Linux-stable-mirror July 2025

linux-stable-mirror@lists.linaro.org

532 participants
1246 discussions

[PATCH v2] media: pci: ivtv: Add missing check after DMA map

by Thomas Fourier

The DMA map functions can fail and should be tested for errors. If the mapping fails, free blanking_ptr and set it to 0. As 0 is a valid DMA address, use blanking_ptr to test if the DMA address is set. Fixes: 1a0adaf37c30 ("V4L/DVB (5345): ivtv driver for Conexant cx23416/cx23415 MPEG encoder/decoder") Cc: stable(a)vger.kernel.org Signed-off-by: Thomas Fourier <fourier.thomas(a)gmail.com> --- v1 -> v2: - Fix Fixes: line - Add Cc: stable drivers/media/pci/ivtv/ivtv-irq.c | 2 +- drivers/media/pci/ivtv/ivtv-yuv.c | 8 +++++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/media/pci/ivtv/ivtv-irq.c b/drivers/media/pci/ivtv/ivtv-irq.c index 748c14e87963..4d63daa01eed 100644 --- a/drivers/media/pci/ivtv/ivtv-irq.c +++ b/drivers/media/pci/ivtv/ivtv-irq.c @@ -351,7 +351,7 @@ void ivtv_dma_stream_dec_prepare(struct ivtv_stream *s, u32 offset, int lock) /* Insert buffer block for YUV if needed */ if (s->type == IVTV_DEC_STREAM_TYPE_YUV && f->offset_y) { - if (yi->blanking_dmaptr) { + if (yi->blanking_ptr) { s->sg_pending[idx].src = yi->blanking_dmaptr; s->sg_pending[idx].dst = offset; s->sg_pending[idx].size = 720 * 16; diff --git a/drivers/media/pci/ivtv/ivtv-yuv.c b/drivers/media/pci/ivtv/ivtv-yuv.c index 2d9274537725..71f040106647 100644 --- a/drivers/media/pci/ivtv/ivtv-yuv.c +++ b/drivers/media/pci/ivtv/ivtv-yuv.c @@ -125,7 +125,7 @@ static int ivtv_yuv_prep_user_dma(struct ivtv *itv, struct ivtv_user_dma *dma, ivtv_udma_fill_sg_array(dma, y_buffer_offset, uv_buffer_offset, y_size); /* If we've offset the y plane, ensure top area is blanked */ - if (f->offset_y && yi->blanking_dmaptr) { + if (f->offset_y && yi->blanking_ptr) { dma->SGarray[dma->SG_length].size = cpu_to_le32(720*16); dma->SGarray[dma->SG_length].src = cpu_to_le32(yi->blanking_dmaptr); dma->SGarray[dma->SG_length].dst = cpu_to_le32(IVTV_DECODER_OFFSET + yuv_offset[frame]); @@ -929,6 +929,12 @@ static void ivtv_yuv_init(struct ivtv *itv) yi->blanking_dmaptr = dma_map_single(&itv->pdev->dev, yi->blanking_ptr, 720 * 16, DMA_TO_DEVICE); + if (dma_mapping_error(&itv->pdev->dev, yi->blanking_dmaptr)) { + kfree(yi->blanking_ptr); + yi->blanking_ptr = NULL; + yi->blanking_dmaptr = 0; + IVTV_DEBUG_WARN("Failed to dma_map yuv blanking buffer\n"); + } } else { yi->blanking_dmaptr = 0; IVTV_DEBUG_WARN("Failed to allocate yuv blanking buffer\n"); -- 2.43.0

5 months, 2 weeks

[PATCH 6.6.y] arm64: Filter out SME hwcaps when FEAT_SME isn't implemented

by Mark Brown

[ Upstream commit a75ad2fc76a2ab70817c7eed3163b66ea84ca6ac ] We have a number of hwcaps for various SME subfeatures enumerated via ID_AA64SMFR0_EL1. Currently we advertise these without cross checking against the main SME feature, advertised in ID_AA64PFR1_EL1.SME which means that if the two are out of sync userspace can see a confusing situation where SME subfeatures are advertised without the base SME hwcap. This can be readily triggered by using the arm64.nosme override which only masks out ID_AA64PFR1_EL1.SME, and there have also been reports of VMMs which do the same thing. Fix this as we did previously for SVE in 064737920bdb ("arm64: Filter out SVE hwcaps when FEAT_SVE isn't implemented") by filtering out the SME subfeature hwcaps when FEAT_SME is not present. Fixes: 5e64b862c482 ("arm64/sme: Basic enumeration support") Reported-by: Yury Khrustalev <yury.khrustalev(a)arm.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20250620-arm64-sme-filter-hwcaps-v1-1-02b9d3c2d8e… Signed-off-by: Will Deacon <will(a)kernel.org> Signed-off-by: Mark Brown <broonie(a)kernel.org> --- arch/arm64/kernel/cpufeature.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 82778258855d..b6d381f743f3 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2804,6 +2804,13 @@ static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope) } #endif +#ifdef CONFIG_ARM64_SME +static bool has_sme_feature(const struct arm64_cpu_capabilities *cap, int scope) +{ + return system_supports_sme() && has_user_cpuid_feature(cap, scope); +} +#endif + static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL), HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES), @@ -2875,20 +2882,20 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR2_EL1, MOPS, IMP, CAP_HWCAP, KERNEL_HWCAP_MOPS), HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC), #ifdef CONFIG_ARM64_SME - HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), - HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), - HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), - HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), - HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), - HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), - HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), - HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), - HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), - HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), - HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), - HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), + HWCAP_CAP(ID_MATCH_ID(has_sme_feature, AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), #endif /* CONFIG_ARM64_SME */ {}, }; --- base-commit: 9247f4e6573a4d05fe70c3e90dbd53da26e8c5cb change-id: 20250715-stable-6-6-sme-feat-filt-5e942478105f Best regards, -- Mark Brown <broonie(a)kernel.org>

