cf9d661..77c90ed8f5d7 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -871,6 +871,9 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, } if (new_ctx) { + /* recalc considering the link we'll use it for now */ + ieee80211_recalc_chanctx_min_def(local, new_ctx, link); + ret = drv_assign_vif_chanctx(local, sdata, link->conf, new_ctx); if (ret) goto out; From 783336b05f06821c9af3b057ecd5a7aa082ed973 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:44 +0300 Subject: [PATCH 236/358] wifi: iwlwifi: mvm: always free dup_data There are some assertions in the STA removal code that can fail, and in that case we may leak memory since we skip the freeing. Fix this by freeing the dup_data earlier in the function, we already have a check for when we free the station, and this we don't need to do it with and without MLD API, so it's a win all around. Fixes: a571f5f635ef ("iwlwifi: mvm: add duplicate packet detection per rx queue") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.173938681d72.Iff4b55fc52943825d6e3e28d78a24b155ea5cd22@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 3 +++ drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c | 2 -- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 3 --- 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 0f01b62357c6..1c96cf020801 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3889,6 +3889,9 @@ int iwl_mvm_mac_sta_state_common(struct ieee80211_hw *hw, * from the AP now. */ iwl_mvm_reset_cca_40mhz_workaround(mvm, vif); + + /* Also free dup data just in case any assertions below fail */ + kfree(mvm_sta->dup_data); } mutex_lock(&mvm->mutex); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index 0bfdf4462755..f877be850589 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -791,8 +791,6 @@ int iwl_mvm_mld_rm_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, lockdep_assert_held(&mvm->mutex); - kfree(mvm_sta->dup_data); - /* flush its queues here since we are freeing mvm_sta */ for_each_sta_active_link(vif, sta, link_sta, link_id) { struct iwl_mvm_link_sta *mvm_link_sta = diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 5469d634e289..1e8592d3bcd6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2089,9 +2089,6 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm, lockdep_assert_held(&mvm->mutex); - if (iwl_mvm_has_new_rx_api(mvm)) - kfree(mvm_sta->dup_data); - ret = iwl_mvm_drain_sta(mvm, mvm_sta, true); if (ret) return ret; From 9e949dfdc5d1697ccbcc19c06f5133e1833d8eea Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:45 +0300 Subject: [PATCH 237/358] wifi: iwlwifi: mvm: don't double-init spinlock We don't need to (and shouldn't) initialize the spinlock during HW restart that was already initialized, so move that into the correct if block. Since then we have two consecutive if statements with the same (though inverted) condition, unify those as well. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.221c22cfdf4e.I2e30113ef4bd8cb5bd9e1a69e52a95671914961c@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index f877be850589..19f1545b3c7e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -667,15 +667,15 @@ int iwl_mvm_mld_add_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, ret = iwl_mvm_mld_alloc_sta_links(mvm, vif, sta); if (ret) return ret; - } - spin_lock_init(&mvm_sta->lock); + spin_lock_init(&mvm_sta->lock); - if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) - ret = iwl_mvm_alloc_sta_after_restart(mvm, vif, sta); - else ret = iwl_mvm_sta_init(mvm, vif, sta, IWL_MVM_INVALID_STA, STATION_TYPE_PEER); + } else { + ret = iwl_mvm_alloc_sta_after_restart(mvm, vif, sta); + } + if (ret) goto err; From c2d8b7f257b2398f2d866205365895e038beca12 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:46 +0300 Subject: [PATCH 238/358] wifi: iwlwifi: mvm: fix cancel_delayed_work_sync() deadlock Lockdep points out that we can deadlock here by calling cancel_delayed_work_sync() because that might be already running and gotten interrupted by the NAPI soft-IRQ. Even just calling something that can sleep is wrong in this context though. Luckily, it doesn't even really matter since the things we need to do are idempotent, so just drop the _sync(). Fixes: e5d153ec54f0 ("iwlwifi: mvm: fix CSA AP side") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.b1813c823b4d.I9d20cc06d24fa40b6774d3dd95ea5e2bf8dd015b@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index e1d02c260e69..01432274a6da 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -2512,7 +2512,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, RCU_INIT_POINTER(mvm->csa_tx_blocked_vif, NULL); /* Unblock BCAST / MCAST station */ iwl_mvm_modify_all_sta_disable_tx(mvm, mvmvif, false); - cancel_delayed_work_sync(&mvm->cs_tx_unblock_dwork); + cancel_delayed_work(&mvm->cs_tx_unblock_dwork); } } From 204bfec9168ddd869a05e7f70dc5b0a9ae513722 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:47 +0300 Subject: [PATCH 239/358] wifi: iwlwifi: mvm: fix number of concurrent link checks The concurrent link checks need to correctly differentiate between AP and non-AP, fix that. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.992b2f981ef6.I7d386c19354e9be39c4822f436dd22c93422b660@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/link.c | 12 +++++++----- .../net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 9 +++++---- 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c index eb828de40a3c..3814915cb1a6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c @@ -123,11 +123,13 @@ int iwl_mvm_link_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (mvmvif->link[i]->phy_ctxt) count++; - /* FIXME: IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM should be - * defined per HW - */ - if (count >= IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM) - return -EINVAL; + if (vif->type == NL80211_IFTYPE_AP) { + if (count > mvm->fw->ucode_capa.num_beacons) + return -EOPNOTSUPP; + /* this should be per HW or such */ + } else if (count >= IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM) { + return -EOPNOTSUPP; + } } /* Catch early if driver tries to activate or deactivate a link diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c index fbc2d5ed1006..7fb66c570959 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c @@ -906,11 +906,12 @@ iwl_mvm_mld_change_vif_links(struct ieee80211_hw *hw, n_active++; } - if (vif->type == NL80211_IFTYPE_AP && - n_active > mvm->fw->ucode_capa.num_beacons) - return -EOPNOTSUPP; - else if (n_active > 1) + if (vif->type == NL80211_IFTYPE_AP) { + if (n_active > mvm->fw->ucode_capa.num_beacons) + return -EOPNOTSUPP; + } else if (n_active > 1) { return -EOPNOTSUPP; + } } for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { From d3ae69180bbd74bcbc03a2b6d10ed7eccbe98c23 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:48 +0300 Subject: [PATCH 240/358] wifi: iwlwifi: fw: fix DBGI dump The DBGI dump is (unsurprisingly) of type DBGI, not SRAM. This leads to bad register accesses because the union is built differently, there's no allocation ID, and thus the allocation ID ends up being 0x8000. Note that this was already wrong for DRAM vs. SMEM since they use different parts of the union, but the allocation ID is at the same place, so it worked. Fix all of this but set the allocation ID in a way that the offset calculation ends up without any offset. Fixes: 34bc27783a31 ("iwlwifi: yoyo: fix DBGI_SRAM ini dump header.") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.19a302ae4c65.I12272599f7c1930666157b9d5e7f81fe9ec4c421@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index d9faaae01abd..55219974b92b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -1664,14 +1664,10 @@ static __le32 iwl_get_mon_reg(struct iwl_fw_runtime *fwrt, u32 alloc_id, } static void * -iwl_dump_ini_mon_fill_header(struct iwl_fw_runtime *fwrt, - struct iwl_dump_ini_region_data *reg_data, +iwl_dump_ini_mon_fill_header(struct iwl_fw_runtime *fwrt, u32 alloc_id, struct iwl_fw_ini_monitor_dump *data, const struct iwl_fw_mon_regs *addrs) { - struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data; - u32 alloc_id = le32_to_cpu(reg->dram_alloc_id); - if (!iwl_trans_grab_nic_access(fwrt->trans)) { IWL_ERR(fwrt, "Failed to get monitor header\n"); return NULL; @@ -1702,8 +1698,10 @@ iwl_dump_ini_mon_dram_fill_header(struct iwl_fw_runtime *fwrt, void *data, u32 data_len) { struct iwl_fw_ini_monitor_dump *mon_dump = (void *)data; + struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data; + u32 alloc_id = le32_to_cpu(reg->dram_alloc_id); - return iwl_dump_ini_mon_fill_header(fwrt, reg_data, mon_dump, + return iwl_dump_ini_mon_fill_header(fwrt, alloc_id, mon_dump, &fwrt->trans->cfg->mon_dram_regs); } @@ -1713,8 +1711,10 @@ iwl_dump_ini_mon_smem_fill_header(struct iwl_fw_runtime *fwrt, void *data, u32 data_len) { struct iwl_fw_ini_monitor_dump *mon_dump = (void *)data; + struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data; + u32 alloc_id = le32_to_cpu(reg->internal_buffer.alloc_id); - return iwl_dump_ini_mon_fill_header(fwrt, reg_data, mon_dump, + return iwl_dump_ini_mon_fill_header(fwrt, alloc_id, mon_dump, &fwrt->trans->cfg->mon_smem_regs); } @@ -1725,7 +1725,10 @@ iwl_dump_ini_mon_dbgi_fill_header(struct iwl_fw_runtime *fwrt, { struct iwl_fw_ini_monitor_dump *mon_dump = (void *)data; - return iwl_dump_ini_mon_fill_header(fwrt, reg_data, mon_dump, + return iwl_dump_ini_mon_fill_header(fwrt, + /* no offset calculation later */ + IWL_FW_INI_ALLOCATION_ID_DBGC1, + mon_dump, &fwrt->trans->cfg->mon_dbgi_regs); } From 6818266283d191549afa87ac5d7b86635a5fb105 Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Sun, 14 May 2023 12:15:49 +0300 Subject: [PATCH 241/358] wifi: iwlwifi: mvm: fix access to fw_id_to_mac_id RCU protected fw_id_to_mac_id can be initialized with either an error code or NULL. Thus, after dereferencing need to check the value with IS_ERR_OR_NULL() and not only that it is not NULL. Fix it. Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.ec5f2880e81c.Ifa8c0f451df2835bde800f5c3670cc46238a3bd8@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c | 5 +++++ drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 7 +++++++ drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 10 +++++++++- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 2 +- 4 files changed, 22 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index 3963a0d4ed04..652a603c4500 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -526,6 +526,11 @@ iwl_mvm_ftm_put_target(struct iwl_mvm *mvm, struct ieee80211_vif *vif, rcu_read_lock(); sta = rcu_dereference(mvm->fw_id_to_mac_id[mvmvif->deflink.ap_sta_id]); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) { + rcu_read_unlock(); + return PTR_ERR_OR_ZERO(sta); + } + if (sta->mfp && (peer->ftm.trigger_based || peer->ftm.non_trigger_based)) FTM_PUT_FLAG(PMF); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 01432274a6da..6226e4e54a51 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -691,6 +691,11 @@ void iwl_mvm_reorder_timer_expired(struct timer_list *t) rcu_read_lock(); sta = rcu_dereference(buf->mvm->fw_id_to_mac_id[sta_id]); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) { + rcu_read_unlock(); + goto out; + } + mvmsta = iwl_mvm_sta_from_mac80211(sta); /* SN is set to the last expired frame + 1 */ @@ -712,6 +717,8 @@ void iwl_mvm_reorder_timer_expired(struct timer_list *t) entries[index].e.reorder_time + 1 + RX_REORDER_BUF_TIMEOUT_MQ); } + +out: spin_unlock(&buf->lock); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 1e8592d3bcd6..05a54a69c135 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -281,7 +281,7 @@ static void iwl_mvm_rx_agg_session_expired(struct timer_list *t) * A-MDPU and hence the timer continues to run. Then, the * timer expires and sta is NULL. */ - if (!sta) + if (IS_ERR_OR_NULL(sta)) goto unlock; mvm_sta = iwl_mvm_sta_from_mac80211(sta); @@ -3782,6 +3782,9 @@ static inline u8 *iwl_mvm_get_mac_addr(struct iwl_mvm *mvm, u8 sta_id = mvmvif->deflink.ap_sta_id; sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id], lockdep_is_held(&mvm->mutex)); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) + return NULL; + return sta->addr; } @@ -3819,6 +3822,11 @@ static int __iwl_mvm_set_sta_key(struct iwl_mvm *mvm, if (keyconf->cipher == WLAN_CIPHER_SUITE_TKIP) { addr = iwl_mvm_get_mac_addr(mvm, vif, sta); + if (!addr) { + IWL_ERR(mvm, "Failed to find mac address\n"); + return -EINVAL; + } + /* get phase 1 key from mac80211 */ ieee80211_get_key_rx_seq(keyconf, 0, &seq); ieee80211_get_tkip_rx_p1k(keyconf, addr, seq.tkip.iv32, p1k); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 10d7178f1071..00719e130438 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1875,7 +1875,7 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm, mvmsta = iwl_mvm_sta_from_staid_rcu(mvm, sta_id); sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]); - if (WARN_ON_ONCE(!sta || !sta->wme)) { + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta) || !sta->wme)) { rcu_read_unlock(); return; } From e234c36290430a833aa87532a7740fef031c2c85 Mon Sep 17 00:00:00 2001 From: Mukesh Sisodiya Date: Sun, 14 May 2023 12:15:50 +0300 Subject: [PATCH 242/358] wifi: iwlwifi: mvm: fix initialization of a return value In iwl_mvm_mld_update_sta(), if the flow doesn't enter for_each_sta_active_link(), the default value is returned. Set this default to -EINVAL instead of 0 to better reflect this. Signed-off-by: Mukesh Sisodiya Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.98b7e3aacf0b.I2fc274dd7e374ef7fac8e26d71c9cd73323da665@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index 19f1545b3c7e..85a4ce8449ad 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -728,7 +728,7 @@ int iwl_mvm_mld_update_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); struct ieee80211_link_sta *link_sta; unsigned int link_id; - int ret = 0; + int ret = -EINVAL; lockdep_assert_held(&mvm->mutex); From eca7296d9a671e9961834d2ace9cc0ce21fc15b3 Mon Sep 17 00:00:00 2001 From: Alon Giladi Date: Sun, 14 May 2023 12:15:51 +0300 Subject: [PATCH 243/358] wifi: iwlwifi: fix OEM's name in the ppag approved list Fix a spelling mistake. Fixes: e8e10a37c51c ("iwlwifi: acpi: move ppag code from mvm to fw/acpi") Signed-off-by: Alon Giladi Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.fdd07f36a8bf.I223e5fb16ab5c95d504c3fdaffd0bd70affad1c2@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 5f4a51310add..cb9181f05501 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -38,7 +38,7 @@ static const struct dmi_system_id dmi_ppag_approved_list[] = { }, { .ident = "ASUS", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek COMPUTER INC."), + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), }, }, {} From d0246a0e49efee0f8649d0e4f2350614cdfe6565 Mon Sep 17 00:00:00 2001 From: Alon Giladi Date: Sun, 14 May 2023 12:15:52 +0300 Subject: [PATCH 244/358] wifi: iwlwifi: mvm: fix OEM's name in the tas approved list Fix a spelling mistake. Fixes: 2856f623ce48 ("iwlwifi: mvm: Add list of OEMs allowed to use TAS") Signed-off-by: Alon Giladi Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.4090de6d1878.If9391ef6da78f1b2cc5eb6cb8f6965816bb7a7f5@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index e2573a9d6f27..205c09bc9863 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1091,7 +1091,7 @@ static const struct dmi_system_id dmi_tas_approved_list[] = { }, { .ident = "LENOVO", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Lenovo"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), }, }, { .ident = "DELL", From 682b6dc29d98e857e6ca4bbc077c7dc2899b7473 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:53 +0300 Subject: [PATCH 245/358] wifi: iwlwifi: mvm: don't trust firmware n_channels If the firmware sends us a corrupted MCC response with n_channels much larger than the command response can be, we might copy far too much (uninitialized) memory and even crash if the n_channels is large enough to make it run out of the one page allocated for the FW response. Fix that by checking the lengths. Doing a < comparison would be sufficient, but the firmware should be doing it correctly, so check more strictly. Fixes: dcaf9f5ecb6f ("iwlwifi: mvm: add MCC update FW API") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.d7b233139eb4.I51fd319df8e9d41881fc8450e83d78049518a79a@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/nvm.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 6d18a1fd649b..fdf60afb0f3f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -445,6 +445,11 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, struct iwl_mcc_update_resp *mcc_resp = (void *)pkt->data; n_channels = __le32_to_cpu(mcc_resp->n_channels); + if (iwl_rx_packet_payload_len(pkt) != + struct_size(mcc_resp, channels, n_channels)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } resp_len = sizeof(struct iwl_mcc_update_resp) + n_channels * sizeof(__le32); resp_cp = kmemdup(mcc_resp, resp_len, GFP_KERNEL); @@ -456,6 +461,11 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, struct iwl_mcc_update_resp_v3 *mcc_resp_v3 = (void *)pkt->data; n_channels = __le32_to_cpu(mcc_resp_v3->n_channels); + if (iwl_rx_packet_payload_len(pkt) != + struct_size(mcc_resp_v3, channels, n_channels)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } resp_len = sizeof(struct iwl_mcc_update_resp) + n_channels * sizeof(__le32); resp_cp = kzalloc(resp_len, GFP_KERNEL); From 207be64f4e60bf5de13fc69fcf7fe2441bf71a97 Mon Sep 17 00:00:00 2001 From: Miri Korenblit Date: Sun, 14 May 2023 12:15:54 +0300 Subject: [PATCH 246/358] wifi: iwlwifi: Don't use valid_links to iterate sta links This bitmap equals to zero when in a non-MLO mode, and then we won't be iterating on any link. Use for_each_sta_active_link() instead, as it handles also the case of non-MLO mode. Signed-off-by: Miri Korenblit Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.f32a8c08730a.Ib02248cd0b7f2bc885f91005c3c110dd027f9dcd@changeid Signed-off-by: Johannes Berg --- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 52 ++++++++----------- 1 file changed, 22 insertions(+), 30 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 1c96cf020801..17f788a5ff6b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2022 Intel Corporation + * Copyright (C) 2012-2014, 2018-2023 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -3607,7 +3607,8 @@ static bool iwl_mvm_vif_conf_from_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - unsigned int i; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; /* Beacon interval check - firmware will crash if the beacon * interval is less than 16. We can't avoid connecting at all, @@ -3616,14 +3617,11 @@ static bool iwl_mvm_vif_conf_from_sta(struct iwl_mvm *mvm, * wpa_s will blocklist the AP... */ - for_each_set_bit(i, (unsigned long *)&sta->valid_links, - IEEE80211_MLD_MAX_NUM_LINKS) { - struct ieee80211_link_sta *link_sta = - link_sta_dereference_protected(sta, i); + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf = - link_conf_dereference_protected(vif, i); + link_conf_dereference_protected(vif, link_id); - if (!link_conf || !link_sta) + if (!link_conf) continue; if (link_conf->beacon_int < IWL_MVM_MIN_BEACON_INTERVAL_TU) { @@ -3645,24 +3643,23 @@ static void iwl_mvm_vif_set_he_support(struct ieee80211_hw *hw, bool is_sta) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - unsigned int i; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; - for_each_set_bit(i, (unsigned long *)&sta->valid_links, - IEEE80211_MLD_MAX_NUM_LINKS) { - struct ieee80211_link_sta *link_sta = - link_sta_dereference_protected(sta, i); + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf = - link_conf_dereference_protected(vif, i); + link_conf_dereference_protected(vif, link_id); - if (!link_conf || !link_sta || !mvmvif->link[i]) + if (!link_conf || !mvmvif->link[link_id]) continue; link_conf->he_support = link_sta->he_cap.has_he; if (is_sta) { - mvmvif->link[i]->he_ru_2mhz_block = false; + mvmvif->link[link_id]->he_ru_2mhz_block = false; if (link_sta->he_cap.has_he) - iwl_mvm_check_he_obss_narrow_bw_ru(hw, vif, i, + iwl_mvm_check_he_obss_narrow_bw_ru(hw, vif, + link_id, link_conf); } } @@ -3675,6 +3672,7 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, struct iwl_mvm_sta_state_ops *callbacks) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); + struct ieee80211_link_sta *link_sta; unsigned int i; int ret; @@ -3699,15 +3697,9 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, NL80211_TDLS_SETUP); } - for (i = 0; i < ARRAY_SIZE(sta->link); i++) { - struct ieee80211_link_sta *link_sta; - - link_sta = link_sta_dereference_protected(sta, i); - if (!link_sta) - continue; - + for_each_sta_active_link(vif, sta, link_sta, i) link_sta->agg.max_rc_amsdu_len = 1; - } + ieee80211_sta_recalc_aggregates(sta); if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls) @@ -3725,7 +3717,8 @@ iwl_mvm_sta_state_auth_to_assoc(struct ieee80211_hw *hw, { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); - unsigned int i; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; lockdep_assert_held(&mvm->mutex); @@ -3751,14 +3744,13 @@ iwl_mvm_sta_state_auth_to_assoc(struct ieee80211_hw *hw, if (!mvm->mld_api_is_used) goto out; - for_each_set_bit(i, (unsigned long *)&sta->valid_links, - IEEE80211_MLD_MAX_NUM_LINKS) { + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf = - link_conf_dereference_protected(vif, i); + link_conf_dereference_protected(vif, link_id); if (WARN_ON(!link_conf)) return -EINVAL; - if (!mvmvif->link[i]) + if (!mvmvif->link[link_id]) continue; iwl_mvm_link_changed(mvm, vif, link_conf, From a8938bc881d2a03f9b77f19fae924fe798a01285 Mon Sep 17 00:00:00 2001 From: Ariel Malamud Date: Sun, 14 May 2023 12:15:55 +0300 Subject: [PATCH 247/358] wifi: iwlwifi: mvm: Add locking to the rate read flow The rs_drv_get_rate flow reads the lq_sta to return the optimal rate for tx frames. This read flow is not protected thereby leaving a small window, a few instructions wide, open to contention by an asynchronous rate update. Indeed this race condition was hit and the update occurred in the middle of the read. Fix this by locking the lq_sta struct during read. Signed-off-by: Ariel Malamud Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.b52c9ed5c379.I15290b78e0d966c1b68278263776ca9de841d5fe@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/rs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index a4c1e3bf4ff1..23266d0c9ce4 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -2691,6 +2691,8 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, return; lq_sta = mvm_sta; + + spin_lock(&lq_sta->pers.lock); iwl_mvm_hwrate_to_tx_rate_v1(lq_sta->last_rate_n_flags, info->band, &info->control.rates[0]); info->control.rates[0].count = 1; @@ -2705,6 +2707,7 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, iwl_mvm_hwrate_to_tx_rate_v1(last_ucode_rate, info->band, &txrc->reported_rate); } + spin_unlock(&lq_sta->pers.lock); } static void *rs_drv_alloc_sta(void *mvm_rate, struct ieee80211_sta *sta, From 098abbd48ec1accf111dde50a2a5392f2a15f59c Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 15 May 2023 17:22:27 +0800 Subject: [PATCH 248/358] mac80211_hwsim: fix memory leak in hwsim_new_radio_nl When parse_pmsr_capa failed in hwsim_new_radio_nl, the memory resources applied for by pmsr_capa are not released. Add release processing to the incorrect path. Fixes: 92d13386ec55 ("mac80211_hwsim: add PMSR capability support") Reported-by: syzbot+904ce6fbb38532d9795c@syzkaller.appspotmail.com Signed-off-by: Zhengchao Shao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230515092227.2691437-1-shaozhengchao@huawei.com Signed-off-by: Johannes Berg --- drivers/net/wireless/virtual/mac80211_hwsim.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 9a8faaf4c6b6..89c7a1420381 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -5964,10 +5964,11 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) ret = -ENOMEM; goto out_free; } + param.pmsr_capa = pmsr_capa; + ret = parse_pmsr_capa(info->attrs[HWSIM_ATTR_PMSR_SUPPORT], pmsr_capa, info); if (ret) goto out_free; - param.pmsr_capa = pmsr_capa; } ret = mac80211_hwsim_new_radio(info, ¶m); From 9dde12767aa19696a7fb28b2320119b87fb9d299 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 15 May 2023 15:45:30 -0700 Subject: [PATCH 249/358] perf metrics: Avoid segv with --topdown for metrics without a group Some metrics may not have a metric_group which can result in segvs with "perf stat --topdown". Add a condition for the no metric_group case. Fixes: 1647cd5b8802698f ("perf stat: Implement --topdown using json metrics") Reported-by: Kan Liang Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230515224530.671331-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 4e7d41d285b4..5e9c657dd3f7 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1672,7 +1672,7 @@ static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm, { unsigned int *max_level = data; unsigned int level; - const char *p = strstr(pm->metric_group, "TopdownL"); + const char *p = strstr(pm->metric_group ?: "", "TopdownL"); if (!p || p[8] == '\0') return 0; From 71852cd8825077d2d90466ac34d3b94e0be3bfae Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 16 May 2023 15:23:47 -0300 Subject: [PATCH 250/358] tools headers UAPI: Sync linux/prctl.h with the kernel sources ddc65971bb677aa9 ("prctl: add PR_GET_AUXV to copy auxv to userspace") To pick the changes in: That don't result in any changes in tooling: $ tools/perf/trace/beauty/prctl_option.sh > before $ cp include/uapi/linux/prctl.h tools/include/uapi/linux/prctl.h $ tools/perf/trace/beauty/prctl_option.sh > after $ diff -u before after $ This actually adds a new prctl arg, but it has to be dealt with differently, as it is not in sequence with the other arguments. Just silences this perf tools build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/prctl.h' differs from latest version at 'include/uapi/linux/prctl.h' diff -u tools/include/uapi/linux/prctl.h include/uapi/linux/prctl.h Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/prctl.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 759b3f53e53f..f23d9a16507f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -290,6 +290,8 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_GET_AUXV 0x41555856 + #define PR_SET_MEMORY_MERGE 67 #define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ From b633896314c0f78f2b4eb7b19a530d68f2a35445 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 16 May 2023 15:27:50 -0300 Subject: [PATCH 251/358] tools headers UAPI: Sync s390 syscall table file that wires up the memfd_secret syscall To pick the changes in these csets: 7608f70adcb1ea69 ("s390: wire up memfd_secret system call") That add support for this new syscall in tools such as 'perf trace'. For instance, this is now possible (adapted from the x86_64 test output): # perf trace -v -e memfd_secret event qualifier tracepoint filter: (common_pid != 13375 && common_pid != 3713) && (id == 447) ^C# That is the filter expression attached to the raw_syscalls:sys_{enter,exit} tracepoints. $ grep memfd_secret tools/perf/arch/x86/entry/syscalls/syscall_64.tbl 447 common memfd_secret sys_memfd_secret $ This addresses this perf build warnings: Warning: Kernel ABI header at 'tools/perf/arch/s390/entry/syscalls/syscall.tbl' differs from latest version at 'arch/s390/kernel/syscalls/syscall.tbl' diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl Cc: Adrian Hunter Cc: Heiko Carstens Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Vasily Gorbik Link: https://lore.kernel.org/lkml/ZGPMW0p++D1Jdvf6@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/entry/syscalls/syscall.tbl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 799147658dee..b68f47541169 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -449,7 +449,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -# 447 reserved for memfd_secret +447 common memfd_secret sys_memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node From 3b44ec8c5c44790a82f07e90db45643c762878c6 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 May 2023 20:44:12 +0200 Subject: [PATCH 252/358] ALSA: hda: Fix Oops by 9.1 surround channel names get_line_out_pfx() may trigger an Oops by overflowing the static array with more than 8 channels. This was reported for MacBookPro 12,1 with Cirrus codec. As a workaround, extend for the 9.1 channels and also fix the potential Oops by unifying the code paths accessing the same array with the proper size check. Reported-by: Olliver Schinagl Cc: Link: https://lore.kernel.org/r/64d95eb0-dbdb-cff8-a8b1-988dc22b24cd@schinagl.nl Link: https://lore.kernel.org/r/20230516184412.24078-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_generic.