August 2025 - Linux-stable-mirror

[PATCH v2 3/3] xen/events: Update virq_to_irq on migration

by Jason Andryuk

VIRQs come in 3 flavors, per-VPU, per-domain, and global, and the VIRQs are tracked in per-cpu virq_to_irq arrays. Per-domain and global VIRQs must be bound on CPU 0, and bind_virq_to_irq() sets the per_cpu virq_to_irq at registration time Later, the interrupt can migrate, and info->cpu is updated. When calling __unbind_from_irq(), the per-cpu virq_to_irq is cleared for a different cpu. If bind_virq_to_irq() is called again with CPU 0, the stale irq is returned. There won't be any irq_info for the irq, so things break. Make xen_rebind_evtchn_to_cpu() update the per_cpu virq_to_irq mappings to keep them update to date with the current cpu. This ensures the correct virq_to_irq is cleared in __unbind_from_irq(). Fixes: e46cdb66c8fc ("xen: event channels") Cc: stable(a)vger.kernel.org Signed-off-by: Jason Andryuk <jason.andryuk(a)amd.com> --- V2: Different approach changing virq_to_irq --- drivers/xen/events/events_base.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index a85bc43f4344..4e9db7b92dde 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -1772,6 +1772,7 @@ static int xen_rebind_evtchn_to_cpu(struct irq_info *info, unsigned int tcpu) { struct evtchn_bind_vcpu bind_vcpu; evtchn_port_t evtchn = info ? info->evtchn : 0; + int old_cpu = info ? info->cpu : tcpu; if (!VALID_EVTCHN(evtchn)) return -1; @@ -1795,8 +1796,18 @@ static int xen_rebind_evtchn_to_cpu(struct irq_info *info, unsigned int tcpu) * it, but don't do the xenlinux-level rebind in that case. */ if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0) + { bind_evtchn_to_cpu(info, tcpu, false); + if (info->type == IRQT_VIRQ) { + int virq = info->u.virq; + int irq = per_cpu(virq_to_irq, old_cpu)[virq]; + + per_cpu(virq_to_irq, old_cpu)[virq] = -1; + per_cpu(virq_to_irq, tcpu)[virq] = irq; + } + } + do_unmask(info, EVT_MASK_REASON_TEMPORARY); return 0; -- 2.50.1

2 months, 1 week

2
1
0 0

[PATCH v3 2/2] drm/amd/display: fix leak of probed modes

by Fedor Pchelkin

amdgpu_dm_connector_ddc_get_modes() reinitializes a connector's probed modes list without cleaning it up. First time it is called during the driver's initialization phase, then via drm_mode_getconnector() ioctl. The leaks observed with Kmemleak are as following: unreferenced object 0xffff88812f91b200 (size 128): comm "(udev-worker)", pid 388, jiffies 4294695475 hex dump (first 32 bytes): ac dd 07 00 80 02 70 0b 90 0b e0 0b 00 00 e0 01 ......p......... 0b 07 10 07 5c 07 00 00 0a 00 00 00 00 00 00 00 ....\........... backtrace (crc 89db554f): __kmalloc_cache_noprof+0x3a3/0x490 drm_mode_duplicate+0x8e/0x2b0 amdgpu_dm_create_common_mode+0x40/0x150 [amdgpu] amdgpu_dm_connector_add_common_modes+0x336/0x488 [amdgpu] amdgpu_dm_connector_get_modes+0x428/0x8a0 [amdgpu] amdgpu_dm_initialize_drm_device+0x1389/0x17b4 [amdgpu] amdgpu_dm_init.cold+0x157b/0x1a1e [amdgpu] dm_hw_init+0x3f/0x110 [amdgpu] amdgpu_device_ip_init+0xcf4/0x1180 [amdgpu] amdgpu_device_init.cold+0xb84/0x1863 [amdgpu] amdgpu_driver_load_kms+0x15/0x90 [amdgpu] amdgpu_pci_probe+0x391/0xce0 [amdgpu] local_pci_probe+0xd9/0x190 pci_call_probe+0x183/0x540 pci_device_probe+0x171/0x2c0 really_probe+0x1e1/0x890 Found by Linux Verification Center (linuxtesting.org). Fixes: acc96ae0d127 ("drm/amd/display: set panel orientation before drm_dev_register") Cc: stable(a)vger.kernel.org Signed-off-by: Fedor Pchelkin <pchelkin(a)ispras.ru> --- v3: drop INIT_LIST_HEAD and use drm_edid_connector_update() (Melissa Wen) v2: use exported drm_mode_remove() (Mario Limonciello) drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index a0ca3b2c6bd8..12685966186b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8230,10 +8230,14 @@ static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector, { struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); + struct drm_display_mode *mode, *t; if (drm_edid) { /* empty probed_modes */ - INIT_LIST_HEAD(&connector->probed_modes); + list_for_each_entry_safe(mode, t, &connector->probed_modes, head) + drm_mode_remove(connector, mode); + + drm_edid_connector_update(connector, drm_edid); amdgpu_dm_connector->num_modes = drm_edid_connector_add_modes(connector); -- 2.50.1