5 months, 2 weeks

[PATCH net 5/5] rxrpc: Fix to use conn aborts for conn-wide failures

by David Howells

Fix rxrpc to use connection-level aborts for things that affect the whole connection, such as the service ID not matching a local service. Fixes: 57af281e5389 ("rxrpc: Tidy up abort generation infrastructure") Reported-by: Jeffrey Altman <jaltman(a)auristor.com> Signed-off-by: David Howells <dhowells(a)redhat.com> Reviewed-by: Jeffrey Altman <jaltman(a)auristor.com> cc: Marc Dionne <marc.dionne(a)auristor.com> cc: Jakub Kicinski <kuba(a)kernel.org> cc: Paolo Abeni <pabeni(a)redhat.com> cc: "David S. Miller" <davem(a)davemloft.net> cc: Eric Dumazet <edumazet(a)google.com> cc: Simon Horman <horms(a)kernel.org> cc: linux-afs(a)lists.infradead.org cc: netdev(a)vger.kernel.org cc: stable(a)vger.kernel.org --- include/trace/events/rxrpc.h | 1 + net/rxrpc/ar-internal.h | 3 +++ net/rxrpc/call_accept.c | 12 ++++++------ net/rxrpc/io_thread.c | 14 ++++++++++++++ net/rxrpc/output.c | 19 ++++++++++--------- net/rxrpc/security.c | 8 ++++---- 6 files changed, 38 insertions(+), 19 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 8e5a73eb5268..de6f6d25767c 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -322,6 +322,7 @@ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ + EM(rxrpc_call_put_release_recvmsg_q, "PUT rls-rcmq") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index df1a618dbf7d..5b7342d43486 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -44,6 +44,7 @@ enum rxrpc_skb_mark { RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */ RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ + RXRPC_SKB_MARK_REJECT_CONN_ABORT, /* Reject with connection ABORT (code in skb->priority) */ }; /* @@ -1253,6 +1254,8 @@ int rxrpc_encap_rcv(struct sock *, struct sk_buff *); void rxrpc_error_report(struct sock *); bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, s32 abort_code, int err); +bool rxrpc_direct_conn_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, + s32 abort_code, int err); int rxrpc_io_thread(void *data); void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb); static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local) diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index a4d76f2da684..00982a030744 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -374,8 +374,8 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, spin_lock(&rx->incoming_lock); if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED || rx->sk.sk_state == RXRPC_CLOSE) { - rxrpc_direct_abort(skb, rxrpc_abort_shut_down, - RX_INVALID_OPERATION, -ESHUTDOWN); + rxrpc_direct_conn_abort(skb, rxrpc_abort_shut_down, + RX_INVALID_OPERATION, -ESHUTDOWN); goto no_call; } @@ -422,12 +422,12 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, unsupported_service: read_unlock_irq(&local->services_lock); - return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, - RX_INVALID_OPERATION, -EOPNOTSUPP); + return rxrpc_direct_conn_abort(skb, rxrpc_abort_service_not_offered, + RX_INVALID_OPERATION, -EOPNOTSUPP); unsupported_security: read_unlock_irq(&local->services_lock); - return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, - RX_INVALID_OPERATION, -EKEYREJECTED); + return rxrpc_direct_conn_abort(skb, rxrpc_abort_service_not_offered, + RX_INVALID_OPERATION, -EKEYREJECTED); no_call: spin_unlock(&rx->incoming_lock); read_unlock_irq(&local->services_lock); diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 27b650d30f4d..e939ecf417c4 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -97,6 +97,20 @@ bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, return false; } +/* + * Directly produce a connection abort from a packet. + */ +bool rxrpc_direct_conn_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, + s32 abort_code, int err) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + trace_rxrpc_abort(0, why, sp->hdr.cid, 0, sp->hdr.seq, abort_code, err); + skb->mark = RXRPC_SKB_MARK_REJECT_CONN_ABORT; + skb->priority = abort_code; + return false; +} + static bool rxrpc_bad_message(struct sk_buff *skb, enum rxrpc_abort_reason why) { return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EBADMSG); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 17c33b5cf7dd..8b5903b6e481 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -829,7 +829,13 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) msg.msg_controllen = 0; msg.msg_flags = 0; - memset(&whdr, 0, sizeof(whdr)); + whdr = (struct rxrpc_wire_header) { + .epoch = htonl(sp->hdr.epoch), + .cid = htonl(sp->hdr.cid), + .callNumber = htonl(sp->hdr.callNumber), + .serviceId = htons(sp->hdr.serviceId), + .flags = ~sp->hdr.flags & RXRPC_CLIENT_INITIATED, + }; switch (skb->mark) { case RXRPC_SKB_MARK_REJECT_BUSY: @@ -837,6 +843,9 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) size = sizeof(whdr); ioc = 1; break; + case RXRPC_SKB_MARK_REJECT_CONN_ABORT: + whdr.callNumber = 0; + fallthrough; case RXRPC_SKB_MARK_REJECT_ABORT: whdr.type = RXRPC_PACKET_TYPE_ABORT; code = htonl(skb->priority); @@ -850,14 +859,6 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) { msg.msg_namelen = srx.transport_len; - whdr.epoch = htonl(sp->hdr.epoch); - whdr.cid = htonl(sp->hdr.cid); - whdr.callNumber = htonl(sp->hdr.callNumber); - whdr.serviceId = htons(sp->hdr.serviceId); - whdr.flags = sp->hdr.flags; - whdr.flags ^= RXRPC_CLIENT_INITIATED; - whdr.flags &= RXRPC_CLIENT_INITIATED; - iov_iter_kvec(&msg.msg_iter, WRITE, iov, ioc, size); ret = do_udp_sendmsg(local->socket, &msg, size); if (ret < 0) diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index 078d91a6b77f..2bfbf2b2bb37 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -140,15 +140,15 @@ const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *rx, sec = rxrpc_security_lookup(sp->hdr.securityIndex); if (!sec) { - rxrpc_direct_abort(skb, rxrpc_abort_unsupported_security, - RX_INVALID_OPERATION, -EKEYREJECTED); + rxrpc_direct_conn_abort(skb, rxrpc_abort_unsupported_security, + RX_INVALID_OPERATION, -EKEYREJECTED); return NULL; } if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE && !rx->securities) { - rxrpc_direct_abort(skb, rxrpc_abort_no_service_key, - sec->no_key_abort, -EKEYREJECTED); + rxrpc_direct_conn_abort(skb, rxrpc_abort_no_service_key, + sec->no_key_abort, -EKEYREJECTED); return NULL; }