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index fc114e522480..dbf7aa88e0e3 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -1155,8 +1155,8 @@ static bool path_has_mixer(struct hda_codec *codec, int path_idx, int ctl_type) return path && path->ctls[ctl_type]; } -static const char * const channel_name[4] = { - "Front", "Surround", "CLFE", "Side" +static const char * const channel_name[] = { + "Front", "Surround", "CLFE", "Side", "Back", }; /* give some appropriate ctl name prefix for the given line out channel */ @@ -1182,7 +1182,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, /* multi-io channels */ if (ch >= cfg->line_outs) - return channel_name[ch]; + goto fixed_name; switch (cfg->line_out_type) { case AUTO_PIN_SPEAKER_OUT: @@ -1234,6 +1234,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, if (cfg->line_outs == 1 && !spec->multi_ios) return "Line Out"; + fixed_name: if (ch >= ARRAY_SIZE(channel_name)) { snd_BUG(); return "PCM"; From 96e3cc270d61cb9945b1c2894effcba15010f097 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 15 May 2023 17:15:18 -0700 Subject: [PATCH 253/358] Documentation: use capitalization for chapters and acronyms Use capital letters in acronyms for CD-ROM, FPGA, and PCMCIA. Use capital letter in the first word of chapter headings for Locking, Timers, and "Brief tutorial on CRC computation". Signed-off-by: Randy Dunlap Cc: Moritz Fischer Cc: Wu Hao Cc: Tom Rix Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Cc: Boqun Feng Cc: Dominik Brodowski Cc: Thomas Gleixner Acked-by: Xu Yilun Reviewed-by: Phillip Potter Link: https://lore.kernel.org/r/20230516001518.14514-1-rdunlap@infradead.org Signed-off-by: Jonathan Corbet --- Documentation/cdrom/index.rst | 6 +++--- Documentation/fpga/index.rst | 2 +- Documentation/locking/index.rst | 2 +- Documentation/pcmcia/index.rst | 2 +- Documentation/staging/crc32.rst | 2 +- Documentation/timers/index.rst | 2 +- 6 files changed, 8 insertions(+), 8 deletions(-) diff --git a/Documentation/cdrom/index.rst b/Documentation/cdrom/index.rst index e87a8785bc1a..e9b022d70939 100644 --- a/Documentation/cdrom/index.rst +++ b/Documentation/cdrom/index.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -===== -cdrom -===== +====== +CD-ROM +====== .. toctree:: :maxdepth: 1 diff --git a/Documentation/fpga/index.rst b/Documentation/fpga/index.rst index f80f95667ca2..43c968871d99 100644 --- a/Documentation/fpga/index.rst +++ b/Documentation/fpga/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ==== -fpga +FPGA ==== .. toctree:: diff --git a/Documentation/locking/index.rst b/Documentation/locking/index.rst index 7003bd5aeff4..6a9ea96c8bcb 100644 --- a/Documentation/locking/index.rst +++ b/Documentation/locking/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ======= -locking +Locking ======= .. toctree:: diff --git a/Documentation/pcmcia/index.rst b/Documentation/pcmcia/index.rst index 7ae1f62fca14..8067236c51ab 100644 --- a/Documentation/pcmcia/index.rst +++ b/Documentation/pcmcia/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -pcmcia +PCMCIA ====== .. toctree:: diff --git a/Documentation/staging/crc32.rst b/Documentation/staging/crc32.rst index 8a6860f33b4e..7542220967cb 100644 --- a/Documentation/staging/crc32.rst +++ b/Documentation/staging/crc32.rst @@ -1,5 +1,5 @@ ================================= -brief tutorial on CRC computation +Brief tutorial on CRC computation ================================= A CRC is a long-division remainder. You add the CRC to the message, diff --git a/Documentation/timers/index.rst b/Documentation/timers/index.rst index df510ad0c989..983f91f8f023 100644 --- a/Documentation/timers/index.rst +++ b/Documentation/timers/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -timers +Timers ====== .. toctree:: From 0d8aa3212e042bfcb7011e4de841dfdea39dc4b7 Mon Sep 17 00:00:00 2001 From: Thorsten Leemhuis Date: Mon, 15 May 2023 10:52:19 +0200 Subject: [PATCH 254/358] docs: quickly-build-trimmed-linux: various small fixes and improvements * improve the short description of localmodconfig in the step-by-step guide while fixing its broken first sentence * briefly mention immutable Linux distributions * use '--shallow-exclude=v6.0' throughout the document * instead of "git reset --hard; git checkout ..." use "git checkout --force ..." in the step-by-step guide: this matches the TLDR and is one command less to execute. This led to a few small adjustments to the text and the flow in the surrounding area. * fix two thinkos in the section explaining full git clones Signed-off-by: Thorsten Leemhuis Link: https://lore.kernel.org/r/6f4684b9a5d11d3adb04e0af3cfc60db8b28eeb2.1684140700.git.linux@leemhuis.info Signed-off-by: Jonathan Corbet --- .../quickly-build-trimmed-linux.rst | 49 ++++++++++--------- 1 file changed, 27 insertions(+), 22 deletions(-) diff --git a/Documentation/admin-guide/quickly-build-trimmed-linux.rst b/Documentation/admin-guide/quickly-build-trimmed-linux.rst index ff4f4cc8522b..f08149bc53f8 100644 --- a/Documentation/admin-guide/quickly-build-trimmed-linux.rst +++ b/Documentation/admin-guide/quickly-build-trimmed-linux.rst @@ -215,12 +215,14 @@ again. reduce the compile time enormously, especially if you are running an universal kernel from a commodity Linux distribution. - There is a catch: the make target 'localmodconfig' will disable kernel - features you have not directly or indirectly through some program utilized - since you booted the system. You can reduce or nearly eliminate that risk by - using tricks outlined in the reference section; for quick testing purposes - that risk is often negligible, but it is an aspect you want to keep in mind - in case your kernel behaves oddly. + There is a catch: 'localmodconfig' is likely to disable kernel features you + did not use since you booted your Linux -- like drivers for currently + disconnected peripherals or a virtualization software not haven't used yet. + You can reduce or nearly eliminate that risk with tricks the reference + section outlines; but when building a kernel just for quick testing purposes + it is often negligible if such features are missing. But you should keep that + aspect in mind when using a kernel built with this make target, as it might + be the reason why something you only use occasionally stopped working. [:ref:`details`] @@ -271,6 +273,9 @@ again. does nothing at all; in that case you have to manually install your kernel, as outlined in the reference section. + If you are running a immutable Linux distribution, check its documentation + and the web to find out how to install your own kernel there. + [:ref:`details`] .. _another_sbs: @@ -291,29 +296,29 @@ again. version you care about, as git otherwise might retrieve the entire commit history:: - git fetch --shallow-exclude=v6.1 origin + git fetch --shallow-exclude=v6.0 origin - If you modified the sources (for example by applying a patch), you now need - to discard those modifications; that's because git otherwise will not be able - to switch to the sources of another version due to potential conflicting - changes:: + Now switch to the version you are interested in -- but be aware the command + used here will discard any modifications you performed, as they would + conflict with the sources you want to checkout:: - git reset --hard - - Now checkout the version you are interested in, as explained above:: - - git checkout --detach origin/master + git checkout --force --detach origin/master At this point you might want to patch the sources again or set/modify a build - tag, as explained earlier; afterwards adjust the build configuration to the - new codebase and build your next kernel:: + tag, as explained earlier. Afterwards adjust the build configuration to the + new codebase using olddefconfig, which will now adjust the configuration file + you prepared earlier using localmodconfig (~/linux/.config) for your next + kernel:: # reminder: if you want to apply patches, do it at this point # reminder: you might want to update your build tag at this point make olddefconfig + + Now build your kernel:: + make -j $(nproc --all) - Install the kernel as outlined above:: + Afterwards install the kernel as outlined above:: command -v installkernel && sudo make modules_install install @@ -584,11 +589,11 @@ versions and individual commits at hand at any time:: curl -L \ https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/clone.bundle \ -o linux-stable.git.bundle - git clone clone.bundle ~/linux/ + git clone linux-stable.git.bundle ~/linux/ rm linux-stable.git.bundle cd ~/linux/ - git remote set-url origin - https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git + git remote set-url origin \ + https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git git fetch origin git checkout --detach origin/master From 7b38ecfdf9fbb133b4d2ea3738c02291a262abe2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 7 May 2023 22:59:38 -0700 Subject: [PATCH 255/358] Documentation/filesystems: sharedsubtree: add section headings Several of the sections are missing underlines. This makes the generated contents have missing entries, so add the underlines. Fixes: 16c01b20ae05 ("doc/filesystems: more mount cleanups") Fixes: 9cfcceea8f7e ("[PATCH] Complete description of shared subtrees.") Signed-off-by: Randy Dunlap Reviewed-by: Christian Brauner Link: https://lore.kernel.org/r/20230508055938.6550-1-rdunlap@infradead.org Signed-off-by: Jonathan Corbet --- Documentation/filesystems/sharedsubtree.rst | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/filesystems/sharedsubtree.rst b/Documentation/filesystems/sharedsubtree.rst index d83395354250..1cf56489ed48 100644 --- a/Documentation/filesystems/sharedsubtree.rst +++ b/Documentation/filesystems/sharedsubtree.rst @@ -147,6 +147,7 @@ replicas continue to be exactly same. 3) Setting mount states +----------------------- The mount command (util-linux package) can be used to set mount states:: @@ -612,6 +613,7 @@ replicas continue to be exactly same. 6) Quiz +------- A. What is the result of the following command sequence? @@ -673,6 +675,7 @@ replicas continue to be exactly same. /mnt/1/test be? 7) FAQ +------ Q1. Why is bind mount needed? How is it different from symbolic links? symbolic links can get stale if the destination mount gets @@ -841,6 +844,7 @@ replicas continue to be exactly same. tmp usr tmp usr tmp usr 8) Implementation +----------------- 8A) Datastructure From bd415b5c9552d44069d4e7c1e018b6d42f25af9e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 7 May 2023 22:59:28 -0700 Subject: [PATCH 256/358] Documentation/filesystems: ramfs-rootfs-initramfs: use :Author: Use the :Author: markup instead of making it a chapter heading. This cleans up the table of contents for this file. Fixes: 7f46a240b0a1 ("[PATCH] ramfs, rootfs, and initramfs docs") Signed-off-by: Randy Dunlap Cc: Rob Landley Reviewed-by: Christian Brauner Link: https://lore.kernel.org/r/20230508055928.3548-1-rdunlap@infradead.org Signed-off-by: Jonathan Corbet --- Documentation/filesystems/ramfs-rootfs-initramfs.rst | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.rst b/Documentation/filesystems/ramfs-rootfs-initramfs.rst index 164960631925..447f767c6462 100644 --- a/Documentation/filesystems/ramfs-rootfs-initramfs.rst +++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst @@ -6,8 +6,7 @@ Ramfs, rootfs and initramfs October 17, 2005 -Rob Landley -============================= +:Author: Rob Landley What is ramfs? -------------- From 5149452ca66289ef33d13897ee845a2f6f5b680f Mon Sep 17 00:00:00 2001 From: Po-Wen Kao Date: Thu, 4 May 2023 23:44:49 +0800 Subject: [PATCH 257/358] scsi: ufs: core: Fix MCQ tag calculation The transfer command descriptor is allocated in ufshcd_memory_alloc() and referenced by the transfer request descriptor with stride size sizeof_utp_transfer_cmd_desc() instead of sizeof(struct utp_transfer_cmd_desc). Consequently, computing tag by address offset should also refer to the same stride. Signed-off-by: Po-Wen Kao Link: https://lore.kernel.org/r/20230504154454.26654-2-powen.kao@mediatek.com Reviewed-by: Bart Van Assche Reviewed-by: Manivannan Sadhasivam Reviewed-by: Stanley Chu Reviewed-by: Ziqi Chen Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 2 +- drivers/ufs/core/ufshcd.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 202ff71e1b58..b7c5f39b50e6 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -265,7 +265,7 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba, addr = (le64_to_cpu(cqe->command_desc_base_addr) & CQE_UCD_BA) - hba->ucdl_dma_addr; - return div_u64(addr, sizeof(struct utp_transfer_cmd_desc)); + return div_u64(addr, sizeof_utp_transfer_cmd_desc(hba)); } static void ufshcd_mcq_process_cqe(struct ufs_hba *hba, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 45fd374fe56c..984abbe1fb93 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8452,7 +8452,7 @@ static void ufshcd_release_sdb_queue(struct ufs_hba *hba, int nutrs) { size_t ucdl_size, utrdl_size; - ucdl_size = sizeof(struct utp_transfer_cmd_desc) * nutrs; + ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * nutrs; dmam_free_coherent(hba->dev, ucdl_size, hba->ucdl_base_addr, hba->ucdl_dma_addr); From 06caeb536b2b21668efd2d6fa97c09461957b3a7 Mon Sep 17 00:00:00 2001 From: Po-Wen Kao Date: Thu, 4 May 2023 23:44:50 +0800 Subject: [PATCH 258/358] scsi: ufs: core: Rename symbol sizeof_utp_transfer_cmd_desc() Naming the functions after standard operators like sizeof() may cause confusion. Rename it to ufshcd_get_ucd_size(). Signed-off-by: Po-Wen Kao Link: https://lore.kernel.org/r/20230504154454.26654-3-powen.kao@mediatek.com Suggested-by: Manivannan Sadhasivam Reviewed-by: Stanley Chu Reviewed-by: Ziqi Chen Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 2 +- drivers/ufs/core/ufshcd.c | 10 +++++----- include/ufs/ufshcd.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index b7c5f39b50e6..937933d3f77c 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -265,7 +265,7 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba, addr = (le64_to_cpu(cqe->command_desc_base_addr) & CQE_UCD_BA) - hba->ucdl_dma_addr; - return div_u64(addr, sizeof_utp_transfer_cmd_desc(hba)); + return div_u64(addr, ufshcd_get_ucd_size(hba)); } static void ufshcd_mcq_process_cqe(struct ufs_hba *hba, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 984abbe1fb93..e7e79f515e14 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2849,10 +2849,10 @@ static void ufshcd_map_queues(struct Scsi_Host *shost) static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) { struct utp_transfer_cmd_desc *cmd_descp = (void *)hba->ucdl_base_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); struct utp_transfer_req_desc *utrdlp = hba->utrdl_base_addr; dma_addr_t cmd_desc_element_addr = hba->ucdl_dma_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); u16 response_offset = offsetof(struct utp_transfer_cmd_desc, response_upiu); u16 prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); @@ -3761,7 +3761,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) size_t utmrdl_size, utrdl_size, ucdl_size; /* Allocate memory for UTP command descriptors */ - ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * hba->nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * hba->nutrs; hba->ucdl_base_addr = dmam_alloc_coherent(hba->dev, ucdl_size, &hba->ucdl_dma_addr, @@ -3861,7 +3861,7 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba) prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); - cmd_desc_size = sizeof_utp_transfer_cmd_desc(hba); + cmd_desc_size = ufshcd_get_ucd_size(hba); cmd_desc_dma_addr = hba->ucdl_dma_addr; for (i = 0; i < hba->nutrs; i++) { @@ -8452,7 +8452,7 @@ static void ufshcd_release_sdb_queue(struct ufs_hba *hba, int nutrs) { size_t ucdl_size, utrdl_size; - ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * nutrs; dmam_free_coherent(hba->dev, ucdl_size, hba->ucdl_base_addr, hba->ucdl_dma_addr); diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index f7553293ba98..df1d04f7a542 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1133,7 +1133,7 @@ static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba) ({ (void)(hba); BUILD_BUG_ON(sg_entry_size != sizeof(struct ufshcd_sg_entry)); }) #endif -static inline size_t sizeof_utp_transfer_cmd_desc(const struct ufs_hba *hba) +static inline size_t ufshcd_get_ucd_size(const struct ufs_hba *hba) { return sizeof(struct utp_transfer_cmd_desc) + SG_ALL * ufshcd_sg_entry_size(hba); } From 72a81bb0b6fc9b759ac0fdaca3ec5884a8b2f304 Mon Sep 17 00:00:00 2001 From: Po-Wen Kao Date: Thu, 4 May 2023 23:44:51 +0800 Subject: [PATCH 259/358] scsi: ufs: core: Fix MCQ nr_hw_queues Since MAXQ is 0-based value, add one to obtain number of hardware queues. Signed-off-by: Po-Wen Kao Link: https://lore.kernel.org/r/20230504154454.26654-4-powen.kao@mediatek.com Reviewed-by: Bean Huo Reviewed-by: Manivannan Sadhasivam Reviewed-by: Bart Van Assche Reviewed-by: Stanley Chu Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 937933d3f77c..51b3c6ae781d 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -150,7 +150,8 @@ static int ufshcd_mcq_config_nr_queues(struct ufs_hba *hba) u32 hba_maxq, rem, tot_queues; struct Scsi_Host *host = hba->host; - hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities); + /* maxq is 0 based value */ + hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities) + 1; tot_queues = UFS_MCQ_NUM_DEV_CMD_QUEUES + read_queues + poll_queues + rw_queues; From 4e81a6cba517cb33584308a331f14f5e3fec369b Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 15 May 2023 10:20:41 -0700 Subject: [PATCH 260/358] scsi: storvsc: Don't pass unused PFNs to Hyper-V host In a SCSI request, storvsc pre-allocates space for up to MAX_PAGE_BUFFER_COUNT physical frame numbers to be passed to Hyper-V. If the size of the I/O request requires more PFNs, a separate memory area of exactly the correct size is dynamically allocated. But when the pre-allocated area is used, current code always passes MAX_PAGE_BUFFER_COUNT PFNs to Hyper-V, even if fewer are needed. While this doesn't break anything because the additional PFNs are always zero, more bytes than necessary are copied into the VMBus channel ring buffer. This takes CPU cycles and wastes space in the ring buffer. For a typical 4 Kbyte I/O that requires only a single PFN, 248 unnecessary bytes are copied. Fix this by setting the payload_sz based on the actual number of PFNs required, not the size of the pre-allocated space. Reported-by: John Starks Fixes: 8f43710543ef ("scsi: storvsc: Support PAGE_SIZE larger than 4K") Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1684171241-16209-1-git-send-email-mikelley@microsoft.com Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index d9ce379c4d2e..e6bc622954cf 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1780,7 +1780,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) length = scsi_bufflen(scmnd); payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb; - payload_sz = sizeof(cmd_request->mpb); + payload_sz = 0; if (scsi_sg_count(scmnd)) { unsigned long offset_in_hvpg = offset_in_hvpage(sgl->offset); @@ -1789,10 +1789,10 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) unsigned long hvpfn, hvpfns_to_add; int j, i = 0, sg_count; - if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { + payload_sz = (hvpg_count * sizeof(u64) + + sizeof(struct vmbus_packet_mpb_array)); - payload_sz = (hvpg_count * sizeof(u64) + - sizeof(struct vmbus_packet_mpb_array)); + if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { payload = kzalloc(payload_sz, GFP_ATOMIC); if (!payload) return SCSI_MLQUEUE_DEVICE_BUSY; From 6ca9818d1624e136a76ae8faedb6b6c95ca66903 Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Mon, 15 May 2023 15:01:55 +0800 Subject: [PATCH 261/358] scsi: Revert "scsi: core: Do not increase scsi_device's iorequest_cnt if dispatch failed" The "atomic_inc(&cmd->device->iorequest_cnt)" in scsi_queue_rq() would cause kernel panic because cmd->device may be freed after returning from scsi_dispatch_cmd(). This reverts commit cfee29ffb45b1c9798011b19d454637d1b0fe87d. Signed-off-by: Wenchao Hao Reported-by: Ming Lei Closes: https://lore.kernel.org/r/ZF+zB+bB7iqe0wGd@ovpn-8-17.pek2.redhat.com Link: https://lore.kernel.org/r/20230515070156.1790181-2-haowenchao2@huawei.com Reviewed-by: Ming Lei Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b7c569a42aa4..03964b26f3f2 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1463,6 +1463,8 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) struct Scsi_Host *host = cmd->device->host; int rtn = 0; + atomic_inc(&cmd->device->iorequest_cnt); + /* check if the device is still usable */ if (unlikely(cmd->device->sdev_state == SDEV_DEL)) { /* in SDEV_DEL we error all commands. DID_NO_CONNECT @@ -1761,7 +1763,6 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, goto out_dec_host_busy; } - atomic_inc(&cmd->device->iorequest_cnt); return BLK_STS_OK; out_dec_host_busy: From 09e797c8641f6ad435c33ae24c223351197ea29a Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Mon, 15 May 2023 15:01:56 +0800 Subject: [PATCH 262/358] scsi: core: Decrease scsi_device's iorequest_cnt if dispatch failed If scsi_dispatch_cmd() failed, the SCSI command was not sent to the target, scsi_queue_rq() would return BLK_STS_RESOURCE and the related request would be requeued. The timeout of this request would not fire, no one would increase iodone_cnt. The above flow would result the iodone_cnt smaller than iorequest_cnt. So decrease the iorequest_cnt if dispatch failed to workaround the issue. Signed-off-by: Wenchao Hao Reported-by: Ming Lei Closes: https://lore.kernel.org/r/ZF+zB+bB7iqe0wGd@ovpn-8-17.pek2.redhat.com Link: https://lore.kernel.org/r/20230515070156.1790181-3-haowenchao2@huawei.com Reviewed-by: Ming Lei Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 03964b26f3f2..0226c9279cef 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1485,6 +1485,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) */ SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd, "queuecommand : device blocked\n")); + atomic_dec(&cmd->device->iorequest_cnt); return SCSI_MLQUEUE_DEVICE_BUSY; } @@ -1517,6 +1518,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) trace_scsi_dispatch_cmd_start(cmd); rtn = host->hostt->queuecommand(host, cmd); if (rtn) { + atomic_dec(&cmd->device->iorequest_cnt); trace_scsi_dispatch_cmd_error(cmd, rtn); if (rtn != SCSI_MLQUEUE_DEVICE_BUSY && rtn != SCSI_MLQUEUE_TARGET_BUSY) From d6352dae0903fe8beae4c007dc320e9e9f1fed45 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 15 May 2023 19:29:25 +0300 Subject: [PATCH 263/358] devlink: Fix crash with CONFIG_NET_NS=n '__net_initdata' becomes a no-op with CONFIG_NET_NS=y, but when this option is disabled it becomes '__initdata', which means the data can be freed after the initialization phase. This annotation is obviously incorrect for the devlink net device notifier block which is still registered after the initialization phase [1]. Fix this crash by removing the '__net_initdata' annotation. [1] general protection fault, probably for non-canonical address 0xcccccccccccccccc: 0000 [#1] PREEMPT SMP CPU: 3 PID: 117 Comm: (udev-worker) Not tainted 6.4.0-rc1-custom-gdf0acdc59b09 #64 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-1.fc37 04/01/2014 RIP: 0010:notifier_call_chain+0x58/0xc0 [...] Call Trace: dev_set_mac_address+0x85/0x120 dev_set_mac_address_user+0x30/0x50 do_setlink+0x219/0x1270 rtnl_setlink+0xf7/0x1a0 rtnetlink_rcv_msg+0x142/0x390 netlink_rcv_skb+0x58/0x100 netlink_unicast+0x188/0x270 netlink_sendmsg+0x214/0x470 __sys_sendto+0x12f/0x1a0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x38/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: e93c9378e33f ("devlink: change per-devlink netdev notifier to static one") Reported-by: Marek Szyprowski Closes: https://lore.kernel.org/netdev/600ddf9e-589a-2aa0-7b69-a438f833ca10@samsung.com/ Tested-by: Marek Szyprowski Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230515162925.1144416-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/devlink/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/devlink/core.c b/net/devlink/core.c index 0e58eee44bdb..c23ebabadc52 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -294,7 +294,7 @@ static struct pernet_operations devlink_pernet_ops __net_initdata = { .pre_exit = devlink_pernet_pre_exit, }; -static struct notifier_block devlink_port_netdevice_nb __net_initdata = { +static struct notifier_block devlink_port_netdevice_nb = { .notifier_call = devlink_port_netdevice_event, }; From cb0ddaaa5db09d7d216fcbf0e68779be223a1128 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Mon, 15 May 2023 21:50:43 +0200 Subject: [PATCH 264/358] wifi: rtw88: sdio: Always use two consecutive bytes for word operations The Allwinner sunxi-mmc controller cannot handle word (16 bit) transfers. So and sdio_{read,write}w fails with messages like the following example using an RTL8822BS (but the same problems were also observed with RTL8822CS and RTL8723DS chips): rtw_8822bs mmc1:0001:1: Firmware version 27.2.0, H2C version 13 sunxi-mmc 4021000.mmc: unaligned scatterlist: os f80 length 2 sunxi-mmc 4021000.mmc: map DMA failed rtw_8822bs mmc1:0001:1: sdio read16 failed (0x10230): -22 Use two consecutive single byte accesses for word operations instead. It turns out that upon closer inspection this is also what the vendor driver does, even though it does have support for sdio_{read,write}w. So we can conclude that the rtw88 chips do support word access but only on SDIO controllers that also support it. Since there's no way to detect if the controller supports word access or not the rtw88 sdio driver switches to the easiest approach: avoiding word access. Reported-by: Larry Finger Closes: https://lore.kernel.org/linux-wireless/527585e5-9cdd-66ed-c3af-6da162f4b720@lwfinger.net/ Reported-by: Rudi Heitbaum Link: https://github.com/LibreELEC/LibreELEC.tv/pull/7837#issue-1708469467 Fixes: 65371a3f14e7 ("wifi: rtw88: sdio: Add HCI implementation for SDIO based chipsets") Reviewed-by: Ping-Ke Shih Signed-off-by: Martin Blumenstingl Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230515195043.572375-1-martin.blumenstingl@googlemail.com --- drivers/net/wireless/realtek/rtw88/sdio.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c index af0459a79899..06fce7c3adda 100644 --- a/drivers/net/wireless/realtek/rtw88/sdio.c +++ b/drivers/net/wireless/realtek/rtw88/sdio.c @@ -87,11 +87,6 @@ static void rtw_sdio_writew(struct rtw_dev *rtwdev, u16 val, u32 addr, u8 buf[2]; int i; - if (rtw_sdio_use_memcpy_io(rtwdev, addr, 2)) { - sdio_writew(rtwsdio->sdio_func, val, addr, err_ret); - return; - } - *(__le16 *)buf = cpu_to_le16(val); for (i = 0; i < 2; i++) { @@ -125,9 +120,6 @@ static u16 rtw_sdio_readw(struct rtw_dev *rtwdev, u32 addr, int *err_ret) u8 buf[2]; int i; - if (rtw_sdio_use_memcpy_io(rtwdev, addr, 2)) - return sdio_readw(rtwsdio->sdio_func, addr, err_ret); - for (i = 0; i < 2; i++) { buf[i] = sdio_readb(rtwsdio->sdio_func, addr + i, err_ret); if (*err_ret) From 212457ccbd60dba34f965e4ffbe62f0e4f970538 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 20:34:22 +0200 Subject: [PATCH 265/358] wifi: b43: fix incorrect __packed annotation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit clang warns about an unpacked structure inside of a packed one: drivers/net/wireless/broadcom/b43/b43.h:654:4: error: field data within 'struct b43_iv' is less aligned than 'union (unnamed union at /home/arnd/arm-soc/drivers/net/wireless/broadcom/b43/b43.h:651:2)' and is usually due to 'struct b43_iv' being packed, which can lead to unaligned accesses [-Werror,-Wunaligned-access] The problem here is that the anonymous union has the default alignment from its members, apparently because the original author mixed up the placement of the __packed attribute by placing it next to the struct member rather than the union definition. As the struct itself is also marked as __packed, there is no need to mark its members, so just move the annotation to the inner type instead. As Michael noted, the same problem is present in b43legacy, so change both at the same time. Acked-by: Michael Büsch Reported-by: kernel test robot Reviewed-by: Simon Horman Tested-by: Larry Finger Link: https://lore.kernel.org/oe-kbuild-all/202305160749.ay1HAoyP-lkp@intel.com/ Signed-off-by: Arnd Bergmann Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230516183442.536589-1-arnd@kernel.org --- drivers/net/wireless/broadcom/b43/b43.h | 2 +- drivers/net/wireless/broadcom/b43legacy/b43legacy.