February 2024 - Linux-stable-mirror

[PATCH net v3] net: stmmac: protect updates of 64-bit statistics counters

by Petr Tesarik

As explained by a comment in <linux/u64_stats_sync.h>, write side of struct u64_stats_sync must ensure mutual exclusion, or one seqcount update could be lost on 32-bit platforms, thus blocking readers forever. Such lockups have been observed in real world after stmmac_xmit() on one CPU raced with stmmac_napi_poll_tx() on another CPU. To fix the issue without introducing a new lock, split the statics into three parts: 1. fields updated only under the tx queue lock, 2. fields updated only during NAPI poll, 3. fields updated only from interrupt context, Updates to fields in the first two groups are already serialized through other locks. It is sufficient to split the existing struct u64_stats_sync so that each group has its own. Note that tx_set_ic_bit is updated from both contexts. Split this counter so that each context gets its own, and calculate their sum to get the total value in stmmac_get_ethtool_stats(). For the third group, multiple interrupts may be processed by different CPUs at the same time, but interrupts on the same CPU will not nest. Move fields from this group to a newly created per-cpu struct stmmac_pcpu_stats. Fixes: 133466c3bbe1 ("net: stmmac: use per-queue 64 bit statistics where necessary") Link: https://lore.kernel.org/netdev/Za173PhviYg-1qIn@torres.zugschlus.de/t/ Cc: stable(a)vger.kernel.org Signed-off-by: Petr Tesarik <petr(a)tesarici.cz> --- drivers/net/ethernet/stmicro/stmmac/common.h | 56 +++++--- .../net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 15 +- .../net/ethernet/stmicro/stmmac/dwmac4_lib.c | 15 +- .../net/ethernet/stmicro/stmmac/dwmac_lib.c | 15 +- .../ethernet/stmicro/stmmac/dwxgmac2_dma.c | 15 +- .../ethernet/stmicro/stmmac/stmmac_ethtool.c | 129 +++++++++++------ .../net/ethernet/stmicro/stmmac/stmmac_main.c | 133 +++++++++--------- 7 files changed, 221 insertions(+), 157 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 721c1f8e892f..4aca20feb4b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -59,28 +59,51 @@ #undef FRAME_FILTER_DEBUG /* #define FRAME_FILTER_DEBUG */ +struct stmmac_q_tx_stats { + u64_stats_t tx_bytes; + u64_stats_t tx_set_ic_bit; + u64_stats_t tx_tso_frames; + u64_stats_t tx_tso_nfrags; +}; + +struct stmmac_napi_tx_stats { + u64_stats_t tx_packets; + u64_stats_t tx_pkt_n; + u64_stats_t poll; + u64_stats_t tx_clean; + u64_stats_t tx_set_ic_bit; +}; + struct stmmac_txq_stats { - u64 tx_bytes; - u64 tx_packets; - u64 tx_pkt_n; - u64 tx_normal_irq_n; - u64 napi_poll; - u64 tx_clean; - u64 tx_set_ic_bit; - u64 tx_tso_frames; - u64 tx_tso_nfrags; - struct u64_stats_sync syncp; + /* Updates protected by tx queue lock. */ + struct u64_stats_sync q_syncp; + struct stmmac_q_tx_stats q; + + /* Updates protected by NAPI poll logic. */ + struct u64_stats_sync napi_syncp; + struct stmmac_napi_tx_stats napi; } ____cacheline_aligned_in_smp; +struct stmmac_napi_rx_stats { + u64_stats_t rx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_pkt_n; + u64_stats_t poll; +}; + struct stmmac_rxq_stats { - u64 rx_bytes; - u64 rx_packets; - u64 rx_pkt_n; - u64 rx_normal_irq_n; - u64 napi_poll; - struct u64_stats_sync syncp; + /* Updates protected by NAPI poll logic. */ + struct u64_stats_sync napi_syncp; + struct stmmac_napi_rx_stats napi; } ____cacheline_aligned_in_smp; +/* Updates on each CPU protected by not allowing nested irqs. */ +struct stmmac_pcpu_stats { + struct u64_stats_sync syncp; + u64_stats_t rx_normal_irq_n[MTL_MAX_TX_QUEUES]; + u64_stats_t tx_normal_irq_n[MTL_MAX_RX_QUEUES]; +}; + /* Extra statistic and debug information exposed by ethtool */ struct stmmac_extra_stats { /* Transmit errors */ @@ -205,6 +228,7 @@ struct stmmac_extra_stats { /* per queue statistics */ struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES]; struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES]; + struct stmmac_pcpu_stats __percpu *pcpu_stats; unsigned long rx_dropped; unsigned long rx_errors; unsigned long tx_dropped; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 137741b94122..b21d99faa2d0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -441,8 +441,7 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv, struct stmmac_extra_stats *x, u32 chan, u32 dir) { - struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; - struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); int ret = 0; u32 v; @@ -455,9 +454,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv, if (v & EMAC_TX_INT) { ret |= handle_tx; - u64_stats_update_begin(&txq_stats->syncp); - txq_stats->tx_normal_irq_n++; - u64_stats_update_end(&txq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); } if (v & EMAC_TX_DMA_STOP_INT) @@ -479,9 +478,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv, if (v & EMAC_RX_INT) { ret |= handle_rx; - u64_stats_update_begin(&rxq_stats->syncp); - rxq_stats->rx_normal_irq_n++; - u64_stats_update_end(&rxq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); } if (v & EMAC_RX_BUF_UA_INT) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 9470d3fd2ded..0d185e54eb7e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -171,8 +171,7 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs; u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(dwmac4_addrs, chan)); u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan)); - struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; - struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); int ret = 0; if (dir == DMA_DIR_RX) @@ -201,15 +200,15 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, } /* TX/RX NORMAL interrupts */ if (likely(intr_status & DMA_CHAN_STATUS_RI)) { - u64_stats_update_begin(&rxq_stats->syncp); - rxq_stats->rx_normal_irq_n++; - u64_stats_update_end(&rxq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_rx; } if (likely(intr_status & DMA_CHAN_STATUS_TI)) { - u64_stats_update_begin(&txq_stats->syncp); - txq_stats->tx_normal_irq_n++; - u64_stats_update_end(&txq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_tx; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index 7907d62d3437..85e18f9a22f9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -162,8 +162,7 @@ static void show_rx_process_state(unsigned int status) int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_extra_stats *x, u32 chan, u32 dir) { - struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; - struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); int ret = 0; /* read the status register (CSR5) */ u32 intr_status = readl(ioaddr + DMA_STATUS); @@ -215,16 +214,16 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, u32 value = readl(ioaddr + DMA_INTR_ENA); /* to schedule NAPI on real RIE event. */ if (likely(value & DMA_INTR_ENA_RIE)) { - u64_stats_update_begin(&rxq_stats->syncp); - rxq_stats->rx_normal_irq_n++; - u64_stats_update_end(&rxq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_rx; } } if (likely(intr_status & DMA_STATUS_TI)) { - u64_stats_update_begin(&txq_stats->syncp); - txq_stats->tx_normal_irq_n++; - u64_stats_update_end(&txq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_tx; } if (unlikely(intr_status & DMA_STATUS_ERI)) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 3cde695fec91..dd2ab6185c40 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -337,8 +337,7 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv, struct stmmac_extra_stats *x, u32 chan, u32 dir) { - struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; - struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan)); u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan)); int ret = 0; @@ -367,15 +366,15 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv, /* TX/RX NORMAL interrupts */ if (likely(intr_status & XGMAC_NIS)) { if (likely(intr_status & XGMAC_RI)) { - u64_stats_update_begin(&rxq_stats->syncp); - rxq_stats->rx_normal_irq_n++; - u64_stats_update_end(&rxq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_rx; } if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) { - u64_stats_update_begin(&txq_stats->syncp); - txq_stats->tx_normal_irq_n++; - u64_stats_update_end(&txq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_tx; } } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 42d27b97dd1d..ec44becf0e2d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -549,44 +549,79 @@ stmmac_set_pauseparam(struct net_device *netdev, } } +static u64 stmmac_get_rx_normal_irq_n(struct stmmac_priv *priv, int q) +{ + u64 total; + int cpu; + + total = 0; + for_each_possible_cpu(cpu) { + struct stmmac_pcpu_stats *pcpu; + unsigned int start; + u64 irq_n; + + pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu); + do { + start = u64_stats_fetch_begin(&pcpu->syncp); + irq_n = u64_stats_read(&pcpu->rx_normal_irq_n[q]); + } while (u64_stats_fetch_retry(&pcpu->syncp, start)); + total += irq_n; + } + return total; +} + +static u64 stmmac_get_tx_normal_irq_n(struct stmmac_priv *priv, int q) +{ + u64 total; + int cpu; + + total = 0; + for_each_possible_cpu(cpu) { + struct stmmac_pcpu_stats *pcpu; + unsigned int start; + u64 irq_n; + + pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu); + do { + start = u64_stats_fetch_begin(&pcpu->syncp); + irq_n = u64_stats_read(&pcpu->tx_normal_irq_n[q]); + } while (u64_stats_fetch_retry(&pcpu->syncp, start)); + total += irq_n; + } + return total; +} + static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data) { u32 tx_cnt = priv->plat->tx_queues_to_use; u32 rx_cnt = priv->plat->rx_queues_to_use; unsigned int start; - int q, stat; - char *p; + int q; for (q = 0; q < tx_cnt; q++) { struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q]; - struct stmmac_txq_stats snapshot; + u64 pkt_n; do { - start = u64_stats_fetch_begin(&txq_stats->syncp); - snapshot = *txq_stats; - } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); + start = u64_stats_fetch_begin(&txq_stats->napi_syncp); + pkt_n = u64_stats_read(&txq_stats->napi.tx_pkt_n); + } while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start)); - p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n); - for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) { - *data++ = (*(u64 *)p); - p += sizeof(u64); - } + *data++ = pkt_n; + *data++ = stmmac_get_tx_normal_irq_n(priv, q); } for (q = 0; q < rx_cnt; q++) { struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q]; - struct stmmac_rxq_stats snapshot; + u64 pkt_n; do { - start = u64_stats_fetch_begin(&rxq_stats->syncp); - snapshot = *rxq_stats; - } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); + start = u64_stats_fetch_begin(&rxq_stats->napi_syncp); + pkt_n = u64_stats_read(&rxq_stats->napi.rx_pkt_n); + } while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start)); - p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n); - for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) { - *data++ = (*(u64 *)p); - p += sizeof(u64); - } + *data++ = pkt_n; + *data++ = stmmac_get_rx_normal_irq_n(priv, q); } } @@ -645,39 +680,49 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, pos = j; for (i = 0; i < rx_queues_count; i++) { struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[i]; - struct stmmac_rxq_stats snapshot; + struct stmmac_napi_rx_stats snapshot; + u64 n_irq; j = pos; do { - start = u64_stats_fetch_begin(&rxq_stats->syncp); - snapshot = *rxq_stats; - } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); - - data[j++] += snapshot.rx_pkt_n; - data[j++] += snapshot.rx_normal_irq_n; - normal_irq_n += snapshot.rx_normal_irq_n; - napi_poll += snapshot.napi_poll; + start = u64_stats_fetch_begin(&rxq_stats->napi_syncp); + snapshot = rxq_stats->napi; + } while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start)); + + data[j++] += u64_stats_read(&snapshot.rx_pkt_n); + n_irq = stmmac_get_rx_normal_irq_n(priv, i); + data[j++] += n_irq; + normal_irq_n += n_irq; + napi_poll += u64_stats_read(&snapshot.poll); } pos = j; for (i = 0; i < tx_queues_count; i++) { struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[i]; - struct stmmac_txq_stats snapshot; + struct stmmac_napi_tx_stats napi_snapshot; + struct stmmac_q_tx_stats q_snapshot; + u64 n_irq; j = pos; do { - start = u64_stats_fetch_begin(&txq_stats->syncp); - snapshot = *txq_stats; - } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); - - data[j++] += snapshot.tx_pkt_n; - data[j++] += snapshot.tx_normal_irq_n; - normal_irq_n += snapshot.tx_normal_irq_n; - data[j++] += snapshot.tx_clean; - data[j++] += snapshot.tx_set_ic_bit; - data[j++] += snapshot.tx_tso_frames; - data[j++] += snapshot.tx_tso_nfrags; - napi_poll += snapshot.napi_poll; + start = u64_stats_fetch_begin(&txq_stats->q_syncp); + q_snapshot = txq_stats->q; + } while (u64_stats_fetch_retry(&txq_stats->q_syncp, start)); + do { + start = u64_stats_fetch_begin(&txq_stats->napi_syncp); + napi_snapshot = txq_stats->napi; + } while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start)); + + data[j++] += u64_stats_read(&napi_snapshot.tx_pkt_n); + n_irq = stmmac_get_tx_normal_irq_n(priv, i); + data[j++] += n_irq; + normal_irq_n += n_irq; + data[j++] += u64_stats_read(&napi_snapshot.tx_clean); + data[j++] += u64_stats_read(&q_snapshot.tx_set_ic_bit) + + u64_stats_read(&napi_snapshot.tx_set_ic_bit); + data[j++] += u64_stats_read(&q_snapshot.tx_tso_frames); + data[j++] += u64_stats_read(&q_snapshot.tx_tso_nfrags); + napi_poll += u64_stats_read(&napi_snapshot.poll); } normal_irq_n += priv->xstats.rx_early_irq; data[j++] = normal_irq_n; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 25519952f754..75d029704503 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2482,7 +2482,6 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) struct xdp_desc xdp_desc; bool work_done = true; u32 tx_set_ic_bit = 0; - unsigned long flags; /* Avoids TX time-out as we are sharing with slow path */ txq_trans_cond_update(nq); @@ -2566,9 +2565,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size); entry = tx_q->cur_tx; } - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_set_ic_bit += tx_set_ic_bit; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->napi_syncp); + u64_stats_add(&txq_stats->napi.tx_set_ic_bit, tx_set_ic_bit); + u64_stats_update_end(&txq_stats->napi_syncp); if (tx_desc) { stmmac_flush_tx_descriptors(priv, queue); @@ -2616,7 +2615,6 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue, unsigned int bytes_compl = 0, pkts_compl = 0; unsigned int entry, xmits = 0, count = 0; u32 tx_packets = 0, tx_errors = 0; - unsigned long flags; __netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue)); @@ -2782,11 +2780,11 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue, if (tx_q->dirty_tx != tx_q->cur_tx) *pending_packets = true; - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_packets += tx_packets; - txq_stats->tx_pkt_n += tx_packets; - txq_stats->tx_clean++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->napi_syncp); + u64_stats_add(&txq_stats->napi.tx_packets, tx_packets); + u64_stats_add(&txq_stats->napi.tx_pkt_n, tx_packets); + u64_stats_inc(&txq_stats->napi.tx_clean); + u64_stats_update_end(&txq_stats->napi_syncp); priv->xstats.tx_errors += tx_errors; @@ -4213,7 +4211,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_tx_queue *tx_q; bool has_vlan, set_ic; u8 proto_hdr_len, hdr; - unsigned long flags; u32 pay_len, mss; dma_addr_t des; int i; @@ -4378,13 +4375,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); } - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_bytes += skb->len; - txq_stats->tx_tso_frames++; - txq_stats->tx_tso_nfrags += nfrags; + u64_stats_update_begin(&txq_stats->q_syncp); + u64_stats_add(&txq_stats->q.tx_bytes, skb->len); + u64_stats_inc(&txq_stats->q.tx_tso_frames); + u64_stats_add(&txq_stats->q.tx_tso_nfrags, nfrags); if (set_ic) - txq_stats->tx_set_ic_bit++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_inc(&txq_stats->q.tx_set_ic_bit); + u64_stats_update_end(&txq_stats->q_syncp); if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -4483,7 +4480,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_tx_queue *tx_q; bool has_vlan, set_ic; int entry, first_tx; - unsigned long flags; dma_addr_t des; tx_q = &priv->dma_conf.tx_queue[queue]; @@ -4653,11 +4649,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); } - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_bytes += skb->len; + u64_stats_update_begin(&txq_stats->q_syncp); + u64_stats_add(&txq_stats->q.tx_bytes, skb->len); if (set_ic) - txq_stats->tx_set_ic_bit++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_inc(&txq_stats->q.tx_set_ic_bit); + u64_stats_update_end(&txq_stats->q_syncp); if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -4921,12 +4917,11 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue, set_ic = false; if (set_ic) { - unsigned long flags; tx_q->tx_count_frames = 0; stmmac_set_tx_ic(priv, tx_desc); - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_set_ic_bit++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->q_syncp); + u64_stats_inc(&txq_stats->q.tx_set_ic_bit); + u64_stats_update_end(&txq_stats->q_syncp); } stmmac_enable_dma_transmission(priv, priv->ioaddr); @@ -5076,7 +5071,6 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue, unsigned int len = xdp->data_end - xdp->data; enum pkt_hash_types hash_type; int coe = priv->hw->rx_csum; - unsigned