5.7.7-rc1 review
Subsystems (3)
Sasha Levin
maintainerPATCH 156/265 cxgb4: move PTP lock and unlock to caller in Tx path
In reply to Sasha LevinFrom: Rahul Lakkireddy <[email protected]>
[ Upstream commit 030c98824deaba205787af501a074b3d7f46e32e ]
Check for whether PTP is enabled or not at the caller and perform locking/unlocking at the caller.
Fixes following sparse warning:
sge.c:1641:26: warning: context imbalance in 'cxgb4_eth_xmit' - different lock contexts for basic block
--- drivers/net/ethernet/chelsio/cxgb4/sge.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-)
drivers/net/ethernet/chelsio/cxgb4/sge.c +11 -12
@@ -1425,12 +1425,10 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) qidx =skb_get_queue_mapping (skb);if (ptp_enabled) { -spin_lock (&adap->ptp_lock);if (!(adap->ptp_tx_skb)) {skb_shinfo (skb)->tx_flags |=SKBTX_IN_PROGRESS ; adap->ptp_tx_skb =skb_get (skb); }else { -spin_unlock (&adap->ptp_lock); goto out_free; } q = &adap->sge.ptptxq;
@@ -1444,11 +1442,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)#ifdef CONFIG_CHELSIO_T4_FCOE ret =cxgb_fcoe_offload (skb, adap, pi, &cntrl); -if (unlikely (ret == -ENOTSUPP )) { -if (ptp_enabled) -spin_unlock (&adap->ptp_lock); +if (unlikely (ret == -EOPNOTSUPP )) goto out_free; - }#endif /* CONFIG_CHELSIO_T4_FCOE */ chip_ver =CHELSIO_CHIP_VERSION (adap->params.chip);
@@ -1461,8 +1456,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)dev_err (adap->pdev_dev,"%s: Tx ring %u full while queue awake!\n" , dev->name, qidx); -if (ptp_enabled) -spin_unlock (&adap->ptp_lock);return NETDEV_TX_BUSY ; }
@@ -1481,8 +1474,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) unlikely(cxgb4_map_skb(adap->pdev_dev, skb, sgl_sdesc->addr) < 0)) {memset (sgl_sdesc->addr,0 ,sizeof (sgl_sdesc->addr)); q->mapping_err++; -if (ptp_enabled) -spin_unlock (&adap->ptp_lock); goto out_free; }
@@ -1630,8 +1621,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)txq_advance (&q->q, ndesc);cxgb4_ring_tx_db (adap, &q->q, ndesc); -if (ptp_enabled) -spin_unlock (&adap->ptp_lock);return NETDEV_TX_OK ; out_free:
@@ -2365,6 +2354,16 @@ netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev)if (unlikely (qid >= pi->nqsets))return cxgb4_ethofld_xmit (skb, dev); +if (is_ptp_enabled (skb, dev)) { +struct adapter *adap =netdev2adap (dev); +netdev_tx_t ret; + +spin_lock (&adap->ptp_lock); + ret =cxgb4_eth_xmit (skb, dev); +spin_unlock (&adap->ptp_lock); +return ret; + } +return cxgb4_eth_xmit (skb, dev); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 157/265 ARM: imx5: add missing put_device() call in imx_suspend_alloc_ocram()
In reply to Sasha LevinFrom: yu kuai <[email protected]>
[ Upstream commit 586745f1598ccf71b0a5a6df2222dee0a865954e ]
if of_find_device_by_node() succeed, imx_suspend_alloc_ocram() doesn't have a corresponding put_device(). Thus add a jump target to fix the exception handling for this function implementation.
--- arch/arm/mach-imx/pm-imx5.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
arch/arm/mach-imx/pm-imx5.c +4 -2
@@ -295,14 +295,14 @@ static int __init imx_suspend_alloc_ocram(if (!ocram_pool) {pr_warn ("%s: ocram pool unavailable!\n" , __func__); ret = -ENODEV ; - goto put_node; + goto put_device; } ocram_base =gen_pool_alloc (ocram_pool, size);if (!ocram_base) {pr_warn ("%s: unable to alloc ocram!\n" , __func__); ret = -ENOMEM ; - goto put_node; + goto put_device; } phys =gen_pool_virt_to_phys (ocram_pool, ocram_base);
@@ -312,6 +312,8 @@ static int __init imx_suspend_alloc_ocram(if (virt_out) *virt_out = virt; +put_device: +put_device (&pdev->dev); put_node:of_node_put (node);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 158/265 scsi: lpfc: Avoid another null dereference in lpfc_sli4_hba_unset()
In reply to Sasha LevinFrom: SeongJae Park <[email protected]>
[ Upstream commit 46da547e21d6cefceec3fb3dba5ebbca056627fc ]
Commit cdb42becdd40 ("scsi: lpfc: Replace io_channels for nvme and fcp with general hdw_queues per cpu") has introduced static checker warnings for potential null dereferences in 'lpfc_sli4_hba_unset()' and commit 1ffdd2c0440d ("scsi: lpfc: resolve static checker warning in lpfc_sli4_hba_unset") has tried to fix it. However, yet another potential null dereference is remaining. This commit fixes it.
This bug was discovered and resolved using Coverity Static Analysis Security Testing (SAST) by Synopsys, Inc.
--- drivers/scsi/lpfc/lpfc_init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/scsi/lpfc/lpfc_init.c +2 -1
@@ -11895,7 +11895,8 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba)lpfc_sli4_xri_exchange_busy_wait (phba);/* per-phba callback de-registration for hotplug event */ -lpfc_cpuhp_remove (phba); +if (phba->pport) +lpfc_cpuhp_remove (phba);/* Disable PCI subsystem interrupt */ lpfc_sli4_disable_intr (phba);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 159/265 usb: gadget: udc: Potential Oops in error handling code
In reply to Sasha LevinFrom: Dan Carpenter <[email protected]>
[ Upstream commit e55f3c37cb8d31c7e301f46396b2ac6a19eb3a7c ]
If this is in "transceiver" mode the the ->qwork isn't required and is a NULL pointer. This can lead to a NULL dereference when we call destroy_workqueue(udc->qwork).
--- drivers/usb/gadget/udc/mv_udc_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/usb/gadget/udc/mv_udc_core.c +2 -1
@@ -2313,7 +2313,8 @@ static int mv_udc_probe(struct platform_device *pdev)return 0 ; err_create_workqueue: -destroy_workqueue (udc->qwork); +if (udc->qwork) +destroy_workqueue (udc->qwork); err_destroy_dma:dma_pool_destroy (udc->dtd_pool); err_free_dma:
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 160/265 usb: renesas_usbhs: getting residue from callback_result
In reply to Sasha LevinFrom: Yoshihiro Shimoda <[email protected]>
[ Upstream commit ea0efd687b01355cd799c8643d0c636ba4859ffc ]
This driver assumed that dmaengine_tx_status() could return the residue even if the transfer was completed. However, this was not correct usage [1] and this caused to break getting the residue after the commit 24461d9792c2 ("dmaengine:
virt-dma: Fix access after free in vchan_complete()") actually. So, this is possible to get wrong received size if the usb controller gets a short packet. For example, g_zero driver causes "bad OUT byte" errors.
The usb-dmac driver will support the callback_result, so this driver can use it to get residue correctly. Note that even if the usb-dmac driver has not supported the callback_result yet, this patch doesn't cause any side-effects.
[1]
https://lore.kernel.org/dmaengine/20200616165550.GP2324254@vkoul-mobl/
--- drivers/usb/renesas_usbhs/fifo.c | 23 +++++++++++++---------- drivers/usb/renesas_usbhs/fifo.h | 2 +- 2 files changed, 14 insertions(+), 11 deletions(-)
drivers/usb/renesas_usbhs/fifo.c +13 -10
@@ -803,7 +803,8 @@ static int __usbhsf_dma_map_ctrl(struct usbhs_pkt *pkt, int map)return info->dma_map_ctrl (chan->device->dev, pkt, map); } -static void usbhsf_dma_complete (void *arg); +static void usbhsf_dma_complete (void *arg, +const struct dmaengine_result *result);static void usbhsf_dma_xfer_preparing (struct usbhs_pkt *pkt) {struct usbhs_pipe *pipe = pkt->pipe;
@@ -813,6 +814,7 @@ static void usbhsf_dma_xfer_preparing(struct usbhs_pkt *pkt)struct dma_chan *chan;struct device *dev =usbhs_priv_to_dev (priv);enum dma_transfer_direction dir; +dma_cookie_t cookie; fifo =usbhs_pipe_to_fifo (pipe);if (!fifo)
@@ -827,11 +829,11 @@ static void usbhsf_dma_xfer_preparing(struct usbhs_pkt *pkt)if (!desc)return ; - desc->callback = usbhsf_dma_complete; - desc->callback_param = pipe; + desc->callback_result = usbhsf_dma_complete; + desc->callback_param = pkt; - pkt->cookie =dmaengine_submit (desc); -if (pkt->cookie <0 ) { + cookie =dmaengine_submit (desc); +if (cookie <0 ) {dev_err (dev,"Failed to submit dma descriptor\n" );return ; }
@@ -1152,12 +1154,10 @@ static size_t usbhs_dma_calc_received_size(struct usbhs_pkt *pkt, struct dma_chan *chan, int dtln) {struct usbhs_pipe *pipe = pkt->pipe; -struct dma_tx_state state;size_t received_size;int maxp =usbhs_pipe_get_maxpacket (pipe); -dmaengine_tx_status (chan, pkt->cookie, &state); - received_size = pkt->length - state.residue; + received_size = pkt->length - pkt->dma_result->residue;if (dtln) { received_size -=USBHS_USB_DMAC_XFER_SIZE ;
@@ -1363,13 +1363,16 @@ static int usbhsf_irq_ready(struct usbhs_priv *priv,return 0 ; } -static void usbhsf_dma_complete (void *arg) +static void usbhsf_dma_complete (void *arg, +const struct dmaengine_result *result) { -struct usbhs_pipe *pipe = arg; +struct usbhs_pkt *pkt = arg; +struct usbhs_pipe *pipe = pkt->pipe;struct usbhs_priv *priv =usbhs_pipe_to_priv (pipe);struct device *dev =usbhs_priv_to_dev (priv);int ret; + pkt->dma_result = result; ret =usbhsf_pkt_handler (pipe,USBHSF_PKT_DMA_DONE );if (ret <0 ) dev_err(dev, "dma_complete run_error %d : %d\n",
drivers/usb/renesas_usbhs/fifo.h +1 -1
@@ -50,7 +50,7 @@ struct usbhs_pkt { struct usbhs_pkt *pkt);struct work_struct work;dma_addr_t dma; -dma_cookie_t cookie; +const struct dmaengine_result *dma_result;void *buf;int length;int trans;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 161/265 nvme-multipath: set bdi capabilities once
In reply to Sasha LevinFrom: Keith Busch <[email protected]>
[ Upstream commit b2ce4d90690bd29ce5b554e203cd03682dd59697 ]
The queues' backing device info capabilities don't change with each namespace revalidation. Set it only when each path's request_queue is initially added to a multipath queue.
--- drivers/nvme/host/core.c | 7 ------- drivers/nvme/host/multipath.c | 8 ++++++++ 2 files changed, 8 insertions(+), 7 deletions(-)
drivers/nvme/host/core.c +0 -7
@@ -1910,13 +1910,6 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)if (ns->head->disk) {nvme_update_disk_info (ns->head->disk, ns, id);blk_queue_stack_limits (ns->head->disk->queue, ns->queue); -if (bdi_cap_stable_pages_required (ns->queue->backing_dev_info)) { -struct backing_dev_info *info = - ns->head->disk->queue->backing_dev_info; - - info->capabilities |=BDI_CAP_STABLE_WRITES ; - } -revalidate_disk (ns->head->disk); }#endif
drivers/nvme/host/multipath.c +8 -0
@@ -3,6 +3,7 @@* Copyright (c) 2017-2018 Christoph Hellwig. */ +#include <linux/backing-dev.h> #include <linux/moduleparam.h> #include <trace/events/block.h> #include "nvme.h"
@@ -666,6 +667,13 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)nvme_mpath_set_live (ns);mutex_unlock (&ns->head->lock); } + +if (bdi_cap_stable_pages_required (ns->queue->backing_dev_info)) { +struct backing_dev_info *info = + ns->head->disk->queue->backing_dev_info; + + info->capabilities |=BDI_CAP_STABLE_WRITES ; + } }void nvme_mpath_remove_disk (struct nvme_ns_head *head)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 162/265 nvme: fix possible deadlock when I/O is blocked
In reply to Sasha LevinFrom: Sagi Grimberg <[email protected]>
[ Upstream commit 3b4b19721ec652ad2c4fe51dfbe5124212b5f581 ]
Revert fab7772bfbcf ("nvme-multipath: revalidate nvme_ns_head gendisk in nvme_validate_ns")
When adding a new namespace to the head disk (via nvme_mpath_set_live) we will see partition scan which triggers I/O on the mpath device node. This process will usually be triggered from the scan_work which holds the scan_lock. If I/O blocks (if we got ana change currently have only available paths but none are accessible) this can deadlock on the head disk bd_mutex as both partition scan I/O takes it, and head disk revalidation takes it to check for resize (also triggered from scan_work on a different path). See trace [1].
The mpath disk revalidation was originally added to detect online disk size change, but this is no longer needed since commit cb224c3af4df ("nvme: Convert to use set_capacity_revalidate_and_notify") which already updates resize info without unnecessarily revalidating the disk (the mpath disk doesn't even implement .revalidate_disk fop).
[1]:
--
kernel: INFO: task kworker/u65:9:494 blocked for more than 241 seconds. kernel: Tainted: G OE 5.3.5-050305-generic #201910071830 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kernel: kworker/u65:9 D 0 494 2 0x80004000 kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: schedule_preempt_disabled+0xe/0x10 kernel: __mutex_lock.isra.0+0x182/0x4f0 kernel: __mutex_lock_slowpath+0x13/0x20 kernel: mutex_lock+0x2e/0x40 kernel: revalidate_disk+0x63/0xa0 kernel: __nvme_revalidate_disk+0xfe/0x110 [nvme_core] kernel: nvme_revalidate_disk+0xa4/0x160 [nvme_core] kernel: ? evict+0x14c/0x1b0 kernel: revalidate_disk+0x2b/0xa0 kernel: nvme_validate_ns+0x49/0x940 [nvme_core] kernel: ? blk_mq_free_request+0xd2/0x100 kernel: ? __nvme_submit_sync_cmd+0xbe/0x1e0 [nvme_core] kernel: nvme_scan_work+0x24f/0x380 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x249/0x400 kernel: kthread+0x104/0x140 kernel: ? process_one_work+0x380/0x380 kernel: ? kthread_park+0x80/0x80 kernel: ret_from_fork+0x1f/0x40 ... kernel: INFO: task kworker/u65:1:2630 blocked for more than 241 seconds. kernel: Tainted: G OE 5.3.5-050305-generic #201910071830 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kernel: kworker/u65:1 D 0 2630 2 0x80004000 kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: io_schedule+0x16/0x40 kernel: do_read_cache_page+0x438/0x830 kernel: ? __switch_to_asm+0x34/0x70 kernel: ? file_fdatawait_range+0x30/0x30 kernel: read_cache_page+0x12/0x20 kernel: read_dev_sector+0x27/0xc0 kernel: read_lba+0xc1/0x220 kernel: ? kmem_cache_alloc_trace+0x19c/0x230 kernel: efi_partition+0x1e6/0x708 kernel: ? vsnprintf+0x39e/0x4e0 kernel: ? snprintf+0x49/0x60 kernel: check_partition+0x154/0x244 kernel: rescan_partitions+0xae/0x280 kernel: __blkdev_get+0x40f/0x560 kernel: blkdev_get+0x3d/0x140 kernel: __device_add_disk+0x388/0x480 kernel: device_add_disk+0x13/0x20 kernel: nvme_mpath_set_live+0x119/0x140 [nvme_core] kernel: nvme_update_ns_ana_state+0x5c/0x60 [nvme_core] kernel: nvme_set_ns_ana_state+0x1e/0x30 [nvme_core] kernel: nvme_parse_ana_log+0xa1/0x180 [nvme_core] kernel: ? nvme_update_ns_ana_state+0x60/0x60 [nvme_core] kernel: nvme_mpath_add_disk+0x47/0x90 [nvme_core] kernel: nvme_validate_ns+0x396/0x940 [nvme_core] kernel: ? blk_mq_free_request+0xd2/0x100 kernel: nvme_scan_work+0x24f/0x380 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x249/0x400 kernel: kthread+0x104/0x140 kernel: ? process_one_work+0x380/0x380 kernel: ? kthread_park+0x80/0x80 kernel: ret_from_fork+0x1f/0x40
--
in nvme_validate_ns")
--- drivers/nvme/host/core.c | 1 - 1 file changed, 1 deletion(-)
drivers/nvme/host/core.c +0 -1
@@ -1910,7 +1910,6 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)if (ns->head->disk) {nvme_update_disk_info (ns->head->disk, ns, id);blk_queue_stack_limits (ns->head->disk->queue, ns->queue); -revalidate_disk (ns->head->disk); }#endif }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 163/265 nvme-multipath: fix deadlock between ana_work and scan_work
In reply to Sasha LevinFrom: Anton Eidelman <[email protected]>
[ Upstream commit 489dd102a2c7c94d783a35f9412eb085b8da1aa4 ]
When scan_work calls nvme_mpath_add_disk() this holds ana_lock and invokes nvme_parse_ana_log(), which may issue IO
in device_add_disk() and hang waiting for an accessible path. While nvme_mpath_set_live() only called when nvme_state_is_live(), a transition may cause NVME_SC_ANA_TRANSITION and requeue the IO.
In order to recover and complete the IO ana_work on the same ctrl should be able to update the path state and remove NVME_NS_ANA_PENDING.
The deadlock occurs because scan_work keeps holding ana_lock, so ana_work hangs [1].
Fix:
Now nvme_mpath_add_disk() uses nvme_parse_ana_log() to obtain a copy of the ANA group desc, and then calls nvme_update_ns_ana_state() without holding ana_lock.
[1]:
kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: io_schedule+0x16/0x40 kernel: do_read_cache_page+0x438/0x830 kernel: read_cache_page+0x12/0x20 kernel: read_dev_sector+0x27/0xc0 kernel: read_lba+0xc1/0x220 kernel: efi_partition+0x1e6/0x708 kernel: check_partition+0x154/0x244 kernel: rescan_partitions+0xae/0x280 kernel: __blkdev_get+0x40f/0x560 kernel: blkdev_get+0x3d/0x140 kernel: __device_add_disk+0x388/0x480 kernel: device_add_disk+0x13/0x20 kernel: nvme_mpath_set_live+0x119/0x140 [nvme_core] kernel: nvme_update_ns_ana_state+0x5c/0x60 [nvme_core] kernel: nvme_set_ns_ana_state+0x1e/0x30 [nvme_core] kernel: nvme_parse_ana_log+0xa1/0x180 [nvme_core] kernel: nvme_mpath_add_disk+0x47/0x90 [nvme_core] kernel: nvme_validate_ns+0x396/0x940 [nvme_core] kernel: nvme_scan_work+0x24f/0x380 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x249/0x400 kernel: kthread+0x104/0x140
kernel: Workqueue: nvme-wq nvme_ana_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: schedule_preempt_disabled+0xe/0x10 kernel: __mutex_lock.isra.0+0x182/0x4f0 kernel: ? __switch_to_asm+0x34/0x70 kernel: ? select_task_rq_fair+0x1aa/0x5c0 kernel: ? kvm_sched_clock_read+0x11/0x20 kernel: ? sched_clock+0x9/0x10 kernel: __mutex_lock_slowpath+0x13/0x20 kernel: mutex_lock+0x2e/0x40 kernel: nvme_read_ana_log+0x3a/0x100 [nvme_core] kernel: nvme_ana_work+0x15/0x20 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x4d/0x400 kernel: kthread+0x104/0x140 kernel: ? process_one_work+0x380/0x380 kernel: ? kthread_park+0x80/0x80 kernel: ret_from_fork+0x35/0x40
--- drivers/nvme/host/multipath.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-)
drivers/nvme/host/multipath.c +16 -8
@@ -641,26 +641,34 @@ static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr, }DEVICE_ATTR_RO (ana_state); -static int nvme_set_ns_ana_state (struct nvme_ctrl *ctrl, +static int nvme_lookup_ana_group_desc (struct nvme_ctrl *ctrl,struct nvme_ana_group_desc *desc,void *data) { -struct nvme_ns *ns = data; +struct nvme_ana_group_desc *dst = data; -if (ns->ana_grpid ==le32_to_cpu (desc->grpid)) { -nvme_update_ns_ana_state (desc, ns); -return -ENXIO ;/* just break out of the loop */ - } +if (desc->grpid != dst->grpid) +return 0 ; -return 0 ; + *dst = *desc; +return -ENXIO ;/* just break out of the loop */ }void nvme_mpath_add_disk (struct nvme_ns *ns,struct nvme_id_ns *id) {if (nvme_ctrl_use_ana (ns->ctrl)) { +struct nvme_ana_group_desc desc = { + .grpid = id->anagrpid, + .state =0 , + }; +mutex_lock (&ns->ctrl->ana_lock); ns->ana_grpid =le32_to_cpu (id->anagrpid); -nvme_parse_ana_log (ns->ctrl, ns, nvme_set_ns_ana_state); +nvme_parse_ana_log (ns->ctrl, &desc, nvme_lookup_ana_group_desc);mutex_unlock (&ns->ctrl->ana_lock); +if (desc.state) { +/* found the group desc: update */ +nvme_update_ns_ana_state (&desc, ns); + } }else {mutex_lock (&ns->head->lock); ns->ana_state =NVME_ANA_OPTIMIZED ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 164/265 nvme: don't protect ns mutation with ns->head->lock
In reply to Sasha LevinFrom: Sagi Grimberg <[email protected]>
[ Upstream commit e164471dcf19308d154adb69e7760d8ba426a77f ]
Right now ns->head->lock is protecting namespace mutation which is wrong and unneeded. Move it to only protect against head mutations. While we're at it, remove unnecessary ns->head reference as we already have head pointer.
The problem with this is that the head->lock spans mpath disk node I/O that may block under some conditions (if for example the controller is disconnecting or the path became inaccessible), The locking scheme does not allow any other path to enable itself, preventing blocked I/O to complete and forward-progress from there.
This is a preparation patch for the fix in a subsequent patch where the disk I/O will also be done outside the head->lock.
--- drivers/nvme/host/multipath.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-)
drivers/nvme/host/multipath.c +4 -8
@@ -410,11 +410,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) {struct nvme_ns_head *head = ns->head; -lockdep_assert_held (&ns->head->lock); -if (!head->disk)return ; +mutex_lock (&head->lock);if (!(head->disk->flags &GENHD_FL_UP ))device_add_disk (&head->subsys->dev, head->disk, nvme_ns_id_attr_groups);
@@ -427,9 +426,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)__nvme_find_path (head, node);srcu_read_unlock (&head->srcu, srcu_idx); } +mutex_unlock (&head->lock); -synchronize_srcu (&ns->head->srcu); -kblockd_schedule_work (&ns->head->requeue_work); +synchronize_srcu (&head->srcu); +kblockd_schedule_work (&head->requeue_work); } static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
@@ -484,14 +484,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state)static void nvme_update_ns_ana_state (struct nvme_ana_group_desc *desc,struct nvme_ns *ns) { -mutex_lock (&ns->head->lock); ns->ana_grpid =le32_to_cpu (desc->grpid); ns->ana_state = desc->state;clear_bit (NVME_NS_ANA_PENDING , &ns->flags);if (nvme_state_is_live (ns->ana_state))nvme_mpath_set_live (ns); -mutex_unlock (&ns->head->lock); } static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
@@ -670,10 +668,8 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)nvme_update_ns_ana_state (&desc, ns); } }else { -mutex_lock (&ns->head->lock); ns->ana_state =NVME_ANA_OPTIMIZED ;nvme_mpath_set_live (ns); -mutex_unlock (&ns->head->lock); }if (bdi_cap_stable_pages_required (ns->queue->backing_dev_info)) {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 165/265 nvme-multipath: fix deadlock due to head->lock
In reply to Sasha LevinFrom: Anton Eidelman <[email protected]>
[ Upstream commit d8a22f85609fadb46ba699e0136cc3ebdeebff79 ]
In the following scenario scan_work and ana_work will deadlock:
When scan_work calls nvme_mpath_add_disk() this holds ana_lock and invokes nvme_parse_ana_log(), which may issue IO in device_add_disk() and hang waiting for an accessible path.
While nvme_mpath_set_live() only called when nvme_state_is_live(), a transition may cause NVME_SC_ANA_TRANSITION and requeue the IO.
Since nvme_mpath_set_live() holds ns->head->lock, an ana_work on ANY ctrl will not be able to complete nvme_mpath_set_live() on the same ns->head, which is required in order to update the new accessible path and remove NVME_NS_ANA_PENDING.. Therefore IO never completes: deadlock [1].
Fix:
Move device_add_disk out of the head->lock and protect it with an atomic test_and_set for a new NVME_NS_HEAD_HAS_DISK bit.
[1]:
kernel: INFO: task kworker/u8:2:160 blocked for more than 120 seconds. kernel: Tainted: G OE 5.3.5-050305-generic #201910071830 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kernel: kworker/u8:2 D 0 160 2 0x80004000 kernel: Workqueue: nvme-wq nvme_ana_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: schedule_preempt_disabled+0xe/0x10 kernel: __mutex_lock.isra.0+0x182/0x4f0 kernel: __mutex_lock_slowpath+0x13/0x20 kernel: mutex_lock+0x2e/0x40 kernel: nvme_update_ns_ana_state+0x22/0x60 [nvme_core] kernel: nvme_update_ana_state+0xca/0xe0 [nvme_core] kernel: nvme_parse_ana_log+0xa1/0x180 [nvme_core] kernel: nvme_read_ana_log+0x76/0x100 [nvme_core] kernel: nvme_ana_work+0x15/0x20 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x4d/0x400 kernel: kthread+0x104/0x140 kernel: ret_from_fork+0x35/0x40 kernel: INFO: task kworker/u8:4:439 blocked for more than 120 seconds. kernel: Tainted: G OE 5.3.5-050305-generic #201910071830 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kernel: kworker/u8:4 D 0 439 2 0x80004000 kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: io_schedule+0x16/0x40 kernel: do_read_cache_page+0x438/0x830 kernel: read_cache_page+0x12/0x20 kernel: read_dev_sector+0x27/0xc0 kernel: read_lba+0xc1/0x220 kernel: efi_partition+0x1e6/0x708 kernel: check_partition+0x154/0x244 kernel: rescan_partitions+0xae/0x280 kernel: __blkdev_get+0x40f/0x560 kernel: blkdev_get+0x3d/0x140 kernel: __device_add_disk+0x388/0x480 kernel: device_add_disk+0x13/0x20 kernel: nvme_mpath_set_live+0x119/0x140 [nvme_core] kernel: nvme_update_ns_ana_state+0x5c/0x60 [nvme_core] kernel: nvme_mpath_add_disk+0xbe/0x100 [nvme_core] kernel: nvme_validate_ns+0x396/0x940 [nvme_core] kernel: nvme_scan_work+0x256/0x390 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x4d/0x400 kernel: kthread+0x104/0x140 kernel: ret_from_fork+0x35/0x40
--- drivers/nvme/host/multipath.c | 4 ++-- drivers/nvme/host/nvme.h | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-)
drivers/nvme/host/multipath.c +2 -2
@@ -413,11 +413,11 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)if (!head->disk)return ; -mutex_lock (&head->lock); -if (!(head->disk->flags &GENHD_FL_UP )) +if (!test_and_set_bit (NVME_NSHEAD_DISK_LIVE , &head->flags))device_add_disk (&head->subsys->dev, head->disk, nvme_ns_id_attr_groups); +mutex_lock (&head->lock);if (nvme_path_is_optimized (ns)) {int node, srcu_idx;
drivers/nvme/host/nvme.h +2 -0
@@ -359,6 +359,8 @@ struct nvme_ns_head {spinlock_t requeue_lock;struct work_struct requeue_work;struct mutex lock; +unsigned long flags; +#define NVME_NSHEAD_DISK_LIVE 0struct nvme_ns __rcu *current_path[];#endif };
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 166/265 qed: add missing error test for DBG_STATUS_NO_MATCHING_FRAMING_MODE
In reply to Sasha LevinFrom: Colin Ian King <[email protected]>
[ Upstream commit a51243860893615b457b149da1ef5df0a4f1ffc2 ]
The error DBG_STATUS_NO_MATCHING_FRAMING_MODE was added to the enum enum dbg_status however there is a missing corresponding entry for this in the array s_status_str. This causes an out-of-bounds read when indexing into the last entry of s_status_str. Fix this by adding in the missing entry.
Addresses-Coverity: ("Out-of-bounds read").
--- drivers/net/ethernet/qlogic/qed/qed_debug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/ethernet/qlogic/qed/qed_debug.c +2 -1
@@ -5568,7 +5568,8 @@ static const char * const s_status_str[] = {/* DBG_STATUS_INVALID_FILTER_TRIGGER_DWORDS */ "The filter/trigger constraint dword offsets are not enabled for recording" , - +/* DBG_STATUS_NO_MATCHING_FRAMING_MODE */ +"No matching framing mode" ,/* DBG_STATUS_VFC_READ_ERROR */ "Error reading from VFC",
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 167/265 netfilter: ipset: fix unaligned atomic access
In reply to Sasha LevinFrom: Russell King <[email protected]>
[ Upstream commit 715028460082d07a7ec6fcd87b14b46784346a72 ]
When using ip_set with counters and comment, traffic causes the kernel to panic on 32-bit ARM:
Alignment trap: not handling instruction e1b82f9f at [<bf01b0dc>] Unhandled fault: alignment exception (0x221) at 0xea08133c PC is at ip_set_match_extensions+0xe0/0x224 [ip_set]
The problem occurs when we try to update the 64-bit counters - the faulting address above is not 64-bit aligned. The problem occurs due to the way elements are allocated, for example:
set->dsize = ip_set_elem_len(set, tb, 0, 0); map = ip_set_alloc(sizeof(*map) + elements * set->dsize);
If the element has a requirement for a member to be 64-bit aligned, and set->dsize is not a multiple of 8, but is a multiple of four, then every odd numbered elements will be misaligned - and hitting an atomic64_add() on that element will cause the kernel to panic.
ip_set_elem_len() must return a size that is rounded to the maximum alignment of any extension field stored in the element. This change ensures that is the case.
--- net/netfilter/ipset/ip_set_core.c | 2 ++ 1 file changed, 2 insertions(+)
net/netfilter/ipset/ip_set_core.c +2 -0
@@ -460,6 +460,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len,for (id =0 ; id <IPSET_EXT_ID_MAX ; id++) {if (!add_extension (id, cadt_flags, tb))continue ; +if (align < ip_set_extensions[id].align) + align = ip_set_extensions[id].align; len =ALIGN (len, ip_set_extensions[id].align); set->offset[id] = len; set->extensions |= ip_set_extensions[id].type;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 168/265 net: bcmgenet: use hardware padding of runt frames
In reply to Sasha LevinFrom: Doug Berger <[email protected]>
[ Upstream commit 20d1f2d1b024f6be199a3bedf1578a1d21592bc5 ]
When commit 474ea9cafc45 ("net: bcmgenet: correctly pad short packets") added the call to skb_padto() it should have been located before the nr_frags parameter was read since that value could be changed when padding packets with lengths between 55 and 59 bytes (inclusive).
The use of a stale nr_frags value can cause corruption of the pad data when tx-scatter-gather is enabled. This corruption of the pad can cause invalid checksum computation when hardware offload of tx-checksum is also enabled.