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/broadcom/b43/b43.h b/drivers/net/wireless/broadcom/b43/b43.h index 9fc7c088a539..67b4bac048e5 100644 --- a/drivers/net/wireless/broadcom/b43/b43.h +++ b/drivers/net/wireless/broadcom/b43/b43.h @@ -651,7 +651,7 @@ struct b43_iv { union { __be16 d16; __be32 d32; - } data __packed; + } __packed data; } __packed; diff --git a/drivers/net/wireless/broadcom/b43legacy/b43legacy.h b/drivers/net/wireless/broadcom/b43legacy/b43legacy.h index 6b0cec467938..f49365d14619 100644 --- a/drivers/net/wireless/broadcom/b43legacy/b43legacy.h +++ b/drivers/net/wireless/broadcom/b43legacy/b43legacy.h @@ -379,7 +379,7 @@ struct b43legacy_iv { union { __be16 d16; __be32 d32; - } data __packed; + } __packed data; } __packed; #define B43legacy_PHYMODE(phytype) (1 << (phytype)) From aed0e6ca7dbb8fbea9bc69c9ac663d5533c8c5d8 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:13 +0200 Subject: [PATCH 266/358] can: kvaser_pciefd: Set CAN_STATE_STOPPED in kvaser_pciefd_stop() Set can.state to CAN_STATE_STOPPED in kvaser_pciefd_stop(). Without this fix, wrong CAN state was repported after the interface was brought down. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-2-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 53e8a914c88b..867b421b9506 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -719,6 +719,7 @@ static int kvaser_pciefd_stop(struct net_device *netdev) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); del_timer(&can->bec_poll_timer); } + can->can.state = CAN_STATE_STOPPED; close_candev(netdev); return ret; From bf7ac55e991ca177f1ac16be51152f1ef291a4df Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:14 +0200 Subject: [PATCH 267/358] can: kvaser_pciefd: Clear listen-only bit if not explicitly requested The listen-only bit was never cleared, causing the controller to always use listen-only mode, if previously set. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-3-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 867b421b9506..cdc894d12885 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -554,6 +554,8 @@ static void kvaser_pciefd_setup_controller(struct kvaser_pciefd_can *can) if (can->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) mode |= KVASER_PCIEFD_KCAN_MODE_LOM; + else + mode &= ~KVASER_PCIEFD_KCAN_MODE_LOM; mode |= KVASER_PCIEFD_KCAN_MODE_EEN; mode |= KVASER_PCIEFD_KCAN_MODE_EPEN; From 84762d8da89d29ba842317eb842973e628c27391 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:15 +0200 Subject: [PATCH 268/358] can: kvaser_pciefd: Call request_irq() before enabling interrupts Make sure the interrupt handler is registered before enabling interrupts. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-4-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index cdc894d12885..4b8591d48735 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -1827,6 +1827,11 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, if (err) goto err_teardown_can_ctrls; + err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, + IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); + if (err) + goto err_teardown_can_ctrls; + iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1, pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG); @@ -1847,11 +1852,6 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); - err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, - IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); - if (err) - goto err_teardown_can_ctrls; - err = kvaser_pciefd_reg_candev(pcie); if (err) goto err_free_irq; From c589557dd1426f5adf90c7a919d4fde5a3e4ef64 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:16 +0200 Subject: [PATCH 269/358] can: kvaser_pciefd: Empty SRB buffer in probe Empty the "Shared receive buffer" (SRB) in probe, to assure we start in a known state, and don't process any irrelevant packets. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-5-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 4b8591d48735..0e03c1cd47b3 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -71,10 +71,12 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_SYSID_BUILD_REG (KVASER_PCIEFD_SYSID_BASE + 0x14) /* Shared receive buffer registers */ #define KVASER_PCIEFD_SRB_BASE 0x1f200 +#define KVASER_PCIEFD_SRB_FIFO_LAST_REG (KVASER_PCIEFD_SRB_BASE + 0x1f4) #define KVASER_PCIEFD_SRB_CMD_REG (KVASER_PCIEFD_SRB_BASE + 0x200) #define KVASER_PCIEFD_SRB_IEN_REG (KVASER_PCIEFD_SRB_BASE + 0x204) #define KVASER_PCIEFD_SRB_IRQ_REG (KVASER_PCIEFD_SRB_BASE + 0x20c) #define KVASER_PCIEFD_SRB_STAT_REG (KVASER_PCIEFD_SRB_BASE + 0x210) +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG (KVASER_PCIEFD_SRB_BASE + 0x214) #define KVASER_PCIEFD_SRB_CTRL_REG (KVASER_PCIEFD_SRB_BASE + 0x218) /* EPCS flash controller registers */ #define KVASER_PCIEFD_SPI_BASE 0x1fc00 @@ -111,6 +113,9 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); /* DMA support */ #define KVASER_PCIEFD_SRB_STAT_DMA BIT(24) +/* SRB current packet level */ +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK 0xff + /* DMA Enable */ #define KVASER_PCIEFD_SRB_CTRL_DMA_ENABLE BIT(0) @@ -1061,6 +1066,7 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) { int i; u32 srb_status; + u32 srb_packet_count; dma_addr_t dma_addr[KVASER_PCIEFD_DMA_COUNT]; /* Disable the DMA */ @@ -1088,6 +1094,15 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + /* Empty Rx FIFO */ + srb_packet_count = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG) & + KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK; + while (srb_packet_count) { + /* Drop current packet in FIFO */ + ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_FIFO_LAST_REG); + srb_packet_count--; + } + srb_status = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_STAT_REG); if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DI)) { dev_err(&pcie->pci->dev, "DMA not idle before enabling\n"); From 262d7a52ba27525e3c1203230c9f0524e48bbb34 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:17 +0200 Subject: [PATCH 270/358] can: kvaser_pciefd: Do not send EFLUSH command on TFD interrupt Under certain circumstances we send two EFLUSH commands, resulting in two EFLUSH ack packets, while only expecting a single EFLUSH ack. This can cause the driver Tx flush completion to get out of sync. To avoid this problem, don't enable the "Transmit buffer flush done" (TFD) interrupt and remove the code handling it. Now we only send EFLUSH command after receiving status packet with "Init detected" (IDET) bit set. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-6-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 0e03c1cd47b3..4fafb7658349 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -531,7 +531,7 @@ static int kvaser_pciefd_set_tx_irq(struct kvaser_pciefd_can *can) KVASER_PCIEFD_KCAN_IRQ_TOF | KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TAE | KVASER_PCIEFD_KCAN_IRQ_TAL | KVASER_PCIEFD_KCAN_IRQ_FDIC | KVASER_PCIEFD_KCAN_IRQ_BPP | - KVASER_PCIEFD_KCAN_IRQ_TAR | KVASER_PCIEFD_KCAN_IRQ_TFD; + KVASER_PCIEFD_KCAN_IRQ_TAR; iowrite32(msk, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); @@ -579,7 +579,7 @@ static void kvaser_pciefd_start_controller_flush(struct kvaser_pciefd_can *can) spin_lock_irqsave(&can->lock, irq); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); @@ -622,7 +622,7 @@ static int kvaser_pciefd_bus_on(struct kvaser_pciefd_can *can) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); @@ -1015,8 +1015,7 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) SET_NETDEV_DEV(netdev, &pcie->pci->dev); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | - KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); pcie->can[i] = can; @@ -1443,9 +1442,6 @@ static int kvaser_pciefd_handle_status_packet(struct kvaser_pciefd *pcie, cmd = KVASER_PCIEFD_KCAN_CMD_AT; cmd |= ++can->cmd_seq << KVASER_PCIEFD_KCAN_CMD_SEQ_SHIFT; iowrite32(cmd, can->reg_base + KVASER_PCIEFD_KCAN_CMD_REG); - - iowrite32(KVASER_PCIEFD_KCAN_IRQ_TFD, - can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); } else if (p->header[0] & KVASER_PCIEFD_SPACK_IDET && p->header[0] & KVASER_PCIEFD_SPACK_IRM && cmdseq == (p->header[1] & KVASER_PCIEFD_PACKET_SEQ_MSK) && @@ -1732,15 +1728,6 @@ static int kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can) if (irq & KVASER_PCIEFD_KCAN_IRQ_TOF) netdev_err(can->can.dev, "Tx FIFO overflow\n"); - if (irq & KVASER_PCIEFD_KCAN_IRQ_TFD) { - u8 count = ioread32(can->reg_base + - KVASER_PCIEFD_KCAN_TX_NPACKETS_REG) & 0xff; - - if (count == 0) - iowrite32(KVASER_PCIEFD_KCAN_CTRL_EFLUSH, - can->reg_base + KVASER_PCIEFD_KCAN_CTRL_REG); - } - if (irq & KVASER_PCIEFD_KCAN_IRQ_BPP) netdev_err(can->can.dev, "Fail to change bittiming, when not in reset mode\n"); From 11164bc39459335ab93c6e99d53b7e4292fba38b Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:18 +0200 Subject: [PATCH 271/358] can: kvaser_pciefd: Disable interrupts in probe error path Disable interrupts in error path of probe function. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-7-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 4fafb7658349..be189edb256c 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -1861,6 +1861,8 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, return 0; err_free_irq: + /* Disable PCI interrupts */ + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_IEN_REG); free_irq(pcie->pci->irq, pcie); err_teardown_can_ctrls: From 82b2bc279467c875ec36f8ef820f00997c2a4e8e Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 15 May 2023 11:42:04 -0700 Subject: [PATCH 272/358] tun: Fix memory leak for detached NAPI queue. syzkaller reported [0] memory leaks of sk and skb related to the TUN device with no repro, but we can reproduce it easily with: struct ifreq ifr = {} int fd_tun, fd_tmp; char buf[4] = {}; fd_tun = openat(AT_FDCWD, "/dev/net/tun", O_WRONLY, 0); ifr.ifr_flags = IFF_TUN | IFF_NAPI | IFF_MULTI_QUEUE; ioctl(fd_tun, TUNSETIFF, &ifr); ifr.ifr_flags = IFF_DETACH_QUEUE; ioctl(fd_tun, TUNSETQUEUE, &ifr); fd_tmp = socket(AF_PACKET, SOCK_PACKET, 0); ifr.ifr_flags = IFF_UP; ioctl(fd_tmp, SIOCSIFFLAGS, &ifr); write(fd_tun, buf, sizeof(buf)); close(fd_tun); If we enable NAPI and multi-queue on a TUN device, we can put skb into tfile->sk.sk_write_queue after the queue is detached. We should prevent it by checking tfile->detached before queuing skb. Note this must be done under tfile->sk.sk_write_queue.lock because write() and ioctl(IFF_DETACH_QUEUE) can run concurrently. Otherwise, there would be a small race window: write() ioctl(IFF_DETACH_QUEUE) `- tun_get_user `- __tun_detach |- if (tfile->detached) |- tun_disable_queue | `-> false | `- tfile->detached = tun | `- tun_queue_purge |- spin_lock_bh(&queue->lock) `- __skb_queue_tail(queue, skb) Another solution is to call tun_queue_purge() when closing and reattaching the detached queue, but it could paper over another problems. Also, we do the same kind of test for IFF_NAPI_FRAGS. [0]: unreferenced object 0xffff88801edbc800 (size 2048): comm "syz-executor.1", pid 33269, jiffies 4295743834 (age 18.756s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00 ...@............ backtrace: [<000000008c16ea3d>] __do_kmalloc_node mm/slab_common.c:965 [inline] [<000000008c16ea3d>] __kmalloc+0x4a/0x130 mm/slab_common.c:979 [<000000003addde56>] kmalloc include/linux/slab.h:563 [inline] [<000000003addde56>] sk_prot_alloc+0xef/0x1b0 net/core/sock.c:2035 [<000000003e20621f>] sk_alloc+0x36/0x2f0 net/core/sock.c:2088 [<0000000028e43843>] tun_chr_open+0x3d/0x190 drivers/net/tun.c:3438 [<000000001b0f1f28>] misc_open+0x1a6/0x1f0 drivers/char/misc.c:165 [<000000004376f706>] chrdev_open+0x111/0x300 fs/char_dev.c:414 [<00000000614d379f>] do_dentry_open+0x2f9/0x750 fs/open.c:920 [<000000008eb24774>] do_open fs/namei.c:3636 [inline] [<000000008eb24774>] path_openat+0x143f/0x1a30 fs/namei.c:3791 [<00000000955077b5>] do_filp_open+0xce/0x1c0 fs/namei.c:3818 [<00000000b78973b0>] do_sys_openat2+0xf0/0x260 fs/open.c:1356 [<00000000057be699>] do_sys_open fs/open.c:1372 [inline] [<00000000057be699>] __do_sys_openat fs/open.c:1388 [inline] [<00000000057be699>] __se_sys_openat fs/open.c:1383 [inline] [<00000000057be699>] __x64_sys_openat+0x83/0xf0 fs/open.c:1383 [<00000000a7d2182d>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<00000000a7d2182d>] do_syscall_64+0x3c/0x90 arch/x86/entry/common.c:80 [<000000004cc4e8c4>] entry_SYSCALL_64_after_hwframe+0x72/0xdc unreferenced object 0xffff88802f671700 (size 240): comm "syz-executor.1", pid 33269, jiffies 4295743854 (age 18.736s) hex dump (first 32 bytes): 68 c9 db 1e 80 88 ff ff 68 c9 db 1e 80 88 ff ff h.......h....... 00 c0 7b 2f 80 88 ff ff 00 c8 db 1e 80 88 ff ff ..{/............ backtrace: [<00000000e9d9fdb6>] __alloc_skb+0x223/0x250 net/core/skbuff.c:644 [<000000002c3e4e0b>] alloc_skb include/linux/skbuff.h:1288 [inline] [<000000002c3e4e0b>] alloc_skb_with_frags+0x6f/0x350 net/core/skbuff.c:6378 [<00000000825f98d7>] sock_alloc_send_pskb+0x3ac/0x3e0 net/core/sock.c:2729 [<00000000e9eb3df3>] tun_alloc_skb drivers/net/tun.c:1529 [inline] [<00000000e9eb3df3>] tun_get_user+0x5e1/0x1f90 drivers/net/tun.c:1841 [<0000000053096912>] tun_chr_write_iter+0xac/0x120 drivers/net/tun.c:2035 [<00000000b9282ae0>] call_write_iter include/linux/fs.h:1868 [inline] [<00000000b9282ae0>] new_sync_write fs/read_write.c:491 [inline] [<00000000b9282ae0>] vfs_write+0x40f/0x530 fs/read_write.c:584 [<00000000524566e4>] ksys_write+0xa1/0x170 fs/read_write.c:637 [<00000000a7d2182d>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<00000000a7d2182d>] do_syscall_64+0x3c/0x90 arch/x86/entry/common.c:80 [<000000004cc4e8c4>] entry_SYSCALL_64_after_hwframe+0x72/0xdc Fixes: cde8b15f1aab ("tuntap: add ioctl to attach or detach a file form tuntap device") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- drivers/net/tun.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d4d0a41a905a..d75456adc62a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1977,6 +1977,14 @@ napi_busy: int queue_len; spin_lock_bh(&queue->lock); + + if (unlikely(tfile->detached)) { + spin_unlock_bh(&queue->lock); + rcu_read_unlock(); + err = -EBUSY; + goto free_skb; + } + __skb_queue_tail(queue, skb); queue_len = skb_queue_len(queue); spin_unlock(&queue->lock); @@ -2512,6 +2520,13 @@ build: if (tfile->napi_enabled) { queue = &tfile->sk.sk_write_queue; spin_lock(&queue->lock); + + if (unlikely(tfile->detached)) { + spin_unlock(&queue->lock); + kfree_skb(skb); + return -EBUSY; + } + __skb_queue_tail(queue, skb); spin_unlock(&queue->lock); ret = 1; From 412cd77a2c24b191c65ea53025222418db09817c Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 15 May 2023 21:09:11 +0200 Subject: [PATCH 273/358] cassini: Fix a memory leak in the error handling path of cas_init_one() cas_saturn_firmware_init() allocates some memory using vmalloc(). This memory is freed in the .remove() function but not it the error handling path of the probe. Add the missing vfree() to avoid a memory leak, should an error occur. Fixes: fcaa40669cd7 ("cassini: use request_firmware") Signed-off-by: Christophe JAILLET Reviewed-by: Pavan Chebbi Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/cassini.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 4ef05bad4613..d61dfa250feb 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -5077,6 +5077,8 @@ err_out_iounmap: cas_shutdown(cp); mutex_unlock(&cp->pm_mutex); + vfree(cp->fw_data); + pci_iounmap(pdev, cp->regs); From 1323e0c6e1d7e103d59384c3ac50f72b17a6936c Mon Sep 17 00:00:00 2001 From: Marco Migliore Date: Tue, 16 May 2023 09:38:54 +0200 Subject: [PATCH 274/358] net: dsa: mv88e6xxx: Fix mv88e6393x EPC write command offset According to datasheet, the command opcode must be specified into bits [14:12] of the Extended Port Control register (EPC). Fixes: de776d0d316f ("net: dsa: mv88e6xxx: add support for mv88e6393x family") Signed-off-by: Marco Migliore Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/port.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index aec9d4fd20e3..d19b6303b91f 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -276,7 +276,7 @@ /* Offset 0x10: Extended Port Control Command */ #define MV88E6393X_PORT_EPC_CMD 0x10 #define MV88E6393X_PORT_EPC_CMD_BUSY 0x8000 -#define MV88E6393X_PORT_EPC_CMD_WRITE 0x0300 +#define MV88E6393X_PORT_EPC_CMD_WRITE 0x3000 #define MV88E6393X_PORT_EPC_INDEX_PORT_ETYPE 0x02 /* Offset 0x11: Extended Port Control Data */ From 60d758659f1fb49e0d5b6ac2691ede8c0958795b Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Tue, 16 May 2023 10:41:46 -0700 Subject: [PATCH 275/358] igb: fix bit_shift to be in [1..8] range In igb_hash_mc_addr() the expression: "mc_addr[4] >> 8 - bit_shift", right shifting "mc_addr[4]" shift by more than 7 bits always yields zero, so hash becomes not so different. Add initialization with bit_shift = 1 and add a loop condition to ensure bit_shift will be always in [1..8] range. Fixes: 9d5c824399de ("igb: PCI-Express 82575 Gigabit Ethernet driver") Signed-off-by: Aleksandr Loktionov Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/igb/e1000_mac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index 205d577bdbba..caf91c6f52b4 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -426,7 +426,7 @@ void igb_mta_set(struct e1000_hw *hw, u32 hash_value) static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) { u32 hash_value, hash_mask; - u8 bit_shift = 0; + u8 bit_shift = 1; /* Register count multiplied by bits per register */ hash_mask = (hw->mac.mta_reg_count * 32) - 1; @@ -434,7 +434,7 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) /* For a mc_filter_type of 0, bit_shift is the number of left-shifts * where 0xFF would still fall within the hash mask. */ - while (hash_mask >> bit_shift != 0xFF) + while (hash_mask >> bit_shift != 0xFF && bit_shift < 4) bit_shift++; /* The portion of the address that is used for the hash table From 66353baf3762fa0968b4424a2075fb395b329e9d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 16 May 2023 11:48:49 +0300 Subject: [PATCH 276/358] mailmap: add entries for Nikolay Aleksandrov Turns out I missed a few patches due to use of old addresses by senders. Add a mailmap entry with my old addresses. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- .mailmap | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/.mailmap b/.mailmap index 71127b2608d2..bf076bbc36b1 100644 --- a/.mailmap +++ b/.mailmap @@ -364,6 +364,11 @@ Nicolas Pitre Nicolas Saenz Julienne Nicolas Saenz Julienne Niklas Söderlund +Nikolay Aleksandrov +Nikolay Aleksandrov +Nikolay Aleksandrov +Nikolay Aleksandrov +Nikolay Aleksandrov Oleksandr Natalenko Oleksij Rempel Oleksij Rempel From 6049674b5720edbbb13a7cb3e2f3d2affaa40c19 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sun, 9 Apr 2023 11:28:31 +0900 Subject: [PATCH 277/358] tracing: fprobe: Initialize ret valiable to fix smatch error The commit 39d954200bf6 ("fprobe: Skip exit_handler if entry_handler returns !0") introduced a hidden dependency of 'ret' local variable in the fprobe_handler(), Smatch warns the `ret` can be accessed without initialization. kernel/trace/fprobe.c:59 fprobe_handler() error: uninitialized symbol 'ret'. kernel/trace/fprobe.c 49 fpr->entry_ip = ip; 50 if (fp->entry_data_size) 51 entry_data = fpr->data; 52 } 53 54 if (fp->entry_handler) 55 ret = fp->entry_handler(fp, ip, ftrace_get_regs(fregs), entry_data); ret is only initialized if there is an ->entry_handler 56 57 /* If entry_handler returns !0, nmissed is not counted. */ 58 if (rh) { rh is only true if there is an ->exit_handler. Presumably if you have and ->exit_handler that means you also have a ->entry_handler but Smatch is not smart enough to figure it out. --> 59 if (ret) ^^^ Warning here. 60 rethook_recycle(rh); 61 else 62 rethook_hook(rh, ftrace_get_regs(fregs), true); 63 } 64 out: 65 ftrace_test_recursion_unlock(bit); 66 } Link: https://lore.kernel.org/all/168100731160.79534.374827110083836722.stgit@devnote2/ Reported-by: Dan Carpenter Link: https://lore.kernel.org/all/85429a5c-a4b9-499e-b6c0-cbd313291c49@kili.mountain Fixes: 39d954200bf6 ("fprobe: Skip exit_handler if entry_handler returns !0") Acked-by: Dan Carpenter Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9abb3905bc8e..293184227394 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -27,7 +27,7 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, struct rethook_node *rh = NULL; struct fprobe *fp; void *entry_data = NULL; - int bit, ret; + int bit, ret = 0; fp = container_of(ops, struct fprobe, ops); if (fprobe_disabled(fp)) From dacab578c7c6cd06c50c89dfa36b0e0f10decd4e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2023 14:23:42 +0000 Subject: [PATCH 278/358] vlan: fix a potential uninit-value in vlan_dev_hard_start_xmit() syzbot triggered the following splat [1], sending an empty message through pppoe_sendmsg(). When VLAN_FLAG_REORDER_HDR flag is set, vlan_dev_hard_header() does not push extra bytes for the VLAN header, because vlan is offloaded. Unfortunately vlan_dev_hard_start_xmit() first reads veth->h_vlan_proto before testing (vlan->flags & VLAN_FLAG_REORDER_HDR). We need to swap the two conditions. [1] BUG: KMSAN: uninit-value in vlan_dev_hard_start_xmit+0x171/0x7f0 net/8021q/vlan_dev.c:111 vlan_dev_hard_start_xmit+0x171/0x7f0 net/8021q/vlan_dev.c:111 __netdev_start_xmit include/linux/netdevice.h:4883 [inline] netdev_start_xmit include/linux/netdevice.h:4897 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x253/0xa20 net/core/dev.c:3596 __dev_queue_xmit+0x3c7f/0x5ac0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3053 [inline] pppoe_sendmsg+0xa93/0xb80 drivers/net/ppp/pppoe.c:900 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0xa24/0xe40 net/socket.c:2501 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2555 __sys_sendmmsg+0x411/0xa50 net/socket.c:2641 __do_sys_sendmmsg net/socket.c:2670 [inline] __se_sys_sendmmsg net/socket.c:2667 [inline] __x64_sys_sendmmsg+0xbc/0x120 net/socket.c:2667 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook+0x12d/0xb60 mm/slab.h:774 slab_alloc_node mm/slub.c:3452 [inline] kmem_cache_alloc_node+0x543/0xab0 mm/slub.c:3497 kmalloc_reserve+0x148/0x470 net/core/skbuff.c:520 __alloc_skb+0x3a7/0x850 net/core/skbuff.c:606 alloc_skb include/linux/skbuff.h:1277 [inline] sock_wmalloc+0xfe/0x1a0 net/core/sock.c:2583 pppoe_sendmsg+0x3af/0xb80 drivers/net/ppp/pppoe.c:867 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0xa24/0xe40 net/socket.c:2501 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2555 __sys_sendmmsg+0x411/0xa50 net/socket.c:2641 __do_sys_sendmmsg net/socket.c:2670 [inline] __se_sys_sendmmsg net/socket.c:2667 [inline] __x64_sys_sendmmsg+0xbc/0x120 net/socket.c:2667 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd CPU: 0 PID: 29770 Comm: syz-executor.0 Not tainted 6.3.0-rc6-syzkaller-gc478e5b17829 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 870e4935d6e6..b90781b9ece6 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -109,8 +109,8 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... */ - if (veth->h_vlan_proto != vlan->vlan_proto || - vlan->flags & VLAN_FLAG_REORDER_HDR) { + if (vlan->flags & VLAN_FLAG_REORDER_HDR || + veth->h_vlan_proto != vlan->vlan_proto) { u16 vlan_tci; vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); From 60829145f1e2650b31ebe6a0ec70a9725b38fa2c Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Tue, 16 May 2023 21:09:46 +0530 Subject: [PATCH 279/358] net: wwan: iosm: fix NULL pointer dereference when removing device In suspend and resume cycle, the removal and rescan of device ends up in NULL pointer dereference. During driver initialization, if the ipc_imem_wwan_channel_init() fails to get the valid device capabilities it returns an error and further no resource (wwan struct) will be allocated. Now in this situation if driver removal procedure is initiated it would result in NULL pointer exception since unallocated wwan struct is dereferenced inside ipc_wwan_deinit(). ipc_imem_run_state_worker() to handle the called functions return value and to release the resource in failure case. It also reports the link down event in failure cases. The user space application can handle this event to do a device reset for restoring the device communication. Fixes: 3670970dd8c6 ("net: iosm: shared memory IPC interface") Reported-by: Samuel Wein PhD Closes: https://lore.kernel.org/netdev/20230427140819.1310f4bd@kernel.org/T/ Signed-off-by: M Chetan Kumar Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_imem.c | 27 ++++++++++++++++++----- drivers/net/wwan/iosm/iosm_ipc_imem_ops.c | 12 ++++++---- drivers/net/wwan/iosm/iosm_ipc_imem_ops.h | 6 +++-- 3 files changed, 33 insertions(+), 12 deletions(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index c066b0040a3f..829515a601b3 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -565,24 +565,32 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) struct ipc_mux_config mux_cfg; struct iosm_imem *ipc_imem; u8 ctrl_chl_idx = 0; + int ret; ipc_imem = container_of(instance, struct iosm_imem, run_state_worker); if (ipc_imem->phase != IPC_P_RUN) { dev_err(ipc_imem->dev, "Modem link down. Exit run state worker."); - return; + goto err_out; } if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag)) ipc_devlink_deinit(ipc_imem->ipc_devlink); - if (!ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg)) - ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); + ret = ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg); + if (ret < 0) + goto err_out; - ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol); - if (ipc_imem->mux) - ipc_imem->mux->wwan = ipc_imem->wwan; + ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); + if (!ipc_imem->mux) + goto err_out; + + ret = ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol); + if (ret < 0) + goto err_ipc_mux_deinit; + + ipc_imem->mux->wwan = ipc_imem->wwan; while (ctrl_chl_idx < IPC_MEM_MAX_CHANNELS) { if (!ipc_chnl_cfg_get(&chnl_cfg_port, ctrl_chl_idx)) { @@ -622,6 +630,13 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) /* Complete all memory stores after setting bit */ smp_mb__after_atomic(); + + return; + +err_ipc_mux_deinit: + ipc_mux_deinit(ipc_imem->mux); +err_out: + ipc_uevent_send(ipc_imem->dev, UEVENT_CD_READY_LINK_DOWN); } static void ipc_imem_handle_irq(struct iosm_imem *ipc_imem, int irq) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index 66b90cc4c346..109cf8930488 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -77,8 +77,8 @@ out: } /* Initialize wwan channel */ -void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, - enum ipc_mux_protocol mux_type) +int ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type) { struct ipc_chnl_cfg chnl_cfg = { 0 }; @@ -87,7 +87,7 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, /* If modem version is invalid (0xffffffff), do not initialize WWAN. */ if (ipc_imem->cp_version == -1) { dev_err(ipc_imem->dev, "invalid CP version"); - return; + return -EIO; } ipc_chnl_cfg_get(&chnl_cfg, ipc_imem->nr_of_channels); @@ -104,9 +104,13 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, /* WWAN registration. */ ipc_imem->wwan = ipc_wwan_init(ipc_imem, ipc_imem->dev); - if (!ipc_imem->wwan) + if (!ipc_imem->wwan) { dev_err(ipc_imem->dev, "failed to register the ipc_wwan interfaces"); + return -ENOMEM; + } + + return 0; } /* Map SKB to DMA for transfer */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h index f8afb217d9e2..026c5bd0f999 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -91,9 +91,11 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, int if_id, * MUX. * @ipc_imem: Pointer to iosm_imem struct. * @mux_type: Type of mux protocol. + * + * Return: 0 on success and failure value on error */ -void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, - enum ipc_mux_protocol mux_type); +int ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type); /** * ipc_imem_sys_devlink_open - Open a Flash/CD Channel link to CP From c46e78ba9a7a09da4f192dc8df15c4e8a07fb9e0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 16 May 2023 18:44:10 +0300 Subject: [PATCH 280/358] net: pcs: xpcs: fix C73 AN not getting enabled The XPCS expects clause 73 (copper backplane) autoneg to follow the ethtool autoneg bit. It actually did that until the blamed commit inaptly replaced state->an_enabled (coming from ethtool) with phylink_autoneg_inband() (coming from the device tree or struct phylink_config), as part of an unrelated phylink_pcs API conversion. Russell King suggests that state->an_enabled from the original code was just a proxy for the ethtool Autoneg bit, and that the correct way of restoring the functionality is to check for this bit in the advertising mask. Fixes: 11059740e616 ("net: pcs: xpcs: convert to phylink_pcs_ops") Link: https://lore.kernel.org/netdev/ZGNt2MFeRolKGFck@shell.armlinux.org.uk/ Suggested-by: Russell King (Oracle) Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/pcs/pcs-xpcs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index f19d48c94fe0..72f25e778840 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -873,7 +873,7 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, switch (compat->an_mode) { case DW_AN_C73: - if (phylink_autoneg_inband(mode)) { + if (test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, advertising)) { ret = xpcs_config_aneg_c73(xpcs, compat); if (ret) return ret; From 9ba9485b87ac97fd159abdb4cbd53099bc9f01c6 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Tue, 16 May 2023 14:49:24 -0400 Subject: [PATCH 281/358] net: selftests: Fix optstring The cited commit added a stray colon to the 'v' option. That makes the option work incorrectly. ex: tools/testing/selftests/net# ./fib_nexthops.sh -v (should enable verbose mode, instead it shows help text due to missing arg) Fixes: 5feba4727395 ("selftests: fib_nexthops: Make ping timeout configurable") Reviewed-by: Ido Schimmel Signed-off-by: Benjamin Poirier Signed-off-by: David S. Miller --- tools/testing/selftests/net/fib_nexthops.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index a47b26ab48f2..0f5e88c8f4ff 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2283,7 +2283,7 @@ EOF ################################################################################ # main -while getopts :t:pP46hv:w: o +while getopts :t:pP46hvw: o do case $o in t) TESTS=$OPTARG;; From ab87603b251134441a67385ecc9d3371be17b7a7 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Wed, 17 May 2023 13:24:51 +0800 Subject: [PATCH 282/358] net: wwan: t7xx: Ensure init is completed before system sleep When the system attempts to sleep while mtk_t7xx is not ready, the driver cannot put the device to sleep: [ 12.472918] mtk_t7xx 0000:57:00.0: [PM] Exiting suspend, modem in invalid state [ 12.472936] mtk_t7xx 0000:57:00.0: PM: pci_pm_suspend(): t7xx_pci_pm_suspend+0x0/0x20 [mtk_t7xx] returns -14 [ 12.473678] mtk_t7xx 0000:57:00.0: PM: dpm_run_callback(): pci_pm_suspend+0x0/0x1b0 returns -14 [ 12.473711] mtk_t7xx 0000:57:00.0: PM: failed to suspend async: error -14 [ 12.764776] PM: Some devices failed to suspend, or early wake event detected Mediatek confirmed the device can take a rather long time to complete its initialization, so wait for up to 20 seconds until init is done. Signed-off-by: Kai-Heng Feng Signed-off-by: David S. Miller --- drivers/net/wwan/t7xx/t7xx_pci.c | 18 ++++++++++++++++++ drivers/net/wwan/t7xx/t7xx_pci.h | 1 + 2 files changed, 19 insertions(+) diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 226fc1703e90..91256e005b84 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -45,6 +45,7 @@ #define T7XX_PCI_IREG_BASE 0 #define T7XX_PCI_EREG_BASE 2 +#define T7XX_INIT_TIMEOUT 20 #define PM_SLEEP_DIS_TIMEOUT_MS 20 #define PM_ACK_TIMEOUT_MS 1500 #define PM_AUTOSUSPEND_MS 20000 @@ -96,6 +97,7 @@ static int t7xx_pci_pm_init(struct t7xx_pci_dev *t7xx_dev) spin_lock_init(&t7xx_dev->md_pm_lock); init_completion(&t7xx_dev->sleep_lock_acquire); init_completion(&t7xx_dev->pm_sr_ack); + init_completion(&t7xx_dev->init_done); atomic_set(&t7xx_dev->md_pm_state, MTK_PM_INIT); device_init_wakeup(&pdev->dev, true); @@ -124,6 +126,7 @@ void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev) pm_runtime_mark_last_busy(&t7xx_dev->pdev->dev); pm_runtime_allow(&t7xx_dev->pdev->dev); pm_runtime_put_noidle(&t7xx_dev->pdev->dev); + complete_all(&t7xx_dev->init_done); } static int t7xx_pci_pm_reinit(struct t7xx_pci_dev *t7xx_dev) @@ -529,6 +532,20 @@ static void t7xx_pci_shutdown(struct pci_dev *pdev) __t7xx_pci_pm_suspend(pdev); } +static int t7xx_pci_pm_prepare(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct t7xx_pci_dev *t7xx_dev; + + t7xx_dev = pci_get_drvdata(pdev); + if (!wait_for_completion_timeout(&t7xx_dev->init_done, T7XX_INIT_TIMEOUT * HZ)) { + dev_warn(dev, "Not ready for system sleep.\n"); + return -ETIMEDOUT; + } + + return 0; +} + static int t7xx_pci_pm_suspend(struct device *dev) { return __t7xx_pci_pm_suspend(to_pci_dev(dev)); @@ -555,6 +572,7 @@ static int t7xx_pci_pm_runtime_resume(struct device *dev) } static const struct dev_pm_ops t7xx_pci_pm_ops = { + .prepare = t7xx_pci_pm_prepare, .suspend = t7xx_pci_pm_suspend, .resume = t7xx_pci_pm_resume, .resume_noirq = t7xx_pci_pm_resume_noirq, diff --git a/drivers/net/wwan/t7xx/t7xx_pci.h b/drivers/net/wwan/t7xx/t7xx_pci.h index 112efa534eac..f08f1ab74469 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.h +++ b/drivers/net/wwan/t7xx/t7xx_pci.h @@ -69,6 +69,7 @@ struct t7xx_pci_dev { struct t7xx_modem *md; struct t7xx_ccmni_ctrl *ccmni_ctlb; bool rgu_pci_irq_en; + struct completion init_done; /* Low Power Items */ struct list_head md_pm_entities; From 224a876e37543eee111bf9b6aa4935080e619335 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 14 May 2023 10:00:10 -0400 Subject: [PATCH 283/358] netfilter: conntrack: define variables exp_nat_nla_policy and any_addr with CONFIG_NF_NAT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc with W=1 and ! CONFIG_NF_NAT net/netfilter/nf_conntrack_netlink.c:3463:32: error: ‘exp_nat_nla_policy’ defined but not used [-Werror=unused-const-variable=] 3463 | static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { | ^~~~~~~~~~~~~~~~~~ net/netfilter/nf_conntrack_netlink.c:2979:33: error: ‘any_addr’ defined but not used [-Werror=unused-const-variable=] 2979 | static const union nf_inet_addr any_addr; | ^~~~~~~~ These variables use is controlled by CONFIG_NF_NAT, so should their definitions. Signed-off-by: Tom Rix Reviewed-by: Simon Horman Signed-off-by: Florian Westphal --- net/netfilter/nf_conntrack_netlink.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d40544cd61a6..69c8c8c7e9b8 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2976,7 +2976,9 @@ nla_put_failure: return -1; } +#if IS_ENABLED(CONFIG_NF_NAT) static const union nf_inet_addr any_addr; +#endif static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { @@ -3460,10 +3462,12 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x, return 0; } +#if IS_ENABLED(CONFIG_NF_NAT) static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; +#endif static int ctnetlink_parse_expect_nat(const struct nlattr *attr, From e3c361b8acd636f5fe80c02849ca175201edf10c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 11 May 2023 14:15:15 +0200 Subject: [PATCH 284/358] netfilter: nf_tables: fix nft_trans type confusion nft_trans_FOO objects all share a common nft_trans base structure, but trailing fields depend on the real object size. Access is only safe after trans->msg_type check. Check for rule type first. Found by code inspection. Fixes: 1a94e38d254b ("netfilter: nf_tables: add NFTA_RULE_ID attribute") Signed-off-by: Florian Westphal --- net/netfilter/nf_tables_api.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 59fb8320ab4d..dc5675962de4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3865,12 +3865,10 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { - struct nft_rule *rule = nft_trans_rule(trans); - if (trans->msg_type == NFT_MSG_NEWRULE && trans->ctx.chain == chain && id == nft_trans_rule_id(trans)) - return rule; + return nft_trans_rule(trans); } return ERR_PTR(-ENOENT); } From 61ae320a29b0540c16931816299eb86bf2b66c08 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 11 May 2023 22:39:30 +0200 Subject: [PATCH 285/358] netfilter: nft_set_rbtree: fix null deref on element insertion There is no guarantee that rb_prev() will not return NULL in nft_rbtree_gc_elem(): general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] nft_add_set_elem+0x14b0/0x2990 nf_tables_newsetelem+0x528/0xb30 Furthermore, there is a possible use-after-free while iterating, 'node' can be free'd so we need to cache the next value to use. Fixes: c9e6978e2725 ("netfilter: nft_set_rbtree: Switch to node list walk for overlap detection") Signed-off-by: Florian Westphal --- net/netfilter/nft_set_rbtree.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 19ea4d3c3553..2f114aa10f1a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -221,7 +221,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); - struct nft_rbtree_elem *rbe_prev; + struct nft_rbtree_elem *rbe_prev = NULL; struct nft_set_gc_batch *gcb; gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); @@ -229,17 +229,21 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, return -ENOMEM; /* search for expired end interval coming before this element. */ - do { + while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev)) break; prev = rb_prev(prev); - } while (prev != NULL); + } + + if (rbe_prev) { + rb_erase(&rbe_prev->node, &priv->root); + atomic_dec(&set->nelems); + } - rb_erase(&rbe_prev->node, &priv->root); rb_erase(&rbe->node, &priv->root); - atomic_sub(2, &set->nelems); + atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); nft_set_gc_batch_complete(gcb); @@ -268,7 +272,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_set_ext **ext) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; - struct rb_node *node, *parent, **p, *first = NULL; + struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); int d, err; @@ -307,7 +311,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, * Values stored in the tree are in reversed order, starting from * highest to lowest value. */ - for (node = first; node != NULL; node = rb_next(node)) { + for (node = first; node != NULL; node = next) { + next = rb_next(node); + rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_set_elem_active(&rbe->ext, genmask)) From 2862a2fdfae875888e3c1c3634e3422e01d98147 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 11 May 2023 17:04:41 +0200 Subject: [PATCH 286/358] s390/qdio: fix do_sqbs() inline assembly constraint Use "a" constraint instead of "d" constraint to pass the state parameter to the do_sqbs() inline assembly. This prevents that general purpose register zero is used for the state parameter. If the compiler would select general purpose register zero this would be problematic for the used instruction in rsy format: the register used for the state parameter is a base register. If the base register is general purpose register zero the contents of the register are unexpectedly ignored when the instruction is executed. This only applies to z/VM guests using QIOASSIST with dedicated (pass through) QDIO-based devices such as FCP [zfcp driver] as well as real OSA or HiperSockets [qeth driver]. A possible symptom for this case using zfcp is the following repeating kernel message pattern: zfcp : A QDIO problem occurred zfcp : A QDIO problem occurred zfcp : qdio: ZFCP on SC using AI:1 QEBSM:1 PRI:1 TDD:1 SIGA: W zfcp : A QDIO problem occurred zfcp : A QDIO problem occurred Each of the qdio problem message can be accompanied by the following entries for the affected subchannel in /sys/kernel/debug/s390dbf/qdio_error/hex_ascii for zfcp or qeth: ccq: 69.... SQBS ERROR. Reviewed-by: Benjamin Block Cc: Steffen Maier Fixes: 8129ee164267 ("[PATCH] s390: qdio V=V pass-through") Cc: Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- drivers/s390/cio/qdio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 5ea6249d8180..641f0dbb65a9 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -95,7 +95,7 @@ static inline int do_sqbs(u64 token, unsigned char state, int queue, " lgr 1,%[token]\n" " .insn rsy,0xeb000000008a,%[qs],%[ccq],0(%[state])" : [ccq] "+&d" (_ccq), [qs] "+&d" (_queuestart) - : [state] "d" ((unsigned long)state), [token] "d" (token) + : [state] "a" ((unsigned long)state), [token] "d" (token) : "memory", "cc", "1"); *count = _ccq & 0xff; *start = _queuestart & 0xff; From ed40866ec7d328b3dfb70db7e2011640a16202c3 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Thu, 4 May 2023 16:40:20 +0200 Subject: [PATCH 287/358] statfs: enforce statfs[64] structure initialization s390's struct statfs and struct statfs64 contain padding, which field-by-field copying does not set. Initialize the respective structs with zeros before filling them and copying them to userspace, like it's already done for the compat versions of these structs. Found by KMSAN. [agordeev@linux.ibm.com: fixed typo in patch description] Acked-by: Heiko Carstens Cc: stable@vger.kernel.org # v4.14+ Signed-off-by: Ilya Leoshkevich Reviewed-by: Andrew Morton Link: https://lore.kernel.org/r/20230504144021.808932-2-iii@linux.ibm.com Signed-off-by: Alexander Gordeev --- fs/statfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/statfs.c b/fs/statfs.c index 0ba34c135593..96d1c3edf289 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -130,6 +130,7 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); if (sizeof buf.f_blocks == 4) { if ((st->f_blocks | st->f_bfree | st->f_bavail | st->f_bsize | st->f_frsize) & @@ -158,7 +159,6 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; @@ -171,6 +171,7 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; @@ -182,7 +183,6 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; From 6d9406f80cd82964c8ed75d482d885f18921e0b8 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Thu, 4 May 2023 16:40:21 +0200 Subject: [PATCH 288/358] s390/uapi: cover statfs padding by growing f_spare pahole says: struct compat_statfs64 { ... u32 f_spare[4]; /* 68 16 */ /* size: 88, cachelines: 1, members: 12 */ /* padding: 4 */ struct statfs { ... unsigned int f_spare[4]; /* 68 16 */ /* size: 88, cachelines: 1, members: 12 */ /* padding: 4 */ struct statfs64 { ... unsigned int f_spare[4]; /* 68 16 */ /* size: 88, cachelines: 1, members: 12 */ /* padding: 4 */ One has to keep the existence of padding in mind when working with these structs. Grow f_spare arrays to 5 in order to simplify things. Acked-by: Heiko Carstens Signed-off-by: Ilya Leoshkevich Link: https://lore.kernel.org/r/20230504144021.808932-3-iii@linux.ibm.com Signed-off-by: Alexander Gordeev --- arch/s390/include/asm/compat.h | 2 +- arch/s390/include/uapi/asm/statfs.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index a386070f1d56..3cb9d813f022 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -112,7 +112,7 @@ struct compat_statfs64 { u32 f_namelen; u32 f_frsize; u32 f_flags; - u32 f_spare[4]; + u32 f_spare[5]; }; /* diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h index 72604f7792c3..f85b50723dd3 100644 --- a/arch/s390/include/uapi/asm/statfs.h +++ b/arch/s390/include/uapi/asm/statfs.h @@ -30,7 +30,7 @@ struct statfs { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; struct statfs64 { @@ -45,7 +45,7 @@ struct statfs64 { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; #endif From e534167cee150d900bf800ddb9bf1514d966635f Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 8 May 2023 06:09:16 +0200 Subject: [PATCH 289/358] s390/Kconfig: remove obsolete configs SCHED_{BOOK,DRAWER} Commit f1045056c726 ("topology/sysfs: rework book and drawer topology ifdefery") activates the book and drawer topology, previously activated by CONFIG_SCHED_{BOOK,DRAWER}, dependent on the existence of certain macro definitions. Hence, since then, CONFIG_SCHED_{BOOK,DRAWER} have no effect and any further purpose. Remove the obsolete configs SCHED_{BOOK,DRAWER}. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20230508040916.16733-1-lukas.bulwahn@gmail.com Signed-off-by: Alexander Gordeev --- arch/s390/Kconfig | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index db20c1589a98..886948a6105b 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -469,19 +469,11 @@ config SCHED_SMT config SCHED_MC def_bool n -config SCHED_BOOK - def_bool n - -config SCHED_DRAWER - def_bool n - config SCHED_TOPOLOGY def_bool y prompt "Topology scheduler support" select SCHED_SMT select SCHED_MC - select SCHED_BOOK - select SCHED_DRAWER help Topology scheduler support improves the CPU scheduler's decision making when dealing with machines that have multi-threading, From 0f1cbf941d5949110adf70725a9614e622de8d99 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 1 May 2023 14:11:28 -0300 Subject: [PATCH 290/358] s390/iommu: get rid of S390_CCW_IOMMU and S390_AP_IOMMU These don't do anything anymore, the only user of the symbol was VFIO_CCW/AP which already "depends on VFIO" and VFIO itself selects IOMMU_API. When this was added VFIO was wrongly doing "depends on IOMMU_API" which required some contortions like this to ensure IOMMU_API was turned on. Reviewed-by: Eric Farman Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/0-v2-eb322ce2e547+188f-rm_iommu_ccw_jgg@nvidia.com Signed-off-by: Alexander Gordeev --- Documentation/s390/vfio-ap.rst | 1 - arch/s390/Kconfig | 3 +-- arch/s390/configs/debug_defconfig | 2 -- arch/s390/configs/defconfig | 2 -- drivers/iommu/Kconfig | 16 ---------------- 5 files changed, 1 insertion(+), 23 deletions(-) diff --git a/Documentation/s390/vfio-ap.rst b/Documentation/s390/vfio-ap.rst index d46e98c7c1ec..bb3f4c4e2885 100644 --- a/Documentation/s390/vfio-ap.rst +++ b/Documentation/s390/vfio-ap.rst @@ -551,7 +551,6 @@ These are the steps: * IOMMU_SUPPORT * S390 * ZCRYPT - * S390_AP_IOMMU * VFIO * KVM diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 886948a6105b..6dab9c1be508 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -708,7 +708,6 @@ config EADM_SCH config VFIO_CCW def_tristate n prompt "Support for VFIO-CCW subchannels" - depends on S390_CCW_IOMMU depends on VFIO select VFIO_MDEV help @@ -720,7 +719,7 @@ config VFIO_CCW config VFIO_AP def_tristate n prompt "VFIO support for AP devices" - depends on S390_AP_IOMMU && KVM + depends on KVM depends on VFIO depends on ZCRYPT select VFIO_MDEV diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 1b68156f2040..be3bf03bf361 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -591,8 +591,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index b0643283bbdd..769c7eed8b6a 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -580,8 +580,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index db98c3f86e8c..6de900776e24 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -417,22 +417,6 @@ config S390_IOMMU help Support for the IOMMU API for s390 PCI devices. -config S390_CCW_IOMMU - bool "S390 CCW IOMMU Support" - depends on S390 && CCW || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - -config S390_AP_IOMMU - bool "S390 AP IOMMU Support" - depends on S390 && ZCRYPT || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - config MTK_IOMMU tristate "MediaTek IOMMU Support" depends on ARCH_MEDIATEK || COMPILE_TEST From 9bc83d6e3824f09cef73b01256962d950965ddc4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 17 May 2023 10:10:57 -0300 Subject: [PATCH 291/358] tools headers x86 cpufeatures: Sync with the kernel sources To pick the changes from: 3d8f61bf8bcd69bc ("x86: KVM: Add common feature flag for AMD's PSFD") 3763bf58029f3459 ("x86/cpufeatures: Redefine synthetic virtual NMI bit as AMD's "real" vNMI") 6449dcb0cac73821 ("x86: CPUID and CR3/CR4 flags for Linear Address Masking") be8de49bea505e77 ("x86/speculation: Identify processors vulnerable to SMT RSB predictions") e7862eda309ecfcc ("x86/cpu: Support AMD Automatic IBRS") faabfcb194a8d068 ("x86/cpu, kvm: Add the SMM_CTL MSR not present feature") 5b909d4ae59aedc7 ("x86/cpu, kvm: Add the Null Selector Clears Base feature") 84168ae786f8a15a ("x86/cpu, kvm: Move X86_FEATURE_LFENCE_RDTSC to its native leaf") a9dc9ec5a1fafc3d ("x86/cpu, kvm: Add the NO_NESTED_DATA_BP feature") f8df91e73a6827a4 ("x86/cpufeatures: Add macros for Intel's new fast rep string features") 78335aac6156eada ("x86/cpufeatures: Add Bandwidth Monitoring Event Configuration feature flag") f334f723a63cfc25 ("x86/cpufeatures: Add Slow Memory Bandwidth Allocation feature flag") a018d2e3d4b1abc4 ("x86/cpufeatures: Add Architectural PerfMon Extension bit") This causes these perf files to be rebuilt and brings some X86_FEATURE that will be used when updating the copies of tools/arch/x86/lib/mem{cpy,set}_64.S with the kernel sources: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Cc: Borislav Petkov (AMD) Cc: Kim Phillips Cc: Jim Mattson Cc: Babu Moger Cc: Ingo Molnar Cc: Kan Liang Cc: Sean Christopherson Cc: Dave Hansen Cc: Kirill A. Shutemov Cc: Paolo Bonzini Cc: Tom Lendacky Link: https://lore.kernel.org/lkml/ZGTTw642q8mWgv2Y@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 26 +++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b89005819cd5..cb8ca46213be 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -226,10 +226,9 @@ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -307,14 +306,21 @@ #define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ #define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ @@ -331,6 +337,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ @@ -363,6 +370,7 @@ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ #define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -427,6 +435,13 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ + /* * BUG word(s) */ @@ -467,5 +482,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ From 7f02ce62a6cfc0feb164bb7eb36c6647c00b43c8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 17 May 2023 10:34:59 -0300 Subject: [PATCH 292/358] tools headers: Update the copy of x86's mem{cpy,set}_64.S used in 'perf bench' This is to get the changes from: 68674f94ffc9dddc ("x86: don't use REP_GOOD or ERMS for small memory copies") 20f3337d350c4e1b ("x86: don't use REP_GOOD or ERMS for small memory clearing") This also make the 'perf bench mem' files stop referring to the erms versions that gone away with the above patches. That addresses these perf tools build warning: Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S' diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S Warning: Kernel ABI header at 'tools/arch/x86/lib/memset_64.S' differs from latest version at 'arch/x86/lib/memset_64.S' diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/lib/memcpy_64.S | 34 +++++--------- tools/arch/x86/lib/memset_64.S | 47 +++++--------------- tools/include/asm/alternative.h | 3 +- tools/perf/bench/mem-memcpy-x86-64-asm-def.h | 4 -- tools/perf/bench/mem-memcpy-x86-64-asm.S | 2 +- tools/perf/bench/mem-memset-x86-64-asm-def.h | 4 -- tools/perf/bench/mem-memset-x86-64-asm.S | 2 +- 7 files changed, 24 insertions(+), 72 deletions(-) diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index a91ac666f758..d055b82d22cc 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -9,13 +9,6 @@ .section .noinstr.text, "ax" -/* - * We build a jump to memcpy_orig by default which gets NOPped out on - * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which - * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs - * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. - */ - /* * memcpy - Copy a memory block. * @@ -26,17 +19,21 @@ * * Output: * rax original destination + * + * The FSRM alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep movsb' itself is small enough to replace the call, but the + * two register moves blow up the code. And one of them is "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_TYPED_FUNC_START(__memcpy) - ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memcpy_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM movq %rdi, %rax movq %rdx, %rcx - shrq $3, %rcx - andl $7, %edx - rep movsq - movl %edx, %ecx rep movsb RET SYM_FUNC_END(__memcpy) @@ -45,17 +42,6 @@ EXPORT_SYMBOL(__memcpy) SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) -/* - * memcpy_erms() - enhanced fast string memcpy. This is faster and - * simpler than memcpy. Use memcpy_erms when possible. - */ -SYM_FUNC_START_LOCAL(memcpy_erms) - movq %rdi, %rax - movq %rdx, %rcx - rep movsb - RET -SYM_FUNC_END(memcpy_erms) - SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 6143b1a6fa2c..7c59a704c458 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -18,27 +18,22 @@ * rdx count (bytes) * * rax original destination + * + * The FSRS alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep stosb' itself is small enough to replace the call, but all + * the register moves blow up the code. And two of them are "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_FUNC_START(__memset) - /* - * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended - * to use it when possible. If not available, use fast string instructions. - * - * Otherwise, use original memset function. - */ - ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memset_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS movq %rdi,%r9 + movb %sil,%al movq %rdx,%rcx - andl $7,%edx - shrq $3,%rcx - /* expand byte value */ - movzbl %sil,%esi - movabs $0x0101010101010101,%rax - imulq %rsi,%rax - rep stosq - movl %edx,%ecx rep stosb movq %r9,%rax RET @@ -48,26 +43,6 @@ EXPORT_SYMBOL(__memset) SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) -/* - * ISO C memset - set a memory block to a byte value. This function uses - * enhanced rep stosb to override the fast string function. - * The code is simpler and shorter than the fast string function as well. - * - * rdi destination - * rsi value (char) - * rdx count (bytes) - * - * rax original destination - */ -SYM_FUNC_START_LOCAL(memset_erms) - movq %rdi,%r9 - movb %sil,%al - movq %rdx,%rcx - rep stosb - movq %r9,%rax - RET -SYM_FUNC_END(memset_erms) - SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h index b54bd860dff6..7ce02a223732 100644 --- a/tools/include/asm/alternative.h +++ b/tools/include/asm/alternative.h @@ -4,7 +4,6 @@ /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ -#define altinstruction_entry # -#define ALTERNATIVE_2 # +#define ALTERNATIVE # #endif diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h index 50ae8bd58296..6188e19d3129 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMCPY_FN(memcpy_orig, MEMCPY_FN(__memcpy, "x86-64-movsq", "movsq-based memcpy() in arch/x86/lib/memcpy_64.S") - -MEMCPY_FN(memcpy_erms, - "x86-64-movsb", - "movsb-based memcpy() in arch/x86/lib/memcpy_64.S") diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 6eb45a2aa8db..1b9fef7efcdc 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,7 +2,7 @@ /* Various wrappers to make the kernel .S file build in user-space: */ -// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +// memcpy_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h index dac6d2b7c39b..247c72fdfb9d 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMSET_FN(memset_orig, MEMSET_FN(__memset, "x86-64-stosq", "movsq-based memset() in arch/x86/lib/memset_64.S") - -MEMSET_FN(memset_erms, - "x86-64-stosb", - "movsb-based memset() in arch/x86/lib/memset_64.S") diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index 6f093c483842..abd26c95f1aa 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +// memset_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ From 29719e319869c6b3f09e6e92310b019e32943696 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 17 May 2023 11:15:53 -0300 Subject: [PATCH 293/358] tools headers UAPI: Sync arch prctl headers with the kernel sources To pick the changes in this cset: a03c376ebaf38394 ("x86/arch_prctl: Add AMX feature numbers as ABI constants") 23e5d9ec2bab53c4 ("x86/mm/iommu/sva: Make LAM and SVA mutually exclusive") 2f8794bd087e7958 ("x86/mm: Provide arch_prctl() interface for LAM") This picks these new prctls in a third range, that was also added to the tools/perf/trace/beauty/arch_prctl.c beautifier. $ tools/perf/trace/beauty/x86_arch_prctl.sh > /tmp/before $ cp arch/x86/include/uapi/asm/prctl.h tools/arch/x86/include/uapi/asm/prctl.h $ tools/perf/trace/beauty/x86_arch_prctl.sh > /tmp/after $ diff -u /tmp/before /tmp/after @@ -20,3 +20,11 @@ [0x2003 - 0x2001]= "MAP_VDSO_64", }; +#define x86_arch_prctl_codes_3_offset 0x4001 +static const char *x86_arch_prctl_codes_3[] = { + [0x4001 - 0x4001]= "GET_UNTAG_MASK", + [0x4002 - 0x4001]= "ENABLE_TAGGED_ADDR", + [0x4003 - 0x4001]= "GET_MAX_TAG_BITS", + [0x4004 - 0x4001]= "FORCE_TAGGED_SVA", +}; + $ With this 'perf trace' can translate those numbers into strings and use the strings in filter expressions: # perf trace -e prctl 0.000 ( 0.011 ms): DOM Worker/3722622 prctl(option: SET_NAME, arg2: 0x7f9c014b7df5) = 0 0.032 ( 0.002 ms): DOM Worker/3722622 prctl(option: SET_NAME, arg2: 0x7f9bb6b51580) = 0 5.452 ( 0.003 ms): StreamT~ns #30/3722623 prctl(option: SET_NAME, arg2: 0x7f9bdbdfeb70) = 0 5.468 ( 0.002 ms): StreamT~ns #30/3722623 prctl(option: SET_NAME, arg2: 0x7f9bdbdfea70) = 0 24.494 ( 0.009 ms): IndexedDB #556/3722624 prctl(option: SET_NAME, arg2: 0x7f562a32ae28) = 0 24.540 ( 0.002 ms): IndexedDB #556/3722624 prctl(option: SET_NAME, arg2: 0x7f563c6d4b30) = 0 670.281 ( 0.008 ms): systemd-userwo/3722339 prctl(option: SET_NAME, arg2: 0x564be30805c8) = 0 670.293 ( 0.002 ms): systemd-userwo/3722339 prctl(option: SET_NAME, arg2: 0x564be30800f0) = 0 ^C# This addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/prctl.h' differs from latest version at 'arch/x86/include/uapi/asm/prctl.h' diff -u tools/arch/x86/include/uapi/asm/prctl.h arch/x86/include/uapi/asm/prctl.h Cc: Adrian Hunter Cc: Chang S. Bae Cc: Dave Hansen Cc: Ian Rogers Cc: Jiri Olsa Cc: Kirill A. Shutemov Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZGTjNPpD3FOWfetM@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/prctl.h | 8 ++++++++ tools/perf/trace/beauty/arch_prctl.c | 2 ++ tools/perf/trace/beauty/x86_arch_prctl.sh | 1 + 3 files changed, 11 insertions(+) diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h index 500b96e71f18..e8d7ebbca1a4 100644 --- a/tools/arch/x86/include/uapi/asm/prctl.h +++ b/tools/arch/x86/include/uapi/asm/prctl.h @@ -16,8 +16,16 @@ #define ARCH_GET_XCOMP_GUEST_PERM 0x1024 #define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 +#define ARCH_XCOMP_TILECFG 17 +#define ARCH_XCOMP_TILEDATA 18 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 +#define ARCH_GET_UNTAG_MASK 0x4001 +#define ARCH_ENABLE_TAGGED_ADDR 0x4002 +#define ARCH_GET_MAX_TAG_BITS 0x4003 +#define ARCH_FORCE_TAGGED_SVA 0x4004 + #endif /* _ASM_X86_PRCTL_H */ diff --git a/tools/perf/trace/beauty/arch_prctl.c b/tools/perf/trace/beauty/arch_prctl.c index fe022ca67e60..a211348d3204 100644 --- a/tools/perf/trace/beauty/arch_prctl.c +++ b/tools/perf/trace/beauty/arch_prctl.c @@ -12,10 +12,12 @@ static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_1, "ARCH_", x86_arch_prctl_codes_1_offset); static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_2, "ARCH_", x86_arch_prctl_codes_2_offset); +static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_3, "ARCH_", x86_arch_prctl_codes_3_offset); static struct strarray *x86_arch_prctl_codes[] = { &strarray__x86_arch_prctl_codes_1, &strarray__x86_arch_prctl_codes_2, + &strarray__x86_arch_prctl_codes_3, }; static DEFINE_STRARRAYS(x86_arch_prctl_codes); diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh index 57fa6aaffe70..fd5c740512c5 100755 --- a/tools/perf/trace/beauty/x86_arch_prctl.sh +++ b/tools/perf/trace/beauty/x86_arch_prctl.sh @@ -24,3 +24,4 @@ print_range () { print_range 1 0x1 0x1001 print_range 2 0x2 0x2001 +print_range 3 0x4 0x4001 From 1743e5f6000901a11f4e1cd741bfa9136f3ec9b1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 17 May 2023 09:53:45 +0200 Subject: [PATCH 294/358] nvme-multipath: don't call blk_mark_disk_dead in nvme_mpath_remove_disk nvme_mpath_remove_disk is called after del_gendisk, at which point a blk_mark_disk_dead call doesn't make any sense. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- drivers/nvme/host/multipath.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index fc39d01e7b63..187c9de0d6d5 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -884,7 +884,6 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) { if (!head->disk) return; - blk_mark_disk_dead(head->disk); /* make sure all pending bios are cleaned up */ kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); From 2eb94dd56a4a4e3fe286def3e2ba207804a37345 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Thu, 11 May 2023 13:07:41 +0200 Subject: [PATCH 295/358] nvme: do not let the user delete a ctrl before a complete initialization If a userspace application performes a "delete_controller" command early during the ctrl initialization, the delete operation may race against the init code and the kernel will crash. nvme nvme5: Connect command failed: host path error nvme nvme5: failed to connect queue: 0 ret=880 PF: supervisor write access in kernel mode PF: error_code(0x0002) - not-present page blk_mq_quiesce_queue+0x18/0x90 nvme_tcp_delete_ctrl+0x24/0x40 [nvme_tcp] nvme_do_delete_ctrl+0x7f/0x8b [nvme_core] nvme_sysfs_delete.cold+0x8/0xd [nvme_core] kernfs_fop_write_iter+0x124/0x1b0 new_sync_write+0xff/0x190 vfs_write+0x1ef/0x280 Fix the crash by checking the NVME_CTRL_STARTED_ONCE bit; if it's not set it means that the nvme controller is still in the process of getting initialized and the kernel will return an -EBUSY error to userspace. Set the NVME_CTRL_STARTED_ONCE later in the nvme_start_ctrl() function, after the controller start operation is completed. Signed-off-by: Maurizio Lombardi Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 6c1e7d6709e0..22e9e90aa671 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3574,6 +3574,9 @@ static ssize_t nvme_sysfs_delete(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags)) + return -EBUSY; + if (device_remove_file_self(dev, attr)) nvme_delete_ctrl_sync(ctrl); return count; @@ -5034,7 +5037,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) * that were missed. We identify persistent discovery controllers by * checking that they started once before, hence are reconnecting back. */ - if (test_and_set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && + if (test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && nvme_discovery_ctrl(ctrl)) nvme_change_uevent(ctrl, "NVME_EVENT=rediscover"); @@ -5045,6 +5048,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) } nvme_change_uevent(ctrl, "NVME_EVENT=connected"); + set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags); } EXPORT_SYMBOL_GPL(nvme_start_ctrl); From 1b5f159ce8751b61aea426293cd71a510a081939 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 17 May 2023 11:47:38 -0300 Subject: [PATCH 296/358] tools headers disabled-features: Sync with the kernel sources To pick the changes from: e0bddc19ba9578bc ("x86/mm: Reduce untagged_addr() overhead for systems without LAM") This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/disabled-features.h' differs from latest version at 'arch/x86/include/asm/disabled-features.h' diff -u tools/arch/x86/include/asm/disabled-features.h arch/x86/include/asm/disabled-features.h Cc: Adrian Hunter Cc: Dave Hansen Cc: Ian Rogers Cc: Jiri Olsa Cc: Kirill A. Shutemov Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZGTpdlzrlRjjnY6K@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/disabled-features.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dfa4fb76f4b..fafe9be7a6f4 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -75,6 +75,12 @@ # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) #endif +#ifdef CONFIG_ADDRESS_MASKING +# define DISABLE_LAM 0 +#else +# define DISABLE_LAM (1 << (X86_FEATURE_LAM & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -115,7 +121,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING) -#define DISABLED_MASK12 0 +#define DISABLED_MASK12 (DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 From ccecefa4f89971e34745abbffdaf4d2c3fb2f457 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:50:41 +0200 Subject: [PATCH 297/358] ALSA: cs46xx: mark snd_cs46xx_download_image as static snd_cs46xx_download_image() was originally called from dsp_spos.c, but is now local to cs46xx_lib.c. Mark it as 'static' to avoid a warning about it lacking a declaration, and '__maybe_unused' to avoid a warning about it being unused when CONFIG_SND_CS46XX_NEW_DSP is disabled: sound/pci/cs46xx/cs46xx_lib.c:534:5: error: no previous prototype for 'snd_cs46xx_download_image' Fixes: 89f157d9e6bf ("[ALSA] cs46xx - Fix PM resume") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516195046.550584-1-arnd@kernel.org Signed-off-by: Takashi Iwai --- sound/pci/cs46xx/cs46xx_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c index 62f45847b351..7d882b33d45e 100644 --- a/sound/pci/cs46xx/cs46xx_lib.c +++ b/sound/pci/cs46xx/cs46xx_lib.c @@ -531,7 +531,7 @@ static int load_firmware(struct snd_cs46xx *chip) return err; } -int snd_cs46xx_download_image(struct snd_cs46xx *chip) +static __maybe_unused int snd_cs46xx_download_image(struct snd_cs46xx *chip) { int idx, err; unsigned int offset = 0; From 040b5a046a9e18098580d3ccd029e2318fca7859 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:50:42 +0200 Subject: [PATCH 298/358] ALSA: oss: avoid missing-prototype warnings Two functions are defined and used in pcm_oss.c but also optionally used from io.c, with an optional prototype. If CONFIG_SND_PCM_OSS_PLUGINS is disabled, this causes a warning as the functions are not static and have no prototype: sound/core/oss/pcm_oss.c:1235:19: error: no previous prototype for 'snd_pcm_oss_write3' [-Werror=missing-prototypes] sound/core/oss/pcm_oss.c:1266:19: error: no previous prototype for 'snd_pcm_oss_read3' [-Werror=missing-prototypes] Avoid this by making the prototypes unconditional. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516195046.550584-2-arnd@kernel.org Signed-off-by: Takashi Iwai --- sound/core/oss/pcm_plugin.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/sound/core/oss/pcm_plugin.h b/sound/core/oss/pcm_plugin.h index 46e273bd4a78..50a6b50f5db4 100644 --- a/sound/core/oss/pcm_plugin.h +++ b/sound/core/oss/pcm_plugin.h @@ -141,6 +141,14 @@ int snd_pcm_area_copy(const struct snd_pcm_channel_area *src_channel, void *snd_pcm_plug_buf_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t size); void snd_pcm_plug_buf_unlock(struct snd_pcm_substream *plug, void *ptr); +#else + +static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } +static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } +static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } + +#endif + snd_pcm_sframes_t snd_pcm_oss_write3(struct snd_pcm_substream *substream, const char *ptr, snd_pcm_uframes_t size, int in_kernel); @@ -151,14 +159,6 @@ snd_pcm_sframes_t snd_pcm_oss_writev3(struct snd_pcm_substream *substream, snd_pcm_sframes_t snd_pcm_oss_readv3(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames); -#else - -static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } -static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } -static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } - -#endif - #ifdef PLUGIN_DEBUG #define pdprintf(fmt, args...) printk(KERN_DEBUG "plugin: " fmt, ##args) #else From dc4f2ccaedddb489a83e7b12ebbdc347272aacc9 Mon Sep 17 00:00:00 2001 From: Nikhil Mahale Date: Wed, 17 May 2023 14:37:36 +0530 Subject: [PATCH 299/358] ALSA: hda: Add NVIDIA codec IDs a3 through a7 to patch table These IDs are for AD102, AD103, AD104, AD106, and AD107 gpus with audio functions that are largely similar to the existing ones. Tested audio using gnome-settings, over HDMI, DP-SST and DP-MST connections on AD106 gpu. Signed-off-by: Nikhil Mahale Cc: Link: https://lore.kernel.org/r/20230517090736.15088-1-nmahale@nvidia.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_hdmi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 64a944016c78..5c0b1a09fd57 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4589,6 +4589,11 @@ HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi), From e36ca2fad6bb4ef0603bdb5556578e9082fe0056 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 16 May 2023 15:20:36 -0700 Subject: [PATCH 300/358] iommu/arm-smmu-qcom: Fix missing adreno_smmu's When the special handling of qcom,adreno-smmu was moved into qcom_smmu_create(), it was overlooked that we didn't have all the required entries in qcom_smmu_impl_of_match. So we stopped getting adreno_smmu_priv on sc7180, breaking per-process pgtables. Fixes: 30b912a03d91 ("iommu/arm-smmu-qcom: Move the qcom,adreno-smmu check into qcom_smmu_create") Cc: Suggested-by: Lepton Wu Signed-off-by: Rob Clark Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/537357/ Link: https://lore.kernel.org/r/20230516222039.907690-1-robdclark@gmail.com --- drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index d1b296b95c86..ec743a9ec67a 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -503,6 +503,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = { { .compatible = "qcom,qcm2290-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,qdu1000-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc7180-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sc7180-smmu-v2", .data = &qcom_smmu_v2_data }, { .compatible = "qcom,sc7280-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8180x-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8280xp-smmu-500", .data = &qcom_smmu_500_impl0_data }, @@ -547,5 +548,14 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) if (match) return qcom_smmu_create(smmu, match->data); + /* + * If you hit this WARN_ON() you are missing an entry in the + * qcom_smmu_impl_of_match[] table, and GPU per-process page- + * tables will be broken. + */ + WARN(of_device_is_compatible(np, "qcom,adreno-smmu"), + "Missing qcom_smmu_impl_of_match entry for: %s", + dev_name(smmu->dev)); + return smmu; } From 5c054db54c43a5fcb5cc81012361f5e3fac37637 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 16 May 2023 15:20:37 -0700 Subject: [PATCH 301/358] drm/msm: Be more shouty if per-process pgtables aren't working Otherwise it is not always obvious if a dt or iommu change is causing us to fall back to global pgtable. Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/537359/ Link: https://lore.kernel.org/r/20230516222039.907690-2-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_iommu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 5080319ae4cf..5cc8d358cc97 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -234,7 +234,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Get the pagetable configuration from the domain */ if (adreno_smmu->cookie) ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); - if (!ttbr1_cfg) + + /* + * If you hit this WARN_ONCE() you are probably missing an entry in + * qcom_smmu_impl_of_match[] in arm-smmu-qcom.c + */ + if (WARN_ONCE(!ttbr1_cfg, "No per-process page tables")) return ERR_PTR(-ENODEV); pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL); From a18ef64fe1e4558b14a6e0ca9fbe8264475b7013 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 17 May 2023 14:47:12 +0200 Subject: [PATCH 302/358] tracing: make ftrace_likely_update() declaration visible This function is only used when CONFIG_TRACE_BRANCH_PROFILING is set and DISABLE_BRANCH_PROFILING is not set, and the declaration is hidden behind this combination of tests. But that causes a warning when building with CONFIG_TRACING_BRANCHES, since that sets DISABLE_BRANCH_PROFILING for the tracing code, and the declaration is thus hidden: kernel/trace/trace_branch.c:205:6: error: no previous prototype for 'ftrace_likely_update' [-Werror=missing-prototypes] Move the declaration out of the #ifdef to avoid the warning. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 947a60b801db..d7779a18b24f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -12,11 +12,10 @@ * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. */ -#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ - && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant); - +#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ + && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) From d5aa417808cf14c052ca042920b3c6b9f1dc6aa4 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 10 Apr 2023 12:02:29 -0400 Subject: [PATCH 303/358] drm/amdgpu/gfx11: update gpu_clock_counter logic This code was written prior to previous updates to this logic for other chips. The RSC registers are part of SMUIO which is an always on block so there is no need to disable gfxoff. Additionally add the carryover and preemption checks. v2: rebase Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.y: 5591a051b86b: drm/amdgpu: refine get gpu clock counter method Cc: stable@vger.kernel.org # 6.2.y: 5591a051b86b: drm/amdgpu: refine get gpu clock counter method Cc: stable@vger.kernel.org # 6.3.y: 5591a051b86b: drm/amdgpu: refine get gpu clock counter method --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index f5c376276984..db2543d8fde9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -4667,24 +4667,27 @@ static uint64_t gfx_v11_0_get_gpu_clock_counter(struct amdgpu_device *adev) uint64_t clock; uint64_t clock_counter_lo, clock_counter_hi_pre, clock_counter_hi_after; - amdgpu_gfx_off_ctrl(adev, false); - mutex_lock(&adev->gfx.gpu_clock_mutex); if (amdgpu_sriov_vf(adev)) { + amdgpu_gfx_off_ctrl(adev, false); + mutex_lock(&adev->gfx.gpu_clock_mutex); clock_counter_hi_pre = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_HI); clock_counter_lo = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_LO); clock_counter_hi_after = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_HI); if (clock_counter_hi_pre != clock_counter_hi_after) clock_counter_lo = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_LO); + mutex_unlock(&adev->gfx.gpu_clock_mutex); + amdgpu_gfx_off_ctrl(adev, true); } else { + preempt_disable(); clock_counter_hi_pre = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); clock_counter_hi_after = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); if (clock_counter_hi_pre != clock_counter_hi_after) clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); + preempt_enable(); } clock = clock_counter_lo | (clock_counter_hi_after << 32ULL); - mutex_unlock(&adev->gfx.gpu_clock_mutex); - amdgpu_gfx_off_ctrl(adev, true); + return clock; } From 47592fa8eb03742048b096b4696ec133384c45eb Mon Sep 17 00:00:00 2001 From: Bharath SM Date: Wed, 3 May 2023 14:38:35 +0000 Subject: [PATCH 304/358] SMB3: Close all deferred handles of inode in case of handle lease break Oplock break may occur for different file handle than the deferred handle. Check for inode deferred closes list, if it's not empty then close all the deferred handles of inode because we should not cache handles if we dont have handle lease. Eg: If openfilelist has one deferred file handle and another open file handle from app for a same file, then on a lease break we choose the first handle in openfile list. The first handle in list can be deferred handle or actual open file handle from app. In case if it is actual open handle then today, we don't close deferred handles if we lose handle lease on a file. Problem with this is, later if app decides to close the existing open handle then we still be caching deferred handles until deferred close timeout. Leaving open handle may result in sharing violation when windows client tries to open a file with limited file share access. So we should check for deferred list of inode and walk through the list of deferred files in inode and close all deferred files. Fixes: 9e31678fb403 ("SMB3: fix lease break timeout when multiple deferred close handles for the same file.") Cc: stable@kernel.org Signed-off-by: Bharath SM Signed-off-by: Steve French --- fs/cifs/file.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index c5fcefdfd797..e7868e47c61c 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4882,8 +4882,6 @@ void cifs_oplock_break(struct work_struct *work) struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; bool purge_cache = false; - struct cifs_deferred_close *dclose; - bool is_deferred = false; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -4924,14 +4922,9 @@ oplock_break_ack: * file handles but cached, then schedule deferred close immediately. * So, new open will not use cached handle. */ - spin_lock(&CIFS_I(inode)->deferred_lock); - is_deferred = cifs_is_deferred_close(cfile, &dclose); - spin_unlock(&CIFS_I(inode)->deferred_lock); - if (!CIFS_CACHE_HANDLE(cinode) && is_deferred && - cfile->deferred_close_scheduled && delayed_work_pending(&cfile->deferred)) { + if (!CIFS_CACHE_HANDLE(cinode) && !list_empty(&cinode->deferred_closes)) cifs_close_deferred_file(cinode); - } /* * releasing stale oplock after recent reconnect of smb session using From 59a556aebc43dded08535fe97d94ca3f657915e4 Mon Sep 17 00:00:00 2001 From: Bharath SM Date: Mon, 15 May 2023 21:25:12 +0000 Subject: [PATCH 305/358] SMB3: drop reference to cfile before sending oplock break In cifs_oplock_break function we drop reference to a cfile at the end of function, due to which close command goes on wire after lease break acknowledgment even if file is already closed by application but we had deferred the handle close. If other client with limited file shareaccess waiting on lease break ack proceeds operation on that file as soon as first client sends ack, then we may encounter status sharing violation error because of open handle. Solution is to put reference to cfile(send close on wire if last ref) and then send oplock acknowledgment to server. Fixes: 9e31678fb403 ("SMB3: fix lease break timeout when multiple deferred close handles for the same file.") Cc: stable@kernel.org Signed-off-by: Bharath SM Reviewed-by: Shyam Prasad N Signed-off-by: Steve French --- fs/cifs/cifsglob.h | 4 ++-- fs/cifs/file.c | 17 ++++++++++++----- fs/cifs/smb1ops.c | 9 ++++----- fs/cifs/smb2ops.c | 7 +++---- 4 files changed, 21 insertions(+), 16 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 414685c5d530..5f8fd20951af 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -424,8 +424,8 @@ struct smb_version_operations { /* check for STATUS_NETWORK_SESSION_EXPIRED */ bool (*is_session_expired)(char *); /* send oplock break response */ - int (*oplock_response)(struct cifs_tcon *, struct cifs_fid *, - struct cifsInodeInfo *); + int (*oplock_response)(struct cifs_tcon *tcon, __u64 persistent_fid, __u64 volatile_fid, + __u16 net_fid, struct cifsInodeInfo *cifs_inode); /* query remote filesystem */ int (*queryfs)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, struct kstatfs *); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e7868e47c61c..ba7f2e09d6c8 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4881,7 +4881,9 @@ void cifs_oplock_break(struct work_struct *work) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; - bool purge_cache = false; + bool purge_cache = false, oplock_break_cancelled; + __u64 persistent_fid, volatile_fid; + __u16 net_fid; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -4926,19 +4928,24 @@ oplock_break_ack: if (!CIFS_CACHE_HANDLE(cinode) && !list_empty(&cinode->deferred_closes)) cifs_close_deferred_file(cinode); + persistent_fid = cfile->fid.persistent_fid; + volatile_fid = cfile->fid.volatile_fid; + net_fid = cfile->fid.netfid; + oplock_break_cancelled = cfile->oplock_break_cancelled; + + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do * not bother sending an oplock release if session to server still is * disconnected since oplock already released by the server */ - if (!cfile->oplock_break_cancelled) { - rc = tcon->ses->server->ops->oplock_response(tcon, &cfile->fid, - cinode); + if (!oplock_break_cancelled) { + rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, + volatile_fid, net_fid, cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } - _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index abda6148be10..7d1b3fc014d9 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -897,12 +897,11 @@ cifs_close_dir(const unsigned int xid, struct cifs_tcon *tcon, } static int -cifs_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { - return CIFSSMBLock(0, tcon, fid->netfid, current->tgid, 0, 0, 0, 0, - LOCKING_ANDX_OPLOCK_RELEASE, false, - CIFS_CACHE_READ(cinode) ? 1 : 0); + return CIFSSMBLock(0, tcon, net_fid, current->tgid, 0, 0, 0, 0, + LOCKING_ANDX_OPLOCK_RELEASE, false, CIFS_CACHE_READ(cinode) ? 1 : 0); } static int diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index a295e4c2d54e..5065398665f1 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2383,15 +2383,14 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) } static int -smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) return SMB2_lease_break(0, tcon, cinode->lease_key, smb2_get_lease_state(cinode)); - return SMB2_oplock_break(0, tcon, fid->persistent_fid, - fid->volatile_fid, + return SMB2_oplock_break(0, tcon, persistent_fid, volatile_fid, CIFS_CACHE_READ(cinode) ? 1 : 0); } From 36a6418bb125944838b91a33eddca4064a5eb610 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 17 May 2023 20:02:51 +0200 Subject: [PATCH 306/358] Revert "ARM: dts: stm32: add CAN support on stm32f746" This reverts commit 0920ccdf41e3078a4dd2567eb905ea154bc826e6. The commit 0920ccdf41e3 ("ARM: dts: stm32: add CAN support on stm32f746") depends on the patch "dt-bindings: mfd: stm32f7: add binding definition for CAN3" [1], which is not in net/main, yet. This results in a parsing error of "stm32f746.dtsi". So revert this commit. [1] https://lore.kernel.org/all/20230423172528.1398158-2-dario.binacchi@amarulasolutions.com Cc: Dario Binacchi Cc: Alexandre TORGUE Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202305172108.x5acbaQG-lkp@intel.com Closes: https://lore.kernel.org/oe-kbuild-all/202305172130.eGGEUhpi-lkp@intel.com Fixes: 0920ccdf41e3 ("ARM: dts: stm32: add CAN support on stm32f746") Suggested-by: Krzysztof Kozlowski Link: https://lore.kernel.org/20230517181950.1106697-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- arch/arm/boot/dts/stm32f746.dtsi | 47 -------------------------------- 1 file changed, 47 deletions(-) diff --git a/arch/arm/boot/dts/stm32f746.dtsi b/arch/arm/boot/dts/stm32f746.dtsi index 973698bc9ef4..dc868e6da40e 100644 --- a/arch/arm/boot/dts/stm32f746.dtsi +++ b/arch/arm/boot/dts/stm32f746.dtsi @@ -257,23 +257,6 @@ status = "disabled"; }; - can3: can@40003400 { - compatible = "st,stm32f4-bxcan"; - reg = <0x40003400 0x200>; - interrupts = <104>, <105>, <106>, <107>; - interrupt-names = "tx", "rx0", "rx1", "sce"; - resets = <&rcc STM32F7_APB1_RESET(CAN3)>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN3)>; - st,gcan = <&gcan3>; - status = "disabled"; - }; - - gcan3: gcan@40003600 { - compatible = "st,stm32f4-gcan", "syscon"; - reg = <0x40003600 0x200>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN3)>; - }; - usart2: serial@40004400 { compatible = "st,stm32f7-uart"; reg = <0x40004400 0x400>; @@ -354,36 +337,6 @@ status = "disabled"; }; - can1: can@40006400 { - compatible = "st,stm32f4-bxcan"; - reg = <0x40006400 0x200>; - interrupts = <19>, <20>, <21>, <22>; - interrupt-names = "tx", "rx0", "rx1", "sce"; - resets = <&rcc STM32F7_APB1_RESET(CAN1)>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN1)>; - st,can-primary; - st,gcan = <&gcan1>; - status = "disabled"; - }; - - gcan1: gcan@40006600 { - compatible = "st,stm32f4-gcan", "syscon"; - reg = <0x40006600 0x200>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN1)>; - }; - - can2: can@40006800 { - compatible = "st,stm32f4-bxcan"; - reg = <0x40006800 0x200>; - interrupts = <63>, <64>, <65>, <66>; - interrupt-names = "tx", "rx0", "rx1", "sce"; - resets = <&rcc STM32F7_APB1_RESET(CAN2)>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN2)>; - st,can-secondary; - st,gcan = <&gcan1>; - status = "disabled"; - }; - cec: cec@40006c00 { compatible = "st,stm32-cec"; reg = <0x40006C00 0x400>; From be243bacfb25f5219f2396d787408e8cf1301dd1 Mon Sep 17 00:00:00 2001 From: Ze Gao Date: Wed, 17 May 2023 11:45:06 +0800 Subject: [PATCH 307/358] rethook: use preempt_{disable, enable}_notrace in rethook_trampoline_handler This patch replaces preempt_{disable, enable} with its corresponding notrace version in rethook_trampoline_handler so no worries about stack recursion or overflow introduced by preempt_count_{add, sub} under fprobe + rethook context. Link: https://lore.kernel.org/all/20230517034510.15639-2-zegao@tencent.com/ Fixes: 54ecbe6f1ed5 ("rethook: Add a generic return hook") Signed-off-by: Ze Gao Acked-by: Masami Hiramatsu (Google) Cc: Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/rethook.