long flags; struct sk_buff *skb; u32 hash; @@ -5106,10 +5100,10 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue, skb_record_rx_queue(skb, queue); napi_gro_receive(&ch->rxtx_napi, skb); - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->rx_pkt_n++; - rxq_stats->rx_bytes += len; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_inc(&rxq_stats->napi.rx_pkt_n); + u64_stats_add(&rxq_stats->napi.rx_bytes, len); + u64_stats_update_end(&rxq_stats->napi_syncp); } static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget) @@ -5191,7 +5185,6 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue) unsigned int desc_size; struct bpf_prog *prog; bool failure = false; - unsigned long flags; int xdp_status = 0; int status = 0; @@ -5346,9 +5339,9 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue) stmmac_finalize_xdp_rx(priv, xdp_status); - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->rx_pkt_n += count; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_add(&rxq_stats->napi.rx_pkt_n, count); + u64_stats_update_end(&rxq_stats->napi_syncp); priv->xstats.rx_dropped += rx_dropped; priv->xstats.rx_errors += rx_errors; @@ -5386,7 +5379,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) unsigned int desc_size; struct sk_buff *skb = NULL; struct stmmac_xdp_buff ctx; - unsigned long flags; int xdp_status = 0; int buf_sz; @@ -5646,11 +5638,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) stmmac_rx_refill(priv, queue); - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->rx_packets += rx_packets; - rxq_stats->rx_bytes += rx_bytes; - rxq_stats->rx_pkt_n += count; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_add(&rxq_stats->napi.rx_packets, rx_packets); + u64_stats_add(&rxq_stats->napi.rx_bytes, rx_bytes); + u64_stats_add(&rxq_stats->napi.rx_pkt_n, count); + u64_stats_update_end(&rxq_stats->napi_syncp); priv->xstats.rx_dropped += rx_dropped; priv->xstats.rx_errors += rx_errors; @@ -5665,13 +5657,12 @@ static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget) struct stmmac_priv *priv = ch->priv_data; struct stmmac_rxq_stats *rxq_stats; u32 chan = ch->index; - unsigned long flags; int work_done; rxq_stats = &priv->xstats.rxq_stats[chan]; - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->napi_poll++; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_inc(&rxq_stats->napi.poll); + u64_stats_update_end(&rxq_stats->napi_syncp); work_done = stmmac_rx(priv, budget, chan); if (work_done < budget && napi_complete_done(napi, work_done)) { @@ -5693,13 +5684,12 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget) struct stmmac_txq_stats *txq_stats; bool pending_packets = false; u32 chan = ch->index; - unsigned long flags; int work_done; txq_stats = &priv->xstats.txq_stats[chan]; - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->napi_poll++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->napi_syncp); + u64_stats_inc(&txq_stats->napi.poll); + u64_stats_update_end(&txq_stats->napi_syncp); work_done = stmmac_tx_clean(priv, budget, chan, &pending_packets); work_done = min(work_done, budget); @@ -5729,17 +5719,16 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget) struct stmmac_rxq_stats *rxq_stats; struct stmmac_txq_stats *txq_stats; u32 chan = ch->index; - unsigned long flags; rxq_stats = &priv->xstats.rxq_stats[chan]; - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->napi_poll++; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_inc(&rxq_stats->napi.poll); + u64_stats_update_end(&rxq_stats->napi_syncp); txq_stats = &priv->xstats.txq_stats[chan]; - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->napi_poll++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->napi_syncp); + u64_stats_inc(&txq_stats->napi.poll); + u64_stats_update_end(&txq_stats->napi_syncp); tx_done = stmmac_tx_clean(priv, budget, chan, &tx_pending_packets); tx_done = min(tx_done, budget); @@ -7065,10 +7054,13 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64 u64 tx_bytes; do { - start = u64_stats_fetch_begin(&txq_stats->syncp); - tx_packets = txq_stats->tx_packets; - tx_bytes = txq_stats->tx_bytes; - } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); + start = u64_stats_fetch_begin(&txq_stats->q_syncp); + tx_bytes = u64_stats_read(&txq_stats->q.tx_bytes); + } while (u64_stats_fetch_retry(&txq_stats->q_syncp, start)); + do { + start = u64_stats_fetch_begin(&txq_stats->napi_syncp); + tx_packets = u64_stats_read(&txq_stats->napi.tx_packets); + } while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start)); stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; @@ -7080,10 +7072,10 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64 u64 rx_bytes; do { - start = u64_stats_fetch_begin(&rxq_stats->syncp); - rx_packets = rxq_stats->rx_packets; - rx_bytes = rxq_stats->rx_bytes; - } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); + start = u64_stats_fetch_begin(&rxq_stats->napi_syncp); + rx_packets = u64_stats_read(&rxq_stats->napi.rx_packets); + rx_bytes = u64_stats_read(&rxq_stats->napi.rx_bytes); + } while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; @@ -7477,9 +7469,16 @@ int stmmac_dvr_probe(struct device *device, priv->dev = ndev; for (i = 0; i < MTL_MAX_RX_QUEUES; i++) - u64_stats_init(&priv->xstats.rxq_stats[i].syncp); - for (i = 0; i < MTL_MAX_TX_QUEUES; i++) - u64_stats_init(&priv->xstats.txq_stats[i].syncp); + u64_stats_init(&priv->xstats.rxq_stats[i].napi_syncp); + for (i = 0; i < MTL_MAX_TX_QUEUES; i++) { + u64_stats_init(&priv->xstats.txq_stats[i].q_syncp); + u64_stats_init(&priv->xstats.txq_stats[i].napi_syncp); + } + + priv->xstats.pcpu_stats = + devm_netdev_alloc_pcpu_stats(device, struct stmmac_pcpu_stats); + if (!priv->xstats.pcpu_stats) + return -ENOMEM; stmmac_set_ethtool_ops(ndev); priv->pause = pause; -- 2.43.0

