May 2025 - Linux-stable-mirror

[PATCH net 2/4] can: kvaser_pciefd: Fix echo_skb race

by Marc Kleine-Budde

From: Axel Forsman <axfo(a)kvaser.com> The functions kvaser_pciefd_start_xmit() and kvaser_pciefd_handle_ack_packet() raced to stop/wake TX queues and get/put echo skbs, as kvaser_pciefd_can->echo_lock was only ever taken when transmitting and KCAN_TX_NR_PACKETS_CURRENT gets decremented prior to handling of ACKs. E.g., this caused the following error: can_put_echo_skb: BUG! echo_skb 5 is occupied! Instead, use the synchronization helpers in netdev_queues.h. As those piggyback on BQL barriers, start updating in-flight packets and bytes counts as well. Cc: stable(a)vger.kernel.org Signed-off-by: Axel Forsman <axfo(a)kvaser.com> Tested-by: Jimmy Assarsson <extja(a)kvaser.com> Reviewed-by: Jimmy Assarsson <extja(a)kvaser.com> Link: https://patch.msgid.link/20250520114332.8961-3-axfo@kvaser.com Signed-off-by: Marc Kleine-Budde <mkl(a)pengutronix.de> --- drivers/net/can/kvaser_pciefd.c | 93 +++++++++++++++++++++------------ 1 file changed, 59 insertions(+), 34 deletions(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 9cc9176c2058..a61cbade96d9 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -16,6 +16,7 @@ #include <linux/netdevice.h> #include <linux/pci.h> #include <linux/timer.h> +#include <net/netdev_queues.h> MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Kvaser AB <support(a)kvaser.com>"); @@ -410,10 +411,13 @@ struct kvaser_pciefd_can { void __iomem *reg_base; struct can_berr_counter bec; u8 cmd_seq; + u8 tx_max_count; + u8 tx_idx; + u8 ack_idx; int err_rep_cnt; - int echo_idx; + unsigned int completed_tx_pkts; + unsigned int completed_tx_bytes; spinlock_t lock; /* Locks sensitive registers (e.g. MODE) */ - spinlock_t echo_lock; /* Locks the message echo buffer */ struct timer_list bec_poll_timer; struct completion start_comp, flush_comp; }; @@ -714,6 +718,9 @@ static int kvaser_pciefd_open(struct net_device *netdev) int ret; struct kvaser_pciefd_can *can = netdev_priv(netdev); + can->tx_idx = 0; + can->ack_idx = 0; + ret = open_candev(netdev); if (ret) return ret; @@ -745,21 +752,26 @@ static int kvaser_pciefd_stop(struct net_device *netdev) timer_delete(&can->bec_poll_timer); } can->can.state = CAN_STATE_STOPPED; + netdev_reset_queue(netdev); close_candev(netdev); return ret; } +static unsigned int kvaser_pciefd_tx_avail(const struct kvaser_pciefd_can *can) +{ + return can->tx_max_count - (READ_ONCE(can->tx_idx) - READ_ONCE(can->ack_idx)); +} + static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p, - struct kvaser_pciefd_can *can, + struct can_priv *can, u8 seq, struct sk_buff *skb) { struct canfd_frame *cf = (struct canfd_frame *)skb->data; int packet_size; - int seq = can->echo_idx; memset(p, 0, sizeof(*p)); - if (can->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT) + if (can->ctrlmode & CAN_CTRLMODE_ONE_SHOT) p->header[1] |= KVASER_PCIEFD_TPACKET_SMS; if (cf->can_id & CAN_RTR_FLAG) @@ -782,7 +794,7 @@ static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p, } else { p->header[1] |= FIELD_PREP(KVASER_PCIEFD_RPACKET_DLC_MASK, - can_get_cc_dlc((struct can_frame *)cf, can->can.ctrlmode)); + can_get_cc_dlc((struct can_frame *)cf, can->ctrlmode)); } p->header[1] |= FIELD_PREP(KVASER_PCIEFD_PACKET_SEQ_MASK, seq); @@ -797,22 +809,24 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb, struct net_device *netdev) { struct kvaser_pciefd_can *can = netdev_priv(netdev); - unsigned long irq_flags; struct kvaser_pciefd_tx_packet packet; + unsigned int seq = can->tx_idx & (can->can.echo_skb_max - 1); + unsigned int frame_len; int nr_words; - u8 count; if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; + if (!netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1)) + return NETDEV_TX_BUSY; - nr_words = kvaser_pciefd_prepare_tx_packet(&packet, can, skb); + nr_words = kvaser_pciefd_prepare_tx_packet(&packet, &can->can, seq, skb); - spin_lock_irqsave(&can->echo_lock, irq_flags); /* Prepare and save echo skb in internal slot */ - can_put_echo_skb(skb, netdev, can->echo_idx, 0); - - /* Move echo index to the next slot */ - can->echo_idx = (can->echo_idx + 1) % can->can.echo_skb_max; + WRITE_ONCE(can->can.echo_skb[seq], NULL); + frame_len = can_skb_get_frame_len(skb); + can_put_echo_skb(skb, netdev, seq, frame_len); + netdev_sent_queue(netdev, frame_len); + WRITE_ONCE(can->tx_idx, can->tx_idx + 1); /* Write header to fifo */ iowrite32(packet.header[0], @@ -836,14 +850,7 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb, KVASER_PCIEFD_KCAN_FIFO_LAST_REG); } - count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK, - ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG)); - /* No room for a new message, stop the queue until at least one - * successful transmit - */ - if (count >= can->can.echo_skb_max || can->can.echo_skb[can->echo_idx]) - netif_stop_queue(netdev); - spin_unlock_irqrestore(&can->echo_lock, irq_flags); + netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1); return NETDEV_TX_OK; } @@ -970,6 +977,8 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) can->kv_pcie = pcie; can->cmd_seq = 0; can->err_rep_cnt = 0; + can->completed_tx_pkts = 0; + can->completed_tx_bytes = 0; can->bec.txerr = 0; can->bec.rxerr = 0; @@ -983,11 +992,10 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) tx_nr_packets_max = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_MAX_MASK, ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG)); + can->tx_max_count = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1); can->can.clock.freq = pcie->freq; - can->can.echo_skb_max = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1); - can->echo_idx = 0; - spin_lock_init(&can->echo_lock); + can->can.echo_skb_max = roundup_pow_of_two(can->tx_max_count); spin_lock_init(&can->lock); can->can.bittiming_const = &kvaser_pciefd_bittiming_const; @@ -1510,19 +1518,21 @@ static int kvaser_pciefd_handle_ack_packet(struct kvaser_pciefd *pcie, netdev_dbg(can->can.dev, "Packet was flushed\n"); } else { int echo_idx = FIELD_GET(KVASER_PCIEFD_PACKET_SEQ_MASK, p->header[0]); - int len; - u8 count; + unsigned int len, frame_len = 0; struct sk_buff *skb; + if (echo_idx != (can->ack_idx & (can->can.echo_skb_max - 1))) + return 0; skb = can->can.echo_skb[echo_idx]; - if (skb) - kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp); - len = can_get_echo_skb(can->can.dev, echo_idx, NULL); - count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK, - ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG)); + if (!skb) + return 0; + kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp); + len = can_get_echo_skb(can->can.dev, echo_idx, &frame_len); - if (count < can->can.echo_skb_max && netif_queue_stopped(can->can.dev)) - netif_wake_queue(can->can.dev); + /* Pairs with barrier in kvaser_pciefd_start_xmit() */ + smp_store_release(&can->ack_idx, can->ack_idx + 1); + can->completed_tx_pkts++; + can->completed_tx_bytes += frame_len; if (!one_shot_fail) { can->can.dev->stats.tx_bytes += len; @@ -1638,11 +1648,26 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf) { int pos = 0; int res = 0; + unsigned int i; do { res = kvaser_pciefd_read_packet(pcie, &pos, dma_buf); } while (!res && pos > 0 && pos < KVASER_PCIEFD_DMA_SIZE); + /* Report ACKs in this buffer to BQL en masse for correct periods */ + for (i = 0; i < pcie->nr_channels; ++i) { + struct kvaser_pciefd_can *can = pcie->can[i]; + + if (!can->completed_tx_pkts) + continue; + netif_subqueue_completed_wake(can->can.dev, 0, + can->completed_tx_pkts, + can->completed_tx_bytes, + kvaser_pciefd_tx_avail(can), 1); + can->completed_tx_pkts = 0; + can->completed_tx_bytes = 0; + } + return res; } -- 2.47.2