5 months, 2 weeks

[PATCH net 4/5] rxrpc: Fix transmission of an abort in response to an abort

by David Howells

Under some circumstances, such as when a server socket is closing, ABORT packets will be generated in response to incoming packets. Unfortunately, this also may include generating aborts in response to incoming aborts - which may cause a cycle. It appears this may be made possible by giving the client a multicast address. Fix this such that rxrpc_reject_packet() will refuse to generate aborts in response to aborts. Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code") Signed-off-by: David Howells <dhowells(a)redhat.com> Reviewed-by: Jeffrey Altman <jaltman(a)auristor.com> cc: Marc Dionne <marc.dionne(a)auristor.com> cc: Junvyyang, Tencent Zhuque Lab <zhuque(a)tencent.com> cc: LePremierHomme <kwqcheii(a)proton.me> cc: Linus Torvalds <torvalds(a)linux-foundation.org> cc: Jakub Kicinski <kuba(a)kernel.org> cc: Paolo Abeni <pabeni(a)redhat.com> cc: "David S. Miller" <davem(a)davemloft.net> cc: Eric Dumazet <edumazet(a)google.com> cc: Simon Horman <horms(a)kernel.org> cc: linux-afs(a)lists.infradead.org cc: netdev(a)vger.kernel.org cc: stable(a)vger.kernel.org --- net/rxrpc/output.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index ef7b3096c95e..17c33b5cf7dd 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -814,6 +814,9 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) __be32 code; int ret, ioc; + if (sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) + return; /* Never abort an abort. */ + rxrpc_see_skb(skb, rxrpc_skb_see_reject); iov[0].iov_base = &whdr;