1 year, 1 month

8
15
0 0

[PATCH v3 2/2] of: overlay: Synchronize of_overlay_remove() with the devlink removals

by Herve Codina

In the following sequence: 1) of_platform_depopulate() 2) of_overlay_remove() During the step 1, devices are destroyed and devlinks are removed. During the step 2, OF nodes are destroyed but __of_changeset_entry_destroy() can raise warnings related to missing of_node_put(): ERROR: memory leak, expected refcount 1 instead of 2 ... Indeed, during the devlink removals performed at step 1, the removal itself releasing the device (and the attached of_node) is done by a job queued in a workqueue and so, it is done asynchronously with respect to function calls. When the warning is present, of_node_put() will be called but wrongly too late from the workqueue job. In order to be sure that any ongoing devlink removals are done before the of_node destruction, synchronize the of_overlay_remove() with the devlink removals. Fixes: 80dd33cf72d1 ("drivers: base: Fix device link removal") Cc: stable(a)vger.kernel.org Signed-off-by: Herve Codina <herve.codina(a)bootlin.com> --- drivers/of/overlay.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 2ae7e9d24a64..7a010a62b9d8 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) "OF: overlay: " fmt +#include <linux/device.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> @@ -853,6 +854,14 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs) { int i; + /* + * Wait for any ongoing device link removals before removing some of + * nodes. Drop the global lock while waiting + */ + mutex_unlock(&of_mutex); + device_link_wait_removal(); + mutex_lock(&of_mutex); + if (ovcs->cset.entries.next) of_changeset_destroy(&ovcs->cset); @@ -862,7 +871,6 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs) ovcs->id = 0; } - for (i = 0; i < ovcs->count; i++) { of_node_put(ovcs->fragments[i].target); of_node_put(ovcs->fragments[i].overlay); -- 2.43.0

1 year, 1 month

4
9
0 0

[PATCH v4 1/2] fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio

by Bart Van Assche

If kiocb_set_cancel_fn() is called for I/O submitted via io_uring, the following kernel warning appears: WARNING: CPU: 3 PID: 368 at fs/aio.c:598 kiocb_set_cancel_fn+0x9c/0xa8 Call trace: kiocb_set_cancel_fn+0x9c/0xa8 ffs_epfile_read_iter+0x144/0x1d0 io_read+0x19c/0x498 io_issue_sqe+0x118/0x27c io_submit_sqes+0x25c/0x5fc __arm64_sys_io_uring_enter+0x104/0xab0 invoke_syscall+0x58/0x11c el0_svc_common+0xb4/0xf4 do_el0_svc+0x2c/0xb0 el0_svc+0x2c/0xa4 el0t_64_sync_handler+0x68/0xb4 el0t_64_sync+0x1a4/0x1a8 Fix this by setting the IOCB_AIO_RW flag for read and write I/O that is submitted by libaio. Suggested-by: Jens Axboe <axboe(a)kernel.dk> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Avi Kivity <avi(a)scylladb.com> Cc: Sandeep Dhavale <dhavale(a)google.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> --- fs/aio.c | 9 ++++++++- include/linux/fs.h | 2 ++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/aio.c b/fs/aio.c index bb2ff48991f3..da18dbcfcb22 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -593,6 +593,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1509,7 +1516,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/include/linux/fs.h b/include/linux/fs.h index c9deac59c29a..d47306fe1121 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -352,6 +352,8 @@ enum rw_hint { * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \

1 year, 1 month

4
10
0 0

[PATCH v3 0/4] Disable automatic load CCS load balancing

by Andi Shyti

Hi, this series does basically two things: 1. Disables automatic load balancing as adviced by the hardware workaround. 2. Assigns all the CCS slices to one single user engine. The user will then be able to query only one CCS engine I'm using here the "Requires: " tag, but I'm not sure the commit id will be valid, on the other hand, I don't know what commit id I should use. Thanks Tvrtko, Matt and John for your reviews! Andi Changelog ========= v2 -> v3 - Simplified the algorithm for creating the list of the exported uabi engines. (Patch 1) (Thanks, Tvrtko) - Consider the fused engines when creating the uabi engine list (Patch 2) (Thanks, Matt) - Patch 4 now uses a the refactoring from patch 1, in a cleaner outcome. v1 -> v2 - In Patch 1 use the correct workaround number (thanks Matt). - In Patch 2 do not add the extra CCS engines to the exposed UABI engine list and adapt the engine counting accordingly (thanks Tvrtko). - Reword the commit of Patch 2 (thanks John). Andi Shyti (4): drm/i915/gt: Refactor uabi engine class/instance list creation drm/i915/gt: Do not exposed fused off engines. drm/i915/gt: Disable HW load balancing for CCS drm/i915/gt: Enable only one CCS for compute workload drivers/gpu/drm/i915/gt/intel_engine_user.c | 52 ++++++++++++++++----- drivers/gpu/drm/i915/gt/intel_gt.c | 11 +++++ drivers/gpu/drm/i915/gt/intel_gt_regs.h | 3 ++ drivers/gpu/drm/i915/gt/intel_workarounds.c | 6 +++ 4 files changed, 60 insertions(+), 12 deletions(-) -- 2.43.0