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] NFS: Fix a race when updating an existing write" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 76d2e3890fb169168c73f2e4f8375c7cc24a765e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025082224-payment-unworthy-d165@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 76d2e3890fb169168c73f2e4f8375c7cc24a765e Mon Sep 17 00:00:00 2001 From: Trond Myklebust <trond.myklebust(a)hammerspace.com> Date: Sat, 16 Aug 2025 07:25:20 -0700 Subject: [PATCH] NFS: Fix a race when updating an existing write After nfs_lock_and_join_requests() tests for whether the request is still attached to the mapping, nothing prevents a call to nfs_inode_remove_request() from succeeding until we actually lock the page group. The reason is that whoever called nfs_inode_remove_request() doesn't necessarily have a lock on the page group head. So in order to avoid races, let's take the page group lock earlier in nfs_lock_and_join_requests(), and hold it across the removal of the request in nfs_inode_remove_request(). Reported-by: Jeff Layton <jlayton(a)kernel.org> Tested-by: Joe Quanaim <jdq(a)meta.com> Tested-by: Andrew Steffen <aksteffen(a)meta.com> Reviewed-by: Jeff Layton <jlayton(a)kernel.org> Fixes: bd37d6fce184 ("NFSv4: Convert nfs_lock_and_join_requests() to use nfs_page_find_head_request()") Cc: stable(a)vger.kernel.org Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 11968dcb7243..6e69ce43a13f 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -253,13 +253,14 @@ nfs_page_group_unlock(struct nfs_page *req) nfs_page_clear_headlock(req); } -/* - * nfs_page_group_sync_on_bit_locked +/** + * nfs_page_group_sync_on_bit_locked - Test if all requests have @bit set + * @req: request in page group + * @bit: PG_* bit that is used to sync page group * * must be called with page group lock held */ -static bool -nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) +bool nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) { struct nfs_page *head = req->wb_head; struct nfs_page *tmp; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index fa5c41d0989a..8b7c04737967 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -153,20 +153,10 @@ nfs_page_set_inode_ref(struct nfs_page *req, struct inode *inode) } } -static int -nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) +static void nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) { - int ret; - - if (!test_bit(PG_REMOVE, &req->wb_flags)) - return 0; - ret = nfs_page_group_lock(req); - if (ret) - return ret; if (test_and_clear_bit(PG_REMOVE, &req->wb_flags)) nfs_page_set_inode_ref(req, inode); - nfs_page_group_unlock(req); - return 0; } /** @@ -585,19 +575,18 @@ retry: } } + ret = nfs_page_group_lock(head); + if (ret < 0) + goto out_unlock; + /* Ensure that nobody removed the request before we locked it */ if (head != folio->private) { + nfs_page_group_unlock(head); nfs_unlock_and_release_request(head); goto retry; } - ret = nfs_cancel_remove_inode(head, inode); - if (ret < 0) - goto out_unlock; - - ret = nfs_page_group_lock(head); - if (ret < 0) - goto out_unlock; + nfs_cancel_remove_inode(head, inode); /* lock each request in the page group */ for (subreq = head->wb_this_page; @@ -786,7 +775,8 @@ static void nfs_inode_remove_request(struct nfs_page *req) { struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); - if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { + nfs_page_group_lock(req); + if (nfs_page_group_sync_on_bit_locked(req, PG_REMOVE)) { struct folio *folio = nfs_page_to_folio(req->wb_head); struct address_space *mapping = folio->mapping; @@ -798,6 +788,7 @@ static void nfs_inode_remove_request(struct nfs_page *req) } spin_unlock(&mapping->i_private_lock); } + nfs_page_group_unlock(req); if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { atomic_long_dec(&nfsi->nrequests); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 169b4ae30ff4..9aed39abc94b 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -160,6 +160,7 @@ extern void nfs_join_page_group(struct nfs_page *head, extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); +extern bool nfs_page_group_sync_on_bit_locked(struct nfs_page *, unsigned int); extern int nfs_page_set_headlock(struct nfs_page *req); extern void nfs_page_clear_headlock(struct nfs_page *req); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *);