Since the original reason for the padding was corrected by commit 7dd399130efb ("net: bcmgenet: fix skb_len in bcmgenet_xmit_single()") we can remove the software padding all together and make use of hardware padding of short frames as long as the hardware also always appends the FCS value to the frame.
--- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)
drivers/net/ethernet/broadcom/genet/bcmgenet.c +3 -5
@@ -1520,11 +1520,6 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) goto out; } -if (skb_padto (skb,ETH_ZLEN )) { - ret =NETDEV_TX_OK ; - goto out; - } -/* Retain how many bytes will be sent on the wire, without TSB inserted * by transmit checksum offload */
@@ -1571,6 +1566,9 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) len_stat = (size <<DMA_BUFLENGTH_SHIFT ) | (priv->hw_params->qtag_mask <<DMA_TX_QTAG_SHIFT ); +/* Note: if we ever change from DMA_TX_APPEND_CRC below we +* will need to restore software padding of "runt" packets +*/ if (!i) { len_stat |=DMA_TX_APPEND_CRC |DMA_SOP ;if (skb->ip_summed ==CHECKSUM_PARTIAL )
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 169/265 io_uring: fix hanging iopoll in case of -EAGAIN
In reply to Sasha LevinFrom: Pavel Begunkov <[email protected]>
[ Upstream commit cd664b0e35cb1202f40c259a1a5ea791d18c879d ]
io_do_iopoll() won't do anything with a request unless req->iopoll_completed is set. So io_complete_rw_iopoll() has to set it, otherwise io_do_iopoll() will poll a file again and again even though the request of interest was completed long time ago.
Also, remove -EAGAIN check from io_issue_sqe() as it races with the changed lines. The request will take the long way and be resubmitted from io_iopoll*().
io_kiocb's result and iopoll_completed")
--- fs/io_uring.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-)
fs/io_uring.c +2 -7
@@ -1942,10 +1942,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)WRITE_ONCE (req->result, res);/* order with io_poll_complete() checking ->result */ -if (res != -EAGAIN ) { -smp_wmb (); -WRITE_ONCE (req->iopoll_completed,1 ); - } +smp_wmb (); +WRITE_ONCE (req->iopoll_completed,1 ); }/*
@@ -5425,9 +5423,6 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,if ((ctx->flags &IORING_SETUP_IOPOLL ) && req->file) {const bool in_async =io_wq_current_is_worker (); -if (req->result == -EAGAIN ) -return -EAGAIN ; -/* workqueue context doesn't hold uring_lock, grab it now */ if (in_async)mutex_lock (&ctx->uring_lock);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 170/265 clk: sifive: allocate sufficient memory for struct __prci_data
In reply to Sasha LevinFrom: Vincent Chen <[email protected]>
[ Upstream commit d0a5fdf4cc83dabcdea668f971b8a2e916437711 ]
The (struct __prci_data).hw_clks.hws is an array with dynamic elements. Using struct_size(pd, hw_clks.hws, ARRAY_SIZE(__prci_init_clocks)) instead of sizeof(*pd) to get the correct memory size of struct __prci_data for sifive/fu540-prci. After applying this modifications, the kernel runs smoothly with CONFIG_SLAB_FREELIST_RANDOM enabled on the HiFive unleashed board.
--- drivers/clk/sifive/fu540-prci.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/clk/sifive/fu540-prci.c +4 -1
@@ -586,7 +586,10 @@ static int sifive_fu540_prci_probe(struct platform_device *pdev)struct __prci_data *pd;int r; - pd =devm_kzalloc (dev,sizeof (*pd),GFP_KERNEL ); + pd =devm_kzalloc (dev, +struct_size (pd, hw_clks.hws, +ARRAY_SIZE (__prci_init_clocks)), +GFP_KERNEL );if (!pd)return -ENOMEM ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 171/265 i2c: fsi: Fix the port number field in status register
In reply to Sasha LevinFrom: Eddie James <[email protected]>
[ Upstream commit 502035e284cc7e9efef22b01771d822d49698ab9 ]
The port number field in the status register was not correct, so fix it.
--- drivers/i2c/busses/i2c-fsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/i2c/busses/i2c-fsi.c +1 -1
@@ -98,7 +98,7 @@#define I2C_STAT_DAT_REQ BIT(25)#define I2C_STAT_CMD_COMP BIT(24)#define I2C_STAT_STOP_ERR BIT(23) -#define I2C_STAT_MAX_PORT GENMASK(19, 16) +#define I2C_STAT_MAX_PORT GENMASK(22, 16)#define I2C_STAT_ANY_INT BIT(15)#define I2C_STAT_SCL_IN BIT(11)#define I2C_STAT_SDA_IN BIT(10)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 172/265 net: macb: free resources on failure path of at91ether_open()
In reply to Sasha LevinFrom: Claudiu Beznea <[email protected]>
[ Upstream commit 33fdef24c9ac20c68b71b363e423fbf9ad2bfc1e ]
DMA buffers were not freed on failure path of at91ether_open(). Along with changes for freeing the DMA buffers the enable/disable interrupt instructions were moved to at91ether_start()/at91ether_stop() functions and the operations on at91ether_stop() were done in their reverse order (compared with how is done in at91ether_start()):
before this patch the operation order on interface open path was as follows:
1/ alloc DMA buffers
2/ enable tx, rx
3/ enable interrupts
and the order on interface close path was as follows:
1/ disable tx, rx
2/ disable interrupts
3/ free dma buffers.
--- drivers/net/ethernet/cadence/macb_main.c | 116 ++++++++++++++--------- 1 file changed, 73 insertions(+), 43 deletions(-)
drivers/net/ethernet/cadence/macb_main.c +73 -43
@@ -3762,15 +3762,9 @@ static int macb_init(struct platform_device *pdev)static struct sifive_fu540_macb_mgmt *mgmt; -/* Initialize and start the Receiver and Transmit subsystems */ -static int at91ether_start (struct net_device *dev) +static int at91ether_alloc_coherent (struct macb *lp) { -struct macb *lp =netdev_priv (dev);struct macb_queue *q = &lp->queues[0 ]; -struct macb_dma_desc *desc; -dma_addr_t addr; -u32 ctl; -int i; q->rx_ring = dma_alloc_coherent(&lp->pdev->dev, (AT91ETHER_MAX_RX_DESCR *
@@ -3792,6 +3786,43 @@ static int at91ether_start(struct net_device *dev)return -ENOMEM ; } +return 0 ; +} + +static void at91ether_free_coherent (struct macb *lp) +{ +struct macb_queue *q = &lp->queues[0 ]; + +if (q->rx_ring) { +dma_free_coherent (&lp->pdev->dev, +AT91ETHER_MAX_RX_DESCR * +macb_dma_desc_get_size (lp), + q->rx_ring, q->rx_ring_dma); + q->rx_ring =NULL ; + } + +if (q->rx_buffers) { +dma_free_coherent (&lp->pdev->dev, +AT91ETHER_MAX_RX_DESCR * +AT91ETHER_MAX_RBUFF_SZ , + q->rx_buffers, q->rx_buffers_dma); + q->rx_buffers =NULL ; + } +} + +/* Initialize and start the Receiver and Transmit subsystems */ +static int at91ether_start (struct macb *lp) +{ +struct macb_queue *q = &lp->queues[0 ]; +struct macb_dma_desc *desc; +dma_addr_t addr; +u32 ctl; +int i, ret; + + ret =at91ether_alloc_coherent (lp); +if (ret) +return ret; + addr = q->rx_buffers_dma;for (i =0 ; i <AT91ETHER_MAX_RX_DESCR ; i++) { desc =macb_rx_desc (q, i);
@@ -3813,9 +3844,39 @@ static int at91ether_start(struct net_device *dev) ctl =macb_readl (lp,NCR );macb_writel (lp,NCR , ctl |MACB_BIT (RE ) |MACB_BIT (TE )); +/* Enable MAC interrupts */ +macb_writel (lp,IER ,MACB_BIT (RCOMP ) | +MACB_BIT (RXUBR ) | +MACB_BIT (ISR_TUND ) | +MACB_BIT (ISR_RLE ) | +MACB_BIT (TCOMP ) | +MACB_BIT (ISR_ROVR ) | +MACB_BIT (HRESP )); +return 0 ; } +static void at91ether_stop (struct macb *lp) +{ +u32 ctl; + +/* Disable MAC interrupts */ +macb_writel (lp,IDR ,MACB_BIT (RCOMP ) | +MACB_BIT (RXUBR ) | +MACB_BIT (ISR_TUND ) | +MACB_BIT (ISR_RLE ) | +MACB_BIT (TCOMP ) | +MACB_BIT (ISR_ROVR ) | +MACB_BIT (HRESP )); + +/* Disable Receiver and Transmitter */ + ctl =macb_readl (lp,NCR ); +macb_writel (lp,NCR , ctl & ~(MACB_BIT (TE ) |MACB_BIT (RE ))); + +/* Free resources. */ +at91ether_free_coherent (lp); +} +/* Open the ethernet interface */ static int at91ether_open (struct net_device *dev) {
@@ -3835,27 +3896,20 @@ static int at91ether_open(struct net_device *dev)macb_set_hwaddr (lp); - ret =at91ether_start (dev); + ret =at91ether_start (lp);if (ret) goto pm_exit; -/* Enable MAC interrupts */ -macb_writel (lp,IER ,MACB_BIT (RCOMP ) | -MACB_BIT (RXUBR ) | -MACB_BIT (ISR_TUND ) | -MACB_BIT (ISR_RLE ) | -MACB_BIT (TCOMP ) | -MACB_BIT (ISR_ROVR ) | -MACB_BIT (HRESP )); - ret =macb_phylink_connect (lp);if (ret) - goto pm_exit; + goto stop;netif_start_queue (dev);return 0 ; +stop: +at91ether_stop (lp); pm_exit:pm_runtime_put_sync (&lp->pdev->dev);return ret;
@@ -3865,37 +3919,13 @@ pm_exit:static int at91ether_close (struct net_device *dev) {struct macb *lp =netdev_priv (dev); -struct macb_queue *q = &lp->queues[0 ]; -u32 ctl; - -/* Disable Receiver and Transmitter */ - ctl =macb_readl (lp,NCR ); -macb_writel (lp,NCR , ctl & ~(MACB_BIT (TE ) |MACB_BIT (RE ))); - -/* Disable MAC interrupts */ -macb_writel (lp,IDR ,MACB_BIT (RCOMP ) | -MACB_BIT (RXUBR ) | -MACB_BIT (ISR_TUND ) | -MACB_BIT (ISR_RLE ) | -MACB_BIT (TCOMP ) | -MACB_BIT (ISR_ROVR ) | -MACB_BIT (HRESP ));netif_stop_queue (dev);phylink_stop (lp->phylink);phylink_disconnect_phy (lp->phylink); -dma_free_coherent (&lp->pdev->dev, -AT91ETHER_MAX_RX_DESCR * -macb_dma_desc_get_size (lp), - q->rx_ring, q->rx_ring_dma); - q->rx_ring =NULL ; - -dma_free_coherent (&lp->pdev->dev, -AT91ETHER_MAX_RX_DESCR *AT91ETHER_MAX_RBUFF_SZ , - q->rx_buffers, q->rx_buffers_dma); - q->rx_buffers =NULL ; +at91ether_stop (lp);return pm_runtime_put (&lp->pdev->dev); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 173/265 wireguard: receive: account for napi_gro_receive never returning GRO_DROP
In reply to Sasha LevinFrom: "Jason A. Donenfeld" <[email protected]>
[ Upstream commit df08126e3833e9dca19e2407db5f5860a7c194fb ]
The napi_gro_receive function no longer returns GRO_DROP ever, making handling GRO_DROP dead code. This commit removes that dead code. Further, it's not even clear that device drivers have any business in taking action after passing off received packets; that's arguably out of their hands.
--- drivers/net/wireguard/receive.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-)
drivers/net/wireguard/receive.c +2 -8
@@ -414,14 +414,8 @@ static void wg_packet_consume_data_done(struct wg_peer *peer,if (unlikely (routed_peer != peer)) goto dishonest_packet_peer; -if (unlikely (napi_gro_receive (&peer->napi, skb) ==GRO_DROP )) { - ++dev->stats.rx_dropped; -net_dbg_ratelimited ("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n" , - dev->name, peer->internal_id, - &peer->endpoint.addr); - }else { -update_rx_stats (peer,message_data_len (len_before_trim)); - } +napi_gro_receive (&peer->napi, skb); +update_rx_stats (peer,message_data_len (len_before_trim));return ; dishonest_packet_peer:
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 174/265 socionext: account for napi_gro_receive never returning GRO_DROP
In reply to Sasha LevinFrom: "Jason A. Donenfeld" <[email protected]>
[ Upstream commit e5e7d8052f6140985c03bd49ebaa0af9c2944bc6 ]
The napi_gro_receive function no longer returns GRO_DROP ever, making handling GRO_DROP dead code. This commit removes that dead code. Further, it's not even clear that device drivers have any business in taking action after passing off received packets; that's arguably out of their hands.
--- drivers/net/ethernet/socionext/netsec.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/net/ethernet/socionext/netsec.c +3 -2
@@ -1038,8 +1038,9 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget) skb->ip_summed =CHECKSUM_UNNECESSARY ; next: -if ((skb &&napi_gro_receive (&priv->napi, skb) !=GRO_DROP ) || - xdp_result) { +if (skb) +napi_gro_receive (&priv->napi, skb); +if (skb || xdp_result) { ndev->stats.rx_packets++; ndev->stats.rx_bytes += xdp.data_end - xdp.data; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 175/265 wil6210: account for napi_gro_receive never returning GRO_DROP
In reply to Sasha LevinFrom: "Jason A. Donenfeld" <[email protected]>
[ Upstream commit 045790b7bc66a75070c112a61558c639cef2263e ]
The napi_gro_receive function no longer returns GRO_DROP ever, making handling GRO_DROP dead code. This commit removes that dead code. Further, it's not even clear that device drivers have any business in taking action after passing off received packets; that's arguably out of their hands. In this case, too, the non-gro path didn't bother checking the return value. Plus, this had some clunky debugging functions that duplicated code from elsewhere and was generally pretty messy. So, this commit cleans that all up too.
--- drivers/net/wireless/ath/wil6210/txrx.c | 39 +++++++------------------ 1 file changed, 11 insertions(+), 28 deletions(-)
drivers/net/wireless/ath/wil6210/txrx.c +11 -28
@@ -897,7 +897,6 @@ static void wil_rx_handle_eapol(struct wil6210_vif *vif, struct sk_buff *skb)void wil_netif_rx (struct sk_buff *skb,struct net_device *ndev,int cid,struct wil_net_stats *stats,bool gro) { -gro_result_t rc =GRO_NORMAL ;struct wil6210_vif *vif =ndev_to_vif (ndev);struct wil6210_priv *wil =ndev_to_wil (ndev);struct wireless_dev *wdev =vif_to_wdev (vif);
@@ -908,22 +907,16 @@ void wil_netif_rx(struct sk_buff *skb, struct net_device *ndev, int cid,*/ int mcast =is_multicast_ether_addr (da);struct sk_buff *xmit_skb =NULL ; -static const char *const gro_res_str[] = { - [GRO_MERGED ] ="GRO_MERGED" , - [GRO_MERGED_FREE ] ="GRO_MERGED_FREE" , - [GRO_HELD ] ="GRO_HELD" , - [GRO_NORMAL ] ="GRO_NORMAL" , - [GRO_DROP ] ="GRO_DROP" , - [GRO_CONSUMED ] ="GRO_CONSUMED" , - };if (wdev->iftype ==NL80211_IFTYPE_STATION ) { sa =wil_skb_get_sa (skb);if (mcast &ðer_addr_equal (sa, ndev->dev_addr)) {/* mcast packet looped back to us */ - rc =GRO_DROP ;dev_kfree_skb (skb); - goto stats; + ndev->stats.rx_dropped++; + stats->rx_dropped++; +wil_dbg_txrx (wil,"Rx drop %d bytes\n" , len); +return ; } }else if (wdev->iftype ==NL80211_IFTYPE_AP && !vif->ap_isolate) {if (mcast) {
@@ -967,26 +960,16 @@ void wil_netif_rx(struct sk_buff *skb, struct net_device *ndev, int cid,wil_rx_handle_eapol (vif, skb);if (gro) - rc =napi_gro_receive (&wil->napi_rx, skb); +napi_gro_receive (&wil->napi_rx, skb);else netif_rx_ni (skb); -wil_dbg_txrx (wil,"Rx complete %d bytes => %s\n" , - len, gro_res_str[rc]); - } -stats: -/* statistics. rc set to GRO_NORMAL for AP bridging */ -if (unlikely (rc ==GRO_DROP )) { - ndev->stats.rx_dropped++; - stats->rx_dropped++; -wil_dbg_txrx (wil,"Rx drop %d bytes\n" , len); - }else { - ndev->stats.rx_packets++; - stats->rx_packets++; - ndev->stats.rx_bytes += len; - stats->rx_bytes += len; -if (mcast) - ndev->stats.multicast++; } + ndev->stats.rx_packets++; + stats->rx_packets++; + ndev->stats.rx_bytes += len; + stats->rx_bytes += len; +if (mcast) + ndev->stats.multicast++; }void wil_netif_rx_any (struct sk_buff *skb,struct net_device *ndev)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 176/265 selftests/powerpc: Fix build failure in ebb tests
In reply to Sasha LevinFrom: Harish <[email protected]>
[ Upstream commit 896066aa0685af3434637998b76218c2045142a8 ]
We use OUTPUT directory as TMPOUT for checking no-pie option.
Since commit f2f02ebd8f38 ("kbuild: improve cc-option to clean up all temporary files") when building powerpc/ from selftests directory, the OUTPUT directory points to powerpc/pmu/ebb/ and gets removed when checking for -no-pie option in try-run routine, subsequently build fails with the following:
$ make -C powerpc ... TARGET=ebb; BUILD_TARGET=$OUTPUT/$TARGET; mkdir -p $BUILD_TARGET; make OUTPUT=$BUILD_TARGET -k -C $TARGET all make[2]: Entering directory '/home/linux-master/tools/testing/selftests/powerpc/pmu/ebb' make[2]: *** No rule to make target 'Makefile'. make[2]: Failed to remake makefile 'Makefile'. make[2]: *** No rule to make target 'ebb.c', needed by '/home/linux-master/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test'. make[2]: *** No rule to make target 'ebb_handler.S', needed by '/home/linux-master/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test'. make[2]: *** No rule to make target 'trace.c', needed by '/home/linux-master/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test'. make[2]: *** No rule to make target 'busy_loop.S', needed by '/home/linux-master/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test'. make[2]: Target 'all' not remade because of errors.
Fix this by adding a suffix to the OUTPUT directory so that the failure is avoided.
--- tools/testing/selftests/powerpc/pmu/ebb/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/powerpc/pmu/ebb/Makefile +1 -1
@@ -7,7 +7,7 @@ noarg: # The EBB handler is 64-bit code and everything links against it CFLAGS += -m64 -TMPOUT = $(OUTPUT)/ +TMPOUT = $(OUTPUT)/TMPDIR/ # Toolchains may build PIE by default which breaks the assembly no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 177/265 i2c: core: check returned size of emulated smbus block read
In reply to Sasha LevinFrom: Mans Rullgard <[email protected]>
[ Upstream commit 40e05200593af06633f64ab0effff052eee6f076 ]
If the i2c bus driver ignores the I2C_M_RECV_LEN flag (as some of them do), it is possible for an I2C_SMBUS_BLOCK_DATA read issued on some random device to return an arbitrary value in the first byte (and nothing else). When this happens, i2c_smbus_xfer_emulated() will happily write past the end of the supplied data buffer, thus causing Bad Things to happen. To prevent this, check the size before copying the data block and return an error if it is too large.
--- drivers/i2c/i2c-core-smbus.c | 7 +++++++ 1 file changed, 7 insertions(+)
drivers/i2c/i2c-core-smbus.c +7 -0
@@ -495,6 +495,13 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,break ;case I2C_SMBUS_BLOCK_DATA :case I2C_SMBUS_BLOCK_PROC_CALL : +if (msg[1 ].buf[0 ] >I2C_SMBUS_BLOCK_MAX ) { +dev_err (&adapter->dev, +"Invalid block size returned: %d\n" , + msg[1 ].buf[0 ]); + status = -EPROTO ; + goto cleanup; + }for (i =0 ; i < msg[1 ].buf[0 ] +1 ; i++) data->block[i] = msg[1 ].buf[i];break ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 178/265 afs: Fix storage of cell names
In reply to Sasha LevinFrom: David Howells <[email protected]>
[ Upstream commit 719fdd32921fb7e3208db8832d32ae1c2d68900f ]
The cell name stored in the afs_cell struct is a 64-char + NUL buffer - when it needs to be able to handle up to AFS_MAXCELLNAME (256 chars) + NUL.
Fix this by changing the array to a pointer and allocating the string.
Found using Coverity.
--- fs/afs/cell.c | 9 +++++++++ fs/afs/internal.h | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-)
fs/afs/cell.c +9 -0
@@ -154,10 +154,17 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,return ERR_PTR (-ENOMEM ); } + cell->name =kmalloc (namelen +1 ,GFP_KERNEL ); +if (!cell->name) { +kfree (cell); +return ERR_PTR (-ENOMEM ); + } + cell->net = net; cell->name_len = namelen;for (i =0 ; i < namelen; i++) cell->name[i] =tolower (name[i]); + cell->name[i] =0 ;atomic_set (&cell->usage,2 );INIT_WORK (&cell->manager, afs_manage_cell);
@@ -203,6 +210,7 @@ parse_failed:if (ret == -EINVAL )printk (KERN_ERR "kAFS: bad VL server IP address\n" ); error: +kfree (cell->name);kfree (cell);_leave (" = %d" , ret);return ERR_PTR (ret);
@@ -483,6 +491,7 @@ static void afs_cell_destroy(struct rcu_head *rcu)afs_put_vlserverlist (cell->net,rcu_access_pointer (cell->vl_servers));key_put (cell->anonymous_key); +kfree (cell->name);kfree (cell);_leave (" [destroyed]" );
fs/afs/internal.h +1 -1
@@ -397,7 +397,7 @@ struct afs_cell {struct afs_vlserver_list __rcu *vl_servers;u8 name_len;/* Length of name */ -char name[64 +1 ];/* Cell name, case-flattened and NUL-padded */ +char *name;/* Cell name, case-flattened and NUL-padded */ };/*
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 179/265 sched/deadline: Initialize ->dl_boosted
In reply to Sasha LevinFrom: Juri Lelli <[email protected]>
[ Upstream commit ce9bc3b27f2a21a7969b41ffb04df8cf61bd1592 ]
syzbot reported the following warning triggered via SYSC_sched_setattr():
WARNING: CPU: 0 PID: 6973 at kernel/sched/deadline.c:593 setup_new_dl_entity /kernel/sched/deadline.c:594 [inline] WARNING: CPU: 0 PID: 6973 at kernel/sched/deadline.c:593 enqueue_dl_entity /kernel/sched/deadline.c:1370 [inline] WARNING: CPU: 0 PID: 6973 at kernel/sched/deadline.c:593 enqueue_task_dl+0x1c17/0x2ba0 /kernel/sched/deadline.c:1441
This happens because the ->dl_boosted flag is currently not initialized by __dl_clear_params() (unlike the other flags) and setup_new_dl_entity() rightfully complains about it.
Initialize dl_boosted to 0.
--- kernel/sched/deadline.c | 1 + 1 file changed, 1 insertion(+)
kernel/sched/deadline.c +1 -0
@@ -2692,6 +2692,7 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw =0 ; dl_se->dl_density =0 ; + dl_se->dl_boosted =0 ; dl_se->dl_throttled =0 ; dl_se->dl_yielded =0 ; dl_se->dl_non_contending =0 ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 180/265 sched/core: Fix PI boosting between RT and DEADLINE tasks
In reply to Sasha LevinFrom: Juri Lelli <[email protected]>
[ Upstream commit 740797ce3a124b7dd22b7fb832d87bc8fba1cf6f ]
syzbot reported the following warning:
WARNING: CPU: 1 PID: 6351 at kernel/sched/deadline.c:628 enqueue_task_dl+0x22da/0x38a0 kernel/sched/deadline.c:1504
At deadline.c:628 we have:
623 static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) 624 {
625 struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
626 struct rq *rq = rq_of_dl_rq(dl_rq);
627
628 WARN_ON(dl_se->dl_boosted);
629 WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
[...]
}Which means that setup_new_dl_entity() has been called on a task currently boosted. This shouldn't happen though, as setup_new_dl_entity() is only called when the 'dynamic' deadline of the new entity is in the past w.r.t. rq_clock and boosted tasks shouldn't verify this condition.
Digging through the PI code I noticed that what above might in fact happen if an RT tasks blocks on an rt_mutex hold by a DEADLINE task. In the first branch of boosting conditions we check only if a pi_task 'dynamic' deadline is earlier than mutex holder's and in this case we set mutex holder to be dl_boosted. However, since RT 'dynamic' deadlines are only initialized if such tasks get boosted at some point (or if they become DEADLINE of course), in general RT 'dynamic' deadlines are usually equal to 0 and this verifies the aforementioned condition.
Fix it by checking that the potential donor task is actually (even if temporary because in turn boosted) running at DEADLINE priority before using its 'dynamic' deadline value.
--- kernel/sched/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/sched/core.c +2 -1
@@ -4461,7 +4461,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)*/ if (dl_prio (prio)) {if (!dl_prio (p->normal_prio) || - (pi_task &&dl_entity_preempt (&pi_task->dl, &p->dl))) { + (pi_task &&dl_prio (pi_task->prio) && +dl_entity_preempt (&pi_task->dl, &p->dl))) { p->dl.dl_boosted =1 ; queue_flag |=ENQUEUE_REPLENISH ; }else
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 181/265 sched/cfs: change initial value of runnable_avg
In reply to Sasha LevinFrom: Vincent Guittot <[email protected]>
[ Upstream commit e21cf43406a190adfcc4bfe592768066fb3aaa9b ]
Some performance regression on reaim benchmark have been raised with
commit 070f5e860ee2 ("sched/fair: Take into account runnable_avg to classify group")
The problem comes from the init value of runnable_avg which is initialized with max value. This can be a problem if the newly forked task is finally a short task because the group of CPUs is wrongly set to overloaded and tasks are pulled less agressively.
Set initial value of runnable_avg equals to util_avg to reflect that there is no waiting time so far.
--- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/sched/fair.c +1 -1
@@ -807,7 +807,7 @@ void post_init_entity_util_avg(struct task_struct *p) } } - sa->runnable_avg = cpu_scale; + sa->runnable_avg = sa->util_avg;if (p->sched_class != &fair_sched_class) {/*
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 182/265 sata_rcar: handle pm_runtime_get_sync failure cases
In reply to Sasha LevinFrom: Navid Emamdoost <[email protected]>
[ Upstream commit eea1238867205b9e48a67c1a63219529a73c46fd ]
Calling pm_runtime_get_sync increments the counter even in case of failure, causing incorrect ref count. Call pm_runtime_put if pm_runtime_get_sync fails.
--- drivers/ata/sata_rcar.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)
drivers/ata/sata_rcar.c +7 -4
@@ -907,7 +907,7 @@ static int sata_rcar_probe(struct platform_device *pdev)pm_runtime_enable (dev); ret =pm_runtime_get_sync (dev);if (ret <0 ) - goto err_pm_disable; + goto err_pm_put; host =ata_host_alloc (dev,1 );if (!host) {
@@ -937,7 +937,6 @@ static int sata_rcar_probe(struct platform_device *pdev) err_pm_put:pm_runtime_put (dev); -err_pm_disable:pm_runtime_disable (dev);return ret; }
@@ -991,8 +990,10 @@ static int sata_rcar_resume(struct device *dev)int ret; ret =pm_runtime_get_sync (dev); -if (ret <0 ) +if (ret <0 ) { +pm_runtime_put (dev);return ret; + }if (priv->type ==RCAR_GEN3_SATA ) {sata_rcar_init_module (priv);
@@ -1017,8 +1018,10 @@ static int sata_rcar_restore(struct device *dev)int ret; ret =pm_runtime_get_sync (dev); -if (ret <0 ) +if (ret <0 ) { +pm_runtime_put (dev);return ret; + }sata_rcar_setup_port (host);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 183/265 ata/libata: Fix usage of page address by page_address in ata_scsi_mode_select_xlat function
In reply to Sasha LevinFrom: Ye Bin <[email protected]>
[ Upstream commit f650ef61e040bcb175dd8762164b00a5d627f20e ]
BUG: KASAN: use-after-free in ata_scsi_mode_select_xlat+0x10bd/0x10f0 drivers/ata/libata-scsi.c:4045 Read of size 1 at addr ffff88803b8cd003 by task syz-executor.6/12621 CPU: 1 PID: 12621 Comm: syz-executor.6 Not tainted 4.19.95 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xac/0xee lib/dump_stack.c:118 print_address_description+0x60/0x223 mm/kasan/report.c:253 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report mm/kasan/report.c:409 [inline] kasan_report.cold+0xae/0x2d8 mm/kasan/report.c:393 ata_scsi_mode_select_xlat+0x10bd/0x10f0 drivers/ata/libata-scsi.c:4045 ata_scsi_translate+0x2da/0x680 drivers/ata/libata-scsi.c:2035 __ata_scsi_queuecmd drivers/ata/libata-scsi.c:4360 [inline] ata_scsi_queuecmd+0x2e4/0x790 drivers/ata/libata-scsi.c:4409 scsi_dispatch_cmd+0x2ee/0x6c0 drivers/scsi/scsi_lib.c:1867 scsi_queue_rq+0xfd7/0x1990 drivers/scsi/scsi_lib.c:2170 blk_mq_dispatch_rq_list+0x1e1/0x19a0 block/blk-mq.c:1186 blk_mq_do_dispatch_sched+0x147/0x3d0 block/blk-mq-sched.c:108 blk_mq_sched_dispatch_requests+0x427/0x680 block/blk-mq-sched.c:204 __blk_mq_run_hw_queue+0xbc/0x200 block/blk-mq.c:1308 __blk_mq_delay_run_hw_queue+0x3c0/0x460 block/blk-mq.c:1376 blk_mq_run_hw_queue+0x152/0x310 block/blk-mq.c:1413 blk_mq_sched_insert_request+0x337/0x6c0 block/blk-mq-sched.c:397 blk_execute_rq_nowait+0x124/0x320 block/blk-exec.c:64 blk_execute_rq+0xc5/0x112 block/blk-exec.c:101 sg_scsi_ioctl+0x3b0/0x6a0 block/scsi_ioctl.c:507 sg_ioctl+0xd37/0x23f0 drivers/scsi/sg.c:1106 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:501 [inline] do_vfs_ioctl+0xae6/0x1030 fs/ioctl.c:688 ksys_ioctl+0x76/0xa0 fs/ioctl.c:705 __do_sys_ioctl fs/ioctl.c:712 [inline] __se_sys_ioctl fs/ioctl.c:710 [inline] __x64_sys_ioctl+0x6f/0xb0 fs/ioctl.c:710 do_syscall_64+0xa0/0x2e0 arch/x86/entry/common.c:293 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45c479 Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89
f7 48
89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f
83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fb0e9602c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007fb0e96036d4 RCX: 000000000045c479
RDX: 0000000020000040 RSI: 0000000000000001 RDI: 0000000000000003
RBP: 000000000076bfc0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 000000000000046d R14: 00000000004c6e1a R15: 000000000076bfcc
Allocated by task 12577: set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc mm/kasan/kasan.c:553 [inline] kasan_kmalloc+0xbf/0xe0 mm/kasan/kasan.c:531 __kmalloc+0xf3/0x1e0 mm/slub.c:3749 kmalloc include/linux/slab.h:520 [inline] load_elf_phdrs+0x118/0x1b0 fs/binfmt_elf.c:441 load_elf_binary+0x2de/0x4610 fs/binfmt_elf.c:737 search_binary_handler fs/exec.c:1654 [inline] search_binary_handler+0x15c/0x4e0 fs/exec.c:1632 exec_binprm fs/exec.c:1696 [inline] __do_execve_file.isra.0+0xf52/0x1a90 fs/exec.c:1820 do_execveat_common fs/exec.c:1866 [inline] do_execve fs/exec.c:1883 [inline] __do_sys_execve fs/exec.c:1964 [inline] __se_sys_execve fs/exec.c:1959 [inline] __x64_sys_execve+0x8a/0xb0 fs/exec.c:1959 do_syscall_64+0xa0/0x2e0 arch/x86/entry/common.c:293 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 12577: set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x129/0x170 mm/kasan/kasan.c:521 slab_free_hook mm/slub.c:1370 [inline] slab_free_freelist_hook mm/slub.c:1397 [inline] slab_free mm/slub.c:2952 [inline] kfree+0x8b/0x1a0 mm/slub.c:3904 load_elf_binary+0x1be7/0x4610 fs/binfmt_elf.c:1118 search_binary_handler fs/exec.c:1654 [inline] search_binary_handler+0x15c/0x4e0 fs/exec.c:1632 exec_binprm fs/exec.c:1696 [inline] __do_execve_file.isra.0+0xf52/0x1a90 fs/exec.c:1820 do_execveat_common fs/exec.c:1866 [inline] do_execve fs/exec.c:1883 [inline] __do_sys_execve fs/exec.c:1964 [inline] __se_sys_execve fs/exec.c:1959 [inline] __x64_sys_execve+0x8a/0xb0 fs/exec.c:1959 do_syscall_64+0xa0/0x2e0 arch/x86/entry/common.c:293 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff88803b8ccf00 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 259 bytes inside of 512-byte region [ffff88803b8ccf00, ffff88803b8cd100) The buggy address belongs to the page: page:ffffea0000ee3300 count:1 mapcount:0 mapping:ffff88806cc03080 index:0xffff88803b8cc780 compound_mapcount: 0 flags: 0x100000000008100(slab|head) raw: 0100000000008100 ffffea0001104080 0000000200000002 ffff88806cc03080 raw: ffff88803b8cc780 00000000800c000b 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88803b8ccf00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88803b8ccf80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88803b8cd000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^ffff88803b8cd080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fbffff88803b8cd100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
You can refer to "https://www.lkml.org/lkml/2019/1/17/474" reproduce this error.