1 year, 1 month

4
8
0 0

[PATCH v2 0/3] Support intra-function call validation

by Rui Qi

Since kernel version 5.4.217 LTS, there has been an issue with the kernel live patching feature becoming unavailable. When compiling the sample code for kernel live patching, the following message is displayed when enabled: livepatch: klp_check_stack: kworker/u256:6:23490 has an unreliable stack Reproduction steps: 1.git checkout v5.4.269 -b v5.4.269 2.make defconfig 3. Set CONFIG_LIVEPATCH=y、CONFIG_SAMPLE_LIVEPATCH=m 4. make -j bzImage 5. make samples/livepatch/livepatch-sample.ko 6. qemu-system-x86_64 -kernel arch/x86_64/boot/bzImage -nographic -append "console=ttyS0" -initrd initrd.img -m 1024M 7. insmod livepatch-sample.ko Kernel live patch cannot complete successfully. After some debugging, the immediate cause of the patch failure is an error in stack checking. The logs are as follows: [ 340.974853] livepatch: klp_check_stack: kworker/u256:0:23486 has an unreliable stack [ 340.974858] livepatch: klp_check_stack: kworker/u256:1:23487 has an unreliable stack [ 340.974863] livepatch: klp_check_stack: kworker/u256:2:23488 has an unreliable stack [ 340.974868] livepatch: klp_check_stack: kworker/u256:5:23489 has an unreliable stack [ 340.974872] livepatch: klp_check_stack: kworker/u256:6:23490 has an unreliable stack ...... BTW,if you use the v5.4.217 tag for testing, make sure to set CONFIG_RETPOLINE = y and CONFIG_LIVEPATCH = y, and other steps are consistent with v5.4.269 After investigation, The problem is strongly related to the commit 8afd1c7da2b0 ("x86/speculation: Change FILL_RETURN_BUFFER to work with objtool"), which would cause incorrect ORC entries to be generated, and the v5.4.217 version can undo this commit to make kernel livepatch work normally. It is a back-ported upstream patch with some code adjustments,from the git log, the author also mentioned no intra-function call validation support. Based on commit 6e1f54a4985b63bc1b55a09e5e75a974c5d6719b (Linux 5.4.269), This patchset adds stack validation support for intra-function calls, allowing the kernel live patching feature to work correctly. Alexandre Chartre (2): objtool: is_fentry_call() crashes if call has no destination objtool: Add support for intra-function calls Rui Qi (1): x86/speculation: Support intra-function call validation arch/x86/include/asm/nospec-branch.h | 7 ++ include/linux/frame.h | 11 ++++ .../Documentation/stack-validation.txt | 8 +++ tools/objtool/arch/x86/decode.c | 6 ++ tools/objtool/check.c | 64 +++++++++++++++++-- 5 files changed, 91 insertions(+), 5 deletions(-) -- 2.39.2 (Apple Git-143)

1 year, 1 month

2
9
0 0

[PATCH v2] serial: Lock console when calling into driver before registration

by Peter Collingbourne

During the handoff from earlycon to the real console driver, we have two separate drivers operating on the same device concurrently. In the case of the 8250 driver these concurrent accesses cause problems due to the driver's use of banked registers, controlled by LCR.DLAB. It is possible for the setup(), config_port(), pm() and set_mctrl() callbacks to set DLAB, which can cause the earlycon code that intends to access TX to instead access DLL, leading to missed output and corruption on the serial line due to unintended modifications to the baud rate. In particular, for setup() we have: univ8250_console_setup() -> serial8250_console_setup() -> uart_set_options() -> serial8250_set_termios() -> serial8250_do_set_termios() -> serial8250_do_set_divisor() For config_port() we have: serial8250_config_port() -> autoconfig() For pm() we have: serial8250_pm() -> serial8250_do_pm() -> serial8250_set_sleep() For set_mctrl() we have (for some devices): serial8250_set_mctrl() -> omap8250_set_mctrl() -> __omap8250_set_mctrl() To avoid such problems, let's make it so that the console is locked during pre-registration calls to these callbacks, which will prevent the earlycon driver from running concurrently. Remove the partial solution to this problem in the 8250 driver that locked the console only during autoconfig_irq(), as this would result in a deadlock with the new approach. The console continues to be locked during autoconfig_irq() because it can only be called through uart_configure_port(). Although this patch introduces more locking than strictly necessary (and in particular it also locks during the call to rs485_config() which is not affected by this issue as far as I can tell), it follows the principle that it is the responsibility of the generic console code to manage the earlycon handoff by ensuring that earlycon and real console driver code cannot run concurrently, and not the individual drivers. Signed-off-by: Peter Collingbourne <pcc(a)google.com> Reviewed-by: John Ogness <john.ogness(a)linutronix.de> Link: https://linux-review.googlesource.com/id/I7cf8124dcebf8618e6b2ee543fa5b2553… Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable(a)vger.kernel.org --- drivers/tty/serial/8250/8250_port.c | 6 ------ drivers/tty/serial/serial_core.c | 12 ++++++++++++ kernel/printk/printk.c | 21 ++++++++++++++++++--- 3 files changed, 30 insertions(+), 9 deletions(-) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 8ca061d3bbb9..1d65055dde27 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1329,9 +1329,6 @@ static void autoconfig_irq(struct uart_8250_port *up) inb_p(ICP); } - if (uart_console(port)) - console_lock(); - /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); @@ -1371,9 +1368,6 @@ static void autoconfig_irq(struct uart_8250_port *up) if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); - if (uart_console(port)) - console_unlock(); - port->irq = (irq > 0) ? irq : 0; } diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index d6a58a9e072a..ff85ebd3a007 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2608,7 +2608,12 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); port->ops->config_port(port, flags); + if (uart_console(port)) + console_unlock(); } if (port->type != PORT_UNKNOWN) { @@ -2616,6 +2621,10 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_report_port(drv, port); + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); + /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); @@ -2632,6 +2641,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_rs485_config(port); + if (uart_console(port)) + console_unlock(); + /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index f2444b581e16..f51e4e5a869d 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3263,6 +3263,21 @@ static int __init keep_bootcon_setup(char *str) early_param("keep_bootcon", keep_bootcon_setup); +static int console_call_setup(struct console *newcon, char *options) +{ + int err; + + if (!newcon->setup) + return 0; + + /* Synchronize with possible boot console. */ + console_lock(); + err = newcon->setup(newcon, options); + console_unlock(); + + return err; +} + /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected @@ -3298,8 +3313,8 @@ static int try_enable_preferred_console(struct console *newcon, if (_braille_register_console(newcon, c)) return 0; - if (newcon->setup && - (err = newcon->setup(newcon, c->options)) != 0) + err = console_call_setup(newcon, c->options); + if (err != 0) return err; } newcon->flags |= CON_ENABLED; @@ -3325,7 +3340,7 @@ static void try_enable_default_console(struct console *newcon) if (newcon->index < 0) newcon->index = 0; - if (newcon->setup && newcon->setup(newcon, NULL) != 0) + if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; -- 2.44.0.rc1.240.g4c46232300-goog