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index 32c3dfdb4d6a..60f6cb2b486b 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -288,7 +288,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, * These loops must be protected from rethook_free_rcu() because those * are accessing 'rhn->rethook'. */ - preempt_disable(); + preempt_disable_notrace(); /* * Run the handler on the shadow stack. Do not unlink the list here because @@ -321,7 +321,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, first = first->next; rethook_recycle(rhn); } - preempt_enable(); + preempt_enable_notrace(); return correct_ret_addr; } From 3cc4e2c5fbae84e5033723fb7e350bc6c164e3a2 Mon Sep 17 00:00:00 2001 From: Ze Gao Date: Wed, 17 May 2023 11:45:07 +0800 Subject: [PATCH 308/358] fprobe: make fprobe_kprobe_handler recursion free Current implementation calls kprobe related functions before doing ftrace recursion check in fprobe_kprobe_handler, which opens door to kernel crash due to stack recursion if preempt_count_{add, sub} is traceable in kprobe_busy_{begin, end}. Things goes like this without this patch quoted from Steven: " fprobe_kprobe_handler() { kprobe_busy_begin() { preempt_disable() { preempt_count_add() { <-- trace fprobe_kprobe_handler() { [ wash, rinse, repeat, CRASH!!! ] " By refactoring the common part out of fprobe_kprobe_handler and fprobe_handler and call ftrace recursion detection at the very beginning, the whole fprobe_kprobe_handler is free from recursion. [ Fix the indentation of __fprobe_handler() parameters. ] Link: https://lore.kernel.org/all/20230517034510.15639-3-zegao@tencent.com/ Fixes: ab51e15d535e ("fprobe: Introduce FPROBE_FL_KPROBE_SHARED flag for fprobe") Signed-off-by: Ze Gao Acked-by: Masami Hiramatsu (Google) Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 59 ++++++++++++++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 15 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 293184227394..7a692c02f787 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -20,30 +20,22 @@ struct fprobe_rethook_node { char data[]; }; -static void fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) { struct fprobe_rethook_node *fpr; struct rethook_node *rh = NULL; struct fprobe *fp; void *entry_data = NULL; - int bit, ret = 0; + int ret = 0; fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; - - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; - } if (fp->exit_handler) { rh = rethook_try_get(fp->rethook); if (!rh) { fp->nmissed++; - goto out; + return; } fpr = container_of(rh, struct fprobe_rethook_node, node); fpr->entry_ip = ip; @@ -61,23 +53,60 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, else rethook_hook(rh, ftrace_get_regs(fregs), true); } -out: +} + +static void fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) +{ + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + __fprobe_handler(ip, parent_ip, ops, fregs); ftrace_test_recursion_unlock(bit); + } NOKPROBE_SYMBOL(fprobe_handler); static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { - struct fprobe *fp = container_of(ops, struct fprobe, ops); + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions called before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } if (unlikely(kprobe_running())) { fp->nmissed++; return; } + kprobe_busy_begin(); - fprobe_handler(ip, parent_ip, ops, fregs); + __fprobe_handler(ip, parent_ip, ops, fregs); kprobe_busy_end(); + ftrace_test_recursion_unlock(bit); } static void fprobe_exit_handler(struct rethook_node *rh, void *data, From 2752741080f84f9b2fc93fa92735315d10a415bf Mon Sep 17 00:00:00 2001 From: Ze Gao Date: Wed, 17 May 2023 11:45:08 +0800 Subject: [PATCH 309/358] fprobe: add recursion detection in fprobe_exit_handler fprobe_hander and fprobe_kprobe_handler has guarded ftrace recursion detection but fprobe_exit_handler has not, which possibly introduce recursive calls if the fprobe exit callback calls any traceable functions. Checking in fprobe_hander or fprobe_kprobe_handler is not enough and misses this case. So add recursion free guard the same way as fprobe_hander. Since ftrace recursion check does not employ ip(s), so here use entry_ip and entry_parent_ip the same as fprobe_handler. Link: https://lore.kernel.org/all/20230517034510.15639-4-zegao@tencent.com/ Fixes: 5b0ab78998e3 ("fprobe: Add exit_handler support") Signed-off-by: Ze Gao Cc: stable@vger.kernel.org Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 7a692c02f787..18d36842faf5 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -17,6 +17,7 @@ struct fprobe_rethook_node { struct rethook_node node; unsigned long entry_ip; + unsigned long entry_parent_ip; char data[]; }; @@ -39,6 +40,7 @@ static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, } fpr = container_of(rh, struct fprobe_rethook_node, node); fpr->entry_ip = ip; + fpr->entry_parent_ip = parent_ip; if (fp->entry_data_size) entry_data = fpr->data; } @@ -114,14 +116,26 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, { struct fprobe *fp = (struct fprobe *)data; struct fprobe_rethook_node *fpr; + int bit; if (!fp || fprobe_disabled(fp)) return; fpr = container_of(rh, struct fprobe_rethook_node, node); + /* + * we need to assure no calls to traceable functions in-between the + * end of fprobe_handler and the beginning of fprobe_exit_handler. + */ + bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + fp->exit_handler(fp, fpr->entry_ip, regs, fp->entry_data_size ? (void *)fpr->data : NULL); + ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(fprobe_exit_handler); From 571a2a50a8fc546145ffd3bf673547e9fe128ed2 Mon Sep 17 00:00:00 2001 From: Ze Gao Date: Wed, 17 May 2023 11:45:09 +0800 Subject: [PATCH 310/358] rethook, fprobe: do not trace rethook related functions These functions are already marked as NOKPROBE to prevent recursion and we have the same reason to blacklist them if rethook is used with fprobe, since they are beyond the recursion-free region ftrace can guard. Link: https://lore.kernel.org/all/20230517034510.15639-5-zegao@tencent.com/ Fixes: f3a112c0c40d ("x86,rethook,kprobes: Replace kretprobe with rethook on x86") Signed-off-by: Ze Gao Reviewed-by: Steven Rostedt (Google) Acked-by: Masami Hiramatsu (Google) Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- arch/riscv/kernel/probes/Makefile | 2 ++ arch/s390/kernel/Makefile | 1 + arch/x86/kernel/Makefile | 1 + 3 files changed, 4 insertions(+) diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile index c40139e9ca47..8265ff497977 100644 --- a/arch/riscv/kernel/probes/Makefile +++ b/arch/riscv/kernel/probes/Makefile @@ -4,3 +4,5 @@ obj-$(CONFIG_RETHOOK) += rethook.o rethook_trampoline.o obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o obj-$(CONFIG_UPROBES) += uprobes.o decode-insn.o simulate-insn.o CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE) diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 8983837b3565..6b2a051e1f8a 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -10,6 +10,7 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) # Do not trace early setup code CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index dd61752f4c96..4070a01c11b7 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -17,6 +17,7 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg CFLAGS_REMOVE_sev.o = -pg +CFLAGS_REMOVE_rethook.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n From 0257d9908d38c0b1669af4bb1bc4dbca1f273fe6 Mon Sep 17 00:00:00 2001 From: Peng Zhang Date: Fri, 5 May 2023 22:58:29 +0800 Subject: [PATCH 311/358] maple_tree: make maple state reusable after mas_empty_area() Make mas->min and mas->max point to a node range instead of a leaf entry range. This allows mas to still be usable after mas_empty_area() returns. Users would get unexpected results from other operations on the maple state after calling the affected function. For example, x86 MAP_32BIT mmap() acts as if there is no suitable gap when there should be one. Link: https://lkml.kernel.org/r/20230505145829.74574-1-zhangpeng.00@bytedance.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Peng Zhang Reported-by: "Edgecombe, Rick P" Reported-by: Tad Reported-by: Michael Keyes Link: https://lore.kernel.org/linux-mm/32f156ba80010fd97dbaf0a0cdfc84366608624d.camel@intel.com/ Link: https://lore.kernel.org/linux-mm/e6108286ac025c268964a7ead3aab9899f9bc6e9.camel@spotco.us/ Reviewed-by: Liam R. Howlett Tested-by: Rick Edgecombe Cc: Signed-off-by: Andrew Morton --- lib/maple_tree.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 110a36479dce..8ebc43d4cc8c 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5317,15 +5317,9 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, mt = mte_node_type(mas->node); pivots = ma_pivots(mas_mn(mas), mt); - if (offset) - mas->min = pivots[offset - 1] + 1; - - if (offset < mt_pivots[mt]) - mas->max = pivots[offset]; - - if (mas->index < mas->min) - mas->index = mas->min; - + min = mas_safe_min(mas, pivots, offset); + if (mas->index < min) + mas->index = min; mas->last = mas->index + size - 1; return 0; } From 26e239b37ebdfd189a2e6f94d3407e70313348bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Joan=20Bruguera=20Mic=C3=B3?= Date: Wed, 3 May 2023 01:32:32 +0000 Subject: [PATCH 312/358] mm: shrinkers: fix race condition on debugfs cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When something registers and unregisters many shrinkers, such as: for x in $(seq 10000); do unshare -Ui true; done Sometimes the following error is printed to the kernel log: debugfs: Directory '...' with parent 'shrinker' already present! This occurs since commit badc28d4924b ("mm: shrinkers: fix deadlock in shrinker debugfs") / v6.2: Since the call to `debugfs_remove_recursive` was moved outside the `shrinker_rwsem`/`shrinker_mutex` lock, but the call to `ida_free` stayed inside, a newly registered shrinker can be re-assigned that ID and attempt to create the debugfs directory before the directory from the previous shrinker has been removed. The locking changes in commit f95bdb700bc6 ("mm: vmscan: make global slab shrink lockless") made the race condition more likely, though it existed before then. Commit badc28d4924b ("mm: shrinkers: fix deadlock in shrinker debugfs") could be reverted since the issue is addressed should no longer occur since the count and scan operations are lockless since commit 20cd1892fcc3 ("mm: shrinkers: make count and scan in shrinker debugfs lockless"). However, since this is a contended lock, prefer instead moving `ida_free` outside the lock to avoid the race. Link: https://lkml.kernel.org/r/20230503013232.299211-1-joanbrugueram@gmail.com Fixes: badc28d4924b ("mm: shrinkers: fix deadlock in shrinker debugfs") Signed-off-by: Joan Bruguera Micó Cc: Qi Zheng Cc: Roman Gushchin Signed-off-by: Andrew Morton --- include/linux/shrinker.h | 13 +++++++++++-- mm/shrinker_debug.c | 15 ++++++++++----- mm/vmscan.c | 5 +++-- 3 files changed, 24 insertions(+), 9 deletions(-) diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 7bde8e1c228a..224293b2dd06 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,7 +107,10 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ @@ -115,10 +118,16 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } -static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { + *debugfs_id = -1; return NULL; } +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) +{ +} static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 3f83b10c5031..fe10436d9911 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -237,7 +237,8 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) } EXPORT_SYMBOL(shrinker_debugfs_rename); -struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { struct dentry *entry = shrinker->debugfs_entry; @@ -246,14 +247,18 @@ struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) kfree_const(shrinker->name); shrinker->name = NULL; - if (entry) { - ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); - shrinker->debugfs_entry = NULL; - } + *debugfs_id = entry ? shrinker->debugfs_id : -1; + shrinker->debugfs_entry = NULL; return entry; } +void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) +{ + debugfs_remove_recursive(debugfs_entry); + ida_free(&shrinker_debugfs_ida, debugfs_id); +} + static int __init shrinker_debugfs_init(void) { struct shrinker *shrinker; diff --git a/mm/vmscan.c b/mm/vmscan.c index d257916f39e5..6d0cd2840cf0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -805,6 +805,7 @@ EXPORT_SYMBOL(register_shrinker); void unregister_shrinker(struct shrinker *shrinker) { struct dentry *debugfs_entry; + int debugfs_id; if (!(shrinker->flags & SHRINKER_REGISTERED)) return; @@ -814,13 +815,13 @@ void unregister_shrinker(struct shrinker *shrinker) shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_remove(shrinker); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); mutex_unlock(&shrinker_mutex); atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); - debugfs_remove_recursive(debugfs_entry); + shrinker_debugfs_remove(debugfs_entry, debugfs_id); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; From d461aac924b937bcb4fd0ca1242b3ef6868ecddd Mon Sep 17 00:00:00 2001 From: Nhat Pham Date: Fri, 5 May 2023 11:50:54 -0700 Subject: [PATCH 313/358] zsmalloc: move LRU update from zs_map_object() to zs_malloc() Under memory pressure, we sometimes observe the following crash: [ 5694.832838] ------------[ cut here ]------------ [ 5694.842093] list_del corruption, ffff888014b6a448->next is LIST_POISON1 (dead000000000100) [ 5694.858677] WARNING: CPU: 33 PID: 418824 at lib/list_debug.c:47 __list_del_entry_valid+0x42/0x80 [ 5694.961820] CPU: 33 PID: 418824 Comm: fuse_counters.s Kdump: loaded Tainted: G S 5.19.0-0_fbk3_rc3_hoangnhatpzsdynshrv41_10870_g85a9558a25de #1 [ 5694.990194] Hardware name: Wiwynn Twin Lakes MP/Twin Lakes Passive MP, BIOS YMM16 05/24/2021 [ 5695.007072] RIP: 0010:__list_del_entry_valid+0x42/0x80 [ 5695.017351] Code: 08 48 83 c2 22 48 39 d0 74 24 48 8b 10 48 39 f2 75 2c 48 8b 51 08 b0 01 48 39 f2 75 34 c3 48 c7 c7 55 d7 78 82 e8 4e 45 3b 00 <0f> 0b eb 31 48 c7 c7 27 a8 70 82 e8 3e 45 3b 00 0f 0b eb 21 48 c7 [ 5695.054919] RSP: 0018:ffffc90027aef4f0 EFLAGS: 00010246 [ 5695.065366] RAX: 41fe484987275300 RBX: ffff888008988180 RCX: 0000000000000000 [ 5695.079636] RDX: ffff88886006c280 RSI: ffff888860060480 RDI: ffff888860060480 [ 5695.093904] RBP: 0000000000000002 R08: 0000000000000000 R09: ffffc90027aef370 [ 5695.108175] R10: 0000000000000000 R11: ffffffff82fdf1c0 R12: 0000000010000002 [ 5695.122447] R13: ffff888014b6a448 R14: ffff888014b6a420 R15: 00000000138dc240 [ 5695.136717] FS: 00007f23a7d3f740(0000) GS:ffff888860040000(0000) knlGS:0000000000000000 [ 5695.152899] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 5695.164388] CR2: 0000560ceaab6ac0 CR3: 000000001c06c001 CR4: 00000000007706e0 [ 5695.178659] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 5695.192927] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 5695.207197] PKRU: 55555554 [ 5695.212602] Call Trace: [ 5695.217486] [ 5695.221674] zs_map_object+0x91/0x270 [ 5695.229000] zswap_frontswap_store+0x33d/0x870 [ 5695.237885] ? do_raw_spin_lock+0x5d/0xa0 [ 5695.245899] __frontswap_store+0x51/0xb0 [ 5695.253742] swap_writepage+0x3c/0x60 [ 5695.261063] shrink_page_list+0x738/0x1230 [ 5695.269255] shrink_lruvec+0x5ec/0xcd0 [ 5695.276749] ? shrink_slab+0x187/0x5f0 [ 5695.284240] ? mem_cgroup_iter+0x6e/0x120 [ 5695.292255] shrink_node+0x293/0x7b0 [ 5695.299402] do_try_to_free_pages+0xea/0x550 [ 5695.307940] try_to_free_pages+0x19a/0x490 [ 5695.316126] __folio_alloc+0x19ff/0x3e40 [ 5695.323971] ? __filemap_get_folio+0x8a/0x4e0 [ 5695.332681] ? walk_component+0x2a8/0xb50 [ 5695.340697] ? generic_permission+0xda/0x2a0 [ 5695.349231] ? __filemap_get_folio+0x8a/0x4e0 [ 5695.357940] ? walk_component+0x2a8/0xb50 [ 5695.365955] vma_alloc_folio+0x10e/0x570 [ 5695.373796] ? walk_component+0x52/0xb50 [ 5695.381634] wp_page_copy+0x38c/0xc10 [ 5695.388953] ? filename_lookup+0x378/0xbc0 [ 5695.397140] handle_mm_fault+0x87f/0x1800 [ 5695.405157] do_user_addr_fault+0x1bd/0x570 [ 5695.413520] exc_page_fault+0x5d/0x110 [ 5695.421017] asm_exc_page_fault+0x22/0x30 After some investigation, I have found the following issue: unlike other zswap backends, zsmalloc performs the LRU list update at the object mapping time, rather than when the slot for the object is allocated. This deviation was discussed and agreed upon during the review process of the zsmalloc writeback patch series: https://lore.kernel.org/lkml/Y3flcAXNxxrvy3ZH@cmpxchg.org/ Unfortunately, this introduces a subtle bug that occurs when there is a concurrent store and reclaim, which interleave as follows: zswap_frontswap_store() shrink_worker() zs_malloc() zs_zpool_shrink() spin_lock(&pool->lock) zs_reclaim_page() zspage = find_get_zspage() spin_unlock(&pool->lock) spin_lock(&pool->lock) zspage = list_first_entry(&pool->lru) list_del(&zspage->lru) zspage->lru.next = LIST_POISON1 zspage->lru.prev = LIST_POISON2 spin_unlock(&pool->lock) zs_map_object() spin_lock(&pool->lock) if (!list_empty(&zspage->lru)) list_del(&zspage->lru) CHECK_DATA_CORRUPTION(next == LIST_POISON1) /* BOOM */ With the current upstream code, this issue rarely happens. zswap only triggers writeback when the pool is already full, at which point all further store attempts are short-circuited. This creates an implicit pseudo-serialization between reclaim and store. I am working on a new zswap shrinking mechanism, which makes interleaving reclaim and store more likely, exposing this bug. zbud and z3fold do not have this problem, because they perform the LRU list update in the alloc function, while still holding the pool's lock. This patch fixes the aforementioned bug by moving the LRU update back to zs_malloc(), analogous to zbud and z3fold. Link: https://lkml.kernel.org/r/20230505185054.2417128-1-nphamcs@gmail.com Fixes: 64f768c6b32e ("zsmalloc: add a LRU to zs_pool to keep track of zspages in LRU order") Signed-off-by: Nhat Pham Suggested-by: Johannes Weiner Acked-by: Johannes Weiner Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Dan Streetman Cc: Nitin Gupta Cc: Seth Jennings Cc: Vitaly Wool Cc: Signed-off-by: Andrew Morton --- mm/zsmalloc.c | 36 +++++++++--------------------------- 1 file changed, 9 insertions(+), 27 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 44ddaf5d601e..02f7f414aade 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1331,31 +1331,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); -#ifdef CONFIG_ZPOOL - /* - * Move the zspage to front of pool's LRU. - * - * Note that this is swap-specific, so by definition there are no ongoing - * accesses to the memory while the page is swapped out that would make - * it "hot". A new entry is hot, then ages to the tail until it gets either - * written back or swaps back in. - * - * Furthermore, map is also called during writeback. We must not put an - * isolated page on the LRU mid-reclaim. - * - * As a result, only update the LRU when the page is mapped for write - * when it's first instantiated. - * - * This is a deviation from the other backends, which perform this update - * in the allocation function (zbud_alloc, z3fold_alloc). - */ - if (mm == ZS_MM_WO) { - if (!list_empty(&zspage->lru)) - list_del(&zspage->lru); - list_add(&zspage->lru, &pool->lru); - } -#endif - /* * migration cannot move any zpages in this zspage. Here, pool->lock * is too heavy since callers would take some time until they calls @@ -1525,9 +1500,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, ZS_OBJS_INUSE, 1); - spin_unlock(&pool->lock); - return handle; + goto out; } spin_unlock(&pool->lock); @@ -1550,6 +1524,14 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); +out: +#ifdef CONFIG_ZPOOL + /* Add/move zspage to beginning of LRU */ + if (!list_empty(&zspage->lru)) + list_del(&zspage->lru); + list_add(&zspage->lru, &pool->lru); +#endif + spin_unlock(&pool->lock); return handle; From 7581495ac82d6cb073609284c7f7186a48021d1e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 5 May 2023 13:51:27 +1000 Subject: [PATCH 314/358] mm: kfence: fix false positives on big endian Since commit 1ba3cbf3ec3b ("mm: kfence: improve the performance of __kfence_alloc() and __kfence_free()"), kfence reports failures in random places at boot on big endian machines. The problem is that the new KFENCE_CANARY_PATTERN_U64 encodes the address of each byte in its value, so it needs to be byte swapped on big endian machines. The compiler is smart enough to do the le64_to_cpu() at compile time, so there is no runtime overhead. Link: https://lkml.kernel.org/r/20230505035127.195387-1-mpe@ellerman.id.au Fixes: 1ba3cbf3ec3b ("mm: kfence: improve the performance of __kfence_alloc() and __kfence_free()") Signed-off-by: Michael Ellerman Reviewed-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Peng Zhang Cc: David Laight Signed-off-by: Andrew Morton --- mm/kfence/kfence.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 2aafc46a4aaf..392fb273e7bd 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -29,7 +29,7 @@ * canary of every 8 bytes is the same. 64-bit memory can be filled and checked * at a time instead of byte by byte to improve performance. */ -#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(0x0706050403020100)) +#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(le64_to_cpu(0x0706050403020100))) /* Maximum stack depth for reports. */ #define KFENCE_STACK_DEPTH 64 From 04fc7816089c5a32c29a04ec94b998e219dfb946 Mon Sep 17 00:00:00 2001 From: Domenico Cerasuolo Date: Wed, 3 May 2023 17:12:00 +0200 Subject: [PATCH 315/358] mm: fix zswap writeback race condition The zswap writeback mechanism can cause a race condition resulting in memory corruption, where a swapped out page gets swapped in with data that was written to a different page. The race unfolds like this: 1. a page with data A and swap offset X is stored in zswap 2. page A is removed off the LRU by zpool driver for writeback in zswap-shrink work, data for A is mapped by zpool driver 3. user space program faults and invalidates page entry A, offset X is considered free 4. kswapd stores page B at offset X in zswap (zswap could also be full, if so, page B would then be IOed to X, then skip step 5.) 5. entry A is replaced by B in tree->rbroot, this doesn't affect the local reference held by zswap-shrink work 6. zswap-shrink work writes back A at X, and frees zswap entry A 7. swapin of slot X brings A in memory instead of B The fix: Once the swap page cache has been allocated (case ZSWAP_SWAPCACHE_NEW), zswap-shrink work just checks that the local zswap_entry reference is still the same as the one in the tree. If it's not the same it means that it's either been invalidated or replaced, in both cases the writeback is aborted because the local entry contains stale data. Reproducer: I originally found this by running `stress` overnight to validate my work on the zswap writeback mechanism, it manifested after hours on my test machine. The key to make it happen is having zswap writebacks, so whatever setup pumps /sys/kernel/debug/zswap/written_back_pages should do the trick. In order to reproduce this faster on a vm, I setup a system with ~100M of available memory and a 500M swap file, then running `stress --vm 1 --vm-bytes 300000000 --vm-stride 4000` makes it happen in matter of tens of minutes. One can speed things up even more by swinging /sys/module/zswap/parameters/max_pool_percent up and down between, say, 20 and 1; this makes it reproduce in tens of seconds. It's crucial to set `--vm-stride` to something other than 4096 otherwise `stress` won't realize that memory has been corrupted because all pages would have the same data. Link: https://lkml.kernel.org/r/20230503151200.19707-1-cerasuolodomenico@gmail.com Signed-off-by: Domenico Cerasuolo Acked-by: Johannes Weiner Reviewed-by: Chris Li (Google) Cc: Dan Streetman Cc: Johannes Weiner Cc: Minchan Kim Cc: Nitin Gupta Cc: Seth Jennings Cc: Vitaly Wool Cc: Signed-off-by: Andrew Morton --- mm/zswap.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/mm/zswap.c b/mm/zswap.c index e1e621d0b6a0..59da2a415fbb 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1020,6 +1020,22 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) goto fail; case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* + * Having a local reference to the zswap entry doesn't exclude + * swapping from invalidating and recycling the swap slot. Once + * the swapcache is secured against concurrent swapping to and + * from the slot, recheck that the entry is still current before + * writing. + */ + spin_lock(&tree->lock); + if (zswap_rb_search(&tree->rbroot, entry->offset) != entry) { + spin_unlock(&tree->lock); + delete_from_swap_cache(page_folio(page)); + ret = -ENOMEM; + goto fail; + } + spin_unlock(&tree->lock); + /* decompress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); dlen = PAGE_SIZE; From 9b5a04ac3ad9898c4745cba46ea26de74ba56a8e Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Wed, 10 May 2023 00:29:56 +0900 Subject: [PATCH 316/358] nilfs2: fix use-after-free bug of nilfs_root in nilfs_evict_inode() During unmount process of nilfs2, nothing holds nilfs_root structure after nilfs2 detaches its writer in nilfs_detach_log_writer(). However, since nilfs_evict_inode() uses nilfs_root for some cleanup operations, it may cause use-after-free read if inodes are left in "garbage_list" and released by nilfs_dispose_list() at the end of nilfs_detach_log_writer(). Fix this issue by modifying nilfs_evict_inode() to only clear inode without additional metadata changes that use nilfs_root if the file system is degraded to read-only or the writer is detached. Link: https://lkml.kernel.org/r/20230509152956.8313-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+78d4495558999f55d1da@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/00000000000099e5ac05fb1c3b85@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/inode.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 1310d2d5feb3..a8ce522ac747 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -917,6 +917,7 @@ void nilfs_evict_inode(struct inode *inode) struct nilfs_transaction_info ti; struct super_block *sb = inode->i_sb; struct nilfs_inode_info *ii = NILFS_I(inode); + struct the_nilfs *nilfs; int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { @@ -929,6 +930,23 @@ void nilfs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); + nilfs = sb->s_fs_info; + if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) { + /* + * If this inode is about to be disposed after the file system + * has been degraded to read-only due to file system corruption + * or after the writer has been detached, do not make any + * changes that cause writes, just clear it. + * Do this check after read-locking ns_segctor_sem by + * nilfs_transaction_begin() in order to avoid a race with + * the writer detach operation. + */ + clear_inode(inode); + nilfs_clear_inode(inode); + nilfs_transaction_abort(sb); + return; + } + /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); From 158fb07ba6e77a21f46c3e9c5be44ebd8c4dd2cc Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Tue, 9 May 2023 09:48:34 +0200 Subject: [PATCH 317/358] MAINTAINERS: repair pattern in DIALOG SEMICONDUCTOR DRIVERS Commit 361104b05684c ("dt-bindings: mfd: Convert da9063 to yaml") converts da9063.txt to dlg,da9063.yaml and adds a new file pattern in MAINTAINERS. Unfortunately, the file pattern matches da90*.yaml, but the yaml file is prefixed with dlg,da90. Hence, ./scripts/get_maintainer.pl --self-test=patterns complains about a broken file pattern. Repair this file pattern in DIALOG SEMICONDUCTOR DRIVERS. Link: https://lkml.kernel.org/r/20230509074834.21521-1-lukas.bulwahn@gmail.com Fixes: 361104b05684c ("dt-bindings: mfd: Convert da9063 to yaml") Signed-off-by: Lukas Bulwahn Acked-by: Conor Dooley Cc: Lee Jones Signed-off-by: Andrew Morton --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7e0b87d5aa2e..21d66f969602 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6019,7 +6019,7 @@ W: http://www.dialog-semiconductor.com/products F: Documentation/devicetree/bindings/input/da90??