2 months, 1 week

2
3
0 0

FAILED: patch "[PATCH] NFS: Fix a race when updating an existing write" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 76d2e3890fb169168c73f2e4f8375c7cc24a765e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025082224-submersed-commend-be4c@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 76d2e3890fb169168c73f2e4f8375c7cc24a765e Mon Sep 17 00:00:00 2001 From: Trond Myklebust <trond.myklebust(a)hammerspace.com> Date: Sat, 16 Aug 2025 07:25:20 -0700 Subject: [PATCH] NFS: Fix a race when updating an existing write After nfs_lock_and_join_requests() tests for whether the request is still attached to the mapping, nothing prevents a call to nfs_inode_remove_request() from succeeding until we actually lock the page group. The reason is that whoever called nfs_inode_remove_request() doesn't necessarily have a lock on the page group head. So in order to avoid races, let's take the page group lock earlier in nfs_lock_and_join_requests(), and hold it across the removal of the request in nfs_inode_remove_request(). Reported-by: Jeff Layton <jlayton(a)kernel.org> Tested-by: Joe Quanaim <jdq(a)meta.com> Tested-by: Andrew Steffen <aksteffen(a)meta.com> Reviewed-by: Jeff Layton <jlayton(a)kernel.org> Fixes: bd37d6fce184 ("NFSv4: Convert nfs_lock_and_join_requests() to use nfs_page_find_head_request()") Cc: stable(a)vger.kernel.org Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 11968dcb7243..6e69ce43a13f 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -253,13 +253,14 @@ nfs_page_group_unlock(struct nfs_page *req) nfs_page_clear_headlock(req); } -/* - * nfs_page_group_sync_on_bit_locked +/** + * nfs_page_group_sync_on_bit_locked - Test if all requests have @bit set + * @req: request in page group + * @bit: PG_* bit that is used to sync page group * * must be called with page group lock held */ -static bool -nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) +bool nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) { struct nfs_page *head = req->wb_head; struct nfs_page *tmp; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index fa5c41d0989a..8b7c04737967 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -153,20 +153,10 @@ nfs_page_set_inode_ref(struct nfs_page *req, struct inode *inode) } } -static int -nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) +static void nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) { - int ret; - - if (!test_bit(PG_REMOVE, &req->wb_flags)) - return 0; - ret = nfs_page_group_lock(req); - if (ret) - return ret; if (test_and_clear_bit(PG_REMOVE, &req->wb_flags)) nfs_page_set_inode_ref(req, inode); - nfs_page_group_unlock(req); - return 0; } /** @@ -585,19 +575,18 @@ retry: } } + ret = nfs_page_group_lock(head); + if (ret < 0) + goto out_unlock; + /* Ensure that nobody removed the request before we locked it */ if (head != folio->private) { + nfs_page_group_unlock(head); nfs_unlock_and_release_request(head); goto retry; } - ret = nfs_cancel_remove_inode(head, inode); - if (ret < 0) - goto out_unlock; - - ret = nfs_page_group_lock(head); - if (ret < 0) - goto out_unlock; + nfs_cancel_remove_inode(head, inode); /* lock each request in the page group */ for (subreq = head->wb_this_page; @@ -786,7 +775,8 @@ static void nfs_inode_remove_request(struct nfs_page *req) { struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); - if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { + nfs_page_group_lock(req); + if (nfs_page_group_sync_on_bit_locked(req, PG_REMOVE)) { struct folio *folio = nfs_page_to_folio(req->wb_head); struct address_space *mapping = folio->mapping; @@ -798,6 +788,7 @@ static void nfs_inode_remove_request(struct nfs_page *req) } spin_unlock(&mapping->i_private_lock); } + nfs_page_group_unlock(req); if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { atomic_long_dec(&nfsi->nrequests); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 169b4ae30ff4..9aed39abc94b 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -160,6 +160,7 @@ extern void nfs_join_page_group(struct nfs_page *head, extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); +extern bool nfs_page_group_sync_on_bit_locked(struct nfs_page *, unsigned int); extern int nfs_page_set_headlock(struct nfs_page *req); extern void nfs_page_clear_headlock(struct nfs_page *req); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *);