1 year, 1 month

2
2
0 0

[PATCH] btrfs: qgroup: verify btrfs_qgroup_inherit parameter

by Qu Wenruo

[BUG] Currently btrfs can create subvolume with an invalid qgroup inherit without triggering any error: # mkfs.btrfs -O quota -f $dev # mount $dev $mnt # btrfs subvolume create -i 2/0 $mnt/subv1 # btrfs qgroup show -prce --sync $mnt Qgroupid Referenced Exclusive Path -------- ---------- --------- ---- 0/5 16.00KiB 16.00KiB <toplevel> 0/256 16.00KiB 16.00KiB subv1 [CAUSE] We only do a very basic size check for btrfs_qgroup_inherit structure, but never really verify if the values are correct. Thus in btrfs_qgroup_inherit() function, we have to skip non-existing qgroups, and never return any error. [FIX] Fix the behavior and introduce extra checks: - Introduce early check for btrfs_qgroup_inherit structure Not only the size, but also all the qgroup ids would be verifyed. And the timing is very early, so we can return error early. This early check is very important for snapshot creation, as snapshot is delayed to transaction commit. - Drop support for btrfs_qgroup_inherit::num_ref_copies and num_excl_copies Those two members are used to specify to copy refr/excl numbers from other qgroups. This would definitely mark qgroup inconsistent, and btrfs-progs has dropped the support for them for a long time. It's time to drop the support for kernel. - Verify the supported btrfs_qgroup_inherit::flags Just in case we want to add extra flags for btrfs_qgroup_inherit. Now above subvolume creation would fail with -ENOENT other than silently ignore the non-existing qgroup. CC: stable(a)vger.kernel.org Signed-off-by: Qu Wenruo <wqu(a)suse.com> --- fs/btrfs/ioctl.c | 16 +++--------- fs/btrfs/qgroup.c | 52 ++++++++++++++++++++++++++++++++++++++ fs/btrfs/qgroup.h | 3 +++ include/uapi/linux/btrfs.h | 1 + 4 files changed, 59 insertions(+), 13 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8b80fbea1e72..c19ce2e292dc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1382,7 +1382,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, if (vol_args->flags & BTRFS_SUBVOL_RDONLY) readonly = true; if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) { - u64 nums; + struct btrfs_fs_info *fs_info = inode_to_fs_info(file_inode(file)); if (vol_args->size < sizeof(*inherit) || vol_args->size > PAGE_SIZE) { @@ -1395,19 +1395,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, goto free_args; } - if (inherit->num_qgroups > PAGE_SIZE || - inherit->num_ref_copies > PAGE_SIZE || - inherit->num_excl_copies > PAGE_SIZE) { - ret = -EINVAL; + ret = btrfs_qgroup_check_inherit(fs_info, inherit, vol_args->size); + if (ret < 0) goto free_inherit; - } - - nums = inherit->num_qgroups + 2 * inherit->num_ref_copies + - 2 * inherit->num_excl_copies; - if (vol_args->size != struct_size(inherit, qgroups, nums)) { - ret = -EINVAL; - goto free_inherit; - } } ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file), diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 4fa83c76b37b..66968092b554 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3046,6 +3046,58 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) return ret; } +int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_inherit *inherit, + size_t size) +{ + if (inherit->flags & ~BTRFS_QGROUP_INHERIT_FLAGS_SUPP) + return -EOPNOTSUPP; + if (size < sizeof(*inherit) || size > PAGE_SIZE) + return -EINVAL; + + /* + * In the past we allow btrfs_qgroup_inherit to specify to copy + * refr/excl numbers directly from other qgroups. + * This behavior has been disable in btrfs-progs for a very long time, + * but here we should also disable them for kernel, as this behavior + * is known to mark qgroup inconsistent, and a rescan would wipe out the + * change anyway. + * + * So here we just reject any btrfs_qgroup_inherit with num_ref_copies or + * num_excl_copies. + */ + if (inherit->num_ref_copies || inherit->num_excl_copies) + return -EINVAL; + + if (inherit->num_qgroups > PAGE_SIZE) + return -EINVAL; + + if (size != struct_size(inherit, qgroups, inherit->num_qgroups)) + return -EINVAL; + + /* + * Now check all the remaining qgroups, they should all: + * - Exist + * - Be higher level qgroups. + */ + for (int i = 0; i < inherit->num_qgroups; i++) { + struct btrfs_qgroup *qgroup; + u64 qgroupid = inherit->qgroups[i]; + + if (btrfs_qgroup_level(qgroupid) == 0) + return -EINVAL; + + spin_lock(&fs_info->qgroup_lock); + qgroup = find_qgroup_rb(fs_info, qgroupid); + if (!qgroup) { + spin_unlock(&fs_info->qgroup_lock); + return -ENOENT; + } + spin_unlock(&fs_info->qgroup_lock); + } + return 0; +} + static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info, u64 inode_rootid, struct btrfs_qgroup_inherit **inherit) diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 1f664261c064..706640be0ec2 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -350,6 +350,9 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr, struct ulist *new_roots); int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans); int btrfs_run_qgroups(struct btrfs_trans_handle *trans); +int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_inherit *inherit, + size_t size); int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, u64 objectid, u64 inode_rootid, struct btrfs_qgroup_inherit *inherit); diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index f8bc34a6bcfa..cdf6ad872149 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -92,6 +92,7 @@ struct btrfs_qgroup_limit { * struct btrfs_qgroup_inherit.flags */ #define BTRFS_QGROUP_INHERIT_SET_LIMITS (1ULL << 0) +#define BTRFS_QGROUP_INHERIT_FLAGS_SUPP (BTRFS_QGROUP_INHERIT_SET_LIMITS) struct btrfs_qgroup_inherit { __u64 flags; -- 2.43.2