The exception code is "bd_len = p[3];", "p" value is ffff88803b8cd000
which belongs to the cache kmalloc-512 of size 512. The "page_address(sg_page(scsi_sglist(scmd)))" maybe from sg_scsi_ioctl function "buffer" which allocated by kzalloc, so "buffer" may not page aligned.
This also looks completely buggy on highmem systems and really needs to use akmap_atomic. --Christoph Hellwig
To address above bugs, Paolo Bonzini advise to simpler to just make a char array of size CACHE_MPAGE_LEN+8+8+4-2(or just 64 to make it easy), use sg_copy_to_buffer to copy from the sglist into the buffer, and workthere.
--- drivers/ata/libata-scsi.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/ata/libata-scsi.c +6 -3
@@ -3692,12 +3692,13 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc) {struct scsi_cmnd *scmd = qc->scsicmd;const u8 *cdb = scmd->cmnd; -const u8 *p;u8 pg, spg;unsigned six_byte, pg_len, hdr_len, bd_len;int len;u16 fp = (u16)-1 ;u8 bp =0xff ; +u8 buffer[64 ]; +const u8 *p = buffer;VPRINTK ("ENTER\n" );
@@ -3731,12 +3732,14 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)if (!scsi_sg_count (scmd) ||scsi_sglist (scmd)->length < len) goto invalid_param_len; - p =page_address (sg_page (scsi_sglist (scmd))); -/* Move past header and block descriptors. */ if (len < hdr_len) goto invalid_param_len; +if (!sg_copy_to_buffer (scsi_sglist (scmd),scsi_sg_count (scmd), + buffer,sizeof (buffer))) + goto invalid_param_len; +if (six_byte) bd_len = p[3 ];else
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 184/265 drm/amd/display: Use kfree() to free rgb_user in calculate_user_regamma_ramp()
In reply to Sasha LevinFrom: Denis Efremov <[email protected]>
[ Upstream commit 43a562774fceba867e8eebba977d7d42f8a2eac7 ]
Use kfree() instead of kvfree() to free rgb_user in calculate_user_regamma_ramp() because the memory is allocated with kcalloc().
--- drivers/gpu/drm/amd/display/modules/color/color_gamma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/display/modules/color/color_gamma.c +1 -1
@@ -1777,7 +1777,7 @@ bool calculate_user_regamma_ramp(struct dc_transfer_func *output_tf,kfree (rgb_regamma); rgb_regamma_alloc_fail: -kvfree (rgb_user); +kfree (rgb_user); rgb_user_alloc_fail:return ret; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 185/265 riscv/atomic: Fix sign extension for RV64I
In reply to Sasha LevinFrom: Nathan Huckleberry <[email protected]>
[ Upstream commit 6c58f25e6938c073198af8b1e1832f83f8f0df33 ]
The argument passed to cmpxchg is not guaranteed to be sign extended, but lr.w sign extends on RV64I. This makes cmpxchg fail on clang built kernels when __old is negative.
To fix this, we just cast __old to long which sign extends on RV64I. With this fix, clang built RISC-V kernels now boot.
--- arch/riscv/include/asm/cmpxchg.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
arch/riscv/include/asm/cmpxchg.h +4 -4
@@ -179,7 +179,7 @@" bnez %1, 0b\n" \"1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ -: " rJ" (__old), " rJ" (__new) \ +: " rJ" ((long)__old), " rJ" (__new) \ : "memory"); \ break; \ case 8: \
@@ -224,7 +224,7 @@RISCV_ACQUIRE_BARRIER \"1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ -: " rJ" (__old), " rJ" (__new) \ +: " rJ" ((long)__old), " rJ" (__new) \ : "memory"); \ break; \ case 8: \
@@ -270,7 +270,7 @@" bnez %1, 0b\n" \"1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ -: " rJ" (__old), " rJ" (__new) \ +: " rJ" ((long)__old), " rJ" (__new) \ : "memory"); \ break; \ case 8: \
@@ -316,7 +316,7 @@" fence rw, rw\n" \"1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ -: " rJ" (__old), " rJ" (__new) \ +: " rJ" ((long)__old), " rJ" (__new) \ : "memory"); \ break; \ case 8: \
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 186/265 bcache: check and adjust logical block size for backing devices
In reply to Sasha LevinFrom: Mauricio Faria de Oliveira <[email protected]>
[ Upstream commit dcacbc1242c71e18fa9d2eadc5647e115c9c627d ]
It's possible for a block driver to set logical block size to a value greater than page size incorrectly; e.g. bcache takes the value from the superblock, set by the user w/ make-bcache.
This causes a BUG/NULL pointer dereference in the path:
__blkdev_get()
-> set_init_blocksize() // set i_blkbits based on ...
-> bdev_logical_block_size()
-> queue_logical_block_size() // ... this value
-> bdev_disk_changed()
...
-> blkdev_readpage()
-> block_read_full_page()
-> create_page_buffers() // size = 1 << i_blkbits
-> create_empty_buffers() // give size/take pointer
-> alloc_page_buffers() // return NULL
.. BUG!Because alloc_page_buffers() is called with size > PAGE_SIZE, thus it initializes head = NULL, skips the loop, return head; then create_empty_buffers() gets (and uses) the NULL pointer.
This has been around longer than commit ad6bf88a6c19 ("block:
fix an integer overflow in logical block size"); however, it increased the range of values that can trigger the issue.
Previously only 8k/16k/32k (on x86/4k page size) would do it, as greater values overflow unsigned short to zero, and queue_ logical_block_size() would then use the default of 512.
Now the range with unsigned int is much larger, and users w/ the 512k value, which happened to be zero'ed previously and work fine, started to hit this issue -- as the zero is gone, and queue_logical_block_size() does return 512k (>PAGE_SIZE.)
Fix this by checking the bcache device's logical block size, and if it's greater than page size, fallback to the backing/ cached device's logical page size.
This doesn't affect cache devices as those are still checked for block/page size in read_super(); only the backing/cached devices are not.
Apparently it's a regression from commit 2903381fce71 ("bcache:
Take data offset from the bdev superblock."), moving the check into BCACHE_SB_VERSION_CDEV only. Now that we have superblocks of backing devices out there with this larger value, we cannot refuse to load them (i.e., have a similar check in _BDEV.)
Ideally perhaps bcache should use all values from the backing device (physical/logical/io_min block size)? But for now just fix the problematic case.
Test-case:
# IMG=/root/disk.img
# dd if=/dev/zero of=$IMG bs=1 count=0 seek=1G
# DEV=$(losetup --find --show $IMG)
# make-bcache --bdev $DEV --block 8k
< see dmesg >Before:
# uname -r
5.7.0-rc7 [ 55.944046] BUG: kernel NULL pointer dereference, address: 0000000000000000
...
[ 55.949742] CPU: 3 PID: 610 Comm: bcache-register Not tainted 5.7.0-rc7 #4
...
[ 55.952281] RIP: 0010:create_empty_buffers+0x1a/0x100
...
[ 55.966434] Call Trace:
[ 55.967021] create_page_buffers+0x48/0x50
[ 55.967834] block_read_full_page+0x49/0x380
[ 55.972181] do_read_cache_page+0x494/0x610
[ 55.974780] read_part_sector+0x2d/0xaa
[ 55.975558] read_lba+0x10e/0x1e0
[ 55.977904] efi_partition+0x120/0x5a6
[ 55.980227] blk_add_partitions+0x161/0x390
[ 55.982177] bdev_disk_changed+0x61/0xd0
[ 55.982961] __blkdev_get+0x350/0x490
[ 55.983715] __device_add_disk+0x318/0x480
[ 55.984539] bch_cached_dev_run+0xc5/0x270
[ 55.986010] register_bcache.cold+0x122/0x179
[ 55.987628] kernfs_fop_write+0xbc/0x1a0
[ 55.988416] vfs_write+0xb1/0x1a0
[ 55.989134] ksys_write+0x5a/0xd0
[ 55.989825] do_syscall_64+0x43/0x140
[ 55.990563] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 55.991519] RIP: 0033:0x7f7d60ba3154
...After:
# uname -r
5.7.0.bcachelbspgsz [ 31.672460] bcache: bcache_device_init() bcache0: sb/logical block size (8192) greater than page size (4096) falling back to device logical block size (512)
[ 31.675133] bcache: register_bdev() registered backing device loop0 # grep ^ /sys/block/bcache0/queue/*_block_size
/sys/block/bcache0/queue/logical_block_size:512
/sys/block/bcache0/queue/physical_block_size:8192--- drivers/md/bcache/super.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-)
drivers/md/bcache/super.c +19 -3
@@ -819,7 +819,8 @@ static void bcache_device_free(struct bcache_device *d) }static int bcache_device_init (struct bcache_device *d,unsigned int block_size, -sector_t sectors,make_request_fn make_request_fn) +sector_t sectors,make_request_fn make_request_fn, +struct block_device *cached_bdev) {struct request_queue *q; const size_t max_stripes = min_t(size_t, INT_MAX,
@@ -885,6 +886,21 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, q->limits.io_min = block_size; q->limits.logical_block_size = block_size; q->limits.physical_block_size = block_size; + +if (q->limits.logical_block_size >PAGE_SIZE && cached_bdev) { +/* +* This should only happen with BCACHE_SB_VERSION_BDEV. +* Block/page size is checked for BCACHE_SB_VERSION_CDEV. +*/ +pr_info ("%s: sb/logical block size (%u) greater than page size " +"(%lu) falling back to device logical block size (%u)" , + d->disk->disk_name, q->limits.logical_block_size, +PAGE_SIZE ,bdev_logical_block_size (cached_bdev)); + +/* This also adjusts physical block size/min io size if needed */ +blk_queue_logical_block_size (q,bdev_logical_block_size (cached_bdev)); + } +blk_queue_flag_set (QUEUE_FLAG_NONROT , d->disk->queue);blk_queue_flag_clear (QUEUE_FLAG_ADD_RANDOM , d->disk->queue);blk_queue_flag_set (QUEUE_FLAG_DISCARD , d->disk->queue);
@@ -1342,7 +1358,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) ret =bcache_device_init (&dc->disk, block_size, dc->bdev->bd_part->nr_sects - dc->sb.data_offset, - cached_dev_make_request); + cached_dev_make_request, dc->bdev);if (ret)return ret;
@@ -1455,7 +1471,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)kobject_init (&d->kobj, &bch_flash_dev_ktype);if (bcache_device_init (d,block_bytes (c), u->sectors, - flash_dev_make_request)) + flash_dev_make_request,NULL )) goto err;bcache_device_attach (d, c, u - c->uuids);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 187/265 hwrng: ks-sa - Fix runtime PM imbalance on error
In reply to Sasha LevinFrom: Dinghao Liu <[email protected]>
[ Upstream commit 95459261c99f1621d90bc628c2a48e60b7cf9a88 ]
pm_runtime_get_sync() increments the runtime PM usage counter even the call returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.
--- drivers/char/hw_random/ks-sa-rng.c | 1 + 1 file changed, 1 insertion(+)
drivers/char/hw_random/ks-sa-rng.c +1 -0
@@ -244,6 +244,7 @@ static int ks_sa_rng_probe(struct platform_device *pdev) ret =pm_runtime_get_sync (dev);if (ret <0 ) {dev_err (dev,"Failed to enable SA power-domain\n" ); +pm_runtime_put_noidle (dev);pm_runtime_disable (dev);return ret; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 188/265 arm64/sve: Eliminate data races on sve_default_vl
In reply to Sasha LevinFrom: Dave Martin <[email protected]>
[ Upstream commit 1e570f512cbdc5e9e401ba640d9827985c1bea1e ]
sve_default_vl can be modified via the /proc/sys/abi/sve_default_vl sysctl concurrently with use, and modified concurrently by multiple threads.
Adding a lock for this seems overkill, and I don't want to think any more than necessary, so just define wrappers using READ_ONCE()/ WRITE_ONCE().
This will avoid the possibility of torn accesses and repeated loads and stores.
There's no evidence yet that this is going wrong in practice: this is just hygiene. For generic sysctl users, it would be better to build this kind of thing into the sysctl common code somehow.
--- arch/arm64/kernel/fpsimd.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-)
arch/arm64/kernel/fpsimd.c +18 -7
@@ -12,6 +12,7 @@#include <linux/bug.h> #include <linux/cache.h> #include <linux/compat.h> +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/kernel.h>
@@ -119,10 +120,20 @@ struct fpsimd_last_state_struct { static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);/* Default VL for tasks that don't set it explicitly: */ -static int sve_default_vl =-1 ; +static int __sve_default_vl =-1 ; + +static int get_sve_default_vl (void ) +{ +return READ_ONCE (__sve_default_vl); +}#ifdef CONFIG_ARM64_SVE +static void set_sve_default_vl (int val) +{ +WRITE_ONCE (__sve_default_vl, val); +} +/* Maximum supported vector length across all CPUs (initially poisoned) */ int __ro_after_init sve_max_vl =SVE_VL_MIN ;int __ro_after_init sve_max_virtualisable_vl =SVE_VL_MIN ;
@@ -345,7 +356,7 @@ static int sve_proc_do_default_vl(struct ctl_table *table, int write, loff_t *ppos) {int ret; -int vl = sve_default_vl; +int vl =get_sve_default_vl ();struct ctl_table tmp_table = { .data = &vl, .maxlen =sizeof (vl),
@@ -362,7 +373,7 @@ static int sve_proc_do_default_vl(struct ctl_table *table, int write,if (!sve_vl_valid (vl))return -EINVAL ; - sve_default_vl =find_supported_vector_length (vl); +set_sve_default_vl (find_supported_vector_length (vl));return 0 ; }
@@ -869,7 +880,7 @@ void __init sve_setup(void)* For the default VL, pick the maximum supported value <= 64. * VL == 64 is guaranteed not to grow the signal frame. */ - sve_default_vl =find_supported_vector_length (64 ); +set_sve_default_vl (find_supported_vector_length (64 ));bitmap_andnot (tmp_map, sve_vq_partial_map, sve_vq_map,SVE_VQ_MAX );
@@ -890,7 +901,7 @@ void __init sve_setup(void)pr_info ("SVE: maximum available vector length %u bytes per vector\n" , sve_max_vl);pr_info ("SVE: default vector length %u bytes per vector\n" , - sve_default_vl); +get_sve_default_vl ());/* KVM decides whether to support mismatched systems. Just warn here: */ if (sve_max_virtualisable_vl < sve_max_vl)
@@ -1030,13 +1041,13 @@ void fpsimd_flush_thread(void)* vector length configured: no kernel task can become a user * task without an exec and hence a call to this function. * By the time the first call to this function is made, all -* early hardware probing is complete, so sve_default_vl +* early hardware probing is complete, so __sve_default_vl * should be valid. * If a bug causes this to go wrong, we make some noise and * try to fudge thread.sve_vl to a safe value here. */ vl = current->thread.sve_vl_onexec ? - current->thread.sve_vl_onexec : sve_default_vl; + current->thread.sve_vl_onexec :get_sve_default_vl ();if (WARN_ON (!sve_vl_valid (vl))) vl =SVE_VL_MIN ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 189/265 ibmvnic: Harden device login requests
In reply to Sasha LevinFrom: Thomas Falcon <[email protected]>
[ Upstream commit dff515a3e71dc8ab3b9dcc2e23a9b5fca88b3c18 ]
The VNIC driver's "login" command sequence is the final step in the driver's initialization process with device firmware, confirming the available device queue resources to be utilized by the driver. Under high system load, firmware may not respond to the request in a timely manner or may abort the request. In such cases, the driver should reattempt the login command sequence. In case of a device error, the number of retries is bounded.
--- drivers/net/ethernet/ibm/ibmvnic.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-)
drivers/net/ethernet/ibm/ibmvnic.c +17 -4
@@ -842,12 +842,13 @@ static int ibmvnic_login(struct net_device *netdev)struct ibmvnic_adapter *adapter =netdev_priv (netdev);unsigned long timeout =msecs_to_jiffies (30000 );int retry_count =0 ; +int retries =10 ;bool retry;int rc; do { retry = false; - if (retry_count > IBMVNIC_MAX_QUEUES) { + if (retry_count > retries) { netdev_warn(netdev, "Login attempts exceeded\n"); return -1; }
@@ -862,11 +863,23 @@ static int ibmvnic_login(struct net_device *netdev)if (!wait_for_completion_timeout (&adapter->init_done, timeout)) { -netdev_warn (netdev,"Login timed out\n" ); -return -1 ; +netdev_warn (netdev,"Login timed out, retrying...\n" ); + retry = true; + adapter->init_done_rc =0 ; + retry_count++; +continue ; } -if (adapter->init_done_rc ==PARTIALSUCCESS ) { +if (adapter->init_done_rc ==ABORTED ) { +netdev_warn (netdev,"Login aborted, retrying...\n" ); + retry = true; + adapter->init_done_rc =0 ; + retry_count++; +/* FW or device may be busy, so +* wait a bit before retrying login +*/ +msleep (500 ); + }else if (adapter->init_done_rc ==PARTIALSUCCESS ) { retry_count++;release_sub_crqs (adapter,1 );
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 190/265 net: alx: fix race condition in alx_remove
In reply to Sasha LevinFrom: Zekun Shen <[email protected]>
[ Upstream commit e89df5c4322c1bf495f62d74745895b5fd2a4393 ]
There is a race condition exist during termination. The path is alx_stop and then alx_remove. An alx_schedule_link_check could be called before alx_stop by interrupt handler and invoke alx_link_check later. Alx_stop frees the napis, and alx_remove cancels any pending works. If any of the work is scheduled before termination and invoked before alx_remove, a null-ptr-deref occurs because both expect alx->napis[i].
This patch fix the race condition by moving cancel_work_sync functions before alx_free_napis inside alx_stop. Because interrupt handler can call alx_schedule_link_check again, alx_free_irq is moved before cancel_work_sync calls too.
--- drivers/net/ethernet/atheros/alx/main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/net/ethernet/atheros/alx/main.c +5 -4
@@ -1249,8 +1249,12 @@ out_disable_adv_intr:static void __alx_stop (struct alx_priv *alx) { -alx_halt (alx);alx_free_irq (alx); + +cancel_work_sync (&alx->link_check_wk); +cancel_work_sync (&alx->reset_wk); + +alx_halt (alx);alx_free_rings (alx);alx_free_napis (alx); }
@@ -1855,9 +1859,6 @@ static void alx_remove(struct pci_dev *pdev)struct alx_priv *alx =pci_get_drvdata (pdev);struct alx_hw *hw = &alx->hw; -cancel_work_sync (&alx->link_check_wk); -cancel_work_sync (&alx->reset_wk); -/* restore permanent mac address */ alx_set_macaddr (hw, hw->perm_addr);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 191/265 test_objagg: Fix potential memory leak in error handling
In reply to Sasha LevinFrom: Aditya Pakki <[email protected]>
[ Upstream commit a6379f0ad6375a707e915518ecd5c2270afcd395 ]
In case of failure of check_expect_hints_stats(), the resources allocated by objagg_hints_get should be freed. The patch fixes this issue.
--- lib/test_objagg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
lib/test_objagg.c +2 -2
@@ -979,10 +979,10 @@ err_check_expect_stats2: err_world2_obj_get:for (i--; i >=0 ; i--)world_obj_put (&world2, objagg, hints_case->key_ids[i]); -objagg_hints_put (hints); -objagg_destroy (objagg2); i = hints_case->key_ids_count; +objagg_destroy (objagg2); err_check_expect_hints_stats: +objagg_hints_put (hints); err_hints_get: err_check_expect_stats: err_world_obj_get:
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 192/265 pinctrl: qcom: spmi-gpio: fix warning about irq chip reusage
In reply to Sasha LevinFrom: Dmitry Baryshkov <[email protected]>
[ Upstream commit 5e50311556c9f409a85740e3cb4c4511e7e27da0 ]
Fix the following warnings caused by reusage of the same irq_chip instance for all spmi-gpio gpio_irq_chip instances. Instead embed irq_chip into pmic_gpio_state struct.
gpio gpiochip2: (c440000.qcom,spmi:pmic@2:gpio@c000): detected irqchip that is shared with multiple gpiochips: please fix the driver. gpio gpiochip3: (c440000.qcom,spmi:pmic@4:gpio@c000): detected irqchip that is shared with multiple gpiochips: please fix the driver. gpio gpiochip4: (c440000.qcom,spmi:pmic@a:gpio@c000): detected irqchip that is shared with multiple gpiochips: please fix the driver.
--- drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-)
drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +10 -11
@@ -170,6 +170,7 @@ struct pmic_gpio_state {struct regmap *map;struct pinctrl_dev *ctrl;struct gpio_chip chip; +struct irq_chip irq; };static const struct pinconf_generic_params pmic_gpio_bindings[] = {
@@ -917,16 +918,6 @@ static int pmic_gpio_populate(struct pmic_gpio_state *state,return 0 ; } -static struct irq_chip pmic_gpio_irq_chip = { - .name ="spmi-gpio" , - .irq_ack = irq_chip_ack_parent, - .irq_mask = irq_chip_mask_parent, - .irq_unmask = irq_chip_unmask_parent, - .irq_set_type = irq_chip_set_type_parent, - .irq_set_wake = irq_chip_set_wake_parent, - .flags =IRQCHIP_MASK_ON_SUSPEND , -}; - static int pmic_gpio_domain_translate(struct irq_domain *domain, struct irq_fwspec *fwspec, unsigned long *hwirq,
@@ -1053,8 +1044,16 @@ static int pmic_gpio_probe(struct platform_device *pdev)if (!parent_domain)return -ENXIO ; + state->irq.name ="spmi-gpio" , + state->irq.irq_ack = irq_chip_ack_parent, + state->irq.irq_mask = irq_chip_mask_parent, + state->irq.irq_unmask = irq_chip_unmask_parent, + state->irq.irq_set_type = irq_chip_set_type_parent, + state->irq.irq_set_wake = irq_chip_set_wake_parent, + state->irq.flags =IRQCHIP_MASK_ON_SUSPEND , + girq = &state->chip.irq; - girq->chip = &pmic_gpio_irq_chip; + girq->chip = &state->irq; girq->default_type =IRQ_TYPE_NONE ; girq->handler = handle_level_irq; girq->fwnode =of_node_to_fwnode (state->dev->of_node);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 193/265 pinctrl: tegra: Use noirq suspend/resume callbacks
In reply to Sasha LevinFrom: Vidya Sagar <[email protected]>
[ Upstream commit 782b6b69847f34dda330530493ea62b7de3fd06a ]
Use noirq suspend/resume callbacks as other drivers which implement noirq suspend/resume callbacks (Ex:- PCIe) depend on pinctrl driver to configure the signals used by their respective devices in the noirq phase.
--- drivers/pinctrl/tegra/pinctrl-tegra.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/pinctrl/tegra/pinctrl-tegra.c +2 -2
@@ -731,8 +731,8 @@ static int tegra_pinctrl_resume(struct device *dev) }const struct dev_pm_ops tegra_pinctrl_pm = { - .suspend = &tegra_pinctrl_suspend, - .resume = &tegra_pinctrl_resume + .suspend_noirq = &tegra_pinctrl_suspend, + .resume_noirq = &tegra_pinctrl_resume };static bool tegra_pinctrl_gpio_node_has_range (struct tegra_pmx *pmx)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 194/265 s390/seccomp: pass syscall arguments via seccomp_data
In reply to Sasha LevinFrom: Sven Schnelle <[email protected]>
[ Upstream commit 664f5f8de825648d1d31f6f5652e3cd117c77b50 ]
Use __secure_computing() and pass the register data via seccomp_data so secure computing doesn't have to fetch it again.
--- arch/s390/kernel/ptrace.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-)
arch/s390/kernel/ptrace.c +26 -5
@@ -839,6 +839,9 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) {unsigned long mask =-1UL ; +if (is_compat_task ()) + mask =0xffffffff ; +/* * The sysc_tracesys code in entry.S stored the system * call number to gprs[2].
@@ -855,17 +858,35 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)return -1 ; } +#ifdef CONFIG_SECCOMP /* Do the secure computing check after ptrace. */ -if (secure_computing ()) { -/* seccomp failures shouldn't expose any additional code. */ -return -1 ; +if (unlikely (test_thread_flag (TIF_SECCOMP ))) { +struct seccomp_data sd; + +if (is_compat_task ()) { + sd.instruction_pointer = regs->psw.addr &0x7fffffff ; + sd.arch =AUDIT_ARCH_S390 ; + }else { + sd.instruction_pointer = regs->psw.addr; + sd.arch =AUDIT_ARCH_S390X ; + } + + sd.nr = regs->gprs[2 ] &0xffff ; + sd.args[0 ] = regs->orig_gpr2 & mask; + sd.args[1 ] = regs->gprs[3 ] & mask; + sd.args[2 ] = regs->gprs[4 ] & mask; + sd.args[3 ] = regs->gprs[5 ] & mask; + sd.args[4 ] = regs->gprs[6 ] & mask; + sd.args[5 ] = regs->gprs[7 ] & mask; + +if (__secure_computing (&sd) ==-1 ) +return -1 ; } +#endif /* CONFIG_SECCOMP */ if (unlikely (test_thread_flag (TIF_SYSCALL_TRACEPOINT )))trace_sys_enter (regs, regs->gprs[2 ]); -if (is_compat_task ()) - mask =0xffffffff ; audit_syscall_entry(regs->gprs[2], regs->orig_gpr2 & mask, regs->gprs[3] &mask, regs->gprs[4] &mask,
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 195/265 s390/ptrace: return -ENOSYS when invalid syscall is supplied
In reply to Sasha LevinFrom: Sven Schnelle <[email protected]>
[ Upstream commit cd29fa798001075a554b978df3a64e6656c25794 ]
The current code returns the syscall number which an invalid syscall number is supplied and tracing is enabled. This makes the strace testsuite fail.
--- arch/s390/kernel/ptrace.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-)
arch/s390/kernel/ptrace.c +13 -6
@@ -838,6 +838,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,asmlinkage long do_syscall_trace_enter (struct pt_regs *regs) {unsigned long mask =-1UL ; +long ret =-1 ;if (is_compat_task ()) mask =0xffffffff ;
@@ -854,8 +855,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)* debugger stored an invalid system call number. Skip * the system call and the system call restart handling. */ -clear_pt_regs_flag (regs,PIF_SYSCALL ); -return -1 ; + goto skip; }#ifdef CONFIG_SECCOMP
@@ -871,7 +871,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) sd.arch =AUDIT_ARCH_S390X ; } - sd.nr = regs->gprs[2 ] &0xffff ; + sd.nr = regs->int_code &0xffff ; sd.args[0 ] = regs->orig_gpr2 & mask; sd.args[1 ] = regs->gprs[3 ] & mask; sd.args[2 ] = regs->gprs[4 ] & mask;
@@ -880,19 +880,26 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) sd.args[5 ] = regs->gprs[7 ] & mask;if (__secure_computing (&sd) ==-1 ) -return -1 ; + goto skip; }#endif /* CONFIG_SECCOMP */ if (unlikely (test_thread_flag (TIF_SYSCALL_TRACEPOINT ))) -trace_sys_enter (regs, regs->gprs[2 ]); +trace_sys_enter (regs, regs->int_code &0xffff ); -audit_syscall_entry (regs->gprs[2 ], regs->orig_gpr2 & mask, +audit_syscall_entry (regs->int_code &0xffff , regs->orig_gpr2 & mask, regs->gprs[3 ] &mask, regs->gprs[4 ] &mask, regs->gprs[5 ] &mask); +if ((signed long )regs->gprs[2 ] >= NR_syscalls) { + regs->gprs[2 ] = -ENOSYS ; + ret = -ENOSYS ; + }return regs->gprs[2 ]; +skip: +clear_pt_regs_flag (regs,PIF_SYSCALL ); +return ret; } asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 196/265 s390/ptrace: pass invalid syscall numbers to tracing
In reply to Sasha LevinFrom: Sven Schnelle <[email protected]>
[ Upstream commit 00332c16b1604242a56289ff2b26e283dbad0812 ]
tracing expects to see invalid syscalls, so pass it through. The syscall path in entry.S checks the syscall number before looking up the handler, so it is still safe.
--- arch/s390/kernel/entry.S | 2 +- arch/s390/kernel/ptrace.c | 6 ++---- 2 files changed, 3 insertions(+), 5 deletions(-)
arch/s390/kernel/entry.S +1 -1
@@ -368,9 +368,9 @@ ENTRY(system_call) jnz .Lsysc_nr_ok # svc 0: system call number in %r1 llgfr %r1,%r1 # clear high word in r1 + sth %r1,__PT_INT_CODE+2(%r11) cghi %r1,NR_syscalls jnl .Lsysc_nr_ok - sth %r1,__PT_INT_CODE+2(%r11) slag %r8,%r1,3 .Lsysc_nr_ok: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
arch/s390/kernel/ptrace.c +2 -4
@@ -848,11 +848,9 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)* call number to gprs[2]. */ if (test_thread_flag (TIF_SYSCALL_TRACE ) && - (tracehook_report_syscall_entry (regs) || - regs->gprs[2 ] >= NR_syscalls)) { +tracehook_report_syscall_entry (regs)) {/* -* Tracing decided this syscall should not happen or the -* debugger stored an invalid system call number. Skip +* Tracing decided this syscall should not happen. Skip * the system call and the system call restart handling. */ goto skip;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 197/265 s390/ptrace: fix setting syscall number
In reply to Sasha LevinFrom: Sven Schnelle <[email protected]>
[ Upstream commit 873e5a763d604c32988c4a78913a8dab3862d2f9 ]
When strace wants to update the syscall number, it sets GPR2 to the desired number and updates the GPR via PTRACE_SETREGSET. It doesn't update regs->int_code which would cause the old syscall executed on syscall restart. As we cannot change the ptrace ABI and don't have a field for the interruption code, check whether the tracee is in a syscall and the last instruction was svc. In that case assume that the tracer wants to update the syscall number and copy the GPR2 value to regs->int_code.