2 weeks, 3 days

1
0
0 0

[PATCH net 1/4] can: kvaser_pciefd: Force IRQ edge in case of nested IRQ

by Marc Kleine-Budde

From: Axel Forsman <axfo(a)kvaser.com> Avoid the driver missing IRQs by temporarily masking IRQs in the ISR to enforce an edge even if a different IRQ is signalled before handled IRQs are cleared. Fixes: 48f827d4f48f ("can: kvaser_pciefd: Move reset of DMA RX buffers to the end of the ISR") Cc: stable(a)vger.kernel.org Signed-off-by: Axel Forsman <axfo(a)kvaser.com> Tested-by: Jimmy Assarsson <extja(a)kvaser.com> Reviewed-by: Jimmy Assarsson <extja(a)kvaser.com> Link: https://patch.msgid.link/20250520114332.8961-2-axfo@kvaser.com Signed-off-by: Marc Kleine-Budde <mkl(a)pengutronix.de> --- drivers/net/can/kvaser_pciefd.c | 83 ++++++++++++++++----------------- 1 file changed, 39 insertions(+), 44 deletions(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index cf0d51805272..9cc9176c2058 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -1646,24 +1646,28 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf) return res; } -static u32 kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie) +static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie) { + void __iomem *srb_cmd_reg = KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG; u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG); - if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) - kvaser_pciefd_read_buffer(pcie, 0); + iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG); - if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) + if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) { + kvaser_pciefd_read_buffer(pcie, 0); + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, srb_cmd_reg); /* Rearm buffer */ + } + + if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) { kvaser_pciefd_read_buffer(pcie, 1); + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, srb_cmd_reg); /* Rearm buffer */ + } if (unlikely(irq & KVASER_PCIEFD_SRB_IRQ_DOF0 || irq & KVASER_PCIEFD_SRB_IRQ_DOF1 || irq & KVASER_PCIEFD_SRB_IRQ_DUF0 || irq & KVASER_PCIEFD_SRB_IRQ_DUF1)) dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq); - - iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG); - return irq; } static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can) @@ -1691,29 +1695,22 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev) struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev; const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask; u32 pci_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie)); - u32 srb_irq = 0; - u32 srb_release = 0; int i; if (!(pci_irq & irq_mask->all)) return IRQ_NONE; + iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie)); + if (pci_irq & irq_mask->kcan_rx0) - srb_irq = kvaser_pciefd_receive_irq(pcie); + kvaser_pciefd_receive_irq(pcie); for (i = 0; i < pcie->nr_channels; i++) { if (pci_irq & irq_mask->kcan_tx[i]) kvaser_pciefd_transmit_irq(pcie->can[i]); } - if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0) - srb_release |= KVASER_PCIEFD_SRB_CMD_RDB0; - - if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1) - srb_release |= KVASER_PCIEFD_SRB_CMD_RDB1; - - if (srb_release) - iowrite32(srb_release, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG); + iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie)); return IRQ_HANDLED; } @@ -1733,13 +1730,22 @@ static void kvaser_pciefd_teardown_can_ctrls(struct kvaser_pciefd *pcie) } } +static void kvaser_pciefd_disable_irq_srcs(struct kvaser_pciefd *pcie) +{ + unsigned int i; + + /* Masking PCI_IRQ is insufficient as running ISR will unmask it */ + iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG); + for (i = 0; i < pcie->nr_channels; ++i) + iowrite32(0, pcie->can[i]->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); +} + static int kvaser_pciefd_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int ret; struct kvaser_pciefd *pcie; const struct kvaser_pciefd_irq_mask *irq_mask; - void __iomem *irq_en_base; pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL); if (!pcie) @@ -1805,8 +1811,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG); /* Enable PCI interrupts */ - irq_en_base = KVASER_PCIEFD_PCI_IEN_ADDR(pcie); - iowrite32(irq_mask->all, irq_en_base); + iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie)); /* Ready the DMA buffers */ iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG); @@ -1820,8 +1825,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, return 0; err_free_irq: - /* Disable PCI interrupts */ - iowrite32(0, irq_en_base); + kvaser_pciefd_disable_irq_srcs(pcie); free_irq(pcie->pci->irq, pcie); err_pci_free_irq_vectors: @@ -1844,35 +1848,26 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, return ret; } -static void kvaser_pciefd_remove_all_ctrls(struct kvaser_pciefd *pcie) -{ - int i; - - for (i = 0; i < pcie->nr_channels; i++) { - struct kvaser_pciefd_can *can = pcie->can[i]; - - if (can) { - iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); - unregister_candev(can->can.dev); - timer_delete(&can->bec_poll_timer); - kvaser_pciefd_pwm_stop(can); - free_candev(can->can.dev); - } - } -} - static void kvaser_pciefd_remove(struct pci_dev *pdev) { struct kvaser_pciefd *pcie = pci_get_drvdata(pdev); + unsigned int i; - kvaser_pciefd_remove_all_ctrls(pcie); + for (i = 0; i < pcie->nr_channels; ++i) { + struct kvaser_pciefd_can *can = pcie->can[i]; - /* Disable interrupts */ - iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG); - iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie)); + unregister_candev(can->can.dev); + timer_delete(&can->bec_poll_timer); + kvaser_pciefd_pwm_stop(can); + } + kvaser_pciefd_disable_irq_srcs(pcie); free_irq(pcie->pci->irq, pcie); pci_free_irq_vectors(pcie->pci); + + for (i = 0; i < pcie->nr_channels; ++i) + free_candev(pcie->can[i]->can.dev); + pci_iounmap(pdev, pcie->reg_base); pci_release_regions(pdev); pci_disable_device(pdev); base-commit: 9e89db3d847f2d66d2799c5533d00aebee2be4d1 -- 2.47.2