2 months, 1 week

2
3
0 0

[PATCH rtw v2 2/4] wifi: rtw89: fix tx_wait initialization race

by Fedor Pchelkin

Now that nullfunc skbs are recycled in a separate work item in the driver, the following race during initialization and processing of those skbs might lead to noticeable bugs: Waiting thread Completing thread rtw89_core_send_nullfunc() rtw89_core_tx_write_link() ... rtw89_pci_txwd_submit() skb_data->wait = NULL /* add skb to the queue */ skb_queue_tail(&txwd->queue, skb) rtw89_pci_napi_poll() ... rtw89_pci_release_txwd_skb() /* get skb from the queue */ skb_unlink(skb, &txwd->queue) rtw89_pci_tx_status() rtw89_core_tx_wait_complete() /* use incorrect skb_data->wait */ rtw89_core_tx_kick_off_and_wait() /* assign skb_data->wait but too late */ The value of skb_data->wait indicates whether skb is passed on to the core ieee80211 stack or released by the driver itself. So assure that by the time skb is added to txwd queue and becomes visible to the completing side, it has already allocated tx_wait-related data (in case it's needed). Found by Linux Verification Center (linuxtesting.org). Fixes: 1ae5ca615285 ("wifi: rtw89: add function to wait for completion of TX skbs") Cc: stable(a)vger.kernel.org Signed-off-by: Fedor Pchelkin <pchelkin(a)ispras.ru> --- drivers/net/wireless/realtek/rtw89/core.c | 31 +++++++++++++---------- drivers/net/wireless/realtek/rtw89/pci.c | 2 -- 2 files changed, 18 insertions(+), 15 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c index 48aa02d6abd4..28bbc898b95e 100644 --- a/drivers/net/wireless/realtek/rtw89/core.c +++ b/drivers/net/wireless/realtek/rtw89/core.c @@ -1106,21 +1106,12 @@ int rtw89_core_tx_kick_off_and_wait(struct rtw89_dev *rtwdev, struct sk_buff *sk int qsel, unsigned int timeout) { struct rtw89_tx_skb_data *skb_data = RTW89_TX_SKB_CB(skb); - struct rtw89_tx_wait_info *wait; + struct rtw89_tx_wait_info *wait = skb_data->wait; unsigned long time_left; int ret = 0; lockdep_assert_wiphy(rtwdev->hw->wiphy); - wait = kzalloc(sizeof(*wait), GFP_KERNEL); - if (!wait) { - rtw89_core_tx_kick_off(rtwdev, qsel); - return 0; - } - - init_completion(&wait->completion); - skb_data->wait = wait; - rtw89_core_tx_kick_off(rtwdev, qsel); time_left = wait_for_completion_timeout(&wait->completion, msecs_to_jiffies(timeout)); @@ -1184,10 +1175,12 @@ int rtw89_h2c_tx(struct rtw89_dev *rtwdev, static int rtw89_core_tx_write_link(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link, struct rtw89_sta_link *rtwsta_link, - struct sk_buff *skb, int *qsel, bool sw_mld) + struct sk_buff *skb, int *qsel, bool sw_mld, + struct rtw89_tx_wait_info *wait) { struct ieee80211_sta *sta = rtwsta_link_to_sta_safe(rtwsta_link); struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link); + struct rtw89_tx_skb_data *skb_data = RTW89_TX_SKB_CB(skb); struct rtw89_vif *rtwvif = rtwvif_link->rtwvif; struct rtw89_core_tx_request tx_req = {}; int ret; @@ -1204,6 +1197,8 @@ static int rtw89_core_tx_write_link(struct rtw89_dev *rtwdev, rtw89_core_tx_update_desc_info(rtwdev, &tx_req); rtw89_core_tx_wake(rtwdev, &tx_req); + skb_data->wait = wait; + ret = rtw89_hci_tx_write(rtwdev, &tx_req); if (ret) { rtw89_err(rtwdev, "failed to transmit skb to HCI\n"); @@ -1240,7 +1235,8 @@ int rtw89_core_tx_write(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, } } - return rtw89_core_tx_write_link(rtwdev, rtwvif_link, rtwsta_link, skb, qsel, false); + return rtw89_core_tx_write_link(rtwdev, rtwvif_link, rtwsta_link, skb, qsel, false, + NULL); } static __le32 rtw89_build_txwd_body0(struct rtw89_tx_desc_info *desc_info) @@ -3438,6 +3434,7 @@ int rtw89_core_send_nullfunc(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rt struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link); int link_id = ieee80211_vif_is_mld(vif) ? rtwvif_link->link_id : -1; struct rtw89_sta_link *rtwsta_link; + struct rtw89_tx_wait_info *wait; struct ieee80211_sta *sta; struct ieee80211_hdr *hdr; struct rtw89_sta *rtwsta; @@ -3447,6 +3444,12 @@ int rtw89_core_send_nullfunc(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rt if (vif->type != NL80211_IFTYPE_STATION || !vif->cfg.assoc) return 0; + wait = kzalloc(sizeof(*wait), GFP_KERNEL); + if (!wait) + return -ENOMEM; + + init_completion(&wait->completion); + rcu_read_lock(); sta = ieee80211_find_sta(vif, vif->cfg.ap_addr); if (!sta) { @@ -3471,7 +3474,8 @@ int rtw89_core_send_nullfunc(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rt goto out; } - ret = rtw89_core_tx_write_link(rtwdev, rtwvif_link, rtwsta_link, skb, &qsel, true); + ret = rtw89_core_tx_write_link(rtwdev, rtwvif_link, rtwsta_link, skb, &qsel, true, + wait); if (ret) { rtw89_warn(rtwdev, "nullfunc transmit failed: %d\n", ret); dev_kfree_skb_any(skb); @@ -3484,6 +3488,7 @@ int rtw89_core_send_nullfunc(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rt timeout); out: rcu_read_unlock(); + kfree(wait); return ret; } diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c index 6356c2c224c5..8ad505743a8e 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.c +++ b/drivers/net/wireless/realtek/rtw89/pci.c @@ -1372,7 +1372,6 @@ static int rtw89_pci_txwd_submit(struct rtw89_dev *rtwdev, struct pci_dev *pdev = rtwpci->pdev; struct sk_buff *skb = tx_req->skb; struct rtw89_pci_tx_data *tx_data = RTW89_PCI_TX_SKB_CB(skb); - struct rtw89_tx_skb_data *skb_data = RTW89_TX_SKB_CB(skb); bool en_wd_info = desc_info->en_wd_info; u32 txwd_len; u32 txwp_len; @@ -1388,7 +1387,6 @@ static int rtw89_pci_txwd_submit(struct rtw89_dev *rtwdev, } tx_data->dma = dma; - skb_data->wait = NULL; txwp_len = sizeof(*txwp_info); txwd_len = chip->txwd_body_size; -- 2.50.1