--- arch/s390/kernel/ptrace.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-)
arch/s390/kernel/ptrace.c +30 -1
@@ -324,6 +324,25 @@ static inline void __poke_user_per(struct task_struct *child, child->thread.per_user.end = data; } +static void fixup_int_code (struct task_struct *child,addr_t data) +{ +struct pt_regs *regs =task_pt_regs (child); +int ilc = regs->int_code >>16 ; +u16 insn; + +if (ilc >6 ) +return ; + +if (ptrace_access_vm (child, regs->psw.addr - (regs->int_code >>16 ), + &insn,sizeof (insn),FOLL_FORCE ) !=sizeof (insn)) +return ; + +/* double check that tracee stopped on svc instruction */ +if ((insn >>8 ) !=0xa ) +return ; + + regs->int_code =0x20000 | (data &0xffff ); +}/* * Write a word to the user area of a process at location addr. This * operation does have an additional problem compared to peek_user.
@@ -335,7 +354,9 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)struct user *dummy =NULL ;addr_t offset; +if (addr < (addr_t) &dummy->regs.acrs) { +struct pt_regs *regs =task_pt_regs (child);/* * psw and gprs are stored on the stack */
@@ -353,7 +374,11 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)/* Invalid addressing mode bits */ return -EINVAL ; } - *(addr_t *)((addr_t ) &task_pt_regs (child)->psw + addr) = data; + +if (test_pt_regs_flag (regs,PIF_SYSCALL ) && + addr == offsetof(struct user, regs.gprs[2])) +fixup_int_code (child, data); + *(addr_t *)((addr_t ) ®s->psw + addr) = data; }else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {/*
@@ -719,6 +744,10 @@ static int __poke_user_compat(struct task_struct *child, regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA ) | (__u64)(tmp &PSW32_ADDR_AMODE ); }else { + +if (test_pt_regs_flag (regs,PIF_SYSCALL ) && + addr == offsetof(struct compat_user, regs.gprs[2])) +fixup_int_code (child, data);/* gpr 0-15 */ *(__u32 *)((addr_t ) ®s->psw + addr*2 +4 ) = tmp; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 198/265 s390/vdso: Use $(LD) instead of $(CC) to link vDSO
In reply to Sasha LevinFrom: Nathan Chancellor <[email protected]>
[ Upstream commit 2b2a25845d534ac6d55086e35c033961fdd83a26 ]
Currently, the VDSO is being linked through $(CC). This does not match how the rest of the kernel links objects, which is through the $(LD) variable.
When clang is built in a default configuration, it first attempts to use the target triple's default linker, which is just ld. However, the user can override this through the CLANG_DEFAULT_LINKER cmake define so that clang uses another linker by default, such as LLVM's own linker, ld.lld. This can be useful to get more optimized links across various different projects.
However, this is problematic for the s390 vDSO because ld.lld does not have any s390 emulatiom support:
https://github.com/llvm/llvm-project/blob/llvmorg-10.0.1-rc1/lld/ELF/Driver.cpp#L132-L150
Thus, if a user is using a toolchain with ld.lld as the default, they will see an error, even if they have specified ld.bfd through the LD make variable:
$ make -j"$(nproc)" -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- LLVM=1 \
LD=s390x-linux-gnu-ld \
defconfig arch/s390/kernel/vdso64/
ld.lld: error: unknown emulation: elf64_s390
clang-11: error: linker command failed with exit code 1 (use -v to see invocation)Normally, '-fuse-ld=bfd' could be used to get around this; however, this can be fragile, depending on paths and variable naming. The cleaner solution for the kernel is to take advantage of the fact that $(LD) can be invoked directly, which bypasses the heuristics of $(CC) and respects the user's choice. Similar changes have been done for ARM, ARM64, and MIPS.
--- arch/s390/kernel/vdso64/Makefile | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-)
arch/s390/kernel/vdso64/Makefile +4 -6
@@ -18,8 +18,8 @@ KBUILD_AFLAGS_64 += -m64 -s KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin -KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ - -Wl,--hash-style=both +ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \ + --hash-style=both --build-id -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
@@ -37,8 +37,8 @@ KASAN_SANITIZE := n $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE - $(call if_changed,vdso64ld) +$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) FORCE + $(call if_changed,ld) # strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -50,8 +50,6 @@ $(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands -quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 199/265 s390/vdso: fix vDSO clock_getres()
In reply to Sasha LevinFrom: Vincenzo Frascino <[email protected]>
[ Upstream commit 478237a595120a18e9b52fd2c57a6e8b7a01e411 ]
clock_getres in the vDSO library has to preserve the same behaviour of posix_get_hrtimer_res().
In particular, posix_get_hrtimer_res() does:
sec = 0;
ns = hrtimer_resolution;and hrtimer_resolution depends on the enablement of the high resolution timers that can happen either at compile or at run time.
Fix the s390 vdso implementation of clock_getres keeping a copy of hrtimer_resolution in vdso data and using that directly.
--- arch/s390/include/asm/vdso.h | 1 + arch/s390/kernel/asm-offsets.c | 2 +- arch/s390/kernel/time.c | 1 + arch/s390/kernel/vdso64/clock_getres.S | 10 +++++----- 4 files changed, 8 insertions(+), 6 deletions(-)
arch/s390/include/asm/vdso.h +1 -0
@@ -36,6 +36,7 @@ struct vdso_data {__u32 tk_shift;/* Shift used for xtime_nsec 0x60 */ __u32 ts_dir;/* TOD steering direction 0x64 */ __u64 ts_end;/* TOD steering end 0x68 */ +__u32 hrtimer_res;/* hrtimer resolution 0x70 */ };struct vdso_per_cpu_data {
arch/s390/kernel/asm-offsets.c +1 -1
@@ -76,6 +76,7 @@ int main(void)OFFSET (__VDSO_TK_SHIFT, vdso_data, tk_shift);OFFSET (__VDSO_TS_DIR, vdso_data, ts_dir);OFFSET (__VDSO_TS_END, vdso_data, ts_end); +OFFSET (__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res);OFFSET (__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base);OFFSET (__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time);OFFSET (__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
@@ -86,7 +87,6 @@ int main(void)DEFINE (__CLOCK_REALTIME_COARSE,CLOCK_REALTIME_COARSE );DEFINE (__CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE );DEFINE (__CLOCK_THREAD_CPUTIME_ID,CLOCK_THREAD_CPUTIME_ID ); -DEFINE (__CLOCK_REALTIME_RES,MONOTONIC_RES_NSEC );DEFINE (__CLOCK_COARSE_RES,LOW_RES_NSEC );BLANK ();/* idle data offsets */
arch/s390/kernel/time.c +1 -0
@@ -301,6 +301,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->tk_mult = tk->tkr_mono.mult; vdso_data->tk_shift = tk->tkr_mono.shift; + vdso_data->hrtimer_res = hrtimer_resolution;smp_wmb (); ++vdso_data->tb_update_count; }
arch/s390/kernel/vdso64/clock_getres.S +5 -5
@@ -17,12 +17,14 @@ .type __kernel_clock_getres,@function __kernel_clock_getres: CFI_STARTPROC - larl %r1,4f + larl %r1,3f + lg %r0,0(%r1) cghi %r2,__CLOCK_REALTIME_COARSE je 0f cghi %r2,__CLOCK_MONOTONIC_COARSE je 0f - larl %r1,3f + larl %r1,_vdso_data + llgf %r0,__VDSO_CLOCK_REALTIME_RES(%r1) cghi %r2,__CLOCK_REALTIME je 0f cghi %r2,__CLOCK_MONOTONIC
@@ -36,7 +38,6 @@ __kernel_clock_getres: jz 2f 0: ltgr %r3,%r3 jz 1f /* res == NULL */ - lg %r0,0(%r1) xc 0(8,%r3),0(%r3) /* set tp->tv_sec to zero */ stg %r0,8(%r3) /* store tp->tv_usec */ 1: lghi %r2,0
@@ -45,6 +46,5 @@ __kernel_clock_getres: svc 0 br %r14 CFI_ENDPROC -3: .quad __CLOCK_REALTIME_RES -4: .quad __CLOCK_COARSE_RES +3: .quad __CLOCK_COARSE_RES .size __kernel_clock_getres,.-__kernel_clock_getres
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 200/265 arm64: sve: Fix build failure when ARM64_SVE=y and SYSCTL=n
In reply to Sasha LevinFrom: Will Deacon <[email protected]>
[ Upstream commit e575fb9e76c8e33440fb859572a8b7d430f053d6 ]
When I squashed the 'allnoconfig' compiler warning about the set_sve_default_vl() function being defined but not used in commit 1e570f512cbd ("arm64/sve: Eliminate data races on sve_default_vl"), I accidentally broke the build for configs where ARM64_SVE is enabled, but SYSCTL is not.
Fix this by only compiling the SVE sysctl support if both CONFIG_SVE=y and CONFIG_SYSCTL=y.
--- arch/arm64/kernel/fpsimd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
arch/arm64/kernel/fpsimd.c +3 -3
@@ -349,7 +349,7 @@ static unsigned int find_supported_vector_length(unsigned int vl)return sve_vl_from_vq (__bit_to_vq (bit)); } -#ifdef CONFIG_SYSCTL +#if defined(CONFIG_ARM64_SVE ) && defined(CONFIG_SYSCTL ) static int sve_proc_do_default_vl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp,
@@ -395,9 +395,9 @@ static int __init sve_sysctl_init(void) return 0; } -#else /* ! CONFIG_SYSCTL */ +#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ static int __init sve_sysctl_init (void ) {return 0 ; } -#endif /* ! CONFIG_SYSCTL */ +#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #define ZREG (sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 201/265 kbuild: improve cc-option to clean up all temporary files
In reply to Sasha LevinFrom: Masahiro Yamada <[email protected]>
[ Upstream commit f2f02ebd8f3833626642688b2d2c6a7b3c141fa9 ]
When cc-option and friends evaluate compiler flags, the temporary file $$TMP is created as an output object, and automatically cleaned up. The actual file path of $$TMP is .<pid>.tmp, here <pid> is the process ID of $(shell ...) invoked from cc-option. (Please note $$$$ is the escape sequence of $$).
Such garbage files are cleaned up in most cases, but some compiler flags create additional output files.
For example, -gsplit-dwarf creates a .dwo file.
When CONFIG_DEBUG_INFO_SPLIT=y, you will see a bunch of .<pid>.dwo files left in the top of build directories. You may not notice them unless you do 'ls -a', but the garbage files will increase every time you run 'make'.
This commit changes the temporary object path to .tmp_<pid>/tmp, and removes .tmp_<pid> directory when exiting. Separate build artifacts such as *.dwo will be cleaned up all together because their file paths are usually determined based on the base name of the object.
Another example is -ftest-coverage, which outputs the coverage data into <base-name-of-object>.gcno
--- scripts/Kbuild.include | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)
scripts/Kbuild.include +6 -5
@@ -86,20 +86,21 @@ cc-cross-prefix = $(firstword $(foreach c, $(1), \ $(if $(shell command -v -- $(c)gcc 2>/dev/null), $(c)))) # output directory for tests below -TMPOUT := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/) +TMPOUT = $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/).tmp_$$$$ # try-run # Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise) # Exit code chooses option. "$$TMP" serves as a temporary file and is # automatically cleaned up. try-run = $(shell set -e; \ - TMP="$(TMPOUT).$$$$.tmp"; \ - TMPO="$(TMPOUT).$$$$.o"; \ + TMP=$(TMPOUT)/tmp; \ + TMPO=$(TMPOUT)/tmp.o; \ + mkdir -p $(TMPOUT); \ + trap "rm -rf $(TMPOUT)" EXIT; \ if ($(1)) >/dev/null 2>&1; \ then echo "$(2)"; \ else echo "$(3)"; \ - fi; \ - rm -f "$$TMP" "$$TMPO") + fi) # as-option # Usage: cflags-y += $(call as-option,-Wa$(comma)-isa=foo,)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 202/265 recordmcount: support >64k sections
In reply to Sasha LevinFrom: Sami Tolvanen <[email protected]>
[ Upstream commit 4ef57b21d6fb49d2b25c47e4cff467a0c2c8b6b7 ]
When compiling a kernel with Clang and LTO, we need to run recordmcount on vmlinux.o with a large number of sections, which currently fails as the program doesn't understand extended section indexes. This change adds support for processing binaries with >64k sections.
--- scripts/recordmcount.h | 98 +++++++++++++++++++++++++++++++++++++++--- 1 file changed, 92 insertions(+), 6 deletions(-)
scripts/recordmcount.h +92 -6
@@ -29,6 +29,11 @@#undef has_rel_mcount#undef tot_relsize#undef get_mcountsym +#undef find_symtab +#undef get_shnum +#undef set_shnum +#undef get_shstrndx +#undef get_symindex#undef get_sym_str_and_relp#undef do_func#undef Elf_Addr
@@ -58,6 +63,11 @@# define __has_rel_mcount __has64_rel_mcount# define has_rel_mcount has64_rel_mcount# define tot_relsize tot64_relsize +# define find_symtab find_symtab64 +# define get_shnum get_shnum64 +# define set_shnum set_shnum64 +# define get_shstrndx get_shstrndx64 +# define get_symindex get_symindex64# define get_sym_str_and_relp get_sym_str_and_relp_64# define do_func do64# define get_mcountsym get_mcountsym_64
@@ -91,6 +101,11 @@# define __has_rel_mcount __has32_rel_mcount# define has_rel_mcount has32_rel_mcount# define tot_relsize tot32_relsize +# define find_symtab find_symtab32 +# define get_shnum get_shnum32 +# define set_shnum set_shnum32 +# define get_shstrndx get_shstrndx32 +# define get_symindex get_symindex32# define get_sym_str_and_relp get_sym_str_and_relp_32# define do_func do32# define get_mcountsym get_mcountsym_32
@@ -173,6 +188,67 @@ static int MIPS_is_fake_mcount(Elf_Rel const *rp)return is_fake; } +static unsigned int get_symindex (Elf_Sym const *sym,Elf32_Word const *symtab, +Elf32_Word const *symtab_shndx) +{ +unsigned long offset; +int index; + +if (sym->st_shndx !=SHN_XINDEX ) +return w2 (sym->st_shndx); + + offset = (unsigned long )sym - (unsigned long )symtab; + index = offset /sizeof (*sym); + +return w (symtab_shndx[index]); +} + +static unsigned int get_shnum (Elf_Ehdr const *ehdr,Elf_Shdr const *shdr0) +{ +if (shdr0 && !ehdr->e_shnum) +return w (shdr0->sh_size); + +return w2 (ehdr->e_shnum); +} + +static void set_shnum (Elf_Ehdr *ehdr,Elf_Shdr *shdr0,unsigned int new_shnum) +{ +if (new_shnum >=SHN_LORESERVE ) { + ehdr->e_shnum =0 ; + shdr0->sh_size =w (new_shnum); + }else + ehdr->e_shnum =w2 (new_shnum); +} + +static int get_shstrndx (Elf_Ehdr const *ehdr,Elf_Shdr const *shdr0) +{ +if (ehdr->e_shstrndx !=SHN_XINDEX ) +return w2 (ehdr->e_shstrndx); + +return w (shdr0->sh_link); +} + +static void find_symtab (Elf_Ehdr *const ehdr,Elf_Shdr const *shdr0, +unsigned const nhdr,Elf32_Word **symtab, +Elf32_Word **symtab_shndx) +{ +Elf_Shdr const *relhdr; +unsigned k; + + *symtab =NULL ; + *symtab_shndx =NULL ; + +for (relhdr = shdr0, k = nhdr; k; --k, ++relhdr) { +if (relhdr->sh_type ==SHT_SYMTAB ) + *symtab = (void *)ehdr + relhdr->sh_offset; +else if (relhdr->sh_type ==SHT_SYMTAB_SHNDX ) + *symtab_shndx = (void *)ehdr + relhdr->sh_offset; + +if (*symtab && *symtab_shndx) +break ; + } +} +/* Append the new shstrtab, Elf_Shdr[], __mcount_loc and its relocations. */ static int append_func(Elf_Ehdr *const ehdr, Elf_Shdr *const shstr,
@@ -188,10 +264,12 @@ static int append_func(Elf_Ehdr *const ehdr,char const *mc_name = (sizeof (Elf_Rela) == rel_entsize) ?".rela__mcount_loc" :".rel__mcount_loc" ; -unsigned const old_shnum =w2 (ehdr->e_shnum);uint_t const old_shoff =_w (ehdr->e_shoff);uint_t const old_shstr_sh_size =_w (shstr->sh_size);uint_t const old_shstr_sh_offset =_w (shstr->sh_offset); +Elf_Shdr *const shdr0 = (Elf_Shdr *)(old_shoff + (void *)ehdr); +unsigned int const old_shnum =get_shnum (ehdr, shdr0); +unsigned int const new_shnum =2 + old_shnum;/* {.rel,}__mcount_loc */ uint_t t =1 +strlen (mc_name) +_w (shstr->sh_size);uint_t new_e_shoff;
@@ -201,6 +279,8 @@ static int append_func(Elf_Ehdr *const ehdr, t += (_align & -t);/* word-byte align */ new_e_shoff = t; +set_shnum (ehdr, shdr0, new_shnum); +/* body for new shstrtab */ if (ulseek (sb.st_size,SEEK_SET ) <0 )return -1 ;
@@ -255,7 +335,6 @@ static int append_func(Elf_Ehdr *const ehdr,return -1 ; ehdr->e_shoff =_w (new_e_shoff); - ehdr->e_shnum =w2 (2 +w2 (ehdr->e_shnum));/* {.rel,}__mcount_loc */ if (ulseek (0 ,SEEK_SET ) <0 )return -1 ;if (uwrite (ehdr,sizeof (*ehdr)) <0 )
@@ -434,6 +513,8 @@ static int find_secsym_ndx(unsigned const txtndx,uint_t *const recvalp, unsigned int *sym_index, Elf_Shdr const *const symhdr, + Elf32_Word const *symtab, + Elf32_Word const *symtab_shndx, Elf_Ehdr const *const ehdr) { Elf_Sym const *const sym0 = (Elf_Sym const *)(_w(symhdr->sh_offset)
@@ -445,7 +526,7 @@ static int find_secsym_ndx(unsigned const txtndx,for (symp = sym0, t = nsym; t; --t, ++symp) {unsigned int const st_bind =ELF_ST_BIND (symp->st_info); -if (txtndx ==w2 (symp->st_shndx) +if (txtndx ==get_symindex (symp, symtab, symtab_shndx)/* avoid STB_WEAK */ && (STB_LOCAL == st_bind ||STB_GLOBAL == st_bind)) {/* function symbols on ARM have quirks, avoid them */
@@ -516,21 +597,23 @@ static unsigned tot_relsize(Elf_Shdr const *const shdr0,return totrelsz; } -/* Overall supervision for Elf32 ET_REL file. */ static int do_func (Elf_Ehdr *const ehdr,char const *const fname,unsigned const reltype) {Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w (ehdr->e_shoff) + (void *)ehdr); -unsigned const nhdr =w2 (ehdr->e_shnum); -Elf_Shdr *const shstr = &shdr0[w2 (ehdr->e_shstrndx)]; +unsigned const nhdr =get_shnum (ehdr, shdr0); +Elf_Shdr *const shstr = &shdr0[get_shstrndx (ehdr, shdr0)];char const *const shstrtab = (char const *)(_w (shstr->sh_offset) + (void *)ehdr);Elf_Shdr const *relhdr;unsigned k; +Elf32_Word *symtab; +Elf32_Word *symtab_shndx; +/* Upper bound on space: assume all relevant relocs are for mcount. */ unsigned totrelsz;
@@ -561,6 +644,8 @@ static int do_func(Elf_Ehdr *const ehdr, char const *const fname,return -1 ; } +find_symtab (ehdr, shdr0, nhdr, &symtab, &symtab_shndx); +for (relhdr = shdr0, k = nhdr; k; --k, ++relhdr) {char const *const txtname =has_rel_mcount (relhdr, shdr0, shstrtab, fname);
@@ -577,6 +662,7 @@ static int do_func(Elf_Ehdr *const ehdr, char const *const fname, result =find_secsym_ndx (w (relhdr->sh_info), txtname, &recval, &recsym, &shdr0[symsec_sh_link], + symtab, symtab_shndx, ehdr);if (result) goto out;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 203/265 kprobes: Suppress the suspicious RCU warning on kprobes
In reply to Sasha LevinFrom: Masami Hiramatsu <[email protected]>
[ Upstream commit 6743ad432ec92e680cd0d9db86cb17b949cf5a43 ]
Anders reported that the lockdep warns that suspicious RCU list usage in register_kprobe() (detected by CONFIG_PROVE_RCU_LIST.) This is because get_kprobe() access kprobe_table[] by hlist_for_each_entry_rcu() without rcu_read_lock.
If we call get_kprobe() from the breakpoint handler context, it is run with preempt disabled, so this is not a problem. But in other cases, instead of rcu_read_lock(), we locks kprobe_mutex so that the kprobe_table[] is not updated. So, current code is safe, but still not good from the view point of RCU.
Joel suggested that we can silent that warning by passing lockdep_is_held() to the last argument of hlist_for_each_entry_rcu().
Add lockdep_is_held(&kprobe_mutex) at the end of the hlist_for_each_entry_rcu() to suppress the warning.
--- kernel/kprobes.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/kprobes.c +2 -1
@@ -326,7 +326,8 @@ struct kprobe *get_kprobe(void *addr)struct kprobe *p; head = &kprobe_table[hash_ptr (addr,KPROBE_HASH_BITS )]; -hlist_for_each_entry_rcu (p, head, hlist) { +hlist_for_each_entry_rcu (p, head, hlist, +lockdep_is_held (&kprobe_mutex)) {if (p->addr == addr)return p; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 204/265 blktrace: break out of blktrace setup on concurrent calls
In reply to Sasha LevinFrom: Luis Chamberlain <[email protected]>
[ Upstream commit 1b0b283648163dae2a214ca28ed5a99f62a77319 ]
We use one blktrace per request_queue, that means one per the entire disk. So we cannot run one blktrace on say /dev/vda and then /dev/vda1, or just two calls on /dev/vda.
We check for concurrent setup only at the very end of the blktrace setup though.
If we try to run two concurrent blktraces on the same block device the second one will fail, and the first one seems to go on. However when one tries to kill the first one one will see things like this:
The kernel will show these:
``` debugfs: File 'dropped' in directory 'nvme1n1' already present! debugfs: File 'msg' in directory 'nvme1n1' already present! debugfs: File 'trace0' in directory 'nvme1n1' already present! `` And userspace just sees this error message for the second call: ```
blktrace /dev/nvme1n1
BLKTRACESETUP(2) /dev/nvme1n1 failed: 5/Input/output error ```
The first userspace process #1 will also claim that the files were taken underneath their nose as well. The files are taken away form the first process given that when the second blktrace fails, it will follow up with a BLKTRACESTOP and BLKTRACETEARDOWN. This means that even if go-happy process #1 is waiting for blktrace data, we *have* been asked to take teardown the blktrace.
This can easily be reproduced with break-blktrace [0] run_0005.sh test.
Just break out early if we know we're already going to fail, this will prevent trying to create the files all over again, which we know still exist.
[0] https://github.com/mcgrof/break-blktrace
--- kernel/trace/blktrace.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
kernel/trace/blktrace.c +13 -0
@@ -3,6 +3,9 @@* Copyright (C) 2006 Jens Axboe <[email protected]> * */ + +#define pr_fmt (fmt) KBUILD_MODNAME ": " fmt +#include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/blktrace_api.h>
@@ -494,6 +497,16 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,*/ strreplace (buts->name,'/' ,'_' ); +/* +* bdev can be NULL, as with scsi-generic, this is a helpful as +* we can be. +*/ +if (q->blk_trace) { +pr_warn ("Concurrent blktraces are not allowed on %s\n" , + buts->name); +return -EBUSY ; + } + bt =kzalloc (sizeof (*bt),GFP_KERNEL );if (!bt)return -ENOMEM ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 205/265 nvdimm/region: always show the 'align' attribute
In reply to Sasha LevinFrom: Vishal Verma <[email protected]>
[ Upstream commit 543094e19c82b5d171e139d09a1a3ea0a7361117 ]
It is possible that a platform that is capable of 'namespace labels' comes up without the labels properly initialized. In this case, the region's 'align' attribute is hidden. Howerver, once the user does initialize he labels, the 'align' attribute still stays hidden, which is unexpected.
The sysfs_update_group() API is meant to address this, and could be called during region probe, but it has entanglements with the device 'lockdep_mutex'. Therefore, simply make the 'align' attribute always visible. It doesn't matter what it says for label-less namespaces, since it is not possible to change their allocation anyway.
--- drivers/nvdimm/region_devs.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-)
drivers/nvdimm/region_devs.c +2 -12
@@ -679,18 +679,8 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)return a->mode; } -if (a == &dev_attr_align.attr) { -int i; - -for (i =0 ; i < nd_region->ndr_mappings; i++) { -struct nd_mapping *nd_mapping = &nd_region->mapping[i]; -struct nvdimm *nvdimm = nd_mapping->nvdimm; - -if (test_bit (NDD_LABELING , &nvdimm->flags)) -return a->mode; - } -return 0 ; - } +if (a == &dev_attr_align.attr) +return a->mode;if (a != &dev_attr_set_cookie.attr && a != &dev_attr_available_size.attr)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 206/265 block: update hctx map when use multiple maps
In reply to Sasha LevinFrom: Weiping Zhang <[email protected]>
[ Upstream commit fe35ec58f0d339221643287bbb7cee15c93a5389 ]
There is an issue when tune the number for read and write queues, if the total queue count was not changed. The hctx->type cannot be updated, since __blk_mq_update_nr_hw_queues will return directly if the total queue count has not been changed.
Reproduce:
dmesg | grep "default/read/poll"
[ 2.607459] nvme nvme0: 48/0/0 default/read/poll queues
cat /sys/kernel/debug/block/nvme0n1/hctx*/type | sort | uniq -c
48 default
tune the write queues to 24:
echo 24 > /sys/module/nvme/parameters/write_queues echo 1 > /sys/block/nvme0n1/device/reset_controller
dmesg | grep "default/read/poll"
[ 433.547235] nvme nvme0: 24/24/0 default/read/poll queues
cat /sys/kernel/debug/block/nvme0n1/hctx*/type | sort | uniq -c
48 default
The driver's hardware queue mapping is not same as block layer.
--- block/blk-mq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
block/blk-mq.c +3 -1
@@ -3328,7 +3328,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,if (set->nr_maps ==1 && nr_hw_queues > nr_cpu_ids) nr_hw_queues = nr_cpu_ids; -if (nr_hw_queues <1 || nr_hw_queues == set->nr_hw_queues) +if (nr_hw_queues <1 ) +return ; +if (set->nr_maps ==1 && nr_hw_queues == set->nr_hw_queues)return ;list_for_each_entry (q, &set->tag_list, tag_set_list)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 207/265 RISC-V: Don't allow write+exec only page mapping request in mmap
In reply to Sasha LevinFrom: Yash Shah <[email protected]>
[ Upstream commit e0d17c842c0f824fd4df9f4688709fc6907201e1 ]
As per the table 4.4 of version "20190608-Priv-MSU-Ratified" of the RISC-V instruction set manual[0], the PTE permission bit combination of "write+exec only" is reserved for future use. Hence, don't allow such mapping request in mmap call.
An issue is been reported by David Abdurachmanov, that while running stress-ng with "sysbadaddr" argument, RCU stalls are observed on RISC-V specific kernel.
This issue arises when the stress-sysbadaddr request for pages with "write+exec only" permission bits and then passes the address obtain from this mmap call to various system call. For the riscv kernel, the mmap call should fail for this particular combination of permission bits since it's not valid.
[0]: http://dabbelt.com/~palmer/keep/riscv-isa-manual/riscv-privileged-20190608-1.pdf
[Palmer: Refer to the latest ISA specification at the only link I could find, and update the terminology.]
--- arch/riscv/kernel/sys_riscv.c | 6 ++++++ 1 file changed, 6 insertions(+)
arch/riscv/kernel/sys_riscv.c +6 -0
@@ -8,6 +8,7 @@#include <linux/syscalls.h> #include <asm/unistd.h> #include <asm/cacheflush.h> +#include <asm-generic/mman-common.h> static long riscv_sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags,
@@ -16,6 +17,11 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, {if (unlikely (offset & (~PAGE_MASK >> page_shift_offset)))return -EINVAL ; + +if ((prot &PROT_WRITE ) && (prot &PROT_EXEC )) +if (unlikely (!(prot &PROT_READ ))) +return -EINVAL ; +return ksys_mmap_pgoff (addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 208/265 syscalls: Fix offset type of ksys_ftruncate()
In reply to Sasha LevinFrom: Jiri Slaby <[email protected]>
commit 8e742aa79780b13cd300a42198c1a4cea9c89905 upstream.
After the commit below, truncate() on x86 32bit uses ksys_ftruncate(). But ksys_ftruncate() truncates the offset to unsigned long.
Switch the type of offset to loff_t which is what do_sys_ftruncate() expects.
--- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
include/linux/syscalls.h +1 -1
@@ -1358,7 +1358,7 @@ static inline long ksys_lchown(const char __user *filename, uid_t user,extern long do_sys_ftruncate (unsigned int fd,loff_t length,int small); -static inline long ksys_ftruncate (unsigned int fd,unsigned long length) +static inline long ksys_ftruncate (unsigned int fd,loff_t length) {return do_sys_ftruncate (fd, length,1 ); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 209/265 ALSA: hda: Add NVIDIA codec IDs 9a & 9d through a0 to patch table
In reply to Sasha LevinFrom: Aaron Plattner <[email protected]>
commit adb36a8203831e40494a92095dacd566b2ad4a69 upstream.
These IDs are for upcoming NVIDIA chips with audio functions that are largely similar to the existing ones.
--- sound/pci/hda/patch_hdmi.c | 5 +++++ 1 file changed, 5 insertions(+)
sound/pci/hda/patch_hdmi.c +5 -0
@@ -4145,6 +4145,11 @@ HDA_CODEC_ENTRY(0x10de0095, "GPU 95 HDMI/DP", patch_nvhdmi),HDA_CODEC_ENTRY (0x10de0097 ,"GPU 97 HDMI/DP" , patch_nvhdmi),HDA_CODEC_ENTRY (0x10de0098 ,"GPU 98 HDMI/DP" , patch_nvhdmi),HDA_CODEC_ENTRY (0x10de0099 ,"GPU 99 HDMI/DP" , patch_nvhdmi), +HDA_CODEC_ENTRY (0x10de009a ,"GPU 9a HDMI/DP" , patch_nvhdmi), +HDA_CODEC_ENTRY (0x10de009d ,"GPU 9d HDMI/DP" , patch_nvhdmi), +HDA_CODEC_ENTRY (0x10de009e ,"GPU 9e HDMI/DP" , patch_nvhdmi), +HDA_CODEC_ENTRY (0x10de009f ,"GPU 9f HDMI/DP" , patch_nvhdmi), +HDA_CODEC_ENTRY (0x10de00a0 ,"GPU a0 HDMI/DP" , patch_nvhdmi),HDA_CODEC_ENTRY (0x10de8001 ,"MCP73 HDMI" , patch_nvhdmi_2ch),HDA_CODEC_ENTRY (0x10de8067 ,"MCP67/68 HDMI" , patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP", patch_via_hdmi),
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 210/265 ALSA: hda/realtek - Add quirk for MSI GE63 laptop
In reply to Sasha LevinFrom: Takashi Iwai <[email protected]>
commit a0b03952a797591d4b6d6fa7b9b7872e27783729 upstream.