2 weeks, 3 days

1
0
0 0

[PATCH v1] media: i2c: set lt6911uxe's reset_gpio to GPIOD_OUT_LOW

by Dongcheng Yan

reset_gpio needs to be an output and set to GPIOD_OUT_LOW, to ensure lt6911uxe is in reset state during probe. This issue was found on the onboard lt6911uxe, where the reset_pin was not reset, causing the lt6911uxe to fail to probe. Fixes: e49563c3be09d4 ("media: i2c: add lt6911uxe hdmi bridge driver") Cc: stable(a)vger.kernel.org Signed-off-by: Dongcheng Yan <dongcheng.yan(a)intel.com> --- drivers/media/i2c/lt6911uxe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/lt6911uxe.c b/drivers/media/i2c/lt6911uxe.c index c5b40bb58a37..4e2109db0145 100644 --- a/drivers/media/i2c/lt6911uxe.c +++ b/drivers/media/i2c/lt6911uxe.c @@ -600,7 +600,7 @@ static int lt6911uxe_probe(struct i2c_client *client) v4l2_i2c_subdev_init(&lt6911uxe->sd, client, &lt6911uxe_subdev_ops); - lt6911uxe->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_IN); + lt6911uxe->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(lt6911uxe->reset_gpio)) return dev_err_probe(dev, PTR_ERR(lt6911uxe->reset_gpio), "failed to get reset gpio\n"); base-commit: f2151613e040973c868d28c8b00885dfab69eb75 prerequisite-patch-id: 6cade6d98fab1ea36ed59fe5502d7d2457180ca5 -- 2.34.1

2 weeks, 4 days

1
0
0 0

[PATCH v4] fs: minix: Fix handling of corrupted directories

by Andrey Kriulin

If the directory is corrupted and the number of nlinks is less than 2 (valid nlinks have at least 2), then when the directory is deleted, the minix_rmdir will try to reduce the nlinks(unsigned int) to a negative value. Make nlinks validity check for directories. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable(a)vger.kernel.org Signed-off-by: Andrey Kriulin <kitotavrik.s(a)gmail.com> --- v4: Add nlinks check for parent dirictory to minix_rmdir per Jan Kara <jack(a)suse.cz> request. v3: Move nlinks validaty check to minix_rmdir and minix_rename per Jan Kara <jack(a)suse.cz> request. v2: Move nlinks validaty check to V[12]_minix_iget() per Jan Kara <jack(a)suse.cz> request. Change return error code to EUCLEAN. Don't block directory in r/o mode per Al Viro <viro(a)zeniv.linux.org.uk> request. fs/minix/namei.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 8938536d8d3c..ab86fd16e548 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -161,8 +161,12 @@ static int minix_unlink(struct inode * dir, struct dentry *dentry) static int minix_rmdir(struct inode * dir, struct dentry *dentry) { struct inode * inode = d_inode(dentry); - int err = -ENOTEMPTY; + int err = -EUCLEAN; + if (inode->i_nlink < 2 || dir->i_nlink <= 2) + return err; + + err = -ENOTEMPTY; if (minix_empty_dir(inode)) { err = minix_unlink(dir, dentry); if (!err) { @@ -235,6 +239,10 @@ static int minix_rename(struct mnt_idmap *idmap, mark_inode_dirty(old_inode); if (dir_de) { + if (old_dir->i_nlink <= 2) { + err = -EUCLEAN; + goto out_dir; + } err = minix_set_link(dir_de, dir_folio, new_dir); if (!err) inode_dec_link_count(old_dir); -- 2.47.2

2 weeks, 4 days

1
0
0 0

[PATCH AUTOSEL 6.14 001/642] kconfig: merge_config: use an empty file as initfile

by Sasha Levin

From: Daniel Gomez <da.gomez(a)samsung.com> [ Upstream commit a26fe287eed112b4e21e854f173c8918a6a8596d ] The scripts/kconfig/merge_config.sh script requires an existing $INITFILE (or the $1 argument) as a base file for merging Kconfig fragments. However, an empty $INITFILE can serve as an initial starting point, later referenced by the KCONFIG_ALLCONFIG Makefile variable if -m is not used. This variable can point to any configuration file containing preset config symbols (the merged output) as stated in Documentation/kbuild/kconfig.rst. When -m is used $INITFILE will contain just the merge output requiring the user to run make (i.e. KCONFIG_ALLCONFIG=<$INITFILE> make <allnoconfig/alldefconfig> or make olddefconfig). Instead of failing when `$INITFILE` is missing, create an empty file and use it as the starting point for merges. Signed-off-by: Daniel Gomez <da.gomez(a)samsung.com> Signed-off-by: Masahiro Yamada <masahiroy(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- scripts/kconfig/merge_config.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index 0b7952471c18f..79c09b378be81 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -112,8 +112,8 @@ INITFILE=$1 shift; if [ ! -r "$INITFILE" ]; then - echo "The base file '$INITFILE' does not exist. Exit." >&2 - exit 1 + echo "The base file '$INITFILE' does not exist. Creating one..." >&2 + touch "$INITFILE" fi MERGE_LIST=$* -- 2.39.5