2 months, 1 week

1
0
0 0

[PATCH v4 1/4] x86/cpu/topology: Use initial APIC ID from XTOPOLOGY leaf on AMD/HYGON

by K Prateek Nayak

Prior to the topology parsing rewrite and the switchover to the new parsing logic for AMD processors in commit c749ce393b8f ("x86/cpu: Use common topology code for AMD"), the "initial_apicid" on these platforms was: - First initialized to the LocalApicId from CPUID leaf 0x1 EBX[31:24]. - Then overwritten by the ExtendedLocalApicId in CPUID leaf 0xb EDX[31:0] on processors that supported topoext. With the new parsing flow introduced in commit f7fb3b2dd92c ("x86/cpu: Provide an AMD/HYGON specific topology parser"), parse_8000_001e() now unconditionally overwrites the "initial_apicid" already parsed during cpu_parse_topology_ext(). Although this has not been a problem on baremetal platforms, on virtualized AMD guests that feature more than 255 cores, QEMU 0's out the CPUID leaf 0x8000001e on CPUs with "CoreID" > 255 to prevent collision of these IDs in EBX[7:0] which can only represent a maximum of 255 cores [1]. This results in the following FW_BUG being logged when booting a guest with more than 255 cores: [Firmware Bug]: CPU 512: APIC ID mismatch. CPUID: 0x0000 APIC: 0x0200 AMD64 Architecture Programmer's Manual Volume 2: System Programming Pub. 24593 Rev. 3.42 [2] Section 16.12 "x2APIC_ID" mentions the Extended Enumeration leaf 0x8000001e (which was later superseded by the extended leaf 0x80000026) provides the full x2APIC ID under all circumstances unlike the one reported by CPUID leaf 0x8000001e EAX which depends on the mode in which APIC is configured. Rely on the APIC ID parsed during cpu_parse_topology_ext() from CPUID leaf 0x80000026 or 0xb and only use the APIC ID from leaf 0x8000001e if cpu_parse_topology_ext() failed (has_topoext is false). On platforms that support the 0xb leaf (Zen2 or later, AMD guests on QEMU) or the extended leaf 0x80000026 (Zen4 or later), the "initial_apicid" is now set to the value parsed from EDX[31:0]. On older AMD/Hygon platforms that does not support the 0xb leaf but supports the TOPOEXT extension (Fam 0x15, 0x16, 0x17[Zen1], and Hygon), the current behavior is retained where "initial_apicid" is set using the 0x8000001e leaf. Cc: stable(a)vger.kernel.org Link: https://github.com/qemu/qemu/commit/35ac5dfbcaa4b [1] Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 [2] Debugged-by: Naveen N Rao (AMD) <naveen(a)kernel.org> Debugged-by: Sairaj Kodilkar <sarunkod(a)amd.com> Fixes: c749ce393b8f ("x86/cpu: Use common topology code for AMD") Suggested-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Naveen N Rao (AMD) <naveen(a)kernel.org> Signed-off-by: K Prateek Nayak <kprateek.nayak(a)amd.com> --- Changelog v3..v4: o Refreshed the diff based on Thomas' suggestion. The tags have been retained since there are no functional changes - only comments around the code has changed. o Quoted relevant section of APM justifying the changes. o Moved this patch up ahead. o Cc'd stable. --- arch/x86/kernel/cpu/topology_amd.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c index 843b1655ab45..827dd0dbb6e9 100644 --- a/arch/x86/kernel/cpu/topology_amd.c +++ b/arch/x86/kernel/cpu/topology_amd.c @@ -81,20 +81,25 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_topoext) cpuid_leaf(0x8000001e, &leaf); - tscan->c->topo.initial_apicid = leaf.ext_apic_id; - /* - * If leaf 0xb is available, then the domain shifts are set - * already and nothing to do here. Only valid for family >= 0x17. + * If leaf 0xb/0x26 is available, then the APIC ID and the domain + * shifts are set already. */ - if (!has_topoext && tscan->c->x86 >= 0x17) { + if (!has_topoext) { + tscan->c->topo.initial_apicid = leaf.ext_apic_id; + /* - * Leaf 0x80000008 set the CORE domain shift already. - * Update the SMT domain, but do not propagate it. + * Leaf 0x8000008 sets the CORE domain shift but not the + * SMT domain shift. On CPUs with family >= 0x17, there + * might be hyperthreads. */ - unsigned int nthreads = leaf.core_nthreads + 1; + if (tscan->c->x86 >= 0x17) { + /* Update the SMT domain, but do not propagate it. */ + unsigned int nthreads = leaf.core_nthreads + 1; - topology_update_dom(tscan, TOPO_SMT_DOMAIN, get_count_order(nthreads), nthreads); + topology_update_dom(tscan, TOPO_SMT_DOMAIN, + get_count_order(nthreads), nthreads); + } } store_node(tscan, leaf.nnodes_per_socket + 1, leaf.node_id); -- 2.34.1