MSI GE63 laptop with ALC1220 codec requires the very same quirk (ALC1220_FIXUP_CLEVO_P950) as other MSI devices for the proper sound output.
--- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)
sound/pci/hda/patch_realtek.c +1 -0
@@ -2460,6 +2460,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {SND_PCI_QUIRK (0x1458 ,0xa0b8 ,"Gigabyte AZ370-Gaming" ,ALC1220_FIXUP_GB_DUAL_CODECS ),SND_PCI_QUIRK (0x1458 ,0xa0cd ,"Gigabyte X570 Aorus Master" ,ALC1220_FIXUP_CLEVO_P950 ),SND_PCI_QUIRK (0x1458 ,0xa0ce ,"Gigabyte X570 Aorus Xtreme" ,ALC1220_FIXUP_CLEVO_P950 ), +SND_PCI_QUIRK (0x1462 ,0x11f7 ,"MSI-GE63" ,ALC1220_FIXUP_CLEVO_P950 ),SND_PCI_QUIRK (0x1462 ,0x1228 ,"MSI-GP63" ,ALC1220_FIXUP_CLEVO_P950 ),SND_PCI_QUIRK (0x1462 ,0x1275 ,"MSI-GL63" ,ALC1220_FIXUP_CLEVO_P950 ), SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 211/265 ALSA: hda/realtek: Add mute LED and micmute LED support for HP systems
In reply to Sasha LevinFrom: Kai-Heng Feng <[email protected]>
commit b2c22910fe5aae10b7e17b0721e63a3edf0c9553 upstream.
There are two more HP systems control mute LED from HDA codec and need to expose micmute led class so SoF can control micmute LED.
Add quirks to support them.
--- sound/pci/hda/patch_realtek.c | 2 ++ 1 file changed, 2 insertions(+)
sound/pci/hda/patch_realtek.c +2 -0
@@ -7436,6 +7436,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {SND_PCI_QUIRK (0x103c ,0x83b9 ,"HP Spectre x360" ,ALC269_FIXUP_HP_MUTE_LED_MIC3 ),SND_PCI_QUIRK (0x103c ,0x8497 ,"HP Envy x360" ,ALC269_FIXUP_HP_MUTE_LED_MIC3 ),SND_PCI_QUIRK (0x103c ,0x84e7 ,"HP Pavilion 15" ,ALC269_FIXUP_HP_MUTE_LED_MIC3 ), +SND_PCI_QUIRK (0x103c ,0x869d ,"HP" ,ALC236_FIXUP_HP_MUTE_LED ), +SND_PCI_QUIRK (0x103c ,0x8729 ,"HP" ,ALC285_FIXUP_HP_GPIO_LED ),SND_PCI_QUIRK (0x103c ,0x8736 ,"HP" ,ALC285_FIXUP_HP_GPIO_LED ),SND_PCI_QUIRK (0x103c ,0x877a ,"HP" ,ALC285_FIXUP_HP_MUTE_LED ), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED),
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 212/265 ACPI: sysfs: Fix pm_profile_attr type
In reply to Sasha LevinFrom: Nathan Chancellor <[email protected]>
commit e6d701dca9893990d999fd145e3e07223c002b06 upstream.
When running a kernel with Clang's Control Flow Integrity implemented, there is a violation that happens when accessing /sys/firmware/acpi/pm_profile:
$ cat /sys/firmware/acpi/pm_profile 0
$ dmesg ... [ 17.352564] ------------[ cut here ]------------ [ 17.352568] CFI failure (target: acpi_show_profile+0x0/0x8): [ 17.352572] WARNING: CPU: 3 PID: 497 at kernel/cfi.c:29 __cfi_check_fail+0x33/0x40 [ 17.352573] Modules linked in: [ 17.352575] CPU: 3 PID: 497 Comm: cat Tainted: G W 5.7.0-microsoft-standard+ #1 [ 17.352576] RIP: 0010:__cfi_check_fail+0x33/0x40 [ 17.352577] Code: 48 c7 c7 50 b3 85 84 48 c7 c6 50 0a 4e 84 e8 a4 d8 60 00 85 c0 75 02 5b c3 48 c7 c7 dc 5e 49 84 48 89 de 31 c0 e8 7d 06 eb ff <0f> 0b 5b c3 00 00 cc cc 00 00 cc cc 00 85 f6 74 25 41 b9 ea ff ff [ 17.352577] RSP: 0018:ffffaa6dc3c53d30 EFLAGS: 00010246 [ 17.352578] RAX: 331267e0c06cee00 RBX: ffffffff83d85890 RCX: ffffffff8483a6f8 [ 17.352579] RDX: ffff9cceabbb37c0 RSI: 0000000000000082 RDI: ffffffff84bb9e1c [ 17.352579] RBP: ffffffff845b2bc8 R08: 0000000000000001 R09: ffff9cceabbba200 [ 17.352579] R10: 000000000000019d R11: 0000000000000000 R12: ffff9cc947766f00 [ 17.352580] R13: ffffffff83d6bd50 R14: ffff9ccc6fa80000 R15: ffffffff845bd328 [ 17.352582] FS: 00007fdbc8d13580(0000) GS:ffff9cce91ac0000(0000) knlGS:0000000000000000 [ 17.352582] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 17.352583] CR2: 00007fdbc858e000 CR3: 00000005174d0000 CR4: 0000000000340ea0 [ 17.352584] Call Trace: [ 17.352586] ? rev_id_show+0x8/0x8 [ 17.352587] ? __cfi_check+0x45bac/0x4b640 [ 17.352589] ? kobj_attr_show+0x73/0x80 [ 17.352590] ? sysfs_kf_seq_show+0xc1/0x140 [ 17.352592] ? ext4_seq_options_show.cfi_jt+0x8/0x8 [ 17.352593] ? seq_read+0x180/0x600 [ 17.352595] ? sysfs_create_file_ns.cfi_jt+0x10/0x10 [ 17.352596] ? tlbflush_read_file+0x8/0x8 [ 17.352597] ? __vfs_read+0x6b/0x220 [ 17.352598] ? handle_mm_fault+0xa23/0x11b0 [ 17.352599] ? vfs_read+0xa2/0x130 [ 17.352599] ? ksys_read+0x6a/0xd0 [ 17.352601] ? __do_sys_getpgrp+0x8/0x8 [ 17.352602] ? do_syscall_64+0x72/0x120 [ 17.352603] ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 17.352604] ---[ end trace 7b1fa81dc897e419 ]---
When /sys/firmware/acpi/pm_profile is read, sysfs_kf_seq_show is called, which in turn calls kobj_attr_show, which gets the ->show callback member by calling container_of on attr (casting it to struct kobj_attribute) then calls it.
There is a CFI violation because pm_profile_attr is of type struct device_attribute but kobj_attr_show calls ->show expecting it to be from struct kobj_attribute. CFI checking ensures that function pointer types match when doing indirect calls. Fix pm_profile_attr to be defined in terms of kobj_attribute so there is no violation or mismatch.
--- drivers/acpi/sysfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/acpi/sysfs.c +2 -2
@@ -938,13 +938,13 @@ static void __exit interrupt_stats_exit(void) }static ssize_t -acpi_show_profile (struct device *dev,struct device_attribute *attr, +acpi_show_profile (struct kobject *kobj,struct kobj_attribute *attr,char *buf) {return sprintf (buf,"%d\n" , acpi_gbl_FADT.preferred_profile); } -static const struct device_attribute pm_profile_attr = +static const struct kobj_attribute pm_profile_attr =__ATTR (pm_profile,S_IRUGO , acpi_show_profile,NULL ); static ssize_t hotplug_enabled_show(struct kobject *kobj,
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 213/265 ACPI: configfs: Disallow loading ACPI tables when locked down
In reply to Sasha LevinFrom: "Jason A. Donenfeld" <[email protected]>
commit 75b0cea7bf307f362057cc778efe89af4c615354 upstream.
Like other vectors already patched, this one here allows the root user to load ACPI tables, which enables arbitrary physical address writes, which in turn makes it possible to disable lockdown.
Prevents this by checking the lockdown status before allowing a new ACPI table to be installed. The link in the trailer shows a PoC of how this might be used.
--- drivers/acpi/acpi_configfs.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/acpi/acpi_configfs.c +5 -1
@@ -11,6 +11,7 @@#include <linux/module.h> #include <linux/configfs.h> #include <linux/acpi.h> +#include <linux/security.h> #include "acpica/accommon.h" #include "acpica/actables.h"
@@ -28,7 +29,10 @@ static ssize_t acpi_table_aml_write(struct config_item *cfg, {const struct acpi_table_header *header = data;struct acpi_table *table; -int ret; +int ret =security_locked_down (LOCKDOWN_ACPI_TABLES ); + +if (ret) +return ret; table = container_of(cfg, struct acpi_table, cfg);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 214/265 erofs: fix partially uninitialized misuse in z_erofs_onlinepage_fixup
In reply to Sasha LevinFrom: Gao Xiang <[email protected]>
commit 3c597282887fd55181578996dca52ce697d985a5 upstream.
Hongyu reported "id != index" in z_erofs_onlinepage_fixup() with specific aarch64 environment easily, which wasn't shown before.
After digging into that, I found that high 32 bits of page->private was set to 0xaaaaaaaa rather than 0 (due to z_erofs_onlinepage_init behavior with specific compiler options). Actually we only use low 32 bits to keep the page information since page->private is only 4 bytes on most 32-bit platforms. However z_erofs_onlinepage_fixup() uses the upper 32 bits by mistake.
Let's fix it now.
--- fs/erofs/zdata.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)
fs/erofs/zdata.h +10 -10
@@ -144,22 +144,22 @@ static inline void z_erofs_onlinepage_init(struct page *page)static inline void z_erofs_onlinepage_fixup (struct page *page,uintptr_t index,bool down) { -unsigned long *p, o, v, id; -repeat: - p = &page_private (page); - o =READ_ONCE (*p); +union z_erofs_onlinepage_converter u = { .v = &page_private (page) }; +int orig, orig_index, val; - id = o >>Z_EROFS_ONLINEPAGE_INDEX_SHIFT ; -if (id) { +repeat: + orig =atomic_read (u.o); + orig_index = orig >>Z_EROFS_ONLINEPAGE_INDEX_SHIFT ; +if (orig_index) {if (!index)return ; -DBG_BUGON (id != index); +DBG_BUGON (orig_index != index); } - v = (index <<Z_EROFS_ONLINEPAGE_INDEX_SHIFT ) | - ((o &Z_EROFS_ONLINEPAGE_COUNT_MASK ) + (unsigned int )down); -if (cmpxchg (p, o, v) != o) + val = (index <<Z_EROFS_ONLINEPAGE_INDEX_SHIFT ) | + ((orig &Z_EROFS_ONLINEPAGE_COUNT_MASK ) + (unsigned int )down); +if (atomic_cmpxchg (u.o, orig, val) != orig) goto repeat; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 215/265 KVM: X86: Fix MSR range of APIC registers in X2APIC mode
In reply to Sasha LevinFrom: Xiaoyao Li <[email protected]>
commit bf10bd0be53282183f374af23577b18b5fbf7801 upstream.
Only MSR address range 0x800 through 0x8ff is architecturally reserved and dedicated for accessing APIC registers in x2APIC mode.
Message-Id: <[email protected]>
--- arch/x86/kvm/x86.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/kvm/x86.c +2 -2
@@ -2784,7 +2784,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)return kvm_mtrr_set_msr (vcpu, msr, data);case MSR_IA32_APICBASE :return kvm_set_apic_base (vcpu, msr_info); - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:return kvm_x2apic_msr_write (vcpu, msr, data);case MSR_IA32_TSCDEADLINE :kvm_set_lapic_tscdeadline_msr (vcpu, data);
@@ -3112,7 +3112,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)case MSR_IA32_APICBASE : msr_info->data =kvm_get_apic_base (vcpu);break ; - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:return kvm_x2apic_msr_read (vcpu, msr_info->index, &msr_info->data);case MSR_IA32_TSCDEADLINE : msr_info->data =kvm_get_lapic_tscdeadline_msr (vcpu);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 216/265 kvm: lapic: fix broken vcpu hotplug
In reply to Sasha LevinFrom: Igor Mammedov <[email protected]>
commit af28dfacbe00d53df5dec2bf50640df33138b1fe upstream.
Guest fails to online hotplugged CPU with error
smpboot: do_boot_cpu failed(-1) to wakeup CPU#4
It's caused by the fact that kvm_apic_set_state(), which used to call recalculate_apic_map() unconditionally and pulled hotplugged CPU into apic map, is updating map conditionally on state changes. In this case the APIC map is not considered dirty and the is not updated.
Fix the issue by forcing unconditional update from kvm_apic_set_state(), like it used to be.
Message-Id: <[email protected]>
--- arch/x86/kvm/lapic.c | 1 + 1 file changed, 1 insertion(+)
arch/x86/kvm/lapic.c +1 -0
@@ -2512,6 +2512,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) }memcpy (vcpu->arch.apic->regs, s->regs,sizeof (*s)); + apic->vcpu->kvm->arch.apic_map_dirty = true;kvm_recalculate_apic_map (vcpu->kvm);kvm_apic_set_version (vcpu);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 217/265 KVM: nVMX: Plumb L2 GPA through to PML emulation
In reply to Sasha LevinFrom: Sean Christopherson <[email protected]>
commit 2dbebf7ae1ed9a420d954305e2c9d5ed39ec57c3 upstream.
Explicitly pass the L2 GPA to kvm_arch_write_log_dirty(), which for all intents and purposes is vmx_write_pml_buffer(), instead of having the latter pull the GPA from vmcs.GUEST_PHYSICAL_ADDRESS. If the dirty bit update is the result of KVM emulation (rare for L2), then the GPA in the VMCS may be stale and/or hold a completely unrelated GPA.
Message-Id: <[email protected]>
--- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/mmu.h | 2 +- arch/x86/kvm/mmu/mmu.c | 4 ++-- arch/x86/kvm/mmu/paging_tmpl.h | 7 ++++--- arch/x86/kvm/vmx/vmx.c | 6 +++--- 5 files changed, 11 insertions(+), 10 deletions(-)
arch/x86/include/asm/kvm_host.h +1 -1
@@ -1195,7 +1195,7 @@ struct kvm_x86_ops {void (*enable_log_dirty_pt_masked)(struct kvm *kvm,struct kvm_memory_slot *slot,gfn_t offset,unsigned long mask); -int (*write_log_dirty)(struct kvm_vcpu *vcpu); +int (*write_log_dirty)(struct kvm_vcpu *vcpu,gpa_t l2_gpa);/* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops;
arch/x86/kvm/mmu.h +1 -1
@@ -222,7 +222,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);void kvm_mmu_gfn_allow_lpage (struct kvm_memory_slot *slot,gfn_t gfn);bool kvm_mmu_slot_gfn_write_protect (struct kvm *kvm,struct kvm_memory_slot *slot,u64 gfn); -int kvm_arch_write_log_dirty (struct kvm_vcpu *vcpu); +int kvm_arch_write_log_dirty (struct kvm_vcpu *vcpu,gpa_t l2_gpa);int kvm_mmu_post_init_vm (struct kvm *kvm);void kvm_mmu_pre_destroy_vm (struct kvm *kvm);
arch/x86/kvm/mmu/mmu.c +2 -2
@@ -1746,10 +1746,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,* Emulate arch specific page modification logging for the * nested hypervisor */ -int kvm_arch_write_log_dirty (struct kvm_vcpu *vcpu) +int kvm_arch_write_log_dirty (struct kvm_vcpu *vcpu,gpa_t l2_gpa) {if (kvm_x86_ops.write_log_dirty) -return kvm_x86_ops.write_log_dirty (vcpu); +return kvm_x86_ops.write_log_dirty (vcpu, l2_gpa);return 0 ; }
arch/x86/kvm/mmu/paging_tmpl.h +4 -3
@@ -235,7 +235,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte)static int FNAME (update_accessed_dirty_bits )(struct kvm_vcpu *vcpu,struct kvm_mmu *mmu,struct guest_walker *walker, -int write_fault) +gpa_t addr,int write_fault) {unsigned level, index;pt_element_t pte, orig_pte;
@@ -260,7 +260,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, !(pte & PT_GUEST_DIRTY_MASK)) {trace_kvm_mmu_set_dirty_bit (table_gfn, index,sizeof (pte));#if PTTYPE ==PTTYPE_EPT -if (kvm_arch_write_log_dirty (vcpu)) +if (kvm_arch_write_log_dirty (vcpu, addr))return -EINVAL ;#endif pte |=PT_GUEST_DIRTY_MASK ;
@@ -457,7 +457,8 @@ retry_walk: (PT_GUEST_DIRTY_SHIFT -PT_GUEST_ACCESSED_SHIFT );if (unlikely (!accessed_dirty)) { - ret =FNAME (update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); + ret =FNAME (update_accessed_dirty_bits)(vcpu, mmu, walker, + addr, write_fault);if (unlikely (ret <0 )) goto error;else if (ret)
arch/x86/kvm/vmx/vmx.c +3 -3
@@ -7333,11 +7333,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm)kvm_flush_pml_buffers (kvm); } -static int vmx_write_pml_buffer (struct kvm_vcpu *vcpu) +static int vmx_write_pml_buffer (struct kvm_vcpu *vcpu,gpa_t gpa) {struct vmcs12 *vmcs12;struct vcpu_vmx *vmx =to_vmx (vcpu); -gpa_t gpa, dst; +gpa_t dst;if (is_guest_mode (vcpu)) {WARN_ON_ONCE (vmx->nested.pml_full);
@@ -7356,7 +7356,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)return 1 ; } - gpa =vmcs_read64 (GUEST_PHYSICAL_ADDRESS ) & ~0xFFFull ; + gpa &= ~0xFFFull ; dst = vmcs12->pml_address +sizeof (u64) * vmcs12->guest_pml_index; if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 218/265 KVM: VMX: Stop context switching MSR_IA32_UMWAIT_CONTROL
In reply to Sasha LevinFrom: Sean Christopherson <[email protected]>
commit bf09fb6cba4f7099620cc9ed32d94c27c4af992e upstream.
Remove support for context switching between the guest's and host's desired UMWAIT_CONTROL. Propagating the guest's value to hardware isn't required for correct functionality, e.g. KVM intercepts reads and writes to the MSR, and the latency effects of the settings controlled by the MSR are not architecturally visible.
As a general rule, KVM should not allow the guest to control power management settings unless explicitly enabled by userspace, e.g. see KVM_CAP_X86_DISABLE_EXITS. E.g. Intel's SDM explicitly states that C0.2 can improve the performance of SMT siblings. A devious guest could disable C0.2 so as to improve the performance of their workloads at the detriment to workloads running in the host or on other VMs.
Wholesale removal of UMWAIT_CONTROL context switching also fixes a race condition where updates from the host may cause KVM to enter the guest with the incorrect value. Because updates are are propagated to all CPUs via IPI (SMP function callback), the value in hardware may be stale with respect to the cached value and KVM could enter the guest with the wrong value in hardware. As above, the guest can't observe the bad value, but it's a weird and confusing wart in the implementation.
Removal also fixes the unnecessary usage of VMX's atomic load/store MSR lists. Using the lists is only necessary for MSRs that are required for correct functionality immediately upon VM-Enter/VM-Exit, e.g. EFER on old hardware, or for MSRs that need to-the-uop precision, e.g. perf related MSRs. For UMWAIT_CONTROL, the effects are only visible in the kernel via TPAUSE/delay(), and KVM doesn't do any form of delay in vcpu_vmx_run(). Using the atomic lists is undesirable as they are more expensive than direct RDMSR/WRMSR.
Furthermore, even if giving the guest control of the MSR is legitimate, e.g. in pass-through scenarios, it's not clear that the benefits would outweigh the overhead. E.g. saving and restoring an MSR across a VMX roundtrip costs ~250 cycles, and if the guest diverged from the host that cost would be paid on every run of the guest. In other words, if there is a legitimate use case then it should be enabled by a new per-VM capability.
Note, KVM still needs to emulate MSR_IA32_UMWAIT_CONTROL so that it can correctly expose other WAITPKG features to the guest, e.g. TPAUSE, UMWAIT and UMONITOR.
Message-Id: <[email protected]>
--- arch/x86/include/asm/mwait.h | 2 -- arch/x86/kernel/cpu/umwait.c | 6 ------ arch/x86/kvm/vmx/vmx.c | 18 ------------------ 3 files changed, 26 deletions(-)
arch/x86/include/asm/mwait.h +0 -2
@@ -23,8 +23,6 @@#define MWAITX_MAX_LOOPS ((u32)-1)#define MWAITX_DISABLE_CSTATES 0xf0 -u32 get_umwait_control_msr (void ); -static inline void __monitor (const void *eax,unsigned long ecx,unsigned long edx) {
arch/x86/kernel/cpu/umwait.c +0 -6
@@ -18,12 +18,6 @@*/ static u32 umwait_control_cached =UMWAIT_CTRL_VAL (100000 ,UMWAIT_C02_ENABLE ); -u32 get_umwait_control_msr (void ) -{ -return umwait_control_cached; -} -EXPORT_SYMBOL_GPL (get_umwait_control_msr); -/* * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by * hardware or BIOS before kernel boot.
arch/x86/kvm/vmx/vmx.c +0 -18
@@ -6467,23 +6467,6 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void atomic_switch_umwait_control_msr (struct vcpu_vmx *vmx) -{ -u32 host_umwait_control; - -if (!vmx_has_waitpkg (vmx)) -return ; - - host_umwait_control =get_umwait_control_msr (); - -if (vmx->msr_ia32_umwait_control != host_umwait_control) -add_atomic_switch_msr (vmx,MSR_IA32_UMWAIT_CONTROL , - vmx->msr_ia32_umwait_control, - host_umwait_control, false); -else -clear_atomic_switch_msr (vmx,MSR_IA32_UMWAIT_CONTROL ); -} -static void vmx_update_hv_timer (struct kvm_vcpu *vcpu) {struct vcpu_vmx *vmx =to_vmx (vcpu);
@@ -6576,7 +6559,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)pt_guest_enter (vmx);atomic_switch_perf_msrs (vmx); -atomic_switch_umwait_control_msr (vmx);if (enable_preemption_timer)vmx_update_hv_timer (vcpu);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 219/265 x86/cpu: Use pinning mask for CR4 bits needing to be 0
In reply to Sasha LevinFrom: Kees Cook <[email protected]>
commit a13b9d0b97211579ea63b96c606de79b963c0f47 upstream.
The X86_CR4_FSGSBASE bit of CR4 should not change after boot[1]. Older kernels should enforce this bit to zero, and newer kernels need to enforce it depending on boot-time configuration (e.g. "nofsgsbase"). To support a pinned bit being either 1 or 0, use an explicit mask in combination with the expected pinned bit values.
[1] https://lore.kernel.org/lkml/[email protected]
--- arch/x86/kernel/cpu/common.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)
arch/x86/kernel/cpu/common.c +12 -12
@@ -348,6 +348,9 @@ out:cr4_clear_bits (X86_CR4_UMIP ); } +/* These bits should not change their value after CPU init is finished. */ +static const unsigned long cr4_pinned_mask = +X86_CR4_SMEP |X86_CR4_SMAP |X86_CR4_UMIP |X86_CR4_FSGSBASE ;static DEFINE_STATIC_KEY_FALSE_RO (cr_pinning);static unsigned long cr4_pinned_bits__ro_after_init ;
@@ -372,20 +375,20 @@ EXPORT_SYMBOL(native_write_cr0);void native_write_cr4 (unsigned long val) { -unsigned long bits_missing =0 ; +unsigned long bits_changed =0 ; set_register: asmvolatile ("mov %0,%%cr4" :"+r" (val),"+m" (cr4_pinned_bits));if (static_branch_likely (&cr_pinning)) { -if (unlikely ((val & cr4_pinned_bits) != cr4_pinned_bits)) { - bits_missing = ~val & cr4_pinned_bits; - val |= bits_missing; +if (unlikely ((val & cr4_pinned_mask) != cr4_pinned_bits)) { + bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits; + val = (val & ~cr4_pinned_mask) | cr4_pinned_bits; goto set_register; } -/* Warn after we've set the missing bits. */ -WARN_ONCE (bits_missing,"CR4 bits went missing: %lx!?\n" , - bits_missing); +/* Warn after we've corrected the changed bits. */ +WARN_ONCE (bits_changed,"pinned CR4 bits changed: 0x%lx!?\n" , + bits_changed); } }EXPORT_SYMBOL (native_write_cr4);
@@ -397,7 +400,7 @@ void cr4_init(void)if (boot_cpu_has (X86_FEATURE_PCID )) cr4 |=X86_CR4_PCIDE ;if (static_branch_likely (&cr_pinning)) - cr4 |= cr4_pinned_bits; + cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits;__write_cr4 (cr4);
@@ -412,10 +415,7 @@ void cr4_init(void)*/ static void __init setup_cr_pinning (void ) { -unsigned long mask; - - mask = (X86_CR4_SMEP |X86_CR4_SMAP |X86_CR4_UMIP ); - cr4_pinned_bits =this_cpu_read (cpu_tlbstate.cr4) & mask; + cr4_pinned_bits =this_cpu_read (cpu_tlbstate.cr4) & cr4_pinned_mask;static_key_enable (&cr_pinning.key); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 220/265 x86/cpu: Reinitialize IA32_FEAT_CTL MSR on BSP during wakeup
In reply to Sasha LevinFrom: Sean Christopherson <[email protected]>
commit 5d5103595e9e53048bb7e70ee2673c897ab38300 upstream.
Reinitialize IA32_FEAT_CTL on the BSP during wakeup to handle the case where firmware doesn't initialize or save/restore across S3. This fixes a bug where IA32_FEAT_CTL is left uninitialized and results in VMXON taking a #GP due to VMX not being fully enabled, i.e. breaks KVM.
Use init_ia32_feat_ctl() to "restore" IA32_FEAT_CTL as it already deals with the case where the MSR is locked, and because APs already redo init_ia32_feat_ctl() during suspend by virtue of the SMP boot flow being used to reinitialize APs upon wakeup. Do the call in the early wakeup flow to avoid dependencies in the syscore_ops chain, e.g. simply adding a resume hook is not guaranteed to work, as KVM does VMXON in its own resume hook, kvm_resume(), when KVM has active guests.
--- arch/x86/include/asm/cpu.h | 5 +++++ arch/x86/kernel/cpu/centaur.c | 1 + arch/x86/kernel/cpu/cpu.h | 4 ---- arch/x86/kernel/cpu/zhaoxin.c | 1 + arch/x86/power/cpu.c | 6 ++++++ 5 files changed, 13 insertions(+), 4 deletions(-)
arch/x86/include/asm/cpu.h +5 -0
@@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip)return false; }#endif +#ifdef CONFIG_IA32_FEAT_CTL +void init_ia32_feat_ctl (struct cpuinfo_x86 *c); +#else +static inline void init_ia32_feat_ctl (struct cpuinfo_x86 *c) {} +#endif #endif /* _ASM_X86_CPU_H */
arch/x86/kernel/cpu/centaur.c +1 -0
@@ -3,6 +3,7 @@#include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/e820/api.h> #include <asm/mtrr.h>
arch/x86/kernel/cpu/cpu.h +0 -4
@@ -81,8 +81,4 @@ extern void update_srbds_msr(void);extern u64 x86_read_arch_cap_msr (void ); -#ifdef CONFIG_IA32_FEAT_CTL -void init_ia32_feat_ctl (struct cpuinfo_x86 *c); -#endif -#endif /* ARCH_X86_CPU_H */
arch/x86/kernel/cpu/zhaoxin.c +1 -0
@@ -2,6 +2,7 @@#include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include "cpu.h"
arch/x86/power/cpu.c +6 -0
@@ -193,6 +193,8 @@ static void fix_processor_context(void)*/ static void notrace __restore_processor_state(struct saved_context *ctxt) { +struct cpuinfo_x86 *c; +if (ctxt->misc_enable_saved)wrmsrl (MSR_IA32_MISC_ENABLE , ctxt->misc_enable);/*
@@ -263,6 +265,10 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)mtrr_bp_restore ();perf_restore_debug_store ();msr_restore_context (ctxt); + + c = &cpu_data (smp_processor_id ()); +if (cpu_has (c,X86_FEATURE_MSR_IA32_FEAT_CTL )) +init_ia32_feat_ctl (c); }/* Needed by apm.c */
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 221/265 x86/asm/64: Align start of __clear_user() loop to 16-bytes
In reply to Sasha LevinFrom: Matt Fleming <[email protected]>
commit bb5570ad3b54e7930997aec76ab68256d5236d94 upstream.
x86 CPUs can suffer severe performance drops if a tight loop, such as the ones in __clear_user(), straddles a 16-byte instruction fetch window, or worse, a 64-byte cacheline. This issues was discovered in the SUSE kernel with the following commit,
1153933703d9 ("x86/asm/64: Micro-optimize __clear_user() - Use immediate constants")
which increased the code object size from 10 bytes to 15 bytes and caused the 8-byte copy loop in __clear_user() to be split across a 64-byte cacheline.
Aligning the start of the loop to 16-bytes makes this fit neatly inside a single instruction fetch window again and restores the performance of __clear_user() which is used heavily when reading from /dev/zero.
Here are some numbers from running libmicro's read_z* and pread_z* microbenchmarks which read from /dev/zero:
Zen 1 (Naples)
libmicro-file
5.7.0-rc6 5.7.0-rc6 5.7.0-rc6
revert-1153933703d9+ align16+
Time mean95-pread_z100k 9.9195 ( 0.00%) 5.9856 ( 39.66%) 5.9938 ( 39.58%)
Time mean95-pread_z10k 1.1378 ( 0.00%) 0.7450 ( 34.52%) 0.7467 ( 34.38%)
Time mean95-pread_z1k 0.2623 ( 0.00%) 0.2251 ( 14.18%) 0.2252 ( 14.15%)
Time mean95-pread_zw100k 9.9974 ( 0.00%) 6.0648 ( 39.34%) 6.0756 ( 39.23%)
Time mean95-read_z100k 9.8940 ( 0.00%) 5.9885 ( 39.47%) 5.9994 ( 39.36%)
Time mean95-read_z10k 1.1394 ( 0.00%) 0.7483 ( 34.33%) 0.7482 ( 34.33%)Note that this doesn't affect Haswell or Broadwell microarchitectures which seem to avoid the alignment issue by executing the loop straight out of the Loop Stream Detector (verified using perf events).
--- arch/x86/lib/usercopy_64.c | 1 + 1 file changed, 1 insertion(+)
arch/x86/lib/usercopy_64.c +1 -0
@@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size) asmvolatile (" testq %[size8],%[size8]\n" " jz 4f\n" +" .align 16\n" "0: movq $0,(%[dst])\n" " addq $8,%[dst]\n" " decl %%ecx ; jnz 0b\n"
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 222/265 btrfs: fix bytes_may_use underflow when running balance and scrub in parallel
In reply to Sasha LevinFrom: Filipe Manana <[email protected]>
commit 6bd335b469f945f75474c11e3f577f85409f39c3 upstream.