-onkey.txt F: Documentation/devicetree/bindings/input/dlg,da72??.txt F: Documentation/devicetree/bindings/mfd/da90*.txt -F: Documentation/devicetree/bindings/mfd/da90*.yaml +F: Documentation/devicetree/bindings/mfd/dlg,da90*.yaml F: Documentation/devicetree/bindings/regulator/dlg,da9*.yaml F: Documentation/devicetree/bindings/regulator/da92*.txt F: Documentation/devicetree/bindings/regulator/slg51000.txt From c7394fa9aa4ccd4e477626c4f7aef0b360c92efb Mon Sep 17 00:00:00 2001 From: Liviu Dudau Date: Wed, 10 May 2023 13:28:11 +0100 Subject: [PATCH 318/358] MAINTAINERS: Cleanup Arm Display IP maintainers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some people have moved to different roles and are no longer involved in the upstream development. As there is only one person left, remove the mailing list as well as it serves no purpose. Link: https://lkml.kernel.org/r/20230510122811.1872358-1-liviu.dudau@arm.com Signed-off-by: Liviu Dudau Acked-by: Brian Starkey Cc: Mihail Atanassov Cc: Greg Kroah-Hartman Cc: Joe Perches # "Please use --order" Cc: Mihail Atanassov Cc: Uwe Kleine-König Signed-off-by: Andrew Morton --- MAINTAINERS | 5 ----- 1 file changed, 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 21d66f969602..789ceee3424a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1666,10 +1666,7 @@ F: drivers/power/reset/arm-versatile-reboot.c F: drivers/soc/versatile/ ARM KOMEDA DRM-KMS DRIVER -M: James (Qian) Wang M: Liviu Dudau -M: Mihail Atanassov -L: Mali DP Maintainers S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,komeda.yaml @@ -1690,8 +1687,6 @@ F: include/uapi/drm/panfrost_drm.h ARM MALI-DP DRM DRIVER M: Liviu Dudau -M: Brian Starkey -L: Mali DP Maintainers S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,malidp.yaml From 067dee65751bcd14fcaaee769cee84c65ce99360 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:33 +0200 Subject: [PATCH 319/358] net: isa: include net/Space.h The legacy drivers that still get called from net/Space.c have prototypes in net/Space, but this header is not included in most of the files that define those functions: drivers/net/ethernet/cirrus/cs89x0.c:1649:28: error: no previous prototype for 'cs89x0_probe' [-Werror=missing-prototypes] drivers/net/ethernet/8390/ne.c:947:28: error: no previous prototype for 'ne_probe' [-Werror=missing-prototypes] drivers/net/ethernet/8390/smc-ultra.c:167:28: error: no previous prototype for 'ultra_probe' [-Werror=missing-prototypes] drivers/net/ethernet/amd/lance.c:438:28: error: no previous prototype for 'lance_probe' [-Werror=missing-prototypes] drivers/net/ethernet/3com/3c515.c:422:20: error: no previous prototype for 'tc515_probe' [-Werror=missing-prototypes] Add the inclusion to avoids the warnings. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516194625.549249-1-arnd@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/3com/3c515.c | 4 +++- drivers/net/ethernet/8390/ne.c | 1 + drivers/net/ethernet/8390/smc-ultra.c | 1 + drivers/net/ethernet/8390/wd.c | 1 + drivers/net/ethernet/amd/lance.c | 1 + drivers/net/ethernet/cirrus/cs89x0.c | 2 ++ 6 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index d2f4358cc550..ba3e7aa1a28f 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -66,8 +66,10 @@ static int max_interrupt_work = 20; #include #include #include - #include + +#include + #include #include diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 0a9118b8be0c..bc9c81dc00fd 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -52,6 +52,7 @@ static const char version2[] = #include #include #include +#include #include diff --git a/drivers/net/ethernet/8390/smc-ultra.c b/drivers/net/ethernet/8390/smc-ultra.c index 6e62c37c9400..7465650c8078 100644 --- a/drivers/net/ethernet/8390/smc-ultra.c +++ b/drivers/net/ethernet/8390/smc-ultra.c @@ -66,6 +66,7 @@ static const char version[] = #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/8390/wd.c b/drivers/net/ethernet/8390/wd.c index 5b00c452bede..119021d41451 100644 --- a/drivers/net/ethernet/8390/wd.c +++ b/drivers/net/ethernet/8390/wd.c @@ -37,6 +37,7 @@ static const char version[] = #include #include #include +#include #include diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index 8971665a4b2a..6cf38180cc01 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -59,6 +59,7 @@ static const char version[] = "lance.c:v1.16 2006/11/09 dplatt@3do.com, becker@c #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index 06a0c00af99c..276c32c3926a 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -72,6 +72,8 @@ #include #include +#include + #include #include #if ALLOW_DMA From fb1b7be9b16c1f4626969ba4e95a97da2a452b41 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:34 +0200 Subject: [PATCH 320/358] atm: hide unused procfs functions When CONFIG_PROC_FS is disabled, the function declarations for some procfs functions are hidden, but the definitions are still build, as shown by this compiler warning: net/atm/resources.c:403:7: error: no previous prototype for 'atm_dev_seq_start' [-Werror=missing-prototypes] net/atm/resources.c:409:6: error: no previous prototype for 'atm_dev_seq_stop' [-Werror=missing-prototypes] net/atm/resources.c:414:7: error: no previous prototype for 'atm_dev_seq_next' [-Werror=missing-prototypes] Add another #ifdef to leave these out of the build. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516194625.549249-2-arnd@kernel.org Signed-off-by: Jakub Kicinski --- net/atm/resources.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/atm/resources.c b/net/atm/resources.c index 2b2d33eeaf20..995d29e7fb13 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -400,6 +400,7 @@ done: return error; } +#ifdef CONFIG_PROC_FS void *atm_dev_seq_start(struct seq_file *seq, loff_t *pos) { mutex_lock(&atm_dev_mutex); @@ -415,3 +416,4 @@ void *atm_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &atm_devs, pos); } +#endif From 89dcd87ce534a3a7f267cfd58505803006f51301 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:35 +0200 Subject: [PATCH 321/358] bridge: always declare tunnel functions When CONFIG_BRIDGE_VLAN_FILTERING is disabled, two functions are still defined but have no prototype or caller. This causes a W=1 warning for the missing prototypes: net/bridge/br_netlink_tunnel.c:29:6: error: no previous prototype for 'vlan_tunid_inrange' [-Werror=missing-prototypes] net/bridge/br_netlink_tunnel.c:199:5: error: no previous prototype for 'br_vlan_tunnel_info' [-Werror=missing-prototypes] The functions are already contitional on CONFIG_BRIDGE_VLAN_FILTERING, and I coulnd't easily figure out the right set of #ifdefs, so just move the declarations out of the #ifdef to avoid the warning, at a small cost in code size over a more elaborate fix. Fixes: 188c67dd1906 ("net: bridge: vlan options: add support for tunnel id dumping") Fixes: 569da0822808 ("net: bridge: vlan options: add support for tunnel mapping set/del") Signed-off-by: Arnd Bergmann Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230516194625.549249-3-arnd@kernel.org Signed-off-by: Jakub Kicinski --- net/bridge/br_private_tunnel.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h index 2b053289f016..efb096025151 100644 --- a/net/bridge/br_private_tunnel.h +++ b/net/bridge/br_private_tunnel.h @@ -27,6 +27,10 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br, int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg); int br_fill_vlan_tunnel_info(struct sk_buff *skb, struct net_bridge_vlan_group *vg); +bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *v_last); +int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, + u16 vid, u32 tun_id, bool *changed); #ifdef CONFIG_BRIDGE_VLAN_FILTERING /* br_vlan_tunnel.c */ @@ -43,10 +47,6 @@ void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan_group *vg); int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan); -bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, - const struct net_bridge_vlan *v_last); -int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, - u16 vid, u32 tun_id, bool *changed); #else static inline int vlan_tunnel_init(struct net_bridge_vlan_group *vg) { From 2e9f8ab68f42b059e80db71266c1675c07c664bd Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:36 +0200 Subject: [PATCH 322/358] mdio_bus: unhide mdio_bus_init prototype mdio_bus_init() is either used as a local module_init() entry, or it gets called in phy_device.c. In the former case, there is no declaration, which causes a warning: drivers/net/phy/mdio_bus.c:1371:12: error: no previous prototype for 'mdio_bus_init' [-Werror=missing-prototypes] Remove the #ifdef around the declaration to avoid the warning.. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516194625.549249-4-arnd@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/phy.h b/include/linux/phy.h index c5a0dc829714..6478838405a0 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1900,10 +1900,8 @@ void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int addr, size_t priv_size); -#if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); -#endif int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); From bfa00d8f98f7c5e582b04f874aecb83af8da84c6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:42:53 -0700 Subject: [PATCH 323/358] MAINTAINERS: skip CCing netdev for Bluetooth patches As requested by Marcel skip netdev for Bluetooth patches. Bluetooth has its own mailing list and overloading netdev leads to fewer people reading it. Link: https://lore.kernel.org/netdev/639C8EA4-1F6E-42BE-8F04-E4A753A6EFFC@holtmann.org/ Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230517014253.1233333-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index e884937f0e28..5b02298467fa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14632,6 +14632,7 @@ F: include/uapi/linux/netdevice.h F: lib/net_utils.c F: lib/random32.c F: net/ +X: net/bluetooth/ F: tools/net/ F: tools/testing/selftests/net/ From 9aaa7eb018661b2da221362d9bacb096bd596f52 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Mon, 8 May 2023 14:45:01 +0800 Subject: [PATCH 324/358] ceph: silence smatch warning in reconnect_caps_cb() Smatch static checker warning: fs/ceph/mds_client.c:3968 reconnect_caps_cb() warn: missing error code here? '__get_cap_for_mds()' failed. 'err' = '0' [ idryomov: Dan says that Smatch considers it intentional only if the "ret = 0;" assignment is within 4 or 5 lines of the goto. ] Reported-by: Dan Carpenter Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 29cf00220b09..4c0f22acf53d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3942,7 +3942,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) struct dentry *dentry; struct ceph_cap *cap; char *path; - int pathlen = 0, err = 0; + int pathlen = 0, err; u64 pathbase; u64 snap_follows; @@ -3965,6 +3965,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) cap = __get_cap_for_mds(ci, mds); if (!cap) { spin_unlock(&ci->i_ceph_lock); + err = 0; goto out_err; } dout(" adding %p ino %llx.%llx cap %p %lld %s\n", From 4cafd0400bcb6187c0d4ab4d4b0229a89ac4f8c2 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 18 May 2023 09:47:23 +0800 Subject: [PATCH 325/358] ceph: force updating the msg pointer in non-split case When the MClientSnap reqeust's op is not CEPH_SNAP_OP_SPLIT the request may still contain a list of 'split_realms', and we need to skip it anyway. Or it will be parsed as a corrupt snaptrace. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/61200 Reported-by: Frank Schilder Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/snap.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 87007203f130..0b236ebd989f 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1111,6 +1111,19 @@ skip_inode: continue; adjust_snap_realm_parent(mdsc, child, realm->ino); } + } else { + /* + * In the non-split case both 'num_split_inos' and + * 'num_split_realms' should be 0, making this a no-op. + * However the MDS happens to populate 'split_realms' list + * in one of the UPDATE op cases by mistake. + * + * Skip both lists just in case to ensure that 'p' is + * positioned at the start of realm info, as expected by + * ceph_update_snap_trace(). + */ + p += sizeof(u64) * num_split_inos; + p += sizeof(u64) * num_split_realms; } /* From 8173cab3368a13cdc3cad0bd5cf14e9399b0f501 Mon Sep 17 00:00:00 2001 From: Bas Nieuwenhuizen Date: Tue, 9 May 2023 18:49:46 +0200 Subject: [PATCH 326/358] drm/amdgpu/gfx10: Disable gfxoff before disabling powergating. Otherwise we get a full system lock (looks like a FW mess). Copied the order from the GFX9 powergating code. Fixes: 366468ff6c34 ("drm/amdgpu: Allow GfxOff on Vangogh as default") Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2545 Signed-off-by: Bas Nieuwenhuizen Tested-by: Guilherme G. Piccoli Cc: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f5b5ce1051a2..1ec076517c96 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -8152,8 +8152,14 @@ static int gfx_v10_0_set_powergating_state(void *handle, case IP_VERSION(10, 3, 3): case IP_VERSION(10, 3, 6): case IP_VERSION(10, 3, 7): + if (!enable) + amdgpu_gfx_off_ctrl(adev, false); + gfx_v10_cntl_pg(adev, enable); - amdgpu_gfx_off_ctrl(adev, enable); + + if (enable) + amdgpu_gfx_off_ctrl(adev, true); + break; default: break; From 11fbdda2ab6bf049e2869139c07016022b4e045b Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Tue, 9 May 2023 18:49:47 +0200 Subject: [PATCH 327/358] drm/amdgpu/gfx11: Adjust gfxoff before powergating on gfx11 as well (Bas: speculative change to mirror gfx10/gfx9) Signed-off-by: Guilherme G. Piccoli Signed-off-by: Bas Nieuwenhuizen Cc: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index db2543d8fde9..c4940b6ea1c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -5153,8 +5153,14 @@ static int gfx_v11_0_set_powergating_state(void *handle, break; case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 4): + if (!enable) + amdgpu_gfx_off_ctrl(adev, false); + gfx_v11_cntl_pg(adev, enable); - amdgpu_gfx_off_ctrl(adev, enable); + + if (enable) + amdgpu_gfx_off_ctrl(adev, true); + break; default: break; From 9d2d1827af295fd6971786672c41c4dba3657154 Mon Sep 17 00:00:00 2001 From: Jesse Zhang Date: Fri, 12 May 2023 09:29:17 +0800 Subject: [PATCH 328/358] drm/amdgpu: Differentiate between Raven2 and Raven/Picasso according to revision id Due to the raven2 and raven/picasso maybe have the same GC_HWIP version. So differentiate them by revision id. Signed-off-by: shanshengwang Signed-off-by: Jesse Zhang Acked-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 37 ++++++++++++--------------- 1 file changed, 16 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index f46d4b18a3fa..9818743ec419 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -4003,30 +4003,25 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev) clock = clock_lo | (clock_hi << 32ULL); break; case IP_VERSION(9, 1, 0): - preempt_disable(); - clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); - hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); - /* The PWR TSC clock frequency is 100MHz, which sets 32-bit carry over - * roughly every 42 seconds. - */ - if (hi_check != clock_hi) { - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); - clock_hi = hi_check; - } - preempt_enable(); - clock = clock_lo | (clock_hi << 32ULL); - break; case IP_VERSION(9, 2, 2): preempt_disable(); - clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); - hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); - /* The PWR TSC clock frequency is 100MHz, which sets 32-bit carry over - * roughly every 42 seconds. - */ - if (hi_check != clock_hi) { + if (adev->rev_id >= 0x8) { + clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); + } else { + clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); + hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); + } + /* The PWR TSC clock frequency is 100MHz, which sets 32-bit carry over + * roughly every 42 seconds. + */ + if (hi_check != clock_hi) { + if (adev->rev_id >= 0x8) + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + else + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); clock_hi = hi_check; } preempt_enable(); From 68518294d00da6a2433357af75a63abc6030676e Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 11 May 2023 10:40:03 -0400 Subject: [PATCH 329/358] drm/amdgpu/gmc11: implement get_vbios_fb_size() Implement get_vbios_fb_size() so we can properly reserve the vbios splash screen to avoid potential artifacts on the screen during the transition from the pre-OS console to the OS console. Acked-by: Sunil Khatri Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index d95f9fe8f1c5..4116c112e8a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -31,6 +31,8 @@ #include "umc_v8_10.h" #include "athub/athub_3_0_0_sh_mask.h" #include "athub/athub_3_0_0_offset.h" +#include "dcn/dcn_3_2_0_offset.h" +#include "dcn/dcn_3_2_0_sh_mask.h" #include "oss/osssys_6_0_0_offset.h" #include "ivsrcid/vmc/irqsrcs_vmc_1_0.h" #include "navi10_enum.h" @@ -546,7 +548,24 @@ static void gmc_v11_0_get_vm_pte(struct amdgpu_device *adev, static unsigned gmc_v11_0_get_vbios_fb_size(struct amdgpu_device *adev) { - return 0; + u32 d1vga_control = RREG32_SOC15(DCE, 0, regD1VGA_CONTROL); + unsigned size; + + if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) { + size = AMDGPU_VBIOS_VGA_ALLOCATION; + } else { + u32 viewport; + u32 pitch; + + viewport = RREG32_SOC15(DCE, 0, regHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION); + pitch = RREG32_SOC15(DCE, 0, regHUBPREQ0_DCSURF_SURFACE_PITCH); + size = (REG_GET_FIELD(viewport, + HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) * + REG_GET_FIELD(pitch, HUBPREQ0_DCSURF_SURFACE_PITCH, PITCH) * + 4); + } + + return size; } static const struct amdgpu_gmc_funcs gmc_v11_0_gmc_funcs = { From c1a322a7a4a96cd0a3dde32ce37af437a78bf8cd Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Tue, 9 May 2023 16:15:27 +0800 Subject: [PATCH 330/358] drm/amdgpu: skip disabling fence driver src_irqs when device is unplugged When performing device unbind or halt, we have disabled all irqs at the very begining like amdgpu_pci_remove or amdgpu_device_halt. So amdgpu_irq_put for irqs stored in fence driver should not be called any more, otherwise, below calltrace will arrive. [ 139.114088] WARNING: CPU: 2 PID: 1550 at drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c:616 amdgpu_irq_put+0xf6/0x110 [amdgpu] [ 139.114655] Call Trace: [ 139.114655] [ 139.114657] amdgpu_fence_driver_hw_fini+0x93/0x130 [amdgpu] [ 139.114836] amdgpu_device_fini_hw+0xb6/0x350 [amdgpu] [ 139.114955] amdgpu_driver_unload_kms+0x51/0x70 [amdgpu] [ 139.115075] amdgpu_pci_remove+0x63/0x160 [amdgpu] [ 139.115193] ? __pm_runtime_resume+0x64/0x90 [ 139.115195] pci_device_remove+0x3a/0xb0 [ 139.115197] device_remove+0x43/0x70 [ 139.115198] device_release_driver_internal+0xbd/0x140 Signed-off-by: Guchun Chen Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index f52d0ba91a77..a7d250809da9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -582,7 +582,8 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev) if (r) amdgpu_fence_driver_force_completion(ring); - if (ring->fence_drv.irq_src) + if (!drm_dev_is_unplugged(adev_to_drm(adev)) && + ring->fence_drv.irq_src) amdgpu_irq_put(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); From bf4823267a817f7c155876a125b94336d7113e77 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Thu, 11 May 2023 15:41:27 +0800 Subject: [PATCH 331/358] drm/amd/pm: fix possible power mode mismatch between driver and PMFW PMFW may boots the ASIC with a different power mode from the system's real one. Notify PMFW explicitly the power mode the system in. This is needed only when ACDC switch via gpio is not supported. Signed-off-by: Evan Quan Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 18 +++++++++++++++++ .../gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c | 20 +------------------ .../drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 1 + 3 files changed, 20 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 5633c5797e85..2ddf5198e5c4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -733,6 +733,24 @@ static int smu_late_init(void *handle) return ret; } + /* + * Explicitly notify PMFW the power mode the system in. Since + * the PMFW may boot the ASIC with a different mode. + * For those supporting ACDC switch via gpio, PMFW will + * handle the switch automatically. Driver involvement + * is unnecessary. + */ + if (!smu->dc_controlled_by_gpio) { + ret = smu_set_power_source(smu, + adev->pm.ac_power ? SMU_POWER_SOURCE_AC : + SMU_POWER_SOURCE_DC); + if (ret) { + dev_err(adev->dev, "Failed to switch to %s mode!\n", + adev->pm.ac_power ? "AC" : "DC"); + return ret; + } + } + if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 1)) || (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 3))) return 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index c4000518dc56..275f708db636 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -3413,26 +3413,8 @@ static int navi10_post_smu_init(struct smu_context *smu) return 0; ret = navi10_run_umc_cdr_workaround(smu); - if (ret) { + if (ret) dev_err(adev->dev, "Failed to apply umc cdr workaround!\n"); - return ret; - } - - if (!smu->dc_controlled_by_gpio) { - /* - * For Navi1X, manually switch it to AC mode as PMFW - * may boot it with DC mode. - */ - ret = smu_v11_0_set_power_source(smu, - adev->pm.ac_power ? - SMU_POWER_SOURCE_AC : - SMU_POWER_SOURCE_DC); - if (ret) { - dev_err(adev->dev, "Failed to switch to %s mode!\n", - adev->pm.ac_power ? "AC" : "DC"); - return ret; - } - } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 3d9ff46706fb..98a33f8ee209 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -1770,6 +1770,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .enable_mgpu_fan_boost = smu_v13_0_7_enable_mgpu_fan_boost, .get_power_limit = smu_v13_0_7_get_power_limit, .set_power_limit = smu_v13_0_set_power_limit, + .set_power_source = smu_v13_0_set_power_source, .get_power_profile_mode = smu_v13_0_7_get_power_profile_mode, .set_power_profile_mode = smu_v13_0_7_set_power_profile_mode, .set_tool_table_location = smu_v13_0_set_tool_table_location, From 6d600229df1ed06f46ba68ac706d9f44ba8c5fb4 Mon Sep 17 00:00:00 2001 From: Mustapha Ghaddar Date: Fri, 28 Apr 2023 12:13:21 -0400 Subject: [PATCH 332/358] drm/amd/display: enable dpia validate Use dpia_validate_usb4_bw() function Fixes: a8b537605e22 ("drm/amd/display: Add function pointer for validate bw usb4") Reviewed-by: Roman Li Reviewed-by: Meenakshikumar Somasundaram Acked-by: Aurabindo Pillai Signed-off-by: Mustapha Ghaddar Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/link/link_validation.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c index d4b7da526f0a..e8b2fc4002a5 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c @@ -359,5 +359,8 @@ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const un link[i] = stream[i].link; bw_needed[i] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing); } + + ret = dpia_validate_usb4_bw(link, bw_needed, num_streams); + return ret; } From ac5902f84bb546c64aea02c439c2579cbf40318f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 17 May 2023 21:34:08 +0800 Subject: [PATCH 333/358] ublk: fix AB-BA lockdep warning When handling UBLK_IO_FETCH_REQ, ctx->uring_lock is grabbed first, then ub->mutex is acquired. When handling UBLK_CMD_STOP_DEV or UBLK_CMD_DEL_DEV, ub->mutex is grabbed first, then calling io_uring_cmd_done() for canceling uring command, in which ctx->uring_lock may be required. Real deadlock only happens when all the above commands are issued from same uring context, and in reality different uring contexts are often used for handing control command and IO command. Fix the issue by using io_uring_cmd_complete_in_task() to cancel command in ublk_cancel_dev(ublk_cancel_queue). Reported-by: Shinichiro Kawasaki Closes: https://lore.kernel.org/linux-block/becol2g7sawl4rsjq2dztsbc7mqypfqko6wzsyoyazqydoasml@rcxarzwidrhk Cc: Ziyang Zhang Signed-off-by: Ming Lei Tested-by: Shinichiro Kawasaki Link: https://lore.kernel.org/r/20230517133408.210944-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c7ed5d69e9ee..33d3298a0da1 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1120,6 +1120,11 @@ static inline bool ublk_queue_ready(struct ublk_queue *ubq) return ubq->nr_io_ready == ubq->q_depth; } +static void ublk_cmd_cancel_cb(struct io_uring_cmd *cmd, unsigned issue_flags) +{ + io_uring_cmd_done(cmd, UBLK_IO_RES_ABORT, 0, issue_flags); +} + static void ublk_cancel_queue(struct ublk_queue *ubq) { int i; @@ -1131,8 +1136,8 @@ static void ublk_cancel_queue(struct ublk_queue *ubq) struct ublk_io *io = &ubq->ios[i]; if (io->flags & UBLK_IO_FLAG_ACTIVE) - io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0, - IO_URING_F_UNLOCKED); + io_uring_cmd_complete_in_task(io->cmd, + ublk_cmd_cancel_cb); } /* all io commands are canceled */ From 0649728123cf6a5518e154b4e1735fc85ea4f55c Mon Sep 17 00:00:00 2001 From: Daniel Smith Date: Wed, 17 May 2023 14:32:32 -0700 Subject: [PATCH 334/358] nvme-pci: Add quirk for Teamgroup MP33 SSD Add a quirk for Teamgroup MP33 that reports duplicate ids for disk. Signed-off-by: Daniel Smith [kch: patch formatting] Signed-off-by: Chaitanya Kulkarni Tested-by: Daniel Smith Signed-off-by: Keith Busch --- drivers/nvme/host/pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 922ffe4e2822..e90f824ffed8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3437,6 +3437,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1e4b, 0x1602), /* HS-SSD-FUTURE 2048G */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x10ec, 0x5765), /* TEAMGROUP MP33 2TB SSD */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), From ddaf098ea779b3c1302c7843f6ff01e89b1fd380 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 May 2023 21:20:14 +0200 Subject: [PATCH 335/358] driver core: class: properly reference count class_dev_iter() When class_dev_iter is initialized, the reference count for the subsys private structure is incremented, but never decremented, causing a memory leak over time. To resolve this, save off a pointer to the internal structure into the class_dev_iter structure and then when the iterator is finished, drop the reference count. Reported-and-tested-by: syzbot+e7afd76ad060fa0d2605@syzkaller.appspotmail.com Fixes: 7b884b7f24b4 ("driver core: class.c: convert to only use class_to_subsys") Reported-by: Mirsad Goran Todorovac Cc: Alan Stern Acked-by: Rafael J. Wysocki Tested-by: Mirsad Goran Todorovac Link: https://lore.kernel.org/r/2023051610-stove-condense-9a77@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 2 ++ include/linux/device/class.h | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/base/class.c b/drivers/base/class.c index ac1808d1a2e8..05d9df90f621 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -320,6 +320,7 @@ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, start_knode = &start->p->knode_class; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; + iter->sp = sp; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -361,6 +362,7 @@ EXPORT_SYMBOL_GPL(class_dev_iter_next); void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); + subsys_put(iter->sp); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 9deeaeb457bb..abf3d3bfb6fe 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -74,6 +74,7 @@ struct class { struct class_dev_iter { struct klist_iter ki; const struct device_type *type; + struct subsys_private *sp; }; int __must_check class_register(const struct class *class); From 951efb9976ce453342a86b29d7bfe9fa483c7c4d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 17 May 2023 15:57:05 -0700 Subject: [PATCH 336/358] perf test attr: Update no