2 months, 1 week

2
2
0 0

[PATCH v10] Bluetooth: hci_qca: Fix SSR (SubSystem Restart) fail when BT_EN is pulled up by hw

by Shuai Zhang

When the host actively triggers SSR and collects coredump data, the Bluetooth stack sends a reset command to the controller. However, due to the inability to clear the QCA_SSR_TRIGGERED and QCA_IBS_DISABLED bits, the reset command times out. To address this, this patch clears the QCA_SSR_TRIGGERED and QCA_IBS_DISABLED flags and adds a 50ms delay after SSR, but only when HCI_QUIRK_NON_PERSISTENT_SETUP is not set. This ensures the controller completes the SSR process when BT_EN is always high due to hardware. For the purpose of HCI_QUIRK_NON_PERSISTENT_SETUP, please refer to the comment in `include/net/bluetooth/hci.h`. The HCI_QUIRK_NON_PERSISTENT_SETUP quirk is associated with BT_EN, and its presence can be used to determine whether BT_EN is defined in DTS. After SSR, host will not download the firmware, causing controller to remain in the IBS_WAKE state. Host needs to synchronize with the controller to maintain proper operation. Multiple triggers of SSR only first generate coredump file, due to memcoredump_flag no clear. add clear coredump flag when ssr completed. When the SSR duration exceeds 2 seconds, it triggers host tx_idle_timeout, which sets host TX state to sleep. due to the hardware pulling up bt_en, the firmware is not downloaded after the SSR. As a result, the controller does not enter sleep mode. Consequently, when the host sends a command afterward, it sends 0xFD to the controller, but the controller does not respond, leading to a command timeout. So reset tx_idle_timer after SSR to prevent host enter TX IBS_Sleep mode. --- Changs since v8-v9: -- Update base patch to latest patch. -- add Cc stable(a)vger.kernel.org on signed-of. Changes since v6-7: - Merge the changes into a single patch. - Update commit. Changes since v1-5: - Add an explanation for HCI_QUIRK_NON_PERSISTENT_SETUP. - Add commments for msleep(50). - Update format and commit. Signed-off-by: Shuai Zhang <quic_shuaz(a)quicinc.com> Cc: stable(a)vger.kernel.org --- drivers/bluetooth/hci_qca.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 4cff4d9be..97aaf4985 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1653,6 +1653,39 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code) skb_queue_purge(&qca->rx_memdump_q); } + /* + * If the BT chip's bt_en pin is connected to a 3.3V power supply via + * hardware and always stays high, driver cannot control the bt_en pin. + * As a result, during SSR (SubSystem Restart), QCA_SSR_TRIGGERED and + * QCA_IBS_DISABLED flags cannot be cleared, which leads to a reset + * command timeout. + * Add an msleep delay to ensure controller completes the SSR process. + * + * Host will not download the firmware after SSR, controller to remain + * in the IBS_WAKE state, and the host needs to synchronize with it + * + * Since the bluetooth chip has been reset, clear the memdump state. + */ + if (!test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) { + /* + * When the SSR (SubSystem Restart) duration exceeds 2 seconds, + * it triggers host tx_idle_delay, which sets host TX state + * to sleep. Reset tx_idle_timer after SSR to prevent + * host enter TX IBS_Sleep mode. + */ + mod_timer(&qca->tx_idle_timer, jiffies + + msecs_to_jiffies(qca->tx_idle_delay)); + + /* Controller reset completion time is 50ms */ + msleep(50); + + clear_bit(QCA_SSR_TRIGGERED, &qca->flags); + clear_bit(QCA_IBS_DISABLED, &qca->flags); + + qca->tx_ibs_state = HCI_IBS_TX_AWAKE; + qca->memdump_state = QCA_MEMDUMP_IDLE; + } + clear_bit(QCA_HW_ERROR_EVENT, &qca->flags); } -- 2.34.1