When balance and scrub are running in parallel it is possible to end up with an underflow of the bytes_may_use counter of the data space_info object, which triggers a warning like the following:
[134243.793196] BTRFS info (device sdc): relocating block group 1104150528 flags data [134243.806891] ------------[ cut here ]------------ [134243.807561] WARNING: CPU: 1 PID: 26884 at fs/btrfs/space-info.h:125 btrfs_add_reserved_bytes+0x1da/0x280 [btrfs] [134243.808819] Modules linked in: btrfs blake2b_generic xor (...) [134243.815779] CPU: 1 PID: 26884 Comm: kworker/u8:8 Tainted: G W 5.6.0-rc7-btrfs-next-58 #5 [134243.816944] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 [134243.818389] Workqueue: writeback wb_workfn (flush-btrfs-108483) [134243.819186] RIP: 0010:btrfs_add_reserved_bytes+0x1da/0x280 [btrfs] [134243.819963] Code: 0b f2 85 (...) [134243.822271] RSP: 0018:ffffa4160aae7510 EFLAGS: 00010287 [134243.822929] RAX: 000000000000c000 RBX: ffff96159a8c1000 RCX: 0000000000000000 [134243.823816] RDX: 0000000000008000 RSI: 0000000000000000 RDI: ffff96158067a810 [134243.824742] RBP: ffff96158067a800 R08: 0000000000000001 R09: 0000000000000000 [134243.825636] R10: ffff961501432a40 R11: 0000000000000000 R12: 000000000000c000 [134243.826532] R13: 0000000000000001 R14: ffffffffffff4000 R15: ffff96158067a810 [134243.827432] FS: 0000000000000000(0000) GS:ffff9615baa00000(0000) knlGS:0000000000000000 [134243.828451] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [134243.829184] CR2: 000055bd7e414000 CR3: 00000001077be004 CR4: 00000000003606e0 [134243.830083] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [134243.830975] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [134243.831867] Call Trace: [134243.832211] find_free_extent+0x4a0/0x16c0 [btrfs] [134243.832846] btrfs_reserve_extent+0x91/0x180 [btrfs] [134243.833487] cow_file_range+0x12d/0x490 [btrfs] [134243.834080] fallback_to_cow+0x82/0x1b0 [btrfs] [134243.834689] ? release_extent_buffer+0x121/0x170 [btrfs] [134243.835370] run_delalloc_nocow+0x33f/0xa30 [btrfs] [134243.836032] btrfs_run_delalloc_range+0x1ea/0x6d0 [btrfs] [134243.836725] ? find_lock_delalloc_range+0x221/0x250 [btrfs] [134243.837450] writepage_delalloc+0xe8/0x150 [btrfs] [134243.838059] __extent_writepage+0xe8/0x4c0 [btrfs] [134243.838674] extent_write_cache_pages+0x237/0x530 [btrfs] [134243.839364] extent_writepages+0x44/0xa0 [btrfs] [134243.839946] do_writepages+0x23/0x80 [134243.840401] __writeback_single_inode+0x59/0x700 [134243.841006] writeback_sb_inodes+0x267/0x5f0 [134243.841548] __writeback_inodes_wb+0x87/0xe0 [134243.842091] wb_writeback+0x382/0x590 [134243.842574] ? wb_workfn+0x4a2/0x6c0 [134243.843030] wb_workfn+0x4a2/0x6c0 [134243.843468] process_one_work+0x26d/0x6a0 [134243.843978] worker_thread+0x4f/0x3e0 [134243.844452] ? process_one_work+0x6a0/0x6a0 [134243.844981] kthread+0x103/0x140 [134243.845400] ? kthread_create_worker_on_cpu+0x70/0x70 [134243.846030] ret_from_fork+0x3a/0x50 [134243.846494] irq event stamp: 0 [134243.846892] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [134243.847682] hardirqs last disabled at (0): [<ffffffffb2abdedf>] copy_process+0x74f/0x2020 [134243.848687] softirqs last enabled at (0): [<ffffffffb2abdedf>] copy_process+0x74f/0x2020 [134243.849913] softirqs last disabled at (0): [<0000000000000000>] 0x0 [134243.850698] ---[ end trace bd7c03622e0b0a96 ]--- [134243.851335] ------------[ cut here ]------------
When relocating a data block group, for each extent allocated in the block group we preallocate another extent with the same size for the data relocation inode (we do it at prealloc_file_extent_cluster()). We reserve space by calling btrfs_check_data_free_space(), which ends up incrementing the data space_info's bytes_may_use counter, and then call btrfs_prealloc_file_range() to allocate the extent, which always decrements the bytes_may_use counter by the same amount.
The expectation is that writeback of the data relocation inode always follows a NOCOW path, by writing into the preallocated extents. However, when starting writeback we might end up falling back into the COW path, because the block group that contains the preallocated extent was turned into RO mode by a scrub running in parallel. The COW path then calls the extent allocator which ends up calling btrfs_add_reserved_bytes(), and this function decrements the bytes_may_use counter of the data space_info object by an amount corresponding to the size of the allocated extent, despite we haven't previously incremented it. When the counter currently has a value smaller then the allocated extent we reset the counter to 0 and emit a warning, otherwise we just decrement it and slowly mess up with this counter which is crucial for space reservation, the end result can be granting reserved space to tasks when there isn't really enough free space, and having the tasks fail later in critical places where error handling consists of a transaction abort or hitting a BUG_ON().
Fix this by making sure that if we fallback to the COW path for a data relocation inode, we increment the bytes_may_use counter of the data space_info object. The COW path will then decrement it at btrfs_add_reserved_bytes() on success or through its error handling part by a call to extent_clear_unlock_delalloc() (which ends up calling btrfs_clear_delalloc_extent() that does the decrement operation) in case of an error.
Test case btrfs/061 from fstests could sporadically trigger this.
--- fs/btrfs/inode.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)
fs/btrfs/inode.c +12 -5
@@ -1361,6 +1361,8 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page, int *page_started, unsigned long *nr_written) { const bool is_space_ino = btrfs_is_free_space_inode(BTRFS_I(inode)); +const bool is_reloc_ino = (BTRFS_I (inode)->root->root_key.objectid == +BTRFS_DATA_RELOC_TREE_OBJECTID );const u64 range_bytes = end +1 - start;struct extent_io_tree *io_tree = &BTRFS_I (inode)->io_tree;u64 range_start = start;
@@ -1391,18 +1393,23 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page,* data space info, which we incremented in the step above. * * If we need to fallback to cow and the inode corresponds to a free -* space cache inode, we must also increment bytes_may_use of the data -* space_info for the same reason. Space caches always get a prealloc +* space cache inode or an inode of the data relocation tree, we must +* also increment bytes_may_use of the data space_info for the same +* reason. Space caches and relocated data extents always get a prealloc * extent for them, however scrub or balance may have set the block -* group that contains that extent to RO mode. +* group that contains that extent to RO mode and therefore force COW +* when starting writeback. */ count =count_range_bits (io_tree, &range_start, end, range_bytes,EXTENT_NORESERVE ,0 ); -if (count >0 || is_space_ino) { -const u64 bytes = is_space_ino ? range_bytes : count; +if (count >0 || is_space_ino || is_reloc_ino) { +u64 bytes = count;struct btrfs_fs_info *fs_info =BTRFS_I (inode)->root->fs_info;struct btrfs_space_info *sinfo = fs_info->data_sinfo; +if (is_space_ino || is_reloc_ino) + bytes = range_bytes; +spin_lock (&sinfo->lock);btrfs_space_info_update_bytes_may_use (fs_info, sinfo, bytes);spin_unlock (&sinfo->lock);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 223/265 btrfs: fix data block group relocation failure due to concurrent scrub
In reply to Sasha LevinFrom: Filipe Manana <[email protected]>
commit 432cd2a10f1c10cead91fe706ff5dc52f06d642a upstream.
When running relocation of a data block group while scrub is running in parallel, it is possible that the relocation will fail and abort the current transaction with an -EINVAL error:
[134243.988595] BTRFS info (device sdc): found 14 extents, stage: move data extents [134243.999871] ------------[ cut here ]------------ [134244.000741] BTRFS: Transaction aborted (error -22) [134244.001692] WARNING: CPU: 0 PID: 26954 at fs/btrfs/ctree.c:1071 __btrfs_cow_block+0x6a7/0x790 [btrfs] [134244.003380] Modules linked in: btrfs blake2b_generic xor raid6_pq (...) [134244.012577] CPU: 0 PID: 26954 Comm: btrfs Tainted: G W 5.6.0-rc7-btrfs-next-58 #5 [134244.014162] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 [134244.016184] RIP: 0010:__btrfs_cow_block+0x6a7/0x790 [btrfs] [134244.017151] Code: 48 c7 c7 (...) [134244.020549] RSP: 0018:ffffa41607863888 EFLAGS: 00010286 [134244.021515] RAX: 0000000000000000 RBX: ffff9614bdfe09c8 RCX: 0000000000000000 [134244.022822] RDX: 0000000000000001 RSI: ffffffffb3d63980 RDI: 0000000000000001 [134244.024124] RBP: ffff961589e8c000 R08: 0000000000000000 R09: 0000000000000001 [134244.025424] R10: ffffffffc0ae5955 R11: 0000000000000000 R12: ffff9614bd530d08 [134244.026725] R13: ffff9614ced41b88 R14: ffff9614bdfe2a48 R15: 0000000000000000 [134244.028024] FS: 00007f29b63c08c0(0000) GS:ffff9615ba600000(0000) knlGS:0000000000000000 [134244.029491] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [134244.030560] CR2: 00007f4eb339b000 CR3: 0000000130d6e006 CR4: 00000000003606f0 [134244.031997] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [134244.033153] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [134244.034484] Call Trace: [134244.034984] btrfs_cow_block+0x12b/0x2b0 [btrfs] [134244.035859] do_relocation+0x30b/0x790 [btrfs] [134244.036681] ? do_raw_spin_unlock+0x49/0xc0 [134244.037460] ? _raw_spin_unlock+0x29/0x40 [134244.038235] relocate_tree_blocks+0x37b/0x730 [btrfs] [134244.039245] relocate_block_group+0x388/0x770 [btrfs] [134244.040228] btrfs_relocate_block_group+0x161/0x2e0 [btrfs] [134244.041323] btrfs_relocate_chunk+0x36/0x110 [btrfs] [134244.041345] btrfs_balance+0xc06/0x1860 [btrfs] [134244.043382] ? btrfs_ioctl_balance+0x27c/0x310 [btrfs] [134244.045586] btrfs_ioctl_balance+0x1ed/0x310 [btrfs] [134244.045611] btrfs_ioctl+0x1880/0x3760 [btrfs] [134244.049043] ? do_raw_spin_unlock+0x49/0xc0 [134244.049838] ? _raw_spin_unlock+0x29/0x40 [134244.050587] ? __handle_mm_fault+0x11b3/0x14b0 [134244.051417] ? ksys_ioctl+0x92/0xb0 [134244.052070] ksys_ioctl+0x92/0xb0 [134244.052701] ? trace_hardirqs_off_thunk+0x1a/0x1c [134244.053511] __x64_sys_ioctl+0x16/0x20 [134244.054206] do_syscall_64+0x5c/0x280 [134244.054891] entry_SYSCALL_64_after_hwframe+0x49/0xbe [134244.055819] RIP: 0033:0x7f29b51c9dd7 [134244.056491] Code: 00 00 00 (...) [134244.059767] RSP: 002b:00007ffcccc1dd08 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 [134244.061168] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007f29b51c9dd7 [134244.062474] RDX: 00007ffcccc1dda0 RSI: 00000000c4009420 RDI: 0000000000000003 [134244.063771] RBP: 0000000000000003 R08: 00005565cea4b000 R09: 0000000000000000 [134244.065032] R10: 0000000000000541 R11: 0000000000000202 R12: 00007ffcccc2060a [134244.066327] R13: 00007ffcccc1dda0 R14: 0000000000000002 R15: 00007ffcccc1dec0 [134244.067626] irq event stamp: 0 [134244.068202] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [134244.069351] hardirqs last disabled at (0): [<ffffffffb2abdedf>] copy_process+0x74f/0x2020 [134244.070909] softirqs last enabled at (0): [<ffffffffb2abdedf>] copy_process+0x74f/0x2020 [134244.072392] softirqs last disabled at (0): [<0000000000000000>] 0x0 [134244.073432] ---[ end trace bd7c03622e0b0a99 ]---
The -EINVAL error comes from the following chain of function calls:
__btrfs_cow_block() <-- aborts the transaction
btrfs_reloc_cow_block()
replace_file_extents()
get_new_location() <-- returns -EINVAL
When relocating a data block group, for each allocated extent of the block group, we preallocate another extent (at prealloc_file_extent_cluster()), associated with the data relocation inode, and then dirty all its pages. These preallocated extents have, and must have, the same size that extents from the data block group being relocated have.
Later before we start the relocation stage that updates pointers (bytenr field of file extent items) to point to the the new extents, we trigger writeback for the data relocation inode. The expectation is that writeback will write the pages to the previously preallocated extents, that it follows the NOCOW path. That is generally the case, however, if a scrub is running it may have turned the block group that contains those extents into RO mode, in which case writeback falls back to the COW path.
However in the COW path instead of allocating exactly one extent with the expected size, the allocator may end up allocating several smaller extents due to free space fragmentation - because we tell it at cow_file_range() that the minimum allocation size can match the filesystem's sector size. This later breaks the relocation's expectation that an extent associated to a file extent item in the data relocation inode has the same size as the respective extent pointed by a file extent item in another tree - in this case the extent to which the relocation inode poins to is smaller, causing relocation.c:get_new_location() to return -EINVAL.
For example, if we are relocating a data block group X that has a logical address of X and the block group has an extent allocated at the logical address X + 128KiB with a size of 64KiB:
1) At prealloc_file_extent_cluster() we allocate an extent for the data relocation inode with a size of 64KiB and associate it to the file offset 128KiB (X + 128KiB - X) of the data relocation inode. This preallocated extent was allocated at block group Z;
2) A scrub running in parallel turns block group Z into RO mode and starts scrubing its extents;
3) Relocation triggers writeback for the data relocation inode;
4) When running delalloc (btrfs_run_delalloc_range()), we try first the NOCOW path because the data relocation inode has BTRFS_INODE_PREALLOC set in its flags. However, because block group Z is in RO mode, the NOCOW path (run_delalloc_nocow()) falls back into the COW path, by calling cow_file_range();
5) At cow_file_range(), in the first iteration of the while loop we call btrfs_reserve_extent() to allocate a 64KiB extent and pass it a minimum allocation size of 4KiB (fs_info->sectorsize). Due to free space fragmentation, btrfs_reserve_extent() ends up allocating two extents of 32KiB each, each one on a different iteration of that while loop;
6) Writeback of the data relocation inode completes;
7) Relocation proceeds and ends up at relocation.c:replace_file_extents(), with a leaf which has a file extent item that points to the data extent from block group X, that has a logical address (bytenr) of X + 128KiB and a size of 64KiB. Then it calls get_new_location(), which does a lookup in the data relocation tree for a file extent item starting at offset 128KiB (X + 128KiB - X) and belonging to the data relocation inode. It finds a corresponding file extent item, however that item points to an extent that has a size of 32KiB, which doesn't match the expected size of 64KiB, resuling in -EINVAL being returned from this function and propagated up to __btrfs_cow_block(), which aborts the current transaction.
To fix this make sure that at cow_file_range() when we call the allocator we pass it a minimum allocation size corresponding the desired extent size if the inode belongs to the data relocation tree, otherwise pass it the filesystem's sector size as the minimum allocation size.
--- fs/btrfs/inode.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-)
fs/btrfs/inode.c +18 -1
@@ -985,6 +985,7 @@ static noinline int cow_file_range(struct inode *inode,u64 num_bytes;unsigned long ram_size;u64 cur_alloc_size =0 ; +u64 min_alloc_size;u64 blocksize = fs_info->sectorsize;struct btrfs_key ins;struct extent_map *em;
@@ -1035,10 +1036,26 @@ static noinline int cow_file_range(struct inode *inode,btrfs_drop_extent_cache (BTRFS_I (inode), start, start + num_bytes -1 ,0 ); +/* +* Relocation relies on the relocated extents to have exactly the same +* size as the original extents. Normally writeback for relocation data +* extents follows a NOCOW path because relocation preallocates the +* extents. However, due to an operation such as scrub turning a block +* group to RO mode, it may fallback to COW mode, so we must make sure +* an extent allocated during COW has exactly the requested size and can +* not be split into smaller extents, otherwise relocation breaks and +* fails during the stage where it updates the bytenr of file extent +* items. +*/ +if (root->root_key.objectid ==BTRFS_DATA_RELOC_TREE_OBJECTID ) + min_alloc_size = num_bytes; +else + min_alloc_size = fs_info->sectorsize; +while (num_bytes >0 ) { cur_alloc_size = num_bytes; ret =btrfs_reserve_extent (root, cur_alloc_size, cur_alloc_size, - fs_info->sectorsize,0 , alloc_hint, + min_alloc_size,0 , alloc_hint, &ins,1 ,1 );if (ret <0 ) goto out_unlock;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 224/265 btrfs: check if a log root exists before locking the log_mutex on unlink
In reply to Sasha LevinFrom: Filipe Manana <[email protected]>
commit e7a79811d0db136dc2d336b56d54cf1b774ce972 upstream.
This brings back an optimization that commit e678934cbe5f02 ("btrfs:
Remove unnecessary check from join_running_log_trans") removed, but in a different form. So it's almost equivalent to a revert.
That commit removed an optimization where we avoid locking a root's log_mutex when there is no log tree created in the current transaction. The affected code path is triggered through unlink operations.
That commit was based on the assumption that the optimization was not necessary because we used to have the following checks when the patch was authored:
int btrfs_del_dir_entries_in_log(...)
{
(...)
if (dir->logged_trans < trans->transid)
return 0; ret = join_running_log_trans(root);
(...)}
int btrfs_del_inode_ref_in_log(...)
{
(...)
if (inode->logged_trans < trans->transid)
return 0; ret = join_running_log_trans(root);
(...)}
However before that patch was merged, another patch was merged first which replaced those checks because they were buggy.
That other patch corresponds to commit 803f0f64d17769 ("Btrfs: fix fsync not persisting dentry deletions due to inode evictions"). The assumption that if the logged_trans field of an inode had a smaller value then the current transaction's generation (transid) meant that the inode was not logged in the current transaction was only correct if the inode was not evicted and reloaded in the current transaction. So the corresponding bug fix changed those checks and replaced them with the following helper function:
static bool inode_logged(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode)
{
if (inode->logged_trans == trans->transid)
return true;
if (inode->last_trans == trans->transid &&
test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) &&
!test_bit(BTRFS_FS_LOG_RECOVERING, &trans->fs_info->flags))
return true;
return false;}
So if we have a subvolume without a log tree in the current transaction (because we had no fsyncs), every time we unlink an inode we can end up trying to lock the log_mutex of the root through join_running_log_trans() twice, once for the inode being unlinked (by btrfs_del_inode_ref_in_log()) and once for the parent directory (with btrfs_del_dir_entries_in_log()).
This means if we have several unlink operations happening in parallel for inodes in the same subvolume, and the those inodes and/or their parent inode were changed in the current transaction, we end up having a lot of contention on the log_mutex.
The test robots from intel reported a -30.7% performance regression for a REAIM test after commit e678934cbe5f02 ("btrfs: Remove unnecessary check from join_running_log_trans").
So just bring back the optimization to join_running_log_trans() where we check first if a log root exists before trying to lock the log_mutex. This is done by checking for a bit that is set on the root when a log tree is created and removed when a log tree is freed (at transaction commit time).
Commit e678934cbe5f02 ("btrfs: Remove unnecessary check from join_running_log_trans") was merged in the 5.4 merge window while commit 803f0f64d17769 ("Btrfs: fix fsync not persisting dentry deletions due to inode evictions") was merged in the 5.3 merge window. But the first commit was actually authored before the second commit (May 23 2019 vs June 19 2019).
--- fs/btrfs/ctree.h | 2 ++ fs/btrfs/tree-log.c | 5 +++++ 2 files changed, 7 insertions(+)
fs/btrfs/ctree.h +2 -0
@@ -988,6 +988,8 @@ enum {BTRFS_ROOT_DEAD_RELOC_TREE ,/* Mark dead root stored on device whose cleanup needs to be resumed */ BTRFS_ROOT_DEAD_TREE , +/* The root has a log tree. Used only for subvolume roots. */ + BTRFS_ROOT_HAS_LOG_TREE, };/*
fs/btrfs/tree-log.c +5 -0
@@ -169,6 +169,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans,if (ret) goto out; +set_bit (BTRFS_ROOT_HAS_LOG_TREE , &root->state);clear_bit (BTRFS_ROOT_MULTI_LOG_TASKS , &root->state); root->log_start_pid = current->pid; }
@@ -195,6 +196,9 @@ static int join_running_log_trans(struct btrfs_root *root) {int ret = -ENOENT ; +if (!test_bit (BTRFS_ROOT_HAS_LOG_TREE , &root->state)) +return ret; +mutex_lock (&root->log_mutex);if (root->log_root) { ret =0 ;
@@ -3312,6 +3316,7 @@ int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root)if (root->log_root) {free_log_tree (trans, root->log_root); root->log_root =NULL ; +clear_bit (BTRFS_ROOT_HAS_LOG_TREE , &root->state); }return 0 ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 225/265 btrfs: fix hang on snapshot creation after RWF_NOWAIT write
In reply to Sasha LevinFrom: Filipe Manana <[email protected]>
commit f2cb2f39ccc30fa13d3ac078d461031a63960e5b upstream.
If we do a successful RWF_NOWAIT write we end up locking the snapshot lock of the inode, through a call to check_can_nocow(), but we never unlock it.
This means the next attempt to create a snapshot on the subvolume will hang forever.
Trivial reproducer:
$ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt
$ touch /mnt/foobar $ chattr +C /mnt/foobar $ xfs_io -d -c "pwrite -S 0xab 0 64K" /mnt/foobar $ xfs_io -d -c "pwrite -N -V 1 -S 0xfe 0 64K" /mnt/foobar
$ btrfs subvolume snapshot -r /mnt /mnt/snap
--> hangsFix this by unlocking the snapshot lock if check_can_nocow() returned success.
--- fs/btrfs/file.c | 2 ++ 1 file changed, 2 insertions(+)
fs/btrfs/file.c +2 -0
@@ -1922,6 +1922,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,inode_unlock (inode);return -EAGAIN ; } +/* check_can_nocow() locks the snapshot lock on success */ +btrfs_drew_write_unlock (&root->snapshot_lock); } current->backing_dev_info =inode_to_bdi (inode);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 226/265 btrfs: fix failure of RWF_NOWAIT write into prealloc extent beyond eof
In reply to Sasha LevinFrom: Filipe Manana <[email protected]>
commit 4b1946284dd6641afdb9457101056d9e6ee6204c upstream.
If we attempt to write to prealloc extent located after eof using a RWF_NOWAIT write, we always fail with -EAGAIN.
We do actually check if we have an allocated extent for the write at the start of btrfs_file_write_iter() through a call to check_can_nocow(), but later when we go into the actual direct IO write path we simply return -EAGAIN if the write starts at or beyond EOF.
Trivial to reproduce:
$ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt
$ touch /mnt/foo $ chattr +C /mnt/foo
$ xfs_io -d -c "pwrite -S 0xab 0 64K" /mnt/foo wrote 65536/65536 bytes at offset 0 64 KiB, 16 ops; 0.0004 sec (135.575 MiB/sec and 34707.1584 ops/sec)
$ xfs_io -c "falloc -k 64K 1M" /mnt/foo
$ xfs_io -d -c "pwrite -N -V 1 -S 0xfe -b 64K 64K 64K" /mnt/foo pwrite: Resource temporarily unavailable
On xfs and ext4 the write succeeds, as expected.
Fix this by removing the wrong check at btrfs_direct_IO().
--- fs/btrfs/inode.c | 3 --- 1 file changed, 3 deletions(-)
fs/btrfs/inode.c +0 -3
@@ -8262,9 +8262,6 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.overwrite =1 ;inode_unlock (inode); relock = true; - }else if (iocb->ki_flags &IOCB_NOWAIT ) { - ret = -EAGAIN ; - goto out; } ret =btrfs_delalloc_reserve_space (inode, &data_reserved, offset, count);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 227/265 btrfs: fix RWF_NOWAIT write not failling when we need to cow
In reply to Sasha LevinFrom: Filipe Manana <[email protected]>
commit 260a63395f90f67d6ab89e4266af9e3dc34a77e9 upstream.
If we attempt to do a RWF_NOWAIT write against a file range for which we can only do NOCOW for a part of it, due to the existence of holes or shared extents for example, we proceed with the write as if it were possible to NOCOW the whole range.
Example:
$ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt
$ touch /mnt/sdj/bar $ chattr +C /mnt/sdj/bar
$ xfs_io -d -c "pwrite -S 0xab -b 256K 0 256K" /mnt/bar wrote 262144/262144 bytes at offset 0 256 KiB, 1 ops; 0.0003 sec (694.444 MiB/sec and 2777.7778 ops/sec)
$ xfs_io -c "fpunch 64K 64K" /mnt/bar $ sync
$ xfs_io -d -c "pwrite -N -V 1 -b 128K -S 0xfe 0 128K" /mnt/bar wrote 131072/131072 bytes at offset 0 128 KiB, 1 ops; 0.0007 sec (160.051 MiB/sec and 1280.4097 ops/sec)
This last write should fail with -EAGAIN since the file range from 64K to 128K is a hole. On xfs it fails, as expected, but on ext4 it currently succeeds because apparently it is expensive to check if there are extents allocated for the whole range, but I'll check with the ext4 people.
Fix the issue by checking if check_can_nocow() returns a number of NOCOW'able bytes smaller then the requested number of bytes, and if it does return -EAGAIN.
--- fs/btrfs/file.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)
fs/btrfs/file.c +12 -1
@@ -1912,18 +1912,29 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, pos = iocb->ki_pos; count =iov_iter_count (from);if (iocb->ki_flags &IOCB_NOWAIT ) { +size_t nocow_bytes = count; +/* * We will allocate space in case nodatacow is not set, * so bail */ if (!(BTRFS_I (inode)->flags & (BTRFS_INODE_NODATACOW |BTRFS_INODE_PREALLOC )) || -check_can_nocow (BTRFS_I (inode), pos, &count) <=0 ) { +check_can_nocow (BTRFS_I (inode), pos, &nocow_bytes) <=0 ) {inode_unlock (inode);return -EAGAIN ; }/* check_can_nocow() locks the snapshot lock on success */ btrfs_drew_write_unlock (&root->snapshot_lock); +/* +* There are holes in the range or parts of the range that must +* be COWed (shared extents, RO block groups, etc), so just bail +* out. +*/ +if (nocow_bytes < count) { +inode_unlock (inode); +return -EAGAIN ; + } } current->backing_dev_info =inode_to_bdi (inode);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 228/265 mm, compaction: make capture control handling safe wrt interrupts
In reply to Sasha LevinFrom: Vlastimil Babka <[email protected]>
commit b9e20f0da1f5c9c68689450a8cb436c9486434c8 upstream.
Hugh reports:
"While stressing compaction, one run oopsed on NULL capc->cc in
__free_one_page()'s task_capc(zone): compact_zone_order() had been interrupted, and a page was being freed in the return from interrupt.
Though you would not expect it from the source, both gccs I was using (4.8.1 and 7.5.0) had chosen to compile compact_zone_order() with the ".cc = &cc" implemented by mov %rbx,-0xb0(%rbp) immediately before callq compact_zone - long after the "current->capture_control = &capc". An interrupt in between those finds capc->cc NULL (zeroed by an earlier rep stos).
This could presumably be fixed by a barrier() before setting current->capture_control in compact_zone_order(); but would also need more care on return from compact_zone(), in order not to risk leaking a page captured by interrupt just before capture_control is reset.
Maybe that is the preferable fix, but I felt safer for task_capc() to exclude the rather surprising possibility of capture at interrupt time"
I have checked that gcc10 also behaves the same.
The advantage of fix in compact_zone_order() is that we don't add another test in the page freeing hot path, and that it might prevent future problems if we stop exposing pointers to uninitialized structures in current task.
So this patch implements the suggestion for compact_zone_order() with barrier() (and WRITE_ONCE() to prevent store tearing) for setting current->capture_control, and prevents page leaking with WRITE_ONCE/READ_ONCE in the proper order.
--- mm/compaction.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-)
mm/compaction.c +14 -3
@@ -2318,15 +2318,26 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, .page = NULL, }; - current->capture_control = &capc; +/* +* Make sure the structs are really initialized before we expose the +* capture control, in case we are interrupted and the interrupt handler +* frees a page. +*/ +barrier (); +WRITE_ONCE (current->capture_control, &capc); ret =compact_zone (&cc, &capc);VM_BUG_ON (!list_empty (&cc.freepages));VM_BUG_ON (!list_empty (&cc.migratepages)); - *capture = capc.page; - current->capture_control =NULL ; +/* +* Make sure we hide capture control first before we read the captured +* page pointer, otherwise an interrupt could free and capture a page +* and we would leak it. +*/ +WRITE_ONCE (current->capture_control,NULL ); + *capture =READ_ONCE (capc.page);return ret; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 229/265 mm, slab: fix sign conversion problem in memcg_uncharge_slab()
In reply to Sasha LevinFrom: Waiman Long <[email protected]>
commit d7670879c5c4aa443d518fb234a9e5f30931efa3 upstream.
It was found that running the LTP test on a PowerPC system could produce erroneous values in /proc/meminfo, like:
MemTotal: 531915072 kB MemFree: 507962176 kB MemAvailable: 1100020596352 kB
Using bisection, the problem is tracked down to commit 9c315e4d7d8c ("mm:
memcg/slab: cache page number in memcg_(un)charge_slab()").
In memcg_uncharge_slab() with a "int order" argument:
unsigned int nr_pages = 1 << order;
:
mod_lruvec_state(lruvec, cache_vmstat_idx(s), -nr_pages);The mod_lruvec_state() function will eventually call the __mod_zone_page_state() which accepts a long argument. Depending on the compiler and how inlining is done, "-nr_pages" may be treated as a negative number or a very large positive number. Apparently, it was treated as a large positive number in that PowerPC system leading to incorrect stat counts. This problem hasn't been seen in x86-64 yet, perhaps the gcc compiler there has some slight difference in behavior.
It is fixed by making nr_pages a signed value. For consistency, a similar change is applied to memcg_charge_slab() as well.
--- mm/slab.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
mm/slab.h +2 -2
@@ -348,7 +348,7 @@ static __always_inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order, struct kmem_cache *s) { - unsigned int nr_pages = 1 << order; + int nr_pages = 1 << order;struct mem_cgroup *memcg;struct lruvec *lruvec;int ret;
@@ -388,7 +388,7 @@ out: static __always_inline void memcg_uncharge_slab(struct page *page, int order,struct kmem_cache *s) { -unsigned int nr_pages =1 << order; +int nr_pages =1 << order;struct mem_cgroup *memcg;struct lruvec *lruvec;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 230/265 mm/slab: use memzero_explicit() in kzfree()
In reply to Sasha LevinFrom: Waiman Long <[email protected]>
commit 8982ae527fbef170ef298650c15d55a9ccd33973 upstream.
The kzfree() function is normally used to clear some sensitive information, like encryption keys, in the buffer before freeing it back to the pool. Memset() is currently used for buffer clearing. However unlikely, there is still a non-zero probability that the compiler may choose to optimize away the memory clearing especially if LTO is being used in the future.
To make sure that this optimization will never happen, memzero_explicit(), which is introduced in v3.18, is now used in kzfree() to future-proof it.