5 months, 2 weeks

[PATCH net 2/5] rxrpc: Fix recv-recv race of completed call

by David Howells

If a call receives an event (such as incoming data), the call gets placed on the socket's queue and a thread in recvmsg can be awakened to go and process it. Once the thread has picked up the call off of the queue, further events will cause it to be requeued, and once the socket lock is dropped (recvmsg uses call->user_mutex to allow the socket to be used in parallel), a second thread can come in and its recvmsg can pop the call off the socket queue again. In such a case, the first thread will be receiving stuff from the call and the second thread will be blocked on call->user_mutex. The first thread can, at this point, process both the event that it picked call for and the event that the second thread picked the call for and may see the call terminate - in which case the call will be "released", decoupling the call from the user call ID assigned to it (RXRPC_USER_CALL_ID in the control message). The first thread will return okay, but then the second thread will wake up holding the user_mutex and, if it sees that the call has been released by the first thread, it will BUG thusly: kernel BUG at net/rxrpc/recvmsg.c:474! Fix this by just dequeuing the call and ignoring it if it is seen to be already released. We can't tell userspace about it anyway as the user call ID has become stale. Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code") Reported-by: Junvyyang, Tencent Zhuque Lab <zhuque(a)tencent.com> Signed-off-by: David Howells <dhowells(a)redhat.com> Reviewed-by: Jeffrey Altman <jaltman(a)auristor.com> cc: LePremierHomme <kwqcheii(a)proton.me> cc: Marc Dionne <marc.dionne(a)auristor.com> cc: Jakub Kicinski <kuba(a)kernel.org> cc: Paolo Abeni <pabeni(a)redhat.com> cc: "David S. Miller" <davem(a)davemloft.net> cc: Eric Dumazet <edumazet(a)google.com> cc: Simon Horman <horms(a)kernel.org> cc: linux-afs(a)lists.infradead.org cc: netdev(a)vger.kernel.org cc: stable(a)vger.kernel.org --- include/trace/events/rxrpc.h | 3 +++ net/rxrpc/call_accept.c | 1 + net/rxrpc/recvmsg.c | 19 +++++++++++++++++-- 3 files changed, 21 insertions(+), 2 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 378d2dfc7392..e7dcfb1369b6 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -330,12 +330,15 @@ EM(rxrpc_call_put_userid, "PUT user-id ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ + EM(rxrpc_call_see_already_released, "SEE alrdy-rl") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ EM(rxrpc_call_see_connected, "SEE connect ") \ EM(rxrpc_call_see_conn_abort, "SEE conn-abt") \ + EM(rxrpc_call_see_discard, "SEE discard ") \ EM(rxrpc_call_see_disconnected, "SEE disconn ") \ EM(rxrpc_call_see_distribute_error, "SEE dist-err") \ EM(rxrpc_call_see_input, "SEE input ") \ + EM(rxrpc_call_see_recvmsg, "SEE recvmsg ") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 226b4bf82747..a4d76f2da684 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -219,6 +219,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->call_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_call *call = b->call_backlog[tail]; + rxrpc_see_call(call, rxrpc_call_see_discard); rcu_assign_pointer(call->socket, rx); if (rx->app_ops && rx->app_ops->discard_new_call) { diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 86a27fb55a1c..6990e37697de 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -447,6 +447,16 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto try_again; } + rxrpc_see_call(call, rxrpc_call_see_recvmsg); + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) { + rxrpc_see_call(call, rxrpc_call_see_already_released); + list_del_init(&call->recvmsg_link); + spin_unlock_irq(&rx->recvmsg_lock); + release_sock(&rx->sk); + trace_rxrpc_recvmsg(call->debug_id, rxrpc_recvmsg_unqueue, 0); + rxrpc_put_call(call, rxrpc_call_put_recvmsg); + goto try_again; + } if (!(flags & MSG_PEEK)) list_del_init(&call->recvmsg_link); else @@ -470,8 +480,13 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, release_sock(&rx->sk); - if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) - BUG(); + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) { + rxrpc_see_call(call, rxrpc_call_see_already_released); + mutex_unlock(&call->user_mutex); + if (!(flags & MSG_PEEK)) + rxrpc_put_call(call, rxrpc_call_put_recvmsg); + goto try_again; + } ret = rxrpc_recvmsg_user_id(call, msg, flags); if (ret < 0)

5 months, 2 weeks

[PATCH net 1/5] rxrpc: Fix irq-disabled in local_bh_enable()