2 months, 1 week

2
2
0 0

[PATCH v3] mm: slub: avoid wake up kswapd in set_track_prepare

by yangshiguang1011＠163.com

From: yangshiguang <yangshiguang(a)xiaomi.com> From: yangshiguang <yangshiguang(a)xiaomi.com> set_track_prepare() can incur lock recursion. The issue is that it is called from hrtimer_start_range_ns holding the per_cpu(hrtimer_bases)[n].lock, but when enabled CONFIG_DEBUG_OBJECTS_TIMERS, may wake up kswapd in set_track_prepare, and try to hold the per_cpu(hrtimer_bases)[n].lock. Avoid deadlock caused by implicitly waking up kswapd by passing in allocation flags. The oops looks something like: BUG: spinlock recursion on CPU#3, swapper/3/0 lock: 0xffffff8a4bf29c80, .magic: dead4ead, .owner: swapper/3/0, .owner_cpu: 3 Hardware name: Qualcomm Technologies, Inc. Popsicle based on SM8850 (DT) Call trace: spin_bug+0x0 _raw_spin_lock_irqsave+0x80 hrtimer_try_to_cancel+0x94 task_contending+0x10c enqueue_dl_entity+0x2a4 dl_server_start+0x74 enqueue_task_fair+0x568 enqueue_task+0xac do_activate_task+0x14c ttwu_do_activate+0xcc try_to_wake_up+0x6c8 default_wake_function+0x20 autoremove_wake_function+0x1c __wake_up+0xac wakeup_kswapd+0x19c wake_all_kswapds+0x78 __alloc_pages_slowpath+0x1ac __alloc_pages_noprof+0x298 stack_depot_save_flags+0x6b0 stack_depot_save+0x14 set_track_prepare+0x5c ___slab_alloc+0xccc __kmalloc_cache_noprof+0x470 __set_page_owner+0x2bc post_alloc_hook[jt]+0x1b8 prep_new_page+0x28 get_page_from_freelist+0x1edc __alloc_pages_noprof+0x13c alloc_slab_page+0x244 allocate_slab+0x7c ___slab_alloc+0x8e8 kmem_cache_alloc_noprof+0x450 debug_objects_fill_pool+0x22c debug_object_activate+0x40 enqueue_hrtimer[jt]+0xdc hrtimer_start_range_ns+0x5f8 ... Signed-off-by: yangshiguang <yangshiguang(a)xiaomi.com> Fixes: 5cf909c553e9 ("mm/slub: use stackdepot to save stack trace in objects") Cc: stable(a)vger.kernel.org --- v1 -> v2: propagate gfp flags to set_track_prepare() v2 -> v3: Remove the gfp restriction in set_track_prepare() [1]https://lore.kernel.org/all/20250801065121.876793-1-yangshiguang1011@163.… [2]https://lore.kernel.org/all/20250814111641.380629-2-yangshiguang1011@163.… --- mm/slub.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 30003763d224..443411713e2f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -962,19 +962,21 @@ static struct track *get_track(struct kmem_cache *s, void *object, } #ifdef CONFIG_STACKDEPOT -static noinline depot_stack_handle_t set_track_prepare(void) +static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { depot_stack_handle_t handle; unsigned long entries[TRACK_ADDRS_COUNT]; unsigned int nr_entries; + /* Preemption is disabled in ___slab_alloc() */ + gfp_flags &= ~(__GFP_DIRECT_RECLAIM); nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3); - handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); + handle = stack_depot_save(entries, nr_entries, gfp_flags); return handle; } #else -static inline depot_stack_handle_t set_track_prepare(void) +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } @@ -996,9 +998,9 @@ static void set_track_update(struct kmem_cache *s, void *object, } static __always_inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) { - depot_stack_handle_t handle = set_track_prepare(); + depot_stack_handle_t handle = set_track_prepare(gfp_flags); set_track_update(s, object, alloc, addr, handle); } @@ -1921,9 +1923,9 @@ static inline bool free_debug_processing(struct kmem_cache *s, static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {} static inline int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { return 1; } -static inline depot_stack_handle_t set_track_prepare(void) { return 0; } +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } static inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) {} + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {} static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab) {} static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, @@ -3878,7 +3880,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, * tracking info and return the object. */ if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, gfpflags); return freelist; } @@ -3910,7 +3912,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, goto new_objects; if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, gfpflags); return freelist; } @@ -4422,7 +4424,7 @@ static noinline void free_to_partial_list( depot_stack_handle_t handle = 0; if (s->flags & SLAB_STORE_USER) - handle = set_track_prepare(); + handle = set_track_prepare(__GFP_NOWARN); spin_lock_irqsave(&n->list_lock, flags); -- 2.43.0