1 year, 1 month

3
3
0 0

[PATCH] libceph: init the cursor when preparing the sparse read

by xiubli＠redhat.com

From: Xiubo Li <xiubli(a)redhat.com> The osd code has remove cursor initilizing code and this will make the sparse read state into a infinite loop. We should initialize the cursor just before each sparse-read in messnger v2. Cc: stable(a)vger.kernel.org URL: https://tracker.ceph.com/issues/64607 Fixes: 8e46a2d068c9 ("libceph: just wait for more data to be available on the socket") Reported-by: Luis Henriques <lhenriques(a)suse.de> Signed-off-by: Xiubo Li <xiubli(a)redhat.com> --- net/ceph/messenger_v2.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index a0ca5414b333..7ae0f80100f4 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -2025,6 +2025,7 @@ static int prepare_sparse_read_cont(struct ceph_connection *con) static int prepare_sparse_read_data(struct ceph_connection *con) { struct ceph_msg *msg = con->in_msg; + u64 len = con->in_msg->sparse_read_total ? : data_len(con->in_msg); dout("%s: starting sparse read\n", __func__); @@ -2034,6 +2035,8 @@ static int prepare_sparse_read_data(struct ceph_connection *con) if (!con_secure(con)) con->in_data_crc = -1; + ceph_msg_data_cursor_init(&con->v2.in_cursor, con->in_msg, len); + reset_in_kvecs(con); con->v2.in_state = IN_S_PREPARE_SPARSE_DATA_CONT; con->v2.data_len_remain = data_len(msg); -- 2.43.0

1 year, 1 month

4
10
0 0

[PATCH stable 6.1] NFS: Fix data corruption caused by congestion.

by NeilBrown

when AOP_WRITEPAGE_ACTIVATE is returned (as NFS does when it detects congestion) it is important that the page is redirtied. nfs_writepage_locked() doesn't do this, so files can become corrupted as writes can be lost. Note that this is not needed in v6.8 as AOP_WRITEPAGE_ACTIVATE cannot be returned. It is needed for kernels v5.18..v6.7. From 6.3 onward the patch is different as it needs to mention "folio", not "page". Reported-and-tested-by: Jacek Tomaka <Jacek.Tomaka(a)poczta.fm> Fixes: 6df25e58532b ("nfs: remove reliance on bdi congestion") Signed-off-by: NeilBrown <neilb(a)suse.de> --- fs/nfs/write.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f41d24b54fd1..6a0606668417 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -667,8 +667,10 @@ static int nfs_writepage_locked(struct page *page, int err; if (wbc->sync_mode == WB_SYNC_NONE && - NFS_SERVER(inode)->write_congested) + NFS_SERVER(inode)->write_congested) { + redirty_page_for_writepage(wbc, page); return AOP_WRITEPAGE_ACTIVATE; + } nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_pageio_init_write(&pgio, inode, 0, -- 2.43.0

1 year, 1 month

2
1
0 0

[REGRESSION][PATCH 5.15 v1] Revert "drm/bridge: lt8912b: Register and attach our DSI device at probe"

by max.oss.09＠gmail.com

From: Max Krummenacher <max.krummenacher(a)toradex.com> This reverts commit ef4a40953c8076626875ff91c41e210fcee7a6fd. The commit was applied to make further commits apply cleanly, but the commit depends on other commits in the same patchset. I.e. the controlling DSI host would need a change too. Thus one would need to backport the full patchset changing the DSI hosts and all downstream DSI device drivers. Revert the commit and fix up the conflicts with the backported fixes to the lt8912b driver. Signed-off-by: Max Krummenacher <max.krummenacher(a)toradex.com> Conflicts: drivers/gpu/drm/bridge/lontium-lt8912b.c --- drivers/gpu/drm/bridge/lontium-lt8912b.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c index 6891863ed5104..e16b0fc0cda0f 100644 --- a/drivers/gpu/drm/bridge/lontium-lt8912b.c +++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c @@ -571,6 +571,10 @@ static int lt8912_bridge_attach(struct drm_bridge *bridge, if (ret) goto error; + ret = lt8912_attach_dsi(lt); + if (ret) + goto error; + return 0; error: @@ -726,15 +730,8 @@ static int lt8912_probe(struct i2c_client *client, drm_bridge_add(&lt->bridge); - ret = lt8912_attach_dsi(lt); - if (ret) - goto err_attach; - return 0; -err_attach: - drm_bridge_remove(&lt->bridge); - lt8912_free_i2c(lt); err_i2c: lt8912_put_dt(lt); err_dt_parse: -- 2.42.0

1 year, 1 month

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2024