by David Howells

The rxrpc_assess_MTU_size() function calls down into the IP layer to find out the MTU size for a route. When accepting an incoming call, this is called from rxrpc_new_incoming_call() which holds interrupts disabled across the code that calls down to it. Unfortunately, the IP layer uses local_bh_enable() which, config dependent, throws a warning if IRQs are enabled: WARNING: CPU: 1 PID: 5544 at kernel/softirq.c:387 __local_bh_enable_ip+0x43/0xd0 ... RIP: 0010:__local_bh_enable_ip+0x43/0xd0 ... Call Trace: <TASK> rt_cache_route+0x7e/0xa0 rt_set_nexthop.isra.0+0x3b3/0x3f0 __mkroute_output+0x43a/0x460 ip_route_output_key_hash+0xf7/0x140 ip_route_output_flow+0x1b/0x90 rxrpc_assess_MTU_size.isra.0+0x2a0/0x590 rxrpc_new_incoming_peer+0x46/0x120 rxrpc_alloc_incoming_call+0x1b1/0x400 rxrpc_new_incoming_call+0x1da/0x5e0 rxrpc_input_packet+0x827/0x900 rxrpc_io_thread+0x403/0xb60 kthread+0x2f7/0x310 ret_from_fork+0x2a/0x230 ret_from_fork_asm+0x1a/0x30 ... hardirqs last enabled at (23): _raw_spin_unlock_irq+0x24/0x50 hardirqs last disabled at (24): _raw_read_lock_irq+0x17/0x70 softirqs last enabled at (0): copy_process+0xc61/0x2730 softirqs last disabled at (25): rt_add_uncached_list+0x3c/0x90 Fix this by moving the call to rxrpc_assess_MTU_size() out of rxrpc_init_peer() and further up the stack where it can be done without interrupts disabled. It shouldn't be a problem for rxrpc_new_incoming_call() to do it after the locks are dropped as pmtud is going to be performed by the I/O thread - and we're in the I/O thread at this point. Fixes: a2ea9a907260 ("rxrpc: Use irq-disabling spinlocks between app and I/O thread") Signed-off-by: David Howells <dhowells(a)redhat.com> Reviewed-by: Jeffrey Altman <jaltman(a)auristor.com> cc: Marc Dionne <marc.dionne(a)auristor.com> cc: Junvyyang, Tencent Zhuque Lab <zhuque(a)tencent.com> cc: LePremierHomme <kwqcheii(a)proton.me> cc: Jakub Kicinski <kuba(a)kernel.org> cc: Paolo Abeni <pabeni(a)redhat.com> cc: "David S. Miller" <davem(a)davemloft.net> cc: Eric Dumazet <edumazet(a)google.com> cc: Simon Horman <horms(a)kernel.org> cc: linux-afs(a)lists.infradead.org cc: netdev(a)vger.kernel.org cc: stable(a)vger.kernel.org --- net/rxrpc/ar-internal.h | 1 + net/rxrpc/call_accept.c | 1 + net/rxrpc/peer_object.c | 6 ++---- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 376e33dce8c1..df1a618dbf7d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1383,6 +1383,7 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp); +void rxrpc_assess_MTU_size(struct rxrpc_local *local, struct rxrpc_peer *peer); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t, enum rxrpc_peer_trace); void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 49fccee1a726..226b4bf82747 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -406,6 +406,7 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, spin_unlock(&rx->incoming_lock); read_unlock_irq(&local->services_lock); + rxrpc_assess_MTU_size(local, call->peer); if (hlist_unhashed(&call->error_link)) { spin_lock_irq(&call->peer->lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index e2f35e6c04d6..366431b0736c 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -149,8 +149,7 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, * assess the MTU size for the network interface through which this peer is * reached */ -static void rxrpc_assess_MTU_size(struct rxrpc_local *local, - struct rxrpc_peer *peer) +void rxrpc_assess_MTU_size(struct rxrpc_local *local, struct rxrpc_peer *peer) { struct net *net = local->net; struct dst_entry *dst; @@ -277,8 +276,6 @@ static void rxrpc_init_peer(struct rxrpc_local *local, struct rxrpc_peer *peer, peer->hdrsize += sizeof(struct rxrpc_wire_header); peer->max_data = peer->if_mtu - peer->hdrsize; - - rxrpc_assess_MTU_size(local, peer); } /* @@ -297,6 +294,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, if (peer) { memcpy(&peer->srx, srx, sizeof(*srx)); rxrpc_init_peer(local, peer, hash_key); + rxrpc_assess_MTU_size(local, peer); } _leave(" = %p", peer);

5 months, 2 weeks

Re: [PATCH 6.15 000/192] 6.15.7-rc1 review

by Dileep malepu

> This is the start of the stable review cycle for the 6.15.7 release. > There are 192 patches in this series, all will be posted as a response > to this one. If anyone has any issues with these being applied, please > let me know. > > Responses should be made by Thu, 17 Jul 2025 13:07:32 +0000. > Anything received after that time might be too late. > > The whole patch series can be found in one patch at: > https://www.kernel.org/pub/linux/kernel/v6.x/stable-review/patch-6.15.7-rc1… > or in the git tree and branch at: > git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-6.15.y > and the diffstat can be found below. > > thanks, > > greg k-h Tested Linux kernel 6.15.7-rc1 on Fedora 37 (x86_64) with Intel i7-11800H. All major tests including boot, Wi-Fi, Bluetooth, audio, video, and USB mass storage detection passed successfully. Kernel Version : 6.15.7-rc1 Fedora Version : 37 (Thirty Seven) Processor : 11th Gen Intel(R) Core(TM) i7-11800H @ 2.30GHz Build Architecture: x86_64 Test Results: - Boot Test : PASS - Wi-Fi Test : PASS - Bluetooth Test : PASS - Audio Test : PASS - Video Test : PASS - USB Mass Storage Drive Detect : PASS Tested-by: Dileep Malepu <dileep.debian(a)gmail.com>