2 weeks, 4 days

18
672
0 0

[merged mm-hotfixes-stable] kasan-avoid-sleepable-page-allocation-from-atomic-context-v9.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: kasan: avoid sleepable page allocation from atomic context has been removed from the -mm tree. Its filename was kasan-avoid-sleepable-page-allocation-from-atomic-context-v9.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Alexander Gordeev <agordeev(a)linux.ibm.com> Subject: kasan: avoid sleepable page allocation from atomic context Date: Thu, 15 May 2025 15:55:38 +0200 apply_to_pte_range() enters the lazy MMU mode and then invokes kasan_populate_vmalloc_pte() callback on each page table walk iteration. However, the callback can go into sleep when trying to allocate a single page, e.g. if an architecutre disables preemption on lazy MMU mode enter. On s390 if make arch_enter_lazy_mmu_mode() -> preempt_enable() and arch_leave_lazy_mmu_mode() -> preempt_disable(), such crash occurs: [ 0.663336] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:321 [ 0.663348] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd [ 0.663358] preempt_count: 1, expected: 0 [ 0.663366] RCU nest depth: 0, expected: 0 [ 0.663375] no locks held by kthreadd/2. [ 0.663383] Preemption disabled at: [ 0.663386] [<0002f3284cbb4eda>] apply_to_pte_range+0xfa/0x4a0 [ 0.663405] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.15.0-rc5-gcc-kasan-00043-gd76bb1ebb558-dirty #162 PREEMPT [ 0.663408] Hardware name: IBM 3931 A01 701 (KVM/Linux) [ 0.663409] Call Trace: [ 0.663410] [<0002f3284c385f58>] dump_stack_lvl+0xe8/0x140 [ 0.663413] [<0002f3284c507b9e>] __might_resched+0x66e/0x700 [ 0.663415] [<0002f3284cc4f6c0>] __alloc_frozen_pages_noprof+0x370/0x4b0 [ 0.663419] [<0002f3284ccc73c0>] alloc_pages_mpol+0x1a0/0x4a0 [ 0.663421] [<0002f3284ccc8518>] alloc_frozen_pages_noprof+0x88/0xc0 [ 0.663424] [<0002f3284ccc8572>] alloc_pages_noprof+0x22/0x120 [ 0.663427] [<0002f3284cc341ac>] get_free_pages_noprof+0x2c/0xc0 [ 0.663429] [<0002f3284cceba70>] kasan_populate_vmalloc_pte+0x50/0x120 [ 0.663433] [<0002f3284cbb4ef8>] apply_to_pte_range+0x118/0x4a0 [ 0.663435] [<0002f3284cbc7c14>] apply_to_pmd_range+0x194/0x3e0 [ 0.663437] [<0002f3284cbc99be>] __apply_to_page_range+0x2fe/0x7a0 [ 0.663440] [<0002f3284cbc9e88>] apply_to_page_range+0x28/0x40 [ 0.663442] [<0002f3284ccebf12>] kasan_populate_vmalloc+0x82/0xa0 [ 0.663445] [<0002f3284cc1578c>] alloc_vmap_area+0x34c/0xc10 [ 0.663448] [<0002f3284cc1c2a6>] __get_vm_area_node+0x186/0x2a0 [ 0.663451] [<0002f3284cc1e696>] __vmalloc_node_range_noprof+0x116/0x310 [ 0.663454] [<0002f3284cc1d950>] __vmalloc_node_noprof+0xd0/0x110 [ 0.663457] [<0002f3284c454b88>] alloc_thread_stack_node+0xf8/0x330 [ 0.663460] [<0002f3284c458d56>] dup_task_struct+0x66/0x4d0 [ 0.663463] [<0002f3284c45be90>] copy_process+0x280/0x4b90 [ 0.663465] [<0002f3284c460940>] kernel_clone+0xd0/0x4b0 [ 0.663467] [<0002f3284c46115e>] kernel_thread+0xbe/0xe0 [ 0.663469] [<0002f3284c4e440e>] kthreadd+0x50e/0x7f0 [ 0.663472] [<0002f3284c38c04a>] __ret_from_fork+0x8a/0xf0 [ 0.663475] [<0002f3284ed57ff2>] ret_from_fork+0xa/0x38 Instead of allocating single pages per-PTE, bulk-allocate the shadow memory prior to applying kasan_populate_vmalloc_pte() callback on a page range. Link: https://lkml.kernel.org/r/c61d3560297c93ed044f0b1af085610353a06a58.17473169… Fixes: 3c5c3cfb9ef4 ("kasan: support backing vmalloc space with real shadow memory") Signed-off-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Suggested-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Reviewed-by: Harry Yoo <harry.yoo(a)oracle.com> Cc: Daniel Axtens <dja(a)axtens.net> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kasan/shadow.c | 92 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 78 insertions(+), 14 deletions(-) --- a/mm/kasan/shadow.c~kasan-avoid-sleepable-page-allocation-from-atomic-context-v9 +++ a/mm/kasan/shadow.c @@ -292,33 +292,99 @@ void __init __weak kasan_populate_early_ { } +struct vmalloc_populate_data { + unsigned long start; + struct page **pages; +}; + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, - void *unused) + void *_data) { - unsigned long page; + struct vmalloc_populate_data *data = _data; + struct page *page; pte_t pte; + int index; if (likely(!pte_none(ptep_get(ptep)))) return 0; - page = __get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - __memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); - pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + index = PFN_DOWN(addr - data->start); + page = data->pages[index]; + __memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL); spin_lock(&init_mm.page_table_lock); if (likely(pte_none(ptep_get(ptep)))) { set_pte_at(&init_mm, addr, ptep, pte); - page = 0; + data->pages[index] = NULL; } spin_unlock(&init_mm.page_table_lock); - if (page) - free_page(page); + + return 0; +} + +static void ___free_pages_bulk(struct page **pages, int nr_pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + if (pages[i]) { + __free_pages(pages[i], 0); + pages[i] = NULL; + } + } +} + +static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +{ + unsigned long nr_populated, nr_total = nr_pages; + struct page **page_array = pages; + + while (nr_pages) { + nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + if (!nr_populated) { + ___free_pages_bulk(page_array, nr_total - nr_pages); + return -ENOMEM; + } + pages += nr_populated; + nr_pages -= nr_populated; + } + return 0; } +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +{ + unsigned long nr_pages, nr_total = PFN_UP(end - start); + struct vmalloc_populate_data data; + int ret = 0; + + data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!data.pages) + return -ENOMEM; + + while (nr_total) { + nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); + ret = ___alloc_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + data.start = start; + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, + kasan_populate_vmalloc_pte, &data); + ___free_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + start += nr_pages * PAGE_SIZE; + nr_total -= nr_pages; + } + + free_page((unsigned long)data.pages); + + return ret; +} + int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; @@ -348,9 +414,7 @@ int kasan_populate_vmalloc(unsigned long shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = apply_to_page_range(&init_mm, shadow_start, - shadow_end - shadow_start, - kasan_populate_vmalloc_pte, NULL); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end); if (ret) return ret; _ Patches currently in -mm which might be from agordeev(a)linux.ibm.com are