--- mm/slab_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
mm/slab_common.c +1 -1
@@ -1726,7 +1726,7 @@ void kzfree(const void *p)if (unlikely (ZERO_OR_NULL_PTR (mem)))return ; ks =ksize (mem); -memset (mem,0 , ks); +memzero_explicit (mem, ks);kfree (mem); }EXPORT_SYMBOL (kzfree);
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 231/265 ocfs2: avoid inode removal while nfsd is accessing it
In reply to Sasha LevinFrom: Junxiao Bi <[email protected]>
commit 4cd9973f9ff69e37dd0ba2bd6e6423f8179c329a upstream.
Patch series "ocfs2: fix nfsd over ocfs2 issues", v2.
This is a series of patches to fix issues on nfsd over ocfs2. patch 1 is to avoid inode removed while nfsd access it patch 2 & 3 is to fix a panic issue.
This patch (of 4):
When nfsd is getting file dentry using handle or parent dentry of some dentry, one cluster lock is used to avoid inode removed from other node, but it still could be removed from local node, so use a rw lock to avoid this.
--- fs/ocfs2/dlmglue.c | 17 ++++++++++++++++- fs/ocfs2/ocfs2.h | 1 + 2 files changed, 17 insertions(+), 1 deletion(-)
fs/ocfs2/dlmglue.c +16 -1
@@ -689,6 +689,12 @@ static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res, &ocfs2_nfs_sync_lops, osb); } +static void ocfs2_nfs_sync_lock_init (struct ocfs2_super *osb) +{ +ocfs2_nfs_sync_lock_res_init (&osb->osb_nfs_sync_lockres, osb); +init_rwsem (&osb->nfs_sync_rwlock); +} +void ocfs2_trim_fs_lock_res_init (struct ocfs2_super *osb) {struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres;
@@ -2855,6 +2861,11 @@ int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex)if (ocfs2_is_hard_readonly (osb))return -EROFS ; +if (ex) +down_write (&osb->nfs_sync_rwlock); +else +down_read (&osb->nfs_sync_rwlock); +if (ocfs2_mount_local (osb))return 0 ;
@@ -2873,6 +2884,10 @@ void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex)if (!ocfs2_mount_local (osb))ocfs2_cluster_unlock (osb, lockres, ex ?LKM_EXMODE :LKM_PRMODE ); +if (ex) +up_write (&osb->nfs_sync_rwlock); +else +up_read (&osb->nfs_sync_rwlock); } int ocfs2_trim_fs_lock(struct ocfs2_super *osb,
@@ -3340,7 +3355,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb) local:ocfs2_super_lock_res_init (&osb->osb_super_lockres, osb);ocfs2_rename_lock_res_init (&osb->osb_rename_lockres, osb); -ocfs2_nfs_sync_lock_res_init (&osb->osb_nfs_sync_lockres, osb); +ocfs2_nfs_sync_lock_init (osb);ocfs2_orphan_scan_lock_res_init (&osb->osb_orphan_scan.os_lockres, osb); osb->cconn = conn;
fs/ocfs2/ocfs2.h +1 -0
@@ -394,6 +394,7 @@ struct ocfs2_superstruct ocfs2_lock_res osb_super_lockres;struct ocfs2_lock_res osb_rename_lockres;struct ocfs2_lock_res osb_nfs_sync_lockres; +struct rw_semaphore nfs_sync_rwlock;struct ocfs2_lock_res osb_trim_fs_lockres;struct mutex obs_trim_fs_mutex;struct ocfs2_dlm_debug *osb_dlm_debug;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 232/265 ocfs2: load global_inode_alloc
In reply to Sasha LevinFrom: Junxiao Bi <[email protected]>
commit 7569d3c754e452769a5747eeeba488179e38a5da upstream.
Set global_inode_alloc as OCFS2_FIRST_ONLINE_SYSTEM_INODE, that will make it load during mount. It can be used to test whether some global/system inodes are valid. One use case is that nfsd will test whether root inode is valid.
--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/ocfs2/ocfs2_fs.h +1 -1
@@ -326,8 +326,8 @@ struct ocfs2_system_inode_info {enum {BAD_BLOCK_SYSTEM_INODE =0 ,GLOBAL_INODE_ALLOC_SYSTEM_INODE , +#define OCFS2_FIRST_ONLINE_SYSTEM_INODE GLOBAL_INODE_ALLOC_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE, -#define OCFS2_FIRST_ONLINE_SYSTEM_INODE SLOT_MAP_SYSTEM_INODEHEARTBEAT_SYSTEM_INODE ,GLOBAL_BITMAP_SYSTEM_INODE ,USER_QUOTA_SYSTEM_INODE ,
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 233/265 ocfs2: fix value of OCFS2_INVALID_SLOT
In reply to Sasha LevinFrom: Junxiao Bi <[email protected]>
commit 9277f8334ffc719fe922d776444d6e4e884dbf30 upstream.
In the ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implementation, slot number is 32 bits. Usually this will not cause any issue, because slot number is converted from u16 to u32, but OCFS2_INVALID_SLOT was defined as -1, when an invalid slot number from disk was obtained, its value was (u16)-1, and it was converted to u32. Then the following checking in get_local_system_inode will be always skipped:
static struct inode **get_local_system_inode(struct ocfs2_super *osb,
int type,
u32 slot)
{
BUG_ON(slot == OCFS2_INVALID_SLOT);
...}
--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/ocfs2/ocfs2_fs.h +1 -1
@@ -290,7 +290,7 @@#define OCFS2_MAX_SLOTS 255/* Slot map indicator for an empty slot */ -#define OCFS2_INVALID_SLOT -1 +#define OCFS2_INVALID_SLOT ((u16)-1)#define OCFS2_VOL_UUID_LEN 16#define OCFS2_MAX_VOL_LABEL_LEN 64
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 234/265 ocfs2: fix panic on nfs server over ocfs2
In reply to Sasha LevinFrom: Junxiao Bi <[email protected]>
commit e5a15e17a78d58f933d17cafedfcf7486a29f5b4 upstream.
The following kernel panic was captured when running nfs server over ocfs2, at that time ocfs2_test_inode_bit() was checking whether one inode locating at "blkno" 5 was valid, that is ocfs2 root inode, its "suballoc_slot" was OCFS2_INVALID_SLOT(65535) and it was allocted from //global_inode_alloc, but here it wrongly assumed that it was got from per slot inode alloctor which would cause array overflow and trigger kernel panic.
BUG: unable to handle kernel paging request at 0000000000001088
IP: [<ffffffff816f6898>] _raw_spin_lock+0x18/0xf0
PGD 1e06ba067 PUD 1e9e7d067 PMD 0
Oops: 0002 [#1] SMP
CPU: 6 PID: 24873 Comm: nfsd Not tainted 4.1.12-124.36.1.el6uek.x86_64 #2
Hardware name: Huawei CH121 V3/IT11SGCA1, BIOS 3.87 02/02/2018
RIP: _raw_spin_lock+0x18/0xf0
RSP: e02b:ffff88005ae97908 EFLAGS: 00010206
RAX: ffff88005ae98000 RBX: 0000000000001088 RCX: 0000000000000000
RDX: 0000000000020000 RSI: 0000000000000009 RDI: 0000000000001088
RBP: ffff88005ae97928 R08: 0000000000000000 R09: ffff880212878e00
R10: 0000000000007ff0 R11: 0000000000000000 R12: 0000000000001088
R13: ffff8800063c0aa8 R14: ffff8800650c27d0 R15: 000000000000ffff
FS: 0000000000000000(0000) GS:ffff880218180000(0000) knlGS:ffff880218180000
CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000001088 CR3: 00000002033d0000 CR4: 0000000000042660
Call Trace:
igrab+0x1e/0x60
ocfs2_get_system_file_inode+0x63/0x3a0 [ocfs2]
ocfs2_test_inode_bit+0x328/0xa00 [ocfs2]
ocfs2_get_parent+0xba/0x3e0 [ocfs2]
reconnect_path+0xb5/0x300
exportfs_decode_fh+0xf6/0x2b0
fh_verify+0x350/0x660 [nfsd]
nfsd4_putfh+0x4d/0x60 [nfsd]
nfsd4_proc_compound+0x3d3/0x6f0 [nfsd]
nfsd_dispatch+0xe0/0x290 [nfsd]
svc_process_common+0x412/0x6a0 [sunrpc]
svc_process+0x123/0x210 [sunrpc]
nfsd+0xff/0x170 [nfsd]
kthread+0xcb/0xf0
ret_from_fork+0x61/0x90
Code: 83 c2 02 0f b7 f2 e8 18 dc 91 ff 66 90 eb bf 0f 1f 40 00 55 48 89 e5 41 56 41 55 41 54 53 0f 1f 44 00 00 48 89 fb ba 00 00 02 00 <f0> 0f c1 17 89 d0 45 31 e4 45 31 ed c1 e8 10 66 39 d0 41 89 c6
RIP _raw_spin_lock+0x18/0xf0
CR2: 0000000000001088
---[ end trace 7264463cd1aac8f9 ]---
Kernel panic - not syncing: Fatal exception--- fs/ocfs2/suballoc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
fs/ocfs2/suballoc.c +6 -3
@@ -2825,9 +2825,12 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res) goto bail; } - inode_alloc_inode = -ocfs2_get_system_file_inode (osb,INODE_ALLOC_SYSTEM_INODE , - suballoc_slot); +if (suballoc_slot == (u16 )OCFS2_INVALID_SLOT ) + inode_alloc_inode =ocfs2_get_system_file_inode (osb, +GLOBAL_INODE_ALLOC_SYSTEM_INODE , suballoc_slot); +else + inode_alloc_inode =ocfs2_get_system_file_inode (osb, +INODE_ALLOC_SYSTEM_INODE , suballoc_slot);if (!inode_alloc_inode) {/* the error code could be inaccurate, but we are not able to * get the correct one. */
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 235/265 mm: memcontrol: handle div0 crash race condition in memory.low
In reply to Sasha LevinFrom: Johannes Weiner <[email protected]>
commit cd324edce598ebddde44162a2aa01321c1261b9e upstream.
Tejun reports seeing rare div0 crashes in memory.low stress testing:
RIP: 0010:mem_cgroup_calculate_protection+0xed/0x150
Code: 0f 46 d1 4c 39 d8 72 57 f6 05 16 d6 42 01 40 74 1f 4c 39 d8 76 1a 4c 39 d1 76 15 4c 29 d1 4c 29 d8 4d 29 d9 31 d2 48 0f af c1 <49> f7 f1 49 01 c2 4c 89 96 38 01 00 00 5d c3 48 0f af c7 31 d2 49
RSP: 0018:ffffa14e01d6fcd0 EFLAGS: 00010246
RAX: 000000000243e384 RBX: 0000000000000000 RCX: 0000000000008f4b
RDX: 0000000000000000 RSI: ffff8b89bee84000 RDI: 0000000000000000
RBP: ffffa14e01d6fcd0 R08: ffff8b89ca7d40f8 R09: 0000000000000000
R10: 0000000000000000 R11: 00000000006422f7 R12: 0000000000000000
R13: ffff8b89d9617000 R14: ffff8b89bee84000 R15: ffffa14e01d6fdb8
FS: 0000000000000000(0000) GS:ffff8b8a1f1c0000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f93b1fc175b CR3: 000000016100a000 CR4: 0000000000340ea0
Call Trace:
shrink_node+0x1e5/0x6c0
balance_pgdat+0x32d/0x5f0
kswapd+0x1d7/0x3d0
kthread+0x11c/0x160
ret_from_fork+0x1f/0x30This happens when parent_usage == siblings_protected.
We check that usage is bigger than protected, which should imply parent_usage being bigger than siblings_protected. However, we don't read (or even update) these values atomically, and they can be out of sync as the memory state changes under us. A bit of fluctuation around the target protection isn't a big deal, but we need to handle the div0 case.
Check the parent state explicitly to make sure we have a reasonable positive value for the divisor.
--- mm/memcontrol.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
mm/memcontrol.c +7 -2
@@ -6349,11 +6349,16 @@ static unsigned long effective_protection(unsigned long usage,* We're using unprotected memory for the weight so that if * some cgroups DO claim explicit protection, we don't protect * the same bytes twice. +* +* Check both usage and parent_usage against the respective +* protected values. One should imply the other, but they +* aren't read atomically - make sure the division is sane. */ if (!(cgrp_dfl_root.flags &CGRP_ROOT_MEMORY_RECURSIVE_PROT ))return ep; - -if (parent_effective > siblings_protected && usage > protected) { +if (parent_effective > siblings_protected && + parent_usage > siblings_protected && + usage > protected) {unsigned long unclaimed; unclaimed = parent_effective - siblings_protected;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 236/265 mm/memcontrol.c: add missed css_put()
In reply to Sasha LevinFrom: Muchun Song <[email protected]>
commit 3a98990ae2150277ed34d3b248c60e68bf2244b2 upstream.
We should put the css reference when memory allocation failed.
--- mm/memcontrol.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
mm/memcontrol.c +3 -1
@@ -2790,8 +2790,10 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,return ; cw =kmalloc (sizeof (*cw),GFP_NOWAIT | __GFP_NOWARN); -if (!cw) +if (!cw) { +css_put (&memcg->css);return ; + } cw->memcg = memcg; cw->cachep = cachep;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 237/265 mm/memory_hotplug.c: fix false softlockup during pfn range removal
In reply to Sasha LevinFrom: Ben Widawsky <[email protected]>
commit b7e3debdd0408c0dca5d4750371afa5003f792dc upstream.
When working with very large nodes, poisoning the struct pages (for which there will be very many) can take a very long time. If the system is using voluntary preemptions, the software watchdog will not be able to detect forward progress. This patch addresses this issue by offering to give up time like __remove_pages() does. This behavior was introduced in v5.6 with: commit d33695b16a9f ("mm/memory_hotplug: poison memmap in remove_pfn_range_from_zone()")
Alternately, init_page_poison could do this cond_resched(), but it seems to me that the caller of init_page_poison() is what actually knows whether or not it should relax its own priority.
Based on Dan's notes, I think this is perfectly safe: commit f931ab479dd2 ("mm: fix devm_memremap_pages crash, use mem_hotplug_{begin, done}")
Aside from fixing the lockup, it is also a friendlier thing to do on lower core systems that might wipe out large chunks of hotplug memory (probably not a very common case).
Fixes this kind of splat:
watchdog: BUG: soft lockup - CPU#46 stuck for 22s! [daxctl:9922] irq event stamp: 138450 hardirqs last enabled at (138449): [<ffffffffa1001f26>] trace_hardirqs_on_thunk+0x1a/0x1c hardirqs last disabled at (138450): [<ffffffffa1001f42>] trace_hardirqs_off_thunk+0x1a/0x1c softirqs last enabled at (138448): [<ffffffffa1e00347>] __do_softirq+0x347/0x456 softirqs last disabled at (138443): [<ffffffffa10c416d>] irq_exit+0x7d/0xb0 CPU: 46 PID: 9922 Comm: daxctl Not tainted 5.7.0-BEN-14238-g373c6049b336 #30 Hardware name: Intel Corporation PURLEY/PURLEY, BIOS PLYXCRB1.86B.0578.D07.1902280810 02/28/2019 RIP: 0010:memset_erms+0x9/0x10 Code: c1 e9 03 40 0f b6 f6 48 b8 01 01 01 01 01 01 01 01 48 0f af c6 f3 48 ab 89 d1 f3 aa 4c 89 c8 c3 90 49 89 f9 40 88 f0 48 89 d1 <f3> aa 4c 89 c8 c3 90 49 89 fa 40 0f b6 ce 48 b8 01 01 01 01 01 01 Call Trace: remove_pfn_range_from_zone+0x3a/0x380 memunmap_pages+0x17f/0x280 release_nodes+0x22a/0x260 __device_release_driver+0x172/0x220 device_driver_detach+0x3e/0xa0 unbind_store+0x113/0x130 kernfs_fop_write+0xdc/0x1c0 vfs_write+0xde/0x1d0 ksys_write+0x58/0xd0 do_syscall_64+0x5a/0x120 entry_SYSCALL_64_after_hwframe+0x49/0xb3 Built 2 zonelists, mobility grouping on. Total pages: 49050381 Policy zone: Normal Built 3 zonelists, mobility grouping on. Total pages: 49312525 Policy zone: Normal
David said: "It really only is an issue for devmem. Ordinary hotplugged system memory is not affected (onlined/offlined in memory block granularity)."
--- mm/memory_hotplug.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)
mm/memory_hotplug.c +11 -2
@@ -468,11 +468,20 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { +const unsigned long end_pfn = start_pfn + nr_pages;struct pglist_data *pgdat = zone->zone_pgdat; -unsigned long flags; +unsigned long pfn, cur_nr_pages, flags;/* Poison struct pages because they are now uninitialized again. */ -page_init_poison (pfn_to_page (start_pfn),sizeof (struct page ) * nr_pages); +for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) { +cond_resched (); + +/* Select all remaining pages up to the next section boundary */ + cur_nr_pages = +min (end_pfn - pfn,SECTION_ALIGN_UP (pfn +1 ) - pfn); +page_init_poison (pfn_to_page (pfn), +sizeof (struct page ) * cur_nr_pages); + }#ifdef CONFIG_ZONE_DEVICE /*
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 238/265 arm64: perf: Report the PC value in REGS_ABI_32 mode
In reply to Sasha LevinFrom: Jiping Ma <[email protected]>
commit 8dfe804a4031ca6ba3a3efb2048534249b64f3a5 upstream.
A 32-bit perf querying the registers of a compat task using REGS_ABI_32 will receive zeroes from w15, when it expects to find the PC.
Return the PC value for register dwarf register 15 when returning register values for a compat task to perf.
--- arch/arm64/kernel/perf_regs.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-)
arch/arm64/kernel/perf_regs.c +22 -3
@@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)return 0 ;/* -* Compat (i.e. 32 bit) mode: -* - PC has been set in the pt_regs struct in kernel_entry, -* - Handle SP and LR here. +* Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but +* we're stuck with it for ABI compatability reasons. +* +* For a 32-bit consumer inspecting a 32-bit task, then it will look at +* the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h). +* These correspond directly to a prefix of the registers saved in our +* 'struct pt_regs', with the exception of the PC, so we copy that down +* (x15 corresponds to SP_hyp in the architecture). +* +* So far, so good. +* +* The oddity arises when a 64-bit consumer looks at a 32-bit task and +* asks for registers beyond PERF_REG_ARM_MAX. In this case, we return +* SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and +* PC registers would normally live. The initial idea was to allow a +* 64-bit unwinder to unwind a 32-bit task and, although it's not clear +* how well that works in practice, somebody might be relying on it. +* +* At the time we make a sample, we don't know whether the consumer is +* 32-bit or 64-bit, so we have to cater for both possibilities. */ if (compat_user_mode (regs)) {if ((u32 )idx ==PERF_REG_ARM64_SP )return regs->compat_sp;if ((u32 )idx ==PERF_REG_ARM64_LR )return regs->compat_lr; +if (idx ==15 ) +return regs->pc; }if ((u32 )idx ==PERF_REG_ARM64_SP )
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 239/265 arm64: dts: imx8mm-evk: correct ldo1/ldo2 voltage range
In reply to Sasha LevinFrom: Robin Gong <[email protected]>
commit 4fd6b5735c03c0955d93960d31f17d7144f5578f upstream.
Correct ldo1 voltage range from wrong high group(3.0V~3.3V) to low group (1.6V~1.9V) because the ldo1 should be 1.8V. Actually, two voltage groups have been supported at bd718x7-regulator driver, hence, just corrrect the voltage range to 1.6V~3.3V. For [email protected], correct voltage range too. Otherwise, ldo1 would be kept @3.0V and [email protected] which violate i.mx8mm datasheet as the below warning log in kernel:
[ 0.995524] LDO1: Bringing 1800000uV into 3000000-3000000uV [ 0.999196] LDO2: Bringing 800000uV into 900000-900000uV
--- arch/arm64/boot/dts/freescale/imx8mm-evk.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/arm64/boot/dts/freescale/imx8mm-evk.dts +2 -2
@@ -196,7 +196,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on;
@@ -204,7 +204,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 240/265 arm64: dts: imx8mn-ddr4-evk: correct ldo1/ldo2 voltage range
In reply to Sasha LevinFrom: Robin Gong <[email protected]>
commit cfb12c8952f617df58d73d24161e539a035d82b0 upstream.
Correct ldo1 voltage range from wrong high group(3.0V~3.3V) to low group (1.6V~1.9V) because the ldo1 should be 1.8V. Actually, two voltage groups have been supported at bd718x7-regulator driver, hence, just corrrect the voltage range to 1.6V~3.3V. For [email protected], correct voltage range too. Otherwise, ldo1 would be kept @3.0V and [email protected] which violate i.mx8mn datasheet as the below warning log in kernel:
[ 0.995524] LDO1: Bringing 1800000uV into 3000000-3000000uV [ 0.999196] LDO2: Bringing 800000uV into 900000-900000uV
--- arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +2 -2
@@ -101,7 +101,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on;
@@ -109,7 +109,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 241/265 tracing/boottime: Fix kprobe multiple events
In reply to Sasha LevinFrom: Sascha Ortmann <[email protected]>
commit 20dc3847cc2fc886ee4eb9112e6e2fad9419b0c7 upstream.
Fix boottime kprobe events to report and abort after each failure when adding probes.
As an example, when we try to set multiprobe kprobe events in bootconfig like this:
ftrace.event.kprobes.vfsevents {
probes = "vfs_read $arg1 $arg2,,
!error! not reported;?", // leads to error
"vfs_write $arg1 $arg2"
}This will not work as expected. After
commit da0f1f4167e3af69e ("tracing/boottime: Fix kprobe event API usage"), the function trace_boot_add_kprobe_event will not produce any error message when adding a probe fails at kprobe_event_gen_cmd_start. Furthermore, we continue to add probes when kprobe_event_gen_cmd_end fails (and kprobe_event_gen_cmd_start did not fail). In this case the function even returns successfully when the last call to kprobe_event_gen_cmd_end is successful.
The behaviour of reporting and aborting after failures is not consistent.
The function trace_boot_add_kprobe_event now reports each failure and stops adding probes immediately.
--- kernel/trace/trace_boot.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
kernel/trace/trace_boot.c +6 -2
@@ -101,12 +101,16 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)kprobe_event_cmd_init (&cmd, buf,MAX_BUF_LEN ); ret =kprobe_event_gen_cmd_start (&cmd, event, val); -if (ret) +if (ret) { +pr_err ("Failed to generate probe: %s\n" , buf);break ; + } ret =kprobe_event_gen_cmd_end (&cmd); -if (ret) +if (ret) {pr_err ("Failed to add probe: %s\n" , buf); +break ; + } }return ret;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 242/265 tracing: Fix event trigger to accept redundant spaces
In reply to Sasha LevinFrom: Masami Hiramatsu <[email protected]>
commit 6784beada631800f2c5afd567e5628c843362cee upstream.
Fix the event trigger to accept redundant spaces in the trigger input.
For example, these return -EINVAL
echo " traceon" > events/ftrace/print/trigger
echo "traceon if common_pid == 0" > events/ftrace/print/trigger echo "disable_event:kmem:kmalloc " > events/ftrace/print/trigger
But these are hard to find what is wrong.
To fix this issue, use skip_spaces() to remove spaces in front of actual tokens, and set NULL if there is no token.
--- kernel/trace/trace_events_trigger.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-)
kernel/trace/trace_events_trigger.c +19 -2
@@ -216,11 +216,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)int trigger_process_regex (struct trace_event_file *file,char *buff) { -char *command, *next = buff; +char *command, *next;struct event_command *p;int ret = -EINVAL ; + next = buff =skip_spaces (buff); command =strsep (&next,": \t" ); +if (next) { + next =skip_spaces (next); +if (!*next) + next =NULL ; + } command = (command[0 ] !='!' ) ? command : command +1 ;mutex_lock (&trigger_cmd_mutex);
@@ -630,8 +636,14 @@ event_trigger_callback(struct event_command *cmd_ops,int ret;/* separate the trigger from the filter (t:n [if filter]) */ -if (param &&isdigit (param[0 ])) +if (param &&isdigit (param[0 ])) { trigger =strsep (¶m," \t" ); +if (param) { + param =skip_spaces (param); +if (!*param) + param =NULL ; + } + } trigger_ops = cmd_ops->get_trigger_ops (cmd, trigger);
@@ -1368,6 +1380,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops, trigger =strsep (¶m," \t" );if (!trigger)return -EINVAL ; +if (param) { + param =skip_spaces (param); +if (!*param) + param =NULL ; + } system =strsep (&trigger,":" );if (!trigger)
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 243/265 ring-buffer: Zero out time extend if it is nested and not absolute
In reply to Sasha LevinFrom: "Steven Rostedt (VMware)" <[email protected]>
commit 097350d1c6e1f5808cae142006f18a0bbc57018d upstream.
Currently the ring buffer makes events that happen in interrupts that preempt another event have a delta of zero. (Hopefully we can change this soon). But this is to deal with the races of updating a global counter with lockless and nesting functions updating deltas.
With the addition of absolute time stamps, the time extend didn't follow this rule. A time extend can happen if two events happen longer than 2^27 nanoseconds appart, as the delta time field in each event is only 27 bits. If that happens, then a time extend is injected with 2^59 bits of nanoseconds to use (18 years). But if the 2^27 nanoseconds happen between two events, and as it is writing the event, an interrupt triggers, it will see the 2^27 difference as well and inject a time extend of its own. But a recent change made the time extend logic not take into account the nesting, and this can cause two time extend deltas to happen moving the time stamp much further ahead than the current time. This gets all reset when the ring buffer moves to the next page, but that can cause time to appear to go backwards.
This was observed in a trace-cmd recording, and since the data is saved in a file, with trace-cmd report --debug, it was possible to see that this indeed did happen!
bash-52501 110d... 81778.908247: sched_switch: bash:52501 [120] S ==> swapper/110:0 [120] [12770284:0x2e8:64] <idle>-0 110d... 81778.908757: sched_switch: swapper/110:0 [120] R ==> bash:52501 [120] [509947:0x32c:64]
TIME EXTEND: delta:306454770 length:0
bash-52501 110.... 81779.215212: sched_swap_numa: src_pid=52501 src_tgid=52388 src_ngid=52501 src_cpu=110 src_nid=2 dst_pid=52509 dst_tgid=52388 dst_ngid=52501 dst_cpu=49 dst_nid=1 [0:0x378:48]
TIME EXTEND: delta:306458165 length:0
bash-52501 110dNh. 81779.521670: sched_wakeup: migration/110:565 [0] success=1 CPU:110 [0:0x3b4:40]
and at the next page, caused the time to go backwards:
bash-52504 110d... 81779.685411: sched_switch: bash:52504 [120] S ==> swapper/110:0 [120] [8347057:0xfb4:64]
CPU:110 [SUBBUFFER START] [81779379165886:0x1320000]
<idle>-0 110dN.. 81779.379166: sched_wakeup: bash:52504 [120] success=1 CPU:110 [0:0x10:40] <idle>-0 110d... 81779.379167: sched_switch: swapper/110:0 [120] R ==> bash:52504 [120] [1168:0x3c:64]
--- kernel/trace/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/trace/ring_buffer.c +1 -1
@@ -2427,7 +2427,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,if (unlikely (info->add_timestamp)) {bool abs =ring_buffer_time_stamp_abs (cpu_buffer->buffer); - event =rb_add_time_stamp (event, info->delta, abs); + event =rb_add_time_stamp (event, abs ? info->delta : delta, abs); length -=RB_LEN_TIME_EXTEND ; delta =0 ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 244/265 drm/amd/display: Enable output_bpc property on all outputs
In reply to Sasha LevinFrom: Stylon Wang <[email protected]>
commit 5ae9c378c3d88b40af72f8e8f961808e29f3e70b upstream.
[Why]
Connector property output_bpc is available on DP/eDP only. New IGT tests would benifit if this property works on HDMI.
[How]
Enable this read-only property on all types of connectors.
--- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +3 -1
@@ -1017,7 +1017,6 @@ static const struct { {"link_settings", &dp_link_settings_debugfs_fops}, {"phy_settings", &dp_phy_settings_debugfs_fop}, {"test_pattern", &dp_phy_test_pattern_fops}, - {"output_bpc", &output_bpc_fops}, {"vrr_range", &vrr_range_fops}, {"sdp_message", &sdp_message_fops}, {"aux_dpcd_address", &dp_dpcd_address_debugfs_fops},
@@ -1090,6 +1089,9 @@ void connector_debugfs_init(struct amdgpu_dm_connector *connector)debugfs_create_file_unsafe ("force_yuv420_output" ,0644 , dir, connector, &force_yuv420_output_fops); +debugfs_create_file ("output_bpc" ,0644 , dir, connector, + &output_bpc_fops); + connector->debugfs_dpcd_address =0 ; connector->debugfs_dpcd_size =0 ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 245/265 drm/amd: fix potential memleak in err branch
In reply to Sasha LevinFrom: Bernard Zhao <[email protected]>
commit b5b78a6c8d8cb9c307bc6b16a754603424459d6e upstream.
The function kobject_init_and_add alloc memory like:kobject_init_and_add->kobject_add_varg->kobject_set_name_vargs ->kvasprintf_const->kstrdup_const->kstrdup->kmalloc_track_caller ->kmalloc_slab, in err branch this memory not free. If use kmemleak, this path maybe catched.
These changes are to add kobject_put in kobject_init_and_add failed branch, fix potential memleak.
--- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 1 + 1 file changed, 1 insertion(+)
drivers/gpu/drm/amd/amdkfd/kfd_process.c +1 -0
@@ -396,6 +396,7 @@ struct kfd_process *kfd_create_process(struct file *filep) (int)process->lead_thread->pid);if (ret) {pr_warn ("Creating procfs pid directory failed" ); +kobject_put (process->kobj); goto out; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 246/265 drm: rcar-du: Fix build error
In reply to Sasha LevinFrom: Daniel Gomez <[email protected]>
commit 5f9af404eec82981c4345c9943be48422234e7ab upstream.
Select DRM_KMS_HELPER dependency.
Build error when DRM_KMS_HELPER is not selected:
drivers/gpu/drm/rcar-du/rcar_lvds.o:(.rodata+0xd48): undefined reference to drm_atomic_helper_bridge_duplicate_state' drivers/gpu/drm/rcar-du/rcar_lvds.o:(.rodata+0xd50): undefined reference to drm_atomic_helper_bridge_destroy_state' drivers/gpu/drm/rcar-du/rcar_lvds.o:(.rodata+0xd70): undefined reference to drm_atomic_helper_bridge_reset' drivers/gpu/drm/rcar-du/rcar_lvds.o:(.rodata+0xdc8): undefined reference to drm_atomic_helper_connector_reset' drivers/gpu/drm/rcar-du/rcar_lvds.o:(.rodata+0xde0): undefined reference to drm_helper_probe_single_connector_modes' drivers/gpu/drm/rcar-du/rcar_lvds.o:(.rodata+0xe08): undefined reference to drm_atomic_helper_connector_duplicate_state' drivers/gpu/drm/rcar-du/rcar_lvds.o:(.rodata+0xe10): undefined reference to `drm_atomic_helper_connector_destroy_state'
--- drivers/gpu/drm/rcar-du/Kconfig | 1 + 1 file changed, 1 insertion(+)
drivers/gpu/drm/rcar-du/Kconfig +1 -0
@@ -31,6 +31,7 @@ config DRM_RCAR_DW_HDMI config DRM_RCAR_LVDS tristate "R-Car DU LVDS Encoder Support" depends on DRM && DRM_BRIDGE && OF + select DRM_KMS_HELPER select DRM_PANEL select OF_FLATTREE select OF_OVERLAY
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 247/265 drm/radeon: fix fb_div check in ni_init_smc_spll_table()
In reply to Sasha LevinFrom: Denis Efremov <[email protected]>
commit 35f760b44b1b9cb16a306bdcc7220fbbf78c4789 upstream.
clk_s is checked twice in a row in ni_init_smc_spll_table(). fb_div should be checked instead.