event/metric expectations Previously hard coded events/metrics were used, update for the use of the TopdownL1 json metric group. Reported-by: Arnaldo Carvalho de Melo Fixes: 94b1a603fca78388 ("perf stat: Add TopdownL1 metric as a default if present") Reviewed-by: James Clark Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Tested-by: Kan Liang Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Richter Link: https://lore.kernel.org/r/20230517225707.2682235-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr/base-stat | 2 +- tools/perf/tests/attr/test-stat-default | 96 ++++++++------ tools/perf/tests/attr/test-stat-detailed-1 | 111 +++++++++------- tools/perf/tests/attr/test-stat-detailed-2 | 135 ++++++++++--------- tools/perf/tests/attr/test-stat-detailed-3 | 143 ++++++++++++--------- 5 files changed, 281 insertions(+), 206 deletions(-) diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index a21fb65bc012..fccd8ec4d1b0 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -16,7 +16,7 @@ pinned=0 exclusive=0 exclude_user=0 exclude_kernel=0|1 -exclude_hv=0 +exclude_hv=0|1 exclude_idle=0 mmap=0 comm=0 diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d8ea6a88163f..a1e2da0a9a6d 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -40,7 +40,6 @@ fd=6 type=0 config=7 optional=1 - # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 @@ -89,22 +88,11 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 -disabled=0 -enable_on_exec=0 -read_format=15 -optional=1 - -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) -[event14:base-stat] -fd=14 -group_fd=11 -type=4 config=33280 disabled=0 enable_on_exec=0 @@ -112,8 +100,8 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-be-bound (0x8300) -[event15:base-stat] -fd=15 +[event14:base-stat] +fd=14 group_fd=11 type=4 config=33536 @@ -122,46 +110,76 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index b656ab93c5bf..1c52cb05c900 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -90,22 +90,11 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 -disabled=0 -enable_on_exec=0 -read_format=15 -optional=1 - -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) -[event14:base-stat] -fd=14 -group_fd=11 -type=4 config=33280 disabled=0 enable_on_exec=0 @@ -113,8 +102,8 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-be-bound (0x8300) -[event15:base-stat] -fd=15 +[event14:base-stat] +fd=14 group_fd=11 type=4 config=33536 @@ -123,56 +112,86 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 97625090a1c4..7e961d24a885 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -90,22 +90,11 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 -disabled=0 -enable_on_exec=0 -read_format=15 -optional=1 - -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) -[event14:base-stat] -fd=14 -group_fd=11 -type=4 config=33280 disabled=0 enable_on_exec=0 @@ -113,8 +102,8 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-be-bound (0x8300) -[event15:base-stat] -fd=15 +[event14:base-stat] +fd=14 group_fd=11 type=4 config=33536 @@ -123,56 +112,86 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index d555042e3fbf..e50535f45977 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -90,22 +90,11 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 -disabled=0 -enable_on_exec=0 -read_format=15 -optional=1 - -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) -[event14:base-stat] -fd=14 -group_fd=11 -type=4 config=33280 disabled=0 enable_on_exec=0 @@ -113,8 +102,8 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-be-bound (0x8300) -[event15:base-stat] -fd=15 +[event14:base-stat] +fd=14 group_fd=11 type=4 config=33536 @@ -123,56 +112,86 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 @@ -271,8 +290,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event30:base-stat] -fd=30 +[event35:base-stat] +fd=35 type=3 config=512 optional=1 @@ -281,8 +300,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event31:base-stat] -fd=31 +[event36:base-stat] +fd=36 type=3 config=66048 optional=1 From 75438f24a4d4adcaea6f04ad3a94b7a145e63327 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 17 May 2023 15:57:06 -0700 Subject: [PATCH 337/358] perf test attr: Fix python SafeConfigParser() deprecation warning Address the warning: ``` tests/attr.py:155: DeprecationWarning: The SafeConfigParser class has been renamed to ConfigParser in Python 3.2. This alias will be removed in Python 3.12. Use ConfigParser directly instead. parser = configparser.SafeConfigParser() ``` by removing the word 'Safe'. Reviewed-by: James Clark Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Richter Link: https://lore.kernel.org/r/20230517225707.2682235-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index ccfef861e931..e890c261ad26 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -152,7 +152,7 @@ def parse_version(version): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = configparser.SafeConfigParser() + parser = configparser.ConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -247,7 +247,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = configparser.SafeConfigParser() + parser_event = configparser.ConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -261,7 +261,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = configparser.SafeConfigParser() + parser_base = configparser.ConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') From 46f5dd7439e35ae63cdf04d7967152936c8a511e Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 15 May 2023 13:32:47 +0300 Subject: [PATCH 338/358] fbdev: omapfb: panel-tpo-td043mtea1: fix error code in probe() This was using the wrong variable, "r", instead of "ddata->vcc_reg", so it returned success instead of a negative error code. Fixes: 0d3dbeb8142a ("video: fbdev: omapfb: panel-tpo-td043mtea1: Make use of the helper function dev_err_probe()") Signed-off-by: Dan Carpenter Signed-off-by: Helge Deller --- .../video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c index 1eaa35c27835..477789cff8e0 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c @@ -491,7 +491,8 @@ static int tpo_td043_probe(struct spi_device *spi) ddata->vcc_reg = devm_regulator_get(&spi->dev, "vcc"); if (IS_ERR(ddata->vcc_reg)) { - r = dev_err_probe(&spi->dev, r, "failed to get LCD VCC regulator\n"); + r = dev_err_probe(&spi->dev, PTR_ERR(ddata->vcc_reg), + "failed to get LCD VCC regulator\n"); goto err_regulator; } From 4e111f0cf0ee973ce7e7e012b4ceb07867d2dae5 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 19 May 2023 15:17:37 +0800 Subject: [PATCH 339/358] perf bench syscall: Fix __NR_execve undeclared build error The __NR_execve definition for i386 was deleted by mistake in the commit ece7f7c0507c ("perf bench syscall: Add fork syscall benchmark"), add it to fix the build error on i386. Fixes: ece7f7c0507cc147 ("perf bench syscall: Add fork syscall benchmark") Reported-by: Linux Kernel Functional Testing Signed-off-by: Tiezhu Yang Tested-by: Naresh Kamboju Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Tiezhu Yang Cc: loongson-kernel@lists.loongnix.cn Closes: https://lore.kernel.org/all/CA+G9fYvgBR1iB0CorM8OC4AM_w_tFzyQKHc+rF6qPzJL=TbfDQ@mail.gmail.com/ Link: https://lore.kernel.org/r/1684480657-2375-1-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/unistd_32.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index b8ddfc4c4ab0..bc48a4dabe5d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -2,6 +2,9 @@ #ifndef __NR_fork #define __NR_fork 2 #endif +#ifndef __NR_execve +#define __NR_execve 11 +#endif #ifndef __NR_getppid #define __NR_getppid 64 #endif From 6735150b69978a9f73e3d1bab719e81a5dfafa83 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 12 May 2023 16:31:26 -0700 Subject: [PATCH 340/358] KVM: Use syscore_ops instead of reboot_notifier to hook restart/shutdown Use syscore_ops.shutdown to disable hardware virtualization during a reboot instead of using the dedicated reboot_notifier so that KVM disables virtualization _after_ system_state has been updated. This will allow fixing a race in KVM's handling of a forced reboot where KVM can end up enabling hardware virtualization between kernel_restart_prepare() and machine_restart(). Rename KVM's hook to match the syscore op to avoid any possible confusion from wiring up a "reboot" helper to a "shutdown" hook (neither "shutdown nor "reboot" is completely accurate as the hook handles both). Opportunistically rewrite kvm_shutdown()'s comment to make it less VMX specific, and to explain why kvm_rebooting exists. Cc: Marc Zyngier Cc: Oliver Upton Cc: James Morse Cc: Suzuki K Poulose Cc: Zenghui Yu Cc: kvmarm@lists.linux.dev Cc: Huacai Chen Cc: Aleksandar Markovic Cc: Anup Patel Cc: Atish Patra Cc: kvm-riscv@lists.infradead.org Signed-off-by: Sean Christopherson Acked-by: Marc Zyngier Message-Id: <20230512233127.804012-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cb5c13eee193..2079d6065795 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5213,26 +5213,24 @@ static int hardware_enable_all(void) return r; } -static int kvm_reboot(struct notifier_block *notifier, unsigned long val, - void *v) +static void kvm_shutdown(void) { /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - * - * And Intel TXT required VMX off for all cpu when system shutdown. + * Disable hardware virtualization and set kvm_rebooting to indicate + * that KVM has asynchronously disabled hardware virtualization, i.e. + * that relevant errors and exceptions aren't entirely unexpected. + * Some flavors of hardware virtualization need to be disabled before + * transferring control to firmware (to perform shutdown/reboot), e.g. + * on x86, virtualization can block INIT interrupts, which are used by + * firmware to pull APs back under firmware control. Note, this path + * is used for both shutdown and reboot scenarios, i.e. neither name is + * 100% comprehensive. */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable_nolock, NULL, 1); - return NOTIFY_OK; } -static struct notifier_block kvm_reboot_notifier = { - .notifier_call = kvm_reboot, - .priority = 0, -}; - static int kvm_suspend(void) { /* @@ -5263,6 +5261,7 @@ static void kvm_resume(void) static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, + .shutdown = kvm_shutdown, }; #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static int hardware_enable_all(void) @@ -5967,7 +5966,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (r) return r; - register_reboot_notifier(&kvm_reboot_notifier); register_syscore_ops(&kvm_syscore_ops); #endif @@ -6039,7 +6037,6 @@ err_cpu_kick_mask: err_vcpu_cache: #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif return r; @@ -6065,7 +6062,6 @@ void kvm_exit(void) kvm_async_pf_deinit(); #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif kvm_irqfd_exit(); From e0ceec221f62deb5d6c32c0327030028d3db5f27 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 12 May 2023 16:31:27 -0700 Subject: [PATCH 341/358] KVM: Don't enable hardware after a restart/shutdown is initiated Reject hardware enabling, i.e. VM creation, if a restart/shutdown has been initiated to avoid re-enabling hardware between kvm_reboot() and machine_{halt,power_off,restart}(). The restart case is especially problematic (for x86) as enabling VMX (or clearing GIF in KVM_RUN on SVM) blocks INIT, which results in the restart/reboot hanging as BIOS is unable to wake and rendezvous with APs. Note, this bug, and the original issue that motivated the addition of kvm_reboot(), is effectively limited to a forced reboot, e.g. `reboot -f`. In a "normal" reboot, userspace will gracefully teardown userspace before triggering the kernel reboot (modulo bugs, errors, etc), i.e. any process that might do ioctl(KVM_CREATE_VM) is long gone. Fixes: 8e1c18157d87 ("KVM: VMX: Disable VMX when system shutdown") Signed-off-by: Sean Christopherson Acked-by: Marc Zyngier Message-Id: <20230512233127.804012-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2079d6065795..540e2bbf00f7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5184,7 +5184,20 @@ static void hardware_disable_all(void) static int hardware_enable_all(void) { atomic_t failed = ATOMIC_INIT(0); - int r = 0; + int r; + + /* + * Do not enable hardware virtualization if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling + * after kvm_reboot() is called. Note, this relies on system_state + * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops + * hook instead of registering a dedicated reboot notifier (the latter + * runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) + return -EBUSY; /* * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() @@ -5197,6 +5210,8 @@ static int hardware_enable_all(void) cpus_read_lock(); mutex_lock(&kvm_lock); + r = 0; + kvm_usage_count++; if (kvm_usage_count == 1) { on_each_cpu(hardware_enable_nolock, &failed, 1); From 3367eeab975145e65136c2d091fe6e0c6cb29636 Mon Sep 17 00:00:00 2001 From: Jacob Xu Date: Thu, 24 Feb 2022 17:29:59 -0800 Subject: [PATCH 342/358] KVM: VMX: Fix header file dependency of asm/vmx.h Include a definition of WARN_ON_ONCE() before using it. Fixes: bb1fcc70d98f ("KVM: nVMX: Allow L1 to use 5-level page walks for nested EPT") Cc: Sean Christopherson Signed-off-by: Jacob Xu [reworded commit message; changed to ] Signed-off-by: Jim Mattson Reviewed-by: Sean Christopherson Message-Id: <20220225012959.1554168-1-jmattson@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/vmx.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 498dc600bd5c..0d02c4aafa6f 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -13,7 +13,9 @@ #include +#include #include + #include #include From afb2acb2e3a32e4d56f7fbd819769b98ed1b7520 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Wed, 10 May 2023 16:04:09 +0200 Subject: [PATCH 343/358] KVM: Fix vcpu_array[0] races In kvm_vm_ioctl_create_vcpu(), add vcpu to vcpu_array iff it's safe to access vcpu via kvm_get_vcpu() and kvm_for_each_vcpu(), i.e. when there's no failure path requiring vcpu removal and destruction. Such order is important because vcpu_array accessors may end up referencing vcpu at vcpu_array[0] even before online_vcpus is set to 1. When online_vcpus=0, any call to kvm_get_vcpu() goes through array_index_nospec() and ends with an attempt to xa_load(vcpu_array, 0): int num_vcpus = atomic_read(&kvm->online_vcpus); i = array_index_nospec(i, num_vcpus); return xa_load(&kvm->vcpu_array, i); Similarly, when online_vcpus=0, a kvm_for_each_vcpu() does not iterate over an "empty" range, but actually [0, ULONG_MAX]: xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ (atomic_read(&kvm->online_vcpus) - 1)) In both cases, such online_vcpus=0 edge case, even if leading to unnecessary calls to XArray API, should not be an issue; requesting unpopulated indexes/ranges is handled by xa_load() and xa_for_each_range(). However, this means that when the first vCPU is created and inserted in vcpu_array *and* before online_vcpus is incremented, code calling kvm_get_vcpu()/kvm_for_each_vcpu() already has access to that first vCPU. This should not pose a problem assuming that once a vcpu is stored in vcpu_array, it will remain there, but that's not the case: kvm_vm_ioctl_create_vcpu() first inserts to vcpu_array, then requests a file descriptor. If create_vcpu_fd() fails, newly inserted vcpu is removed from the vcpu_array, then destroyed: vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); kvm_put_kvm_no_destroy(kvm); goto unlock_vcpu_destroy; } atomic_inc(&kvm->online_vcpus); This results in a possible race condition when a reference to a vcpu is acquired (via kvm_get_vcpu() or kvm_for_each_vcpu()) moments before said vcpu is destroyed. Signed-off-by: Michal Luczaj Message-Id: <20230510140410.1093987-2-mhal@rbox.co> Cc: stable@vger.kernel.org Fixes: c5b077549136 ("KVM: Convert the kvm->vcpus array to a xarray", 2021-12-08) Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 540e2bbf00f7..479802a892d4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3962,18 +3962,19 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); - BUG_ON(r == -EBUSY); + r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT); if (r) goto unlock_vcpu_destroy; /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); - if (r < 0) { - xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); - kvm_put_kvm_no_destroy(kvm); - goto unlock_vcpu_destroy; + if (r < 0) + goto kvm_put_xa_release; + + if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) { + r = -EINVAL; + goto kvm_put_xa_release; } /* @@ -3988,6 +3989,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_create_vcpu_debugfs(vcpu); return r; +kvm_put_xa_release: + kvm_put_kvm_no_destroy(kvm); + xa_release(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); From c99bff34290f1b994073557b754aff86e4c7b22e Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Fri, 19 May 2023 12:23:40 +0200 Subject: [PATCH 344/358] s390/dasd: fix command reject error on ESE devices Formatting a thin-provisioned (ESE) device that is part of a PPRC copy relation might fail with the following error: dasd-eckd 0.0.f500: An error occurred in the DASD device driver, reason=09 [...] 24 Byte: 0 MSG 4, no MSGb to SYSOP During format of an ESE disk the Release Allocated Space command is used. A bit in the payload of the command is set that is not allowed to be set for devices in a copy relation. This bit is set to allow the partial release of an extent. Check for the existence of a copy relation before setting the respective bit. Fixes: 91dc4a197569 ("s390/dasd: Add new ioctl to release space") Cc: stable@kernel.org # 5.3+ Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Link: https://lore.kernel.org/r/20230519102340.3854819-2-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_eckd.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index ade1369fe5ed..113c509bf6d0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -127,6 +127,8 @@ static int prepare_itcw(struct itcw *, unsigned int, unsigned int, int, struct dasd_device *, struct dasd_device *, unsigned int, int, unsigned int, unsigned int, unsigned int, unsigned int); +static int dasd_eckd_query_pprc_status(struct dasd_device *, + struct dasd_pprc_data_sc4 *); /* initial attempt at a probe function. this can be simplified once * the other detection code is gone */ @@ -3733,6 +3735,26 @@ static int count_exts(unsigned int from, unsigned int to, int trks_per_ext) return count; } +static int dasd_in_copy_relation(struct dasd_device *device) +{ + struct dasd_pprc_data_sc4 *temp; + int rc; + + if (!dasd_eckd_pprc_enabled(device)) + return 0; + + temp = kzalloc(sizeof(*temp), GFP_KERNEL); + if (!temp) + return -ENOMEM; + + rc = dasd_eckd_query_pprc_status(device, temp); + if (!rc) + rc = temp->dev_info[0].state; + + kfree(temp); + return rc; +} + /* * Release allocated space for a given range or an entire volume. */ @@ -3749,6 +3771,7 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, int cur_to_trk, cur_from_trk; struct dasd_ccw_req *cqr; u32 beg_cyl, end_cyl; + int copy_relation; struct ccw1 *ccw; int trks_per_ext; size_t ras_size; @@ -3760,6 +3783,10 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, if (dasd_eckd_ras_sanity_checks(device, first_trk, last_trk)) return ERR_PTR(-EINVAL); + copy_relation = dasd_in_copy_relation(device); + if (copy_relation < 0) + return ERR_PTR(copy_relation); + rq = req ? blk_mq_rq_to_pdu(req) : NULL; features = &private->features; @@ -3788,9 +3815,11 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, /* * This bit guarantees initialisation of tracks within an extent that is * not fully specified, but is only supported with a certain feature - * subset. + * subset and for devices not in a copy relation. */ - ras_data->op_flags.guarantee_init = !!(features->feature[56] & 0x01); + if (features->feature[56] & 0x01 && !copy_relation) + ras_data->op_flags.guarantee_init = 1; + ras_data->lss = private->conf.ned->ID; ras_data->dev_addr = private->conf.ned->unit_addr; ras_data->nr_exts = nr_exts; From 69baa3a623fd2e58624f24f2f23d46f87b817c93 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Wed, 10 May 2023 09:42:23 +0200 Subject: [PATCH 345/358] block: Deny writable memory mapping if block is read-only User should not be able to write block device if it is read-only at block level (e.g force_ro attribute). This is ensured in the regular fops write operation (blkdev_write_iter) but not when writing via user mapping (mmap), allowing user to actually write a read-only block device via a PROT_WRITE mapping. Example: This can lead to integrity issue of eMMC boot partition (e.g mmcblk0boot0) which is read-only by default. To fix this issue, simply deny shared writable mapping if the block is readonly. Note: Block remains writable if switch to read-only is performed after the initial mapping, but this is expected behavior according to commit a32e236eb93e ("Partially revert "block: fail op_is_write() requests to read-only partitions"")'. Signed-off-by: Loic Poulain Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230510074223.991297-1-loic.poulain@linaro.org Signed-off-by: Jens Axboe --- block/fops.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/block/fops.c b/block/fops.c index d2e6be4e3d1c..58d0aebc7313 100644 --- a/block/fops.c +++ b/block/fops.c @@ -678,6 +678,16 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, return error; } +static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(file); + + if (bdev_read_only(I_BDEV(bd_inode))) + return generic_file_readonly_mmap(file, vma); + + return generic_file_mmap(file, vma); +} + const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, @@ -685,7 +695,7 @@ const struct file_operations def_blk_fops = { .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, .iopoll = iocb_bio_iopoll, - .mmap = generic_file_mmap, + .mmap = blkdev_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = blkdev_ioctl, #ifdef CONFIG_COMPAT From 19abb4583d5eba06459930932e72c862a83cd9c2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 22:22:48 +0200 Subject: [PATCH 346/358] fbdev: fbmem: mark get_fb_unmapped_area() static There is a global function with this name on sparc, but no global declaration: drivers/video/fbdev/core/fbmem.c:1469:15: error: no previous prototype for 'get_fb_unmapped_area' Make the generic definition static to avoid this warning. On sparc, this is never seen. Edit by Helge: Update Kconfig text as suggested by Geert Uytterhoeven. Signed-off-by: Arnd Bergmann Signed-off-by: Helge Deller --- drivers/video/fbdev/Kconfig | 2 +- drivers/video/fbdev/core/fbmem.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 96e91570cdd3..0fdf5f46802c 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -124,7 +124,7 @@ config FB_PROVIDE_GET_FB_UNMAPPED_AREA depends on FB help Allow generic frame-buffer to provide get_fb_unmapped_area - function. + function to provide shareable character device support on nommu. menuconfig FB_FOREIGN_ENDIAN bool "Framebuffer foreign endianness support" diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index e808dc86001c..28739f1cb5e7 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1468,7 +1468,7 @@ __releases(&info->lock) } #if defined(CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA) && !defined(CONFIG_MMU) -unsigned long get_fb_unmapped_area(struct file *filp, +static unsigned long get_fb_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { From f6cd4c96b2c201be1ca3c17daeec52bf20880d69 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 22:28:09 +0200 Subject: [PATCH 347/358] fbdev: i810: include i810_main.h in i810_dvt.c Building with W=1 shows that a header needs to be included to make the prototypes visible: drivers/video/fbdev/i810/i810_dvt.c:194:6: error: no previous prototype for 'round_off_xres' [-Werror=missing-prototypes] drivers/video/fbdev/i810/i810_dvt.c:233:6: error: no previous prototype for 'i810fb_encode_registers' [-Werror=missing-prototypes] drivers/video/fbdev/i810/i810_dvt.c:245:6: error: no previous prototype for 'i810fb_fill_var_timings' [-Werror=missing-prototypes] drivers/video/fbdev/i810/i810_dvt.c:279:5: error: no previous prototype for 'i810_get_watermark' [-Werror=missing-prototypes] Adding the header leads to another warning from a mismatched prototype, so fix this as well: drivers/video/fbdev/i810/i810_dvt.c:280:5: error: conflicting types for 'i810_get_watermark'; have 'u32(struct fb_var_screeninfo *, Signed-off-by: Arnd Bergmann Reviewed-by: Jani Nikula Signed-off-by: Helge Deller --- drivers/video/fbdev/i810/i810_dvt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/i810/i810_dvt.c b/drivers/video/fbdev/i810/i810_dvt.c index b4b3670667ab..2082b5c92e8f 100644 --- a/drivers/video/fbdev/i810/i810_dvt.c +++ b/drivers/video/fbdev/i810/i810_dvt.c @@ -14,6 +14,7 @@ #include "i810_regs.h" #include "i810.h" +#include "i810_main.h" struct mode_registers std_modes[] = { /* 640x480 @ 60Hz */ @@ -276,7 +277,7 @@ void i810fb_fill_var_timings(struct fb_var_screeninfo *var) var->upper_margin = total - (yres + var->lower_margin + var->vsync_len); } -u32 i810_get_watermark(struct fb_var_screeninfo *var, +u32 i810_get_watermark(const struct fb_var_screeninfo *var, struct i810fb_par *par) { struct mode_registers *params = &par->regs; From 93f57c7a10890645d1d3b88eea1692b285bf3f38 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 16 May 2023 13:00:33 +0200 Subject: [PATCH 348/358] fbdev: atyfb: Remove unused clock determination MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Just below the removed lines par->clk_wr_offset is hard coded to 3 so there is no use in determining a different clock just to then ignore it anyway. This also removes the only I/O port use remaining in the driver allowing it to be built without CONFIG_HAS_IOPORT. Link: https://lore.kernel.org/all/ZBx5aLo5h546BzBt@intel.com/ Suggested-by: Ville Syrjälä Signed-off-by: Niklas Schnelle Reviewed-by: Ville Syrjälä Signed-off-by: Helge Deller --- drivers/video/fbdev/aty/atyfb_base.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index b02e4e645035..cba2b113b28b 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -3498,11 +3498,6 @@ static int atyfb_setup_generic(struct pci_dev *pdev, struct fb_info *info, if (ret) goto atyfb_setup_generic_fail; #endif - if (!(aty_ld_le32(CRTC_GEN_CNTL, par) & CRTC_EXT_DISP_EN)) - par->clk_wr_offset = (inb(R_GENMO) & 0x0CU) >> 2; - else - par->clk_wr_offset = aty_ld_8(CLOCK_CNTL, par) & 0x03U; - /* according to ATI, we should use clock 3 for acelerated mode */ par->clk_wr_offset = 3; From ed9de4ed39875706607fb08118a58344ae6c5f42 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 19 May 2023 15:32:30 -0400 Subject: [PATCH 349/358] fbdev: udlfb: Fix endpoint check The syzbot fuzzer detected a problem in the udlfb driver, caused by an endpoint not having the expected type: usb 1-1: Read EDID byte 0 failed: -71 usb 1-1: Unable to get valid EDID from device/display ------------[ cut here ]------------ usb 1-1: BOGUS urb xfer, pipe 3 != type 1 WARNING: CPU: 0 PID: 9 at drivers/usb/core/urb.c:504 usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 Modules linked in: CPU: 0 PID: 9 Comm: kworker/0:1 Not tainted 6.4.0-rc1-syzkaller-00016-ga4422ff22142 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/28/2023 Workqueue: usb_hub_wq hub_event RIP: 0010:usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 ... Call Trace: dlfb_submit_urb+0x92/0x180 drivers/video/fbdev/udlfb.c:1980 dlfb_set_video_mode+0x21f0/0x2950 drivers/video/fbdev/udlfb.c:315 dlfb_ops_set_par+0x2a7/0x8d0 drivers/video/fbdev/udlfb.c:1111 dlfb_usb_probe+0x149a/0x2710 drivers/video/fbdev/udlfb.c:1743 The current approach for this issue failed to catch the problem because it only checks for the existence of a bulk-OUT endpoint; it doesn't check whether this endpoint is the one that the driver will actually use. We can fix the problem by instead checking that the endpoint used by the driver does exist and is bulk-OUT. Reported-and-tested-by: syzbot+0e22d63dcebb802b9bc8@syzkaller.appspotmail.com Signed-off-by: Alan Stern CC: Pavel Skripkin Fixes: aaf7dbe07385 ("video: fbdev: udlfb: properly check endpoint type") Signed-off-by: Helge Deller --- drivers/video/fbdev/udlfb.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index 216d49c9d47e..256d9b61f4ea 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -27,6 +27,8 @@ #include