5 months, 2 weeks

[PATCH] kernel/fork: Increase minimum number of allowed threads

by Hauke Mehrtens

From: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> A modern Linux system creates much more than 20 threads at bootup. When I booted up OpenWrt in qemu the system sometimes failed to boot up when it wanted to create the 419th thread. The VM had 128MB RAM and the calculation in set_max_threads() calculated that max_threads should be set to 419. When the system booted up it tried to notify the user space about every device it created because CONFIG_UEVENT_HELPER was set and used. I counted 1299 calles to call_usermodehelper_setup(), all of them try to create a new thread and call the userspace hotplug script in it. This fixes bootup of Linux on systems with low memory. I saw the problem with qemu 10.0.2 using these commands: qemu-system-aarch64 -machine virt -cpu cortex-a57 -nographic Cc: stable(a)vger.kernel.org Signed-off-by: Hauke Mehrtens <hauke(a)hauke-m.de> --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/fork.c b/kernel/fork.c index 7966c9a1c163..388299525f3c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -115,7 +115,7 @@ /* * Minimum number of threads to boot the kernel */ -#define MIN_THREADS 20 +#define MIN_THREADS 600 /* * Maximum number of threads -- 2.50.1

5 months, 2 weeks

[PATCH v5 2/3] drm/amdgpu: Reset the clear flag in buddy during resume

by Arunpravin Paneer Selvam

- Added a handler in DRM buddy manager to reset the cleared flag for the blocks in the freelist. - This is necessary because, upon resuming, the VRAM becomes cluttered with BIOS data, yet the VRAM backend manager believes that everything has been cleared. v2: - Add lock before accessing drm_buddy_clear_reset_blocks()(Matthew Auld) - Force merge the two dirty blocks.(Matthew Auld) - Add a new unit test case for this issue.(Matthew Auld) - Having this function being able to flip the state either way would be good. (Matthew Brost) v3(Matthew Auld): - Do merge step first to avoid the use of extra reset flag. Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam(a)amd.com> Suggested-by: Christian König <christian.koenig(a)amd.com> Acked-by: Christian König <christian.koenig(a)amd.com> Reviewed-by: Matthew Auld <matthew.auld(a)intel.com> Cc: stable(a)vger.kernel.org Fixes: a68c7eaa7a8f ("drm/amdgpu: Enable clear page functionality") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3812 --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 + drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 17 ++++++++ drivers/gpu/drm/drm_buddy.c | 43 ++++++++++++++++++++ include/drm/drm_buddy.h | 2 + 5 files changed, 65 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 723ab95d8c48..ac92220f9fc3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5327,6 +5327,8 @@ int amdgpu_device_resume(struct drm_device *dev, bool notify_clients) dev->dev->power.disable_depth--; #endif } + + amdgpu_vram_mgr_clear_reset_blocks(adev); adev->in_suspend = false; if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D0)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 215c198e4aff..2309df3f68a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -155,6 +155,7 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, uint64_t start, uint64_t size); int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, uint64_t start); +void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev); bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, struct ttm_resource *res); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index abdc52b0895a..07c936e90d8e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -782,6 +782,23 @@ uint64_t amdgpu_vram_mgr_vis_usage(struct amdgpu_vram_mgr *mgr) return atomic64_read(&mgr->vis_usage); } +/** + * amdgpu_vram_mgr_clear_reset_blocks - reset clear blocks + * + * @adev: amdgpu device pointer + * + * Reset the cleared drm buddy blocks. + */ +void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev) +{ + struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr; + struct drm_buddy *mm = &mgr->mm; + + mutex_lock(&mgr->lock); + drm_buddy_reset_clear(mm, false); + mutex_unlock(&mgr->lock); +} + /** * amdgpu_vram_mgr_intersects - test each drm buddy block for intersection * diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index a1e652b7631d..a94061f373de 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -405,6 +405,49 @@ drm_get_buddy(struct drm_buddy_block *block) } EXPORT_SYMBOL(drm_get_buddy); +/** + * drm_buddy_reset_clear - reset blocks clear state + * + * @mm: DRM buddy manager + * @is_clear: blocks clear state + * + * Reset the clear state based on @is_clear value for each block + * in the freelist. + */ +void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear) +{ + u64 root_size, size, start; + unsigned int order; + int i; + + size = mm->size; + for (i = 0; i < mm->n_roots; ++i) { + order = ilog2(size) - ilog2(mm->chunk_size); + start = drm_buddy_block_offset(mm->roots[i]); + __force_merge(mm, start, start + size, order); + + root_size = mm->chunk_size << order; + size -= root_size; + } + + for (i = 0; i <= mm->max_order; ++i) { + struct drm_buddy_block *block; + + list_for_each_entry_reverse(block, &mm->free_list[i], link) { + if (is_clear != drm_buddy_block_is_clear(block)) { + if (is_clear) { + mark_cleared(block); + mm->clear_avail += drm_buddy_block_size(mm, block); + } else { + clear_reset(block); + mm->clear_avail -= drm_buddy_block_size(mm, block); + } + } + } + } +} +EXPORT_SYMBOL(drm_buddy_reset_clear); + /** * drm_buddy_free_block - free a block * diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index 9689a7c5dd36..513837632b7d 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -160,6 +160,8 @@ int drm_buddy_block_trim(struct drm_buddy *mm, u64 new_size, struct list_head *blocks); +void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear); + void drm_buddy_free_block(struct drm_buddy *mm, struct drm_buddy_block *block); void drm_buddy_free_list(struct drm_buddy *mm, -- 2.43.0