--- drivers/gpu/drm/radeon/ni_dpm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/radeon/ni_dpm.c +1 -1
@@ -2127,7 +2127,7 @@ static int ni_init_smc_spll_table(struct radeon_device *rdev)if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >>SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT )) ret = -EINVAL ; -if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >>SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT )) +if (fb_div & ~(SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_MASK >>SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_SHIFT )) ret = -EINVAL ;if (clk_v & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_MASK >>SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_SHIFT ))
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 248/265 drm/fb-helper: Fix vt restore
In reply to Sasha LevinFrom: Daniel Vetter <[email protected]>
commit dc5bdb68b5b369d5bc7d1de96fa64cc1737a6320 upstream.
In the past we had a pile of hacks to orchestrate access between fbdev emulation and native kms clients. We've tried to streamline this, by always preferring the kms side above fbdev calls when a drm master exists, because drm master controls access to the display resources.
Unfortunately this breaks existing userspace, specifically Xorg. When exiting Xorg first restores the console to text mode using the KDSET ioctl on the vt. This does nothing, because a drm master is still around. Then it drops the drm master status, which again does nothing, because logind is keeping additional drm fd open to be able to orchestrate vt switches. In the past this is the point where fbdev was restored, as part of the ->lastclose hook on the drm side.
Now to fix this regression we don't want to go back to letting fbdev restore things whenever it feels like, or to the pile of hacks we've had before. Instead try and go with a minimal exception to make the KDSET case work again, and nothing else.
This means that if userspace does a KDSET call when switching between graphical compositors, there will be some flickering with fbcon showing up for a bit. But a) that's not a regression and b) userspace can fix it by improving the vt switching dance - logind should have all the information it needs.
While pondering all this I'm also wondering wheter we should have a SWITCH_MASTER ioctl to allow race-free master status handover. But that's for another day.
v2: Somehow forgot to cc all the fbdev people.
v3: Fix typo Alex spotted.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id 8179
--- drivers/gpu/drm/drm_fb_helper.c | 63 +++++++++++++++++++++++++------- drivers/video/fbdev/core/fbcon.c | 3 +- include/uapi/linux/fb.h | 1 + 3 files changed, 52 insertions(+), 15 deletions(-)
drivers/gpu/drm/drm_fb_helper.c +49 -14
@@ -227,18 +227,9 @@ int drm_fb_helper_debug_leave(struct fb_info *info) }EXPORT_SYMBOL (drm_fb_helper_debug_leave); -/** -* drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration -* @fb_helper: driver-allocated fbdev helper, can be NULL -* -* This should be called from driver's drm &drm_driver.lastclose callback -* when implementing an fbcon on top of kms using this helper. This ensures that -* the user isn't greeted with a black screen when e.g. X dies. -* -* RETURNS: -* Zero if everything went ok, negative error code otherwise. -*/ -int drm_fb_helper_restore_fbdev_mode_unlocked (struct drm_fb_helper *fb_helper) +static int +__drm_fb_helper_restore_fbdev_mode_unlocked (struct drm_fb_helper *fb_helper, +bool force) {bool do_delayed;int ret;
@@ -250,7 +241,16 @@ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)return 0 ;mutex_lock (&fb_helper->lock); - ret =drm_client_modeset_commit (&fb_helper->client); +if (force) { +/* +* Yes this is the _locked version which expects the master lock +* to be held. But for forced restores we're intentionally +* racing here, see drm_fb_helper_set_par(). +*/ + ret =drm_client_modeset_commit_locked (&fb_helper->client); + }else { + ret =drm_client_modeset_commit (&fb_helper->client); + } do_delayed = fb_helper->delayed_hotplug;if (do_delayed)
@@ -262,6 +262,22 @@ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)return ret; } + +/** +* drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration +* @fb_helper: driver-allocated fbdev helper, can be NULL +* +* This should be called from driver's drm &drm_driver.lastclose callback +* when implementing an fbcon on top of kms using this helper. This ensures that +* the user isn't greeted with a black screen when e.g. X dies. +* +* RETURNS: +* Zero if everything went ok, negative error code otherwise. +*/ +int drm_fb_helper_restore_fbdev_mode_unlocked (struct drm_fb_helper *fb_helper) +{ +return __drm_fb_helper_restore_fbdev_mode_unlocked (fb_helper, false); +}EXPORT_SYMBOL (drm_fb_helper_restore_fbdev_mode_unlocked);#ifdef CONFIG_MAGIC_SYSRQ
@@ -1310,6 +1326,7 @@ int drm_fb_helper_set_par(struct fb_info *info) {struct drm_fb_helper *fb_helper = info->par;struct fb_var_screeninfo *var = &info->var; +bool force;if (oops_in_progress)return -EBUSY ;
@@ -1319,7 +1336,25 @@ int drm_fb_helper_set_par(struct fb_info *info)return -EINVAL ; } -drm_fb_helper_restore_fbdev_mode_unlocked (fb_helper); +/* +* Normally we want to make sure that a kms master takes precedence over +* fbdev, to avoid fbdev flickering and occasionally stealing the +* display status. But Xorg first sets the vt back to text mode using +* the KDSET IOCTL with KD_TEXT, and only after that drops the master +* status when exiting. +* +* In the past this was caught by drm_fb_helper_lastclose(), but on +* modern systems where logind always keeps a drm fd open to orchestrate +* the vt switching, this doesn't work. +* +* To not break the userspace ABI we have this special case here, which +* is only used for the above case. Everything else uses the normal +* commit function, which ensures that we never steal the display from +* an active drm master. +*/ + force = var->activate &FB_ACTIVATE_KD_TEXT ; + +__drm_fb_helper_restore_fbdev_mode_unlocked (fb_helper, force);return 0 ; }
drivers/video/fbdev/core/fbcon.c +2 -1
@@ -2402,7 +2402,8 @@ static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch) ops->graphics =1 ;if (!blank) { - var.activate =FB_ACTIVATE_NOW |FB_ACTIVATE_FORCE ; + var.activate =FB_ACTIVATE_NOW |FB_ACTIVATE_FORCE | +FB_ACTIVATE_KD_TEXT ;fb_set_var (info, &var); ops->graphics =0 ; ops->var = info->var;
include/uapi/linux/fb.h +1 -0
@@ -205,6 +205,7 @@ struct fb_bitfield {#define FB_ACTIVATE_ALL 64/* change all VCs on this fb */ #define FB_ACTIVATE_FORCE 128/* force apply even when no change*/ #define FB_ACTIVATE_INV_MODE 256/* invalidate videomode */ +#define FB_ACTIVATE_KD_TEXT 512/* for KDSET vt ioctl */ #define FB_ACCELF_TEXT 1/* (OBSOLETE) see fb_info.flags and vc_mode */
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 249/265 drm/amdgpu: add fw release for sdma v5_0
In reply to Sasha LevinFrom: Wenhui Sheng <[email protected]>
commit edfaf6fa73f15568d4337f208b2333f647c35810 upstream.
sdma fw isn't released when module exit
--- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +5 -1
@@ -1261,8 +1261,12 @@ static int sdma_v5_0_sw_fini(void *handle)struct amdgpu_device *adev = (struct amdgpu_device *)handle;int i; -for (i =0 ; i < adev->sdma.num_instances; i++) +for (i =0 ; i < adev->sdma.num_instances; i++) { +if (adev->sdma.instance[i].fw !=NULL ) +release_firmware (adev->sdma.instance[i].fw); +amdgpu_ring_fini (&adev->sdma.instance[i].ring); + }return 0 ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 250/265 drm/amdgpu/display: Unlock mutex on error
In reply to Sasha LevinFrom: John van der Kamp <[email protected]>
commit ee434a4f9f5ea15b0f84bddd8c012838cf9472c5 upstream.
Make sure we pass through ret label to unlock the mutex.
--- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +4 -2
@@ -510,8 +510,10 @@ static ssize_t srm_data_read(struct file *filp, struct kobject *kobj, struct bin srm =psp_get_srm (work->hdcp.config.psp.handle, &srm_version, &srm_size); -if (!srm) -return -EINVAL ; +if (!srm) { + ret = -EINVAL ; + goto ret; + }if (pos >= srm_size) ret =0 ;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 251/265 drm/panel-simple: fix connector type for newhaven_nhd_43_480272ef_atxl
In reply to Sasha LevinFrom: Tomi Valkeinen <[email protected]>
commit 8a4f5e1185db61bce6ce3a5dce6381a77bcf94e6 upstream.
Add connector type for newhaven_nhd_43_480272ef_atxl, as drm_panel_bridge_add() requires connector type to be set.
--- drivers/gpu/drm/panel/panel-simple.c | 1 + 1 file changed, 1 insertion(+)
drivers/gpu/drm/panel/panel-simple.c +1 -0
@@ -2465,6 +2465,7 @@ static const struct panel_desc newhaven_nhd_43_480272ef_atxl = { .bus_format = MEDIA_BUS_FMT_RGB888_1X24, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE | DRM_BUS_FLAG_SYNC_DRIVE_POSEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, };static const struct display_timing nlt_nl192108ac18_02d_timing = {
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 252/265 drm/panel-simple: fix connector type for LogicPD Type28 Display
In reply to Sasha LevinFrom: Adam Ford <[email protected]>
commit efb94790852ae673b18efde1b171d284689ff333 upstream.
The LogicPD Type28 display used by several Logic PD products has not worked since v5.6.
The connector type for the LogicPD Type 28 display is missing and drm_panel_bridge_add() requires connector type to be set.
--- drivers/gpu/drm/panel/panel-simple.c | 1 + 1 file changed, 1 insertion(+)
drivers/gpu/drm/panel/panel-simple.c +1 -0
@@ -2297,6 +2297,7 @@ static const struct panel_desc logicpd_type_28 = { .bus_format = MEDIA_BUS_FMT_RGB888_1X24, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE | DRM_BUS_FLAG_SYNC_DRIVE_NEGEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, };static const struct panel_desc mitsubishi_aa070mc01 = {
Signature · 6 lines
2.25.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Sasha Levin
maintainerPATCH 253/265 ARM: dts: imx6ul-kontron: Move watchdog from Kontron i.MX6UL/ULL board to SoM
In reply to Sasha LevinFrom: Frieder Schrempf <[email protected]>
commit 04a2c05179b732a4c097f0a9c701ef4c9a37e1e3 upstream.
The watchdog's WDOG_ANY signal is used to trigger a POR of the SoC, if a soft reset is issued. As the SoM hardware connects the WDOG_ANY and the POR signals, the watchdog node itself and the pin configuration should be part of the common SoM devicetree. Let's move it from the baseboard's devicetree to its proper place.
--- arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi | 13 ------------- .../boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi | 13 +++++++++++++ 2 files changed, 13 insertions(+), 13 deletions(-)
arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi +0 -13
@@ -232,13 +232,6 @@ status = "okay"; }; -&wdog1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_wdog>; - fsl,ext-reset-output; - status = "okay"; -}; - &iomuxc { pinctrl-0 = <&pinctrl_reset_out &pinctrl_gpio>;
@@ -409,10 +402,4 @@ MX6UL_PAD_NAND_DATA03__USDHC2_DATA3 0x170f9 >; }; - - pinctrl_wdog: wdoggrp { - fsl,pins = < - MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x30b0 - >; - }; };
arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi +13 -0
@@ -57,6 +57,13 @@ status = "okay"; }; +&wdog1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdog>; + fsl,ext-reset-output; + status = "okay"; +}; + &iomuxc { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reset_out>;
@@ -106,4 +113,10 @@ MX6UL_PAD_SNVS_TAMPER9__GPIO5_IO09 0x1b0b0 >; }; + + pinctrl_wdog: wdoggrp { + fsl,pins = < + MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x30b0 + >; + }; };
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 254/265 ARM: dts: imx6ul-kontron: Change WDOG_ANY signal from push-pull to open-drain
In reply to Sasha LevinFrom: Frieder Schrempf <[email protected]>
commit d22a16cc92e04d053fd807ef3587e4f135e4206f upstream.
The WDOG_ANY signal is connected to the RESET_IN signal of the SoM and baseboard. It is currently configured as push-pull, which means that if some external device like a programmer wants to assert the RESET_IN signal by pulling it to ground, it drives against the high level WDOG_ANY output of the SoC.
To fix this we set the WDOG_ANY signal to open-drain configuration. That way we make sure that the RESET_IN can be asserted by the watchdog as well as by external devices.
--- arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi +1 -1
@@ -116,7 +116,7 @@ pinctrl_wdog: wdoggrp { fsl,pins = < - MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x30b0 + MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x18b0 >; }; };
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 255/265 Staging: rtl8723bs: prevent buffer overflow in update_sta_support_rate()
In reply to Sasha LevinFrom: Dan Carpenter <[email protected]>
commit b65a2d8c8614386f7e8d38ea150749f8a862f431 upstream.
The "ie_len" variable is in the 0-255 range and it comes from the network. If it's over NDIS_802_11_LENGTH_RATES_EX (16) then that will lead to memory corruption.
--- drivers/staging/rtl8723bs/core/rtw_wlan_util.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/staging/rtl8723bs/core/rtw_wlan_util.c +3 -1
@@ -1830,12 +1830,14 @@ int update_sta_support_rate(struct adapter *padapter, u8 *pvar_ie, uint var_ie_l pIE = (struct ndis_80211_var_ie *)rtw_get_ie (pvar_ie, _SUPPORTEDRATES_IE_, &ie_len, var_ie_len);if (!pIE)return _FAIL; +if (ie_len >sizeof (pmlmeinfo->FW_sta_info[cam_idx].SupportedRates)) +return _FAIL;memcpy (pmlmeinfo->FW_sta_info[cam_idx].SupportedRates, pIE->data, ie_len); supportRateNum = ie_len; pIE = (struct ndis_80211_var_ie *)rtw_get_ie (pvar_ie, _EXT_SUPPORTEDRATES_IE_, &ie_len, var_ie_len); -if (pIE) +if (pIE && (ie_len <=sizeof (pmlmeinfo->FW_sta_info[cam_idx].SupportedRates) - supportRateNum))memcpy ((pmlmeinfo->FW_sta_info[cam_idx].SupportedRates + supportRateNum), pIE->data, ie_len);return _SUCCESS;
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 256/265 powerpc/fsl_booke/32: Fix build with CONFIG_RANDOMIZE_BASE
In reply to Sasha LevinFrom: Arseny Solokha <[email protected]>
commit 7e4773f73dcfb92e7e33532162f722ec291e75a4 upstream.
Building the current 5.8 kernel for an e500 machine with CONFIG_RANDOMIZE_BASE=y and CONFIG_BLOCK=n yields the following failure:
arch/powerpc/mm/nohash/kaslr_booke.c: In function 'kaslr_early_init':
arch/powerpc/mm/nohash/kaslr_booke.c:387:2: error: implicit declaration of function 'flush_icache_range'; did you mean 'flush_tlb_range'?
Indeed, including asm/cacheflush.h into kaslr_booke.c fixes the build.
--- arch/powerpc/mm/nohash/kaslr_booke.c | 1 + 1 file changed, 1 insertion(+)
arch/powerpc/mm/nohash/kaslr_booke.c +1 -0
@@ -14,6 +14,7 @@#include <linux/memblock.h> #include <linux/libfdt.h> #include <linux/crash_core.h> +#include <asm/cacheflush.h> #include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/kdump.h>
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 257/265 sunrpc: fixed rollback in rpc_gssd_dummy_populate()
In reply to Sasha LevinFrom: Vasily Averin <[email protected]>
commit b7ade38165ca0001c5a3bd5314a314abbbfbb1b7 upstream.
__rpc_depopulate(gssd_dentry) was lost on error path
--- net/sunrpc/rpc_pipe.c | 1 + 1 file changed, 1 insertion(+)
net/sunrpc/rpc_pipe.c +1 -0
@@ -1317,6 +1317,7 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) q.len =strlen (gssd_dummy_clnt_dir[0 ].name); clnt_dentry =d_hash_and_lookup (gssd_dentry, &q);if (!clnt_dentry) { +__rpc_depopulate (gssd_dentry, gssd_dummy_clnt_dir,0 ,1 ); pipe_dentry =ERR_PTR (-ENOENT ); goto out; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 258/265 SUNRPC: Properly set the @subbuf parameter of xdr_buf_subsegment()
In reply to Sasha LevinFrom: Chuck Lever <[email protected]>
commit 89a3c9f5b9f0bcaa9aea3e8b2a616fcaea9aad78 upstream.
@subbuf is an output parameter of xdr_buf_subsegment(). A survey of call sites shows that @subbuf is always uninitialized before xdr_buf_segment() is invoked by callers.
There are some execution paths through xdr_buf_subsegment() that do not set all of the fields in @subbuf, leaving some pointer fields containing garbage addresses. Subsequent processing of that buffer then results in a page fault.
--- net/sunrpc/xdr.c | 4 ++++ 1 file changed, 4 insertions(+)
net/sunrpc/xdr.c +4 -0
@@ -1118,6 +1118,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base =0 ; }else { base -= buf->head[0 ].iov_len; + subbuf->head[0 ].iov_base = buf->head[0 ].iov_base; subbuf->head[0 ].iov_len =0 ; }
@@ -1130,6 +1131,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base =0 ; }else { base -= buf->page_len; + subbuf->pages = buf->pages; + subbuf->page_base =0 ; subbuf->page_len =0 ; }
@@ -1141,6 +1144,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base =0 ; }else { base -= buf->tail[0 ].iov_len; + subbuf->tail[0 ].iov_base = buf->tail[0 ].iov_base; subbuf->tail[0 ].iov_len =0 ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 259/265 pNFS/flexfiles: Fix list corruption if the mirror count changes
In reply to Sasha LevinFrom: Trond Myklebust <[email protected]>
commit 8b04013737341442ed914b336cde866b902664ae upstream.
If the mirror count changes in the new layout we pick up inside ff_layout_pg_init_write(), then we can end up adding the request to the wrong mirror and corrupting the mirror->pg_list.
--- fs/nfs/flexfilelayout/flexfilelayout.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)
fs/nfs/flexfilelayout/flexfilelayout.c +7 -4
@@ -907,9 +907,8 @@ retry: goto out_mds;/* Use a direct mapping of ds_idx to pgio mirror_idx */ -if (WARN_ON_ONCE (pgio->pg_mirror_count != -FF_LAYOUT_MIRROR_COUNT (pgio->pg_lseg))) - goto out_mds; +if (pgio->pg_mirror_count !=FF_LAYOUT_MIRROR_COUNT (pgio->pg_lseg)) + goto out_eagain;for (i =0 ; i < pgio->pg_mirror_count; i++) { mirror =FF_LAYOUT_COMP (pgio->pg_lseg, i);
@@ -931,7 +930,10 @@ retry: (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) pgio->pg_maxretrans = io_maxretrans;return ; - +out_eagain: +pnfs_generic_pg_cleanup (pgio); + pgio->pg_error = -EAGAIN ; +return ; out_mds: trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode, 0, NFS4_MAX_UINT64, IOMODE_RW,
@@ -941,6 +943,7 @@ out_mds: pgio->pg_lseg =NULL ; pgio->pg_maxretrans =0 ;nfs_pageio_reset_write_mds (pgio); + pgio->pg_error = -EAGAIN ; } static unsigned int
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 260/265 NFSv4 fix CLOSE not waiting for direct IO compeletion
In reply to Sasha LevinFrom: Olga Kornievskaia <[email protected]>
commit d03727b248d0dae6199569a8d7b629a681154633 upstream.
Figuring out the root case for the REMOVE/CLOSE race and suggesting the solution was done by Neil Brown.
Currently what happens is that direct IO calls hold a reference on the open context which is decremented as an asynchronous task in the nfs_direct_complete(). Before reference is decremented, control is returned to the application which is free to close the file. When close is being processed, it decrements its reference on the open_context but since directIO still holds one, it doesn't sent a close on the wire. It returns control to the application which is free to do other operations. For instance, it can delete a file. Direct IO is finally releasing its reference and triggering an asynchronous close. Which races with the REMOVE. On the server, REMOVE can be processed before the CLOSE, failing the REMOVE with EACCES as the file is still opened.
--- fs/nfs/direct.c | 13 +++++++++---- fs/nfs/file.c | 1 + 2 files changed, 10 insertions(+), 4 deletions(-)
fs/nfs/direct.c +9 -4
@@ -267,8 +267,6 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) {struct inode *inode = dreq->inode; -inode_dio_end (inode); -if (dreq->iocb) {long res = (long ) dreq->error;if (dreq->count !=0 ) {
@@ -280,7 +278,10 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)complete (&dreq->completion); +igrab (inode);nfs_direct_req_release (dreq); +inode_dio_end (inode); +iput (inode); }static void nfs_direct_read_completion (struct nfs_pgio_header *hdr)
@@ -410,8 +411,10 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,* generic layer handle the completion. */ if (requested_bytes ==0 ) { -inode_dio_end (inode); +igrab (inode);nfs_direct_req_release (dreq); +inode_dio_end (inode); +iput (inode);return result <0 ? result : -EIO ; }
@@ -864,8 +867,10 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,* generic layer handle the completion. */ if (requested_bytes ==0 ) { -inode_dio_end (inode); +igrab (inode);nfs_direct_req_release (dreq); +inode_dio_end (inode); +iput (inode);return result <0 ? result : -EIO ; }
fs/nfs/file.c +1 -0
@@ -83,6 +83,7 @@ nfs_file_release(struct inode *inode, struct file *filp)dprintk ("NFS: release(%pD2)\n" , filp);nfs_inc_stats (inode,NFSIOS_VFSRELEASE ); +inode_dio_wait (inode);nfs_file_clear_open_context (filp);return 0 ; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 261/265 EDAC/amd64: Read back the scrub rate PCI register on F15h
In reply to Sasha LevinFrom: Borislav Petkov <[email protected]>
commit ee470bb25d0dcdf126f586ec0ae6dca66cb340a4 upstream.
Commit:
da92110dfdfa ("EDAC, amd64_edac: Extend scrub rate support to F15hM60h")
added support for F15h, model 0x60 CPUs but in doing so, missed to read back SCRCTRL PCI config register on F15h CPUs which are *not* model 0x60. Add that read so that doing
$ cat /sys/devices/system/edac/mc/mc0/sdram_scrub_rate
can show the previously set DRAM scrub rate.
--- drivers/edac/amd64_edac.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/edac/amd64_edac.c +2 -0
@@ -272,6 +272,8 @@ static int get_scrub_rate(struct mem_ctl_info *mci)if (pvt->model ==0x60 )amd64_read_pci_cfg (pvt->F2,F15H_M60H_SCRCTRL , &scrubval); +else +amd64_read_pci_cfg (pvt->F3,SCRCTRL , &scrubval); }else {amd64_read_pci_cfg (pvt->F3,SCRCTRL , &scrubval); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 262/265 xprtrdma: Fix handling of RDMA_ERROR replies
In reply to Sasha LevinFrom: Chuck Lever <[email protected]>
commit 7b2182ec381f8ea15c7eb1266d6b5d7da620ad93 upstream.
The RPC client currently doesn't handle ERR_CHUNK replies correctly. rpcrdma_complete_rqst() incorrectly passes a negative number to xprt_complete_rqst() as the number of bytes copied. Instead, set task->tk_status to the error value, and return zero bytes copied.
In these cases, return -EIO rather than -EREMOTEIO. The RPC client's finite state machine doesn't know what to do with -EREMOTEIO.
Additional clean ups:
- Don't double-count RDMA_ERROR replies
- Remove a stale comment
--- net/sunrpc/xprtrdma/rpc_rdma.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)
net/sunrpc/xprtrdma/rpc_rdma.c +3 -6
@@ -1349,8 +1349,7 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, be32_to_cpup(p), be32_to_cpu(rep->rr_xid)); } - r_xprt->rx_stats.bad_reply_count++; -return -EREMOTEIO ; +return -EIO ; }/* Perform XID lookup, reconstruction of the RPC reply, and
@@ -1387,13 +1386,11 @@ out:spin_unlock (&xprt->queue_lock);return ; -/* If the incoming reply terminated a pending RPC, the next -* RPC call will post a replacement receive buffer as it is -* being marshaled. -*/ out_badheader:trace_xprtrdma_reply_hdr (rep); r_xprt->rx_stats.bad_reply_count++; + rqst->rq_task->tk_status = status; + status =0 ; goto out; }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 263/265 dm writecache: correct uncommitted_block when discarding uncommitted entry
In reply to Sasha LevinFrom: Huaisheng Ye <[email protected]>
commit 39495b12ef1cf602e6abd350dce2ef4199906531 upstream.
When uncommitted entry has been discarded, correct wc->uncommitted_block for getting the exact number.
--- drivers/md/dm-writecache.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/md/dm-writecache.c +2 -0
@@ -857,6 +857,8 @@ static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_writecache_wait_for_ios (wc,WRITE ); discarded_something = true; } +if (!writecache_entry_is_committed (wc, e)) + wc->uncommitted_blocks--;writecache_free_entry (wc, e); }
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 264/265 dm writecache: add cond_resched to loop in persistent_memory_claim()
In reply to Sasha LevinFrom: Mikulas Patocka <[email protected]>
commit d35bd764e6899a7bea71958f08d16cea5bfa1919 upstream.
Add cond_resched() to a loop that fills in the mapper memory area because the loop can be executed many times.
--- drivers/md/dm-writecache.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/md/dm-writecache.c +2 -0
@@ -286,6 +286,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)while (daa-- && i < p) { pages[i++] =pfn_t_to_page (pfn); pfn.val++; +if (!(i &15 )) +cond_resched (); } }while (i < p); wc->memory_map =vmap (pages, p,VM_MAP ,PAGE_KERNEL );
Signature · 1 line
2.25.1
Sasha Levin
maintainerPATCH 265/265 Linux 5.7.7-rc1
In reply to Sasha Levin--- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
Makefile +2 -2
@@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 7 -SUBLEVEL = 6 -EXTRAVERSION = +SUBLEVEL = 7 +EXTRAVERSION = -rc1 NAME = Kleptomaniac Octopus # *DOCUMENTATION*
Signature · 1 line
2.25.1
Quoted 13 lines · Sasha Levin
This is the start of the stable review cycle for the 5.7.7 release. There are 265 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 Wed 01 Jul 2020 03:14:48 PM UTC. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git/patch/?id=linux-5.7.y&id2=v5.7.6
Quoted 7 lines
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.gitlinux-5.7.y
and the diffstat can be found below.--
Thanks,
Sasha
Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.
Summary
------------------------------------------------------------------------
kernel: 5.7.7-rc1
git repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
git branch: linux-5.7.y
git commit: 97943c6d41ef2b05f4e064eb49a538ff4b405809
git describe: v5.7.6-265-g97943c6d41ef
Test details: https://qa-reports.linaro.org/lkft/linux-stable-rc-5.7-oe/build/v5.7.6-265-g97943c6d41ef
No regressions (compared to build v5.7.6)
No fixes (compared to build v5.7.6)
Ran 36511 total tests in the following environments and test suites.
Environments
--------------
- dragonboard-410c
- hi6220-hikey
- i386
- juno-r2
- juno-r2-compat
- juno-r2-kasan
- nxp-ls2088
- qemu_arm
- qemu_arm64
- qemu_i386
- qemu_x86_64
- x15
- x86
- x86-kasan
Test Suites
-----------
* build
* install-android-platform-tools-r2600
* install-android-platform-tools-r2800
* kselftest
* kselftest/drivers
* kselftest/filesystems
* kselftest/net
* libhugetlbfs
* linux-log-parser
* ltp-containers-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-mm-tests
* ltp-sched-tests
* ltp-syscalls-tests
* perf
* v4l2-compliance
* kvm-unit-tests
* ltp-cap_bounds-tests
* ltp-commands-tests
* ltp-cpuhotplug-tests
* ltp-crypto-tests
* ltp-math-tests
* network-basic-tests
* ltp-controllers-tests
* ltp-nptl-tests
* ltp-open-posix-tests
* ltp-pty-tests
* ltp-securebits-tests
* kselftest-vsyscall-mode-native
* kselftest-vsyscall-mode-native/drivers
* kselftest-vsyscall-mode-native/filesystems
* kselftest-vsyscall-mode-native/net
* kselftest-vsyscall-mode-none
* kselftest-vsyscall-mode-none/drivers
* kselftest-vsyscall-mode-none/filesystems
* kselftest-vsyscall-mode-none/net
Signature · 2 lines
Linaro LKFT https://lkft.linaro.org
Sasha Levin
maintainerQuoted 18 lines · Naresh Kamboju
Quoted 17 lines · Sasha Levin
This is the start of the stable review cycle for the 5.7.7 release. There are 265 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 Wed 01 Jul 2020 03:14:48 PM UTC. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git/patch/?id=linux-5.7.y&id2=v5.7.6or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.gitlinux-5.7.y
and the diffstat can be found below.
Quoted 6 lines
Quoted 3 lines
--
Thanks,
SashaResults from Linaro’s test farm.
No regressions on arm64, arm,x86_64, and i386.
Thanks for testing!
Signature · 2 lines
Thanks, Sasha
Jon Hunter
maintainerQuoted 12 lines · Sasha Levin
This is the start of the stable review cycle for the 5.7.7 release. There are 265 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 Wed 01 Jul 2020 03:14:48 PM UTC. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git/patch/?id=linux-5.7.y&id2=v5.7.6
Quoted 7 lines
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.gitlinux-5.7.y
and the diffstat can be found below.--
Thanks,
Sasha
All tests are passing for Tegra ...
Test results for stable-v5.7:
11 builds: 11 pass, 0 fail
26 boots: 26 pass, 0 fail
56 tests: 56 pass, 0 failLinux version: 5.7.7-rc1-g97943c6d41ef
Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000,
tegra194-p2972-0000, tegra20-ventana,
tegra210-p2371-2180, tegra210-p3450-0000,
tegra30-cardhu-a04Cheers
Jon
Signature · 1 line
nvpublic
Sasha Levin
maintainerQuoted 29 lines · Jon Hunter
Quoted 12 lines · Sasha Levin
This is the start of the stable review cycle for the 5.7.7 release. There are 265 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 Wed 01 Jul 2020 03:14:48 PM UTC. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git/patch/?id=linux-5.7.y&id2=v5.7.6Quoted 7 lines
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.gitlinux-5.7.y
and the diffstat can be found below.--
Thanks,
SashaAll tests are passing for Tegra ...
Test results for stable-v5.7:
11 builds: 11 pass, 0 fail 26 boots: 26 pass, 0 fail 56 tests: 56 pass, 0 fail
Quoted 5 lines
Linux version: 5.7.7-rc1-g97943c6d41ef
Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000,tegra194-p2972-0000, tegra20-ventana, tegra210-p2371-2180, tegra210-p3450-0000, tegra30-cardhu-a04
Thanks for the testing Jon!
Signature · 2 lines
Thanks, Sasha
Quoted 9 lines · Sasha Levin
This is the start of the stable review cycle for the 5.7.7 release. There are 265 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 Wed 01 Jul 2020 03:14:48 PM UTC. Anything received after that time might be too late.
Build results:
total: 155 pass: 155 fail: 0 Qemu test results: total: 430 pass: 430 fail: 0
Guenter
Sasha Levin
maintainerQuoted 7 lines · Guenter Roeck
Quoted 6 lines · Sasha Levin
This is the start of the stable review cycle for the 5.7.7 release. There are 265 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.
Quoted 8 lines
Quoted 3 lines
Responses should be made by Wed 01 Jul 2020 03:14:48 PM UTC. Anything received after that time might be too late.
Build results:
total: 155 pass: 155 fail: 0 Qemu test results: total: 430 pass: 430 fail: 0
Thanks Guenter!
Signature · 2 lines
Thanks, Sasha