2 weeks, 4 days

1
0
0 0

[merged mm-hotfixes-stable] highmem-add-folio_test_partial_kmap.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: highmem: add folio_test_partial_kmap() has been removed from the -mm tree. Its filename was highmem-add-folio_test_partial_kmap.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: "Matthew Wilcox (Oracle)" <willy(a)infradead.org> Subject: highmem: add folio_test_partial_kmap() Date: Wed, 14 May 2025 18:06:02 +0100 In commit c749d9b7ebbc ("iov_iter: fix copy_page_from_iter_atomic() if KMAP_LOCAL_FORCE_MAP"), Hugh correctly noted that if KMAP_LOCAL_FORCE_MAP is enabled, we must limit ourselves to PAGE_SIZE bytes per call to kmap_local(). The same problem exists in memcpy_from_folio(), memcpy_to_folio(), folio_zero_tail(), folio_fill_tail() and memcpy_from_file_folio(), so add folio_test_partial_kmap() to do this more succinctly. Link: https://lkml.kernel.org/r/20250514170607.3000994-2-willy@infradead.org Fixes: 00cdf76012ab ("mm: add memcpy_from_file_folio()") Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: Hugh Dickins <hughd(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/highmem.h | 10 +++++----- include/linux/page-flags.h | 7 +++++++ 2 files changed, 12 insertions(+), 5 deletions(-) --- a/include/linux/highmem.h~highmem-add-folio_test_partial_kmap +++ a/include/linux/highmem.h @@ -461,7 +461,7 @@ static inline void memcpy_from_folio(cha const char *from = kmap_local_folio(folio, offset); size_t chunk = len; - if (folio_test_highmem(folio) && + if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); @@ -489,7 +489,7 @@ static inline void memcpy_to_folio(struc char *to = kmap_local_folio(folio, offset); size_t chunk = len; - if (folio_test_highmem(folio) && + if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); @@ -522,7 +522,7 @@ static inline __must_check void *folio_z { size_t len = folio_size(folio) - offset; - if (folio_test_highmem(folio)) { + if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { @@ -560,7 +560,7 @@ static inline void folio_fill_tail(struc VM_BUG_ON(offset + len > folio_size(folio)); - if (folio_test_highmem(folio)) { + if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { @@ -597,7 +597,7 @@ static inline size_t memcpy_from_file_fo size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); - if (folio_test_highmem(folio)) { + if (folio_test_partial_kmap(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else --- a/include/linux/page-flags.h~highmem-add-folio_test_partial_kmap +++ a/include/linux/page-flags.h @@ -615,6 +615,13 @@ FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE) PAGEFLAG_FALSE(HighMem, highmem) #endif +/* Does kmap_local_folio() only allow access to one page of the folio? */ +#ifdef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP +#define folio_test_partial_kmap(f) true +#else +#define folio_test_partial_kmap(f) folio_test_highmem(f) +#endif + #ifdef CONFIG_SWAP static __always_inline bool folio_test_swapcache(const struct folio *folio) { _ Patches currently in -mm which might be from willy(a)infradead.org are m68k-remove-use-of-page-index.patch mm-rename-page-index-to-page-__folio_index.patch ntfs3-use-folios-more-in-ntfs_compress_write.patch iov-remove-copy_page_from_iter_atomic.patch