5 months, 2 weeks

[PATCH] PCI: j721e: Fix programming sequence of "strap" settings

by Siddharth Vadapalli

The Cadence PCIe Controller integrated in the TI K3 SoCs supports both Root-Complex and Endpoint modes of operation. The Glue Layer allows "strapping" the mode of operation of the Controller, the Link Speed and the Link Width. This is enabled by programming the "PCIEn_CTRL" register (n corresponds to the PCIe instance) within the CTRL_MMR memory-mapped register space. In the PCIe Controller's register space, the same set of registers that correspond to the Root-Port configuration space when the Controller is configured for Root-Complex mode of operation, also correspond to the Physical Function configuration space when the Controller is configured for Endpoint mode of operation. As a result, the "reset-value" of these set of registers _should_ vary depending on the selected mode of operation. This is the expected behavior according to the description of the registers and their reset values in the Technical Reference Manual for the SoCs. However, it is observed that the "reset-value" seen in practice do not match the description. To be precise, when the Controller is configured for Root-Complex mode of operation, the "reset-value" of the Root-Port configuration space reflect the "reset-value" corresponding to the Physical Function configuration space. This can be attributed to the fact that the "strap" settings play a role in "switching" the "reset-value" of the registers to match the expected values as determined by the selected mode of operation. Since the "strap" settings are sampled the moment the PCIe Controller is powered ON, the "reset-value" of the registers are setup at that point in time. As a result, if the "strap" settings are programmed at a later point in time, it _will not_ update the "reset-value" of the registers. This will cause the Physical Function configuration space to be seen when the Root-Port configuration space is accessed after programming the PCIe Controller for Root-Complex mode of operation. Fix this by powering off the PCIe Controller before programming the "strap" settings and powering it on after that. This will ensure that the "strap" settings that have been sampled convey the intended mode of operation, thereby resulting in the "reset-value" of the registers being accurate. Fixes: f3e25911a430 ("PCI: j721e: Add TI J721E PCIe driver") Cc: <stable(a)vger.kernel.org> Signed-off-by: Siddharth Vadapalli <s-vadapalli(a)ti.com> --- Hello, This patch is based on commit 155a3c003e55 Merge tag 'for-6.16/dm-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm of Mainline Linux. Patch has been validated on the J7200 SoC which is affected by the existing programming sequence of the "strap" settings. Regards, Siddharth. drivers/pci/controller/cadence/pci-j721e.c | 82 ++++++++++++++-------- 1 file changed, 53 insertions(+), 29 deletions(-) diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c index 6c93f39d0288..d5e7cb7277dc 100644 --- a/drivers/pci/controller/cadence/pci-j721e.c +++ b/drivers/pci/controller/cadence/pci-j721e.c @@ -19,6 +19,7 @@ #include <linux/of.h> #include <linux/pci.h> #include <linux/platform_device.h> +#include <linux/pm_domain.h> #include <linux/pm_runtime.h> #include <linux/regmap.h> @@ -173,10 +174,9 @@ static const struct cdns_pcie_ops j721e_pcie_ops = { .link_up = j721e_pcie_link_up, }; -static int j721e_pcie_set_mode(struct j721e_pcie *pcie, struct regmap *syscon, - unsigned int offset) +static int j721e_pcie_set_mode(struct j721e_pcie *pcie, struct device *dev, + struct regmap *syscon, unsigned int offset) { - struct device *dev = pcie->cdns_pcie->dev; u32 mask = J721E_MODE_RC; u32 mode = pcie->mode; u32 val = 0; @@ -193,9 +193,9 @@ static int j721e_pcie_set_mode(struct j721e_pcie *pcie, struct regmap *syscon, } static int j721e_pcie_set_link_speed(struct j721e_pcie *pcie, + struct device *dev, struct regmap *syscon, unsigned int offset) { - struct device *dev = pcie->cdns_pcie->dev; struct device_node *np = dev->of_node; int link_speed; u32 val = 0; @@ -214,9 +214,9 @@ static int j721e_pcie_set_link_speed(struct j721e_pcie *pcie, } static int j721e_pcie_set_lane_count(struct j721e_pcie *pcie, + struct device *dev, struct regmap *syscon, unsigned int offset) { - struct device *dev = pcie->cdns_pcie->dev; u32 lanes = pcie->num_lanes; u32 mask = BIT(8); u32 val = 0; @@ -234,9 +234,9 @@ static int j721e_pcie_set_lane_count(struct j721e_pcie *pcie, } static int j721e_enable_acspcie_refclk(struct j721e_pcie *pcie, + struct device *dev, struct regmap *syscon) { - struct device *dev = pcie->cdns_pcie->dev; struct device_node *node = dev->of_node; u32 mask = ACSPCIE_PAD_DISABLE_MASK; struct of_phandle_args args; @@ -263,9 +263,8 @@ static int j721e_enable_acspcie_refclk(struct j721e_pcie *pcie, return 0; } -static int j721e_pcie_ctrl_init(struct j721e_pcie *pcie) +static int j721e_pcie_ctrl_init(struct j721e_pcie *pcie, struct device *dev) { - struct device *dev = pcie->cdns_pcie->dev; struct device_node *node = dev->of_node; struct of_phandle_args args; unsigned int offset = 0; @@ -284,19 +283,19 @@ static int j721e_pcie_ctrl_init(struct j721e_pcie *pcie) if (!ret) offset = args.args[0]; - ret = j721e_pcie_set_mode(pcie, syscon, offset); + ret = j721e_pcie_set_mode(pcie, dev, syscon, offset); if (ret < 0) { dev_err(dev, "Failed to set pci mode\n"); return ret; } - ret = j721e_pcie_set_link_speed(pcie, syscon, offset); + ret = j721e_pcie_set_link_speed(pcie, dev, syscon, offset); if (ret < 0) { dev_err(dev, "Failed to set link speed\n"); return ret; } - ret = j721e_pcie_set_lane_count(pcie, syscon, offset); + ret = j721e_pcie_set_lane_count(pcie, dev, syscon, offset); if (ret < 0) { dev_err(dev, "Failed to set num-lanes\n"); return ret; @@ -308,7 +307,7 @@ static int j721e_pcie_ctrl_init(struct j721e_pcie *pcie) if (!syscon) return 0; - return j721e_enable_acspcie_refclk(pcie, syscon); + return j721e_enable_acspcie_refclk(pcie, dev, syscon); } static int cdns_ti_pcie_config_read(struct pci_bus *bus, unsigned int devfn, @@ -469,6 +468,47 @@ static int j721e_pcie_probe(struct platform_device *pdev) if (!pcie) return -ENOMEM; + pcie->mode = mode; + + ret = of_property_read_u32(node, "num-lanes", &num_lanes); + if (ret || num_lanes > data->max_lanes) { + dev_warn(dev, "num-lanes property not provided or invalid, setting num-lanes to 1\n"); + num_lanes = 1; + } + + pcie->num_lanes = num_lanes; + pcie->max_lanes = data->max_lanes; + + /* + * The PCIe Controller's registers have different "reset-value" depending + * on the "strap" settings programmed into the Controller's Glue Layer. + * This is because the same set of registers are used for representing the + * Physical Function configuration space in Endpoint mode and for + * representing the Root-Port configuration space in Root-Complex mode. + * + * The registers latch onto a "reset-value" based on the "strap" settings + * sampled after the Controller is powered on. Therefore, for the + * "reset-value" to be accurate, it is necessary to program the "strap" + * settings when the Controller is powered off, and power on the Controller + * after the "strap" settings have been programmed. + * + * The "strap" settings are programmed by "j721e_pcie_ctrl_init()". + * Therefore, power off the Controller before invoking "j721e_pcie_ctrl_init()", + * program the "strap" settings, and then power on the Controller. This ensures + * that the reset values are accurate and reflect the "strap" settings. + */ + dev_pm_domain_detach(dev, true); + + ret = j721e_pcie_ctrl_init(pcie, dev); + if (ret < 0) + return ret; + + ret = dev_pm_domain_attach(dev, true); + if (ret < 0) { + dev_err(dev, "failed to power on PCIe Controller\n"); + return ret; + } + switch (mode) { case PCI_MODE_RC: if (!IS_ENABLED(CONFIG_PCI_J721E_HOST)) @@ -510,7 +550,6 @@ static int j721e_pcie_probe(struct platform_device *pdev) return 0; } - pcie->mode = mode; pcie->linkdown_irq_regfield = data->linkdown_irq_regfield; base = devm_platform_ioremap_resource_byname(pdev, "intd_cfg"); @@ -523,15 +562,6 @@ static int j721e_pcie_probe(struct platform_device *pdev) return PTR_ERR(base); pcie->user_cfg_base = base; - ret = of_property_read_u32(node, "num-lanes", &num_lanes); - if (ret || num_lanes > data->max_lanes) { - dev_warn(dev, "num-lanes property not provided or invalid, setting num-lanes to 1\n"); - num_lanes = 1; - } - - pcie->num_lanes = num_lanes; - pcie->max_lanes = data->max_lanes; - if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48))) return -EINVAL; @@ -547,12 +577,6 @@ static int j721e_pcie_probe(struct platform_device *pdev) goto err_get_sync; } - ret = j721e_pcie_ctrl_init(pcie); - if (ret < 0) { - dev_err_probe(dev, ret, "pm_runtime_get_sync failed\n"); - goto err_get_sync; - } - ret = devm_request_irq(dev, irq, j721e_pcie_link_irq_handler, 0, "j721e-pcie-link-down-irq", pcie); if (ret < 0) { @@ -680,7 +704,7 @@ static int j721e_pcie_resume_noirq(struct device *dev) struct cdns_pcie *cdns_pcie = pcie->cdns_pcie; int ret; - ret = j721e_pcie_ctrl_init(pcie); + ret = j721e_pcie_ctrl_init(pcie, dev); if (ret < 0) return ret; -- 2.34.1

5 months, 2 weeks

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2025