2 weeks, 4 days

1
0
0 0

[merged mm-hotfixes-stable] taskstats-fix-struct-taskstats-breaks-backward-compatibility-since-version-15.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: taskstats: fix struct taskstats breaks backward compatibility since version 15 has been removed from the -mm tree. Its filename was taskstats-fix-struct-taskstats-breaks-backward-compatibility-since-version-15.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Wang Yaxin <wang.yaxin(a)zte.com.cn> Subject: taskstats: fix struct taskstats breaks backward compatibility since version 15 Date: Sat, 10 May 2025 15:54:13 +0800 (CST) Problem ======== commit 658eb5ab916d ("delayacct: add delay max to record delay peak") - adding more fields commit f65c64f311ee ("delayacct: add delay min to record delay peak") - adding more fields commit b016d0873777 ("taskstats: modify taskstats version") - version bump to 15 Since version 15 (TASKSTATS_VERSION=15) the new layout of the structure adds fields in the middle of the structure, rendering all old software incompatible with newer kernels and software compiled against the new kernel headers incompatible with older kernels. Solution ========= move delay max and delay min to the end of taskstat, and bump the version to 16 after the change [wang.yaxin(a)zte.com.cn: adjust indentation] Link: https://lkml.kernel.org/r/202505192131489882NSciXV4EGd8zzjLuwoOK@zte.com.cn Link: https://lkml.kernel.org/r/20250510155413259V4JNRXxukdDgzsaL0Fo6a@zte.com.cn Fixes: f65c64f311ee ("delayacct: add delay min to record delay peak") Signed-off-by: Wang Yaxin <wang.yaxin(a)zte.com.cn> Signed-off-by: xu xin <xu.xin16(a)zte.com.cn> Signed-off-by: Kun Jiang <jiang.kun2(a)zte.com.cn> Reviewed-by: Yang Yang <yang.yang29(a)zte.com.cn> Cc: Balbir Singh <bsingharora(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/uapi/linux/taskstats.h | 47 +++++++++++++++++++------------ 1 file changed, 29 insertions(+), 18 deletions(-) --- a/include/uapi/linux/taskstats.h~taskstats-fix-struct-taskstats-breaks-backward-compatibility-since-version-15 +++ a/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 15 +#define TASKSTATS_VERSION 16 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -72,8 +72,6 @@ struct taskstats { */ __u64 cpu_count __attribute__((aligned(8))); __u64 cpu_delay_total; - __u64 cpu_delay_max; - __u64 cpu_delay_min; /* Following four fields atomically updated using task->delays->lock */ @@ -82,14 +80,10 @@ struct taskstats { */ __u64 blkio_count; __u64 blkio_delay_total; - __u64 blkio_delay_max; - __u64 blkio_delay_min; /* Delay waiting for page fault I/O (swap in only) */ __u64 swapin_count; __u64 swapin_delay_total; - __u64 swapin_delay_max; - __u64 swapin_delay_min; /* cpu "wall-clock" running time * On some architectures, value will adjust for cpu time stolen @@ -172,14 +166,11 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; - __u64 freepages_delay_max; - __u64 freepages_delay_min; + /* Delay waiting for thrashing page */ __u64 thrashing_count; __u64 thrashing_delay_total; - __u64 thrashing_delay_max; - __u64 thrashing_delay_min; /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ @@ -187,8 +178,6 @@ struct taskstats { /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; - __u64 compact_delay_max; - __u64 compact_delay_min; /* v12 begin */ __u32 ac_tgid; /* thread group ID */ @@ -210,15 +199,37 @@ struct taskstats { /* v13: Delay waiting for write-protect copy */ __u64 wpcopy_count; __u64 wpcopy_delay_total; - __u64 wpcopy_delay_max; - __u64 wpcopy_delay_min; /* v14: Delay waiting for IRQ/SOFTIRQ */ __u64 irq_count; __u64 irq_delay_total; - __u64 irq_delay_max; - __u64 irq_delay_min; - /* v15: add Delay max */ + + /* v15: add Delay max and Delay min */ + + /* v16: move Delay max and Delay min to the end of taskstat */ + __u64 cpu_delay_max; + __u64 cpu_delay_min; + + __u64 blkio_delay_max; + __u64 blkio_delay_min; + + __u64 swapin_delay_max; + __u64 swapin_delay_min; + + __u64 freepages_delay_max; + __u64 freepages_delay_min; + + __u64 thrashing_delay_max; + __u64 thrashing_delay_min; + + __u64 compact_delay_max; + __u64 compact_delay_min; + + __u64 wpcopy_delay_max; + __u64 wpcopy_delay_min; + + __u64 irq_delay_max; + __u64 irq_delay_min; }; _ Patches currently in -mm which might be from wang.yaxin(a)zte.com.cn are

2 weeks, 4 days

1
0
0 0

[merged mm-hotfixes-stable] mm-fix-vm_uffd_minor-==-vm_shadow_stack-on-userfaultfd=y-arm64_gcs=y.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: fix VM_UFFD_MINOR == VM_SHADOW_STACK on USERFAULTFD=y && ARM64_GCS=y has been removed from the -mm tree. Its filename was mm-fix-vm_uffd_minor-==-vm_shadow_stack-on-userfaultfd=y-arm64_gcs=y.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Florent Revest <revest(a)chromium.org> Subject: mm: fix VM_UFFD_MINOR == VM_SHADOW_STACK on USERFAULTFD=y && ARM64_GCS=y Date: Wed, 7 May 2025 15:09:57 +0200 On configs with CONFIG_ARM64_GCS=y, VM_SHADOW_STACK is bit 38. On configs with CONFIG_HAVE_ARCH_USERFAULTFD_MINOR=y (selected by CONFIG_ARM64 when CONFIG_USERFAULTFD=y), VM_UFFD_MINOR is _also_ bit 38. This bit being shared by two different VMA flags could lead to all sorts of unintended behaviors. Presumably, a process could maybe call into userfaultfd in a way that disables the shadow stack vma flag. I can't think of any attack where this would help (presumably, if an attacker tries to disable shadow stacks, they are trying to hijack control flow so can't arbitrarily call into userfaultfd yet anyway) but this still feels somewhat scary. Link: https://lkml.kernel.org/r/20250507131000.1204175-2-revest@chromium.org Fixes: ae80e1629aea ("mm: Define VM_SHADOW_STACK for arm64 when we support GCS") Signed-off-by: Florent Revest <revest(a)chromium.org> Reviewed-by: Mark Brown <broonie(a)kernel.org> Cc: Borislav Betkov <bp(a)alien8.de> Cc: Brendan Jackman <jackmanb(a)google.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Florent Revest <revest(a)chromium.org> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Thiago Jung Bauermann <thiago.bauermann(a)linaro.org> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: Will Deacon <will(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/include/linux/mm.h~mm-fix-vm_uffd_minor-==-vm_shadow_stack-on-userfaultfd=y-arm64_gcs=y +++ a/include/linux/mm.h @@ -385,7 +385,7 @@ extern unsigned int kobjsize(const void #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR -# define VM_UFFD_MINOR_BIT 38 +# define VM_UFFD_MINOR_BIT 41 # define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ # define VM_UFFD_MINOR VM_NONE _ Patches currently in -mm which might be from revest(a)chromium.org are

2 weeks, 4 days

1
0
0 0

[merged mm-hotfixes-stable] mm-mmap-map-map_stack-to-vm_nohugepage-only-if-thp-is-enabled.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: mmap: map MAP_STACK to VM_NOHUGEPAGE only if THP is enabled has been removed from the -mm tree. Its filename was mm-mmap-map-map_stack-to-vm_nohugepage-only-if-thp-is-enabled.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Ignacio Moreno Gonzalez <Ignacio.MorenoGonzalez(a)kuka.com> Subject: mm: mmap: map MAP_STACK to VM_NOHUGEPAGE only if THP is enabled Date: Wed, 07 May 2025 15:28:06 +0200 commit c4608d1bf7c6 ("mm: mmap: map MAP_STACK to VM_NOHUGEPAGE") maps the mmap option MAP_STACK to VM_NOHUGEPAGE. This is also done if CONFIG_TRANSPARENT_HUGEPAGE is not defined. But in that case, the VM_NOHUGEPAGE does not make sense. I discovered this issue when trying to use the tool CRIU to checkpoint and restore a container. Our running kernel is compiled without CONFIG_TRANSPARENT_HUGEPAGE. CRIU parses the output of /proc/<pid>/smaps and saves the "nh" flag. When trying to restore the container, CRIU fails to restore the "nh" mappings, since madvise() MADV_NOHUGEPAGE always returns an error because CONFIG_TRANSPARENT_HUGEPAGE is not defined. Link: https://lkml.kernel.org/r/20250507-map-map_stack-to-vm_nohugepage-only-if-t… Fixes: c4608d1bf7c6 ("mm: mmap: map MAP_STACK to VM_NOHUGEPAGE") Signed-off-by: Ignacio Moreno Gonzalez <Ignacio.MorenoGonzalez(a)kuka.com> Acked-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reviewed-by: Yang Shi <yang(a)os.amperecomputing.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mman.h | 2 ++ 1 file changed, 2 insertions(+) --- a/include/linux/mman.h~mm-mmap-map-map_stack-to-vm_nohugepage-only-if-thp-is-enabled +++ a/include/linux/mman.h @@ -155,7 +155,9 @@ calc_vm_flag_bits(struct file *file, uns return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | +#ifdef CONFIG_TRANSPARENT_HUGEPAGE _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | +#endif arch_calc_vm_flag_bits(file, flags); } _ Patches currently in -mm which might be from Ignacio.MorenoGonzalez(a)kuka.com are

2 weeks, 4 days

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2025