2 months, 1 week

5
7
0 0

[tip: x86/urgent] x86/cpu/intel: Fix the constant_tsc model check for Pentium 4

by tip-bot2 for Suchit Karunakaran

The following commit has been merged into the x86/urgent branch of tip: Commit-ID: 24963ae1b0b6596dc36e352c18593800056251d8 Gitweb: https://git.kernel.org/tip/24963ae1b0b6596dc36e352c18593800056251d8 Author: Suchit Karunakaran <suchitkarunakaran(a)gmail.com> AuthorDate: Sat, 16 Aug 2025 12:21:26 +05:30 Committer: Dave Hansen <dave.hansen(a)linux.intel.com> CommitterDate: Mon, 25 Aug 2025 08:23:37 -07:00 x86/cpu/intel: Fix the constant_tsc model check for Pentium 4 Pentium 4's which are INTEL_P4_PRESCOTT (model 0x03) and later have a constant TSC. This was correctly captured until commit fadb6f569b10 ("x86/cpu/intel: Limit the non-architectural constant_tsc model checks"). In that commit, an error was introduced while selecting the last P4 model (0x06) as the upper bound. Model 0x06 was transposed to INTEL_P4_WILLAMETTE, which is just plain wrong. That was presumably a simple typo, probably just copying and pasting the wrong P4 model. Fix the constant TSC logic to cover all later P4 models. End at INTEL_P4_CEDARMILL which accurately corresponds to the last P4 model. Fixes: fadb6f569b10 ("x86/cpu/intel: Limit the non-architectural constant_tsc model checks") Signed-off-by: Suchit Karunakaran <suchitkarunakaran(a)gmail.com> Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Reviewed-by: Sohil Mehta <sohil.mehta(a)intel.com> Cc:stable@vger.kernel.org Link: https://lore.kernel.org/all/20250816065126.5000-1-suchitkarunakaran%40gmail… --- arch/x86/kernel/cpu/intel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 076eaa4..98ae4c3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -262,7 +262,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - } else if ((c->x86_vfm >= INTEL_P4_PRESCOTT && c->x86_vfm <= INTEL_P4_WILLAMETTE) || + } else if ((c->x86_vfm >= INTEL_P4_PRESCOTT && c->x86_vfm <= INTEL_P4_CEDARMILL) || (c->x86_vfm >= INTEL_CORE_YONAH && c->x86_vfm <= INTEL_IVYBRIDGE)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); }

2 months, 1 week

1
0
0 0

[PATCH V5 mm-hotfixes 2/3] mm: introduce and use {pgd,p4d}_populate_kernel()

by Harry Yoo

Introduce and use {pgd,p4d}_populate_kernel() in core MM code when populating PGD and P4D entries for the kernel address space. These helpers ensure proper synchronization of page tables when updating the kernel portion of top-level page tables. Until now, the kernel has relied on each architecture to handle synchronization of top-level page tables in an ad-hoc manner. For example, see commit 9b861528a801 ("x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes"). However, this approach has proven fragile for following reasons: 1) It is easy to forget to perform the necessary page table synchronization when introducing new changes. For instance, commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") overlooked the need to synchronize page tables for the vmemmap area. 2) It is also easy to overlook that the vmemmap and direct mapping areas must not be accessed before explicit page table synchronization. For example, commit 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges")) caused crashes by accessing the vmemmap area before calling sync_global_pgds(). To address this, as suggested by Dave Hansen, introduce _kernel() variants of the page table population helpers, which invoke architecture-specific hooks to properly synchronize page tables. These are introduced in a new header file, include/linux/pgalloc.h, so they can be called from common code. They reuse existing infrastructure for vmalloc and ioremap. Synchronization requirements are determined by ARCH_PAGE_TABLE_SYNC_MASK, and the actual synchronization is performed by arch_sync_kernel_mappings(). This change currently targets only x86_64, so only PGD and P4D level helpers are introduced. Currently, these helpers are no-ops since no architecture sets PGTBL_{PGD,P4D}_MODIFIED in ARCH_PAGE_TABLE_SYNC_MASK. In theory, PUD and PMD level helpers can be added later if needed by other architectures. For now, 32-bit architectures (x86-32 and arm) only handle PGTBL_PMD_MODIFIED, so p*d_populate_kernel() will never affect them unless we introduce a PMD level helper. Cc: <stable(a)vger.kernel.org> Fixes: 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges") Suggested-by: Dave Hansen <dave.hansen(a)linux.intel.com> Acked-by: Kiryl Shutsemau <kas(a)kernel.org> Reviewed-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Signed-off-by: Harry Yoo <harry.yoo(a)oracle.com> --- include/linux/pgalloc.h | 24 ++++++++++++++++++++++++ include/linux/pgtable.h | 13 +++++++------ mm/kasan/init.c | 12 ++++++------ mm/percpu.c | 6 +++--- mm/sparse-vmemmap.c | 6 +++--- 5 files changed, 43 insertions(+), 18 deletions(-) create mode 100644 include/linux/pgalloc.h diff --git a/include/linux/pgalloc.h b/include/linux/pgalloc.h new file mode 100644 index 000000000000..290ab864320f --- /dev/null +++ b/include/linux/pgalloc.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PGALLOC_H +#define _LINUX_PGALLOC_H + +#include <linux/pgtable.h> +#include <asm/pgalloc.h> + +static inline void pgd_populate_kernel(unsigned long addr, pgd_t *pgd, + p4d_t *p4d) +{ + pgd_populate(&init_mm, pgd, p4d); + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED) + arch_sync_kernel_mappings(addr, addr); +} + +static inline void p4d_populate_kernel(unsigned long addr, p4d_t *p4d, + pud_t *pud) +{ + p4d_populate(&init_mm, p4d, pud); + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED) + arch_sync_kernel_mappings(addr, addr); +} + +#endif /* _LINUX_PGALLOC_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index ba699df6ef69..2b80fd456c8b 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1469,8 +1469,8 @@ static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values - * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() - * needs to be called. + * and let generic vmalloc, ioremap and page table update code know when + * arch_sync_kernel_mappings() needs to be called. */ #ifndef ARCH_PAGE_TABLE_SYNC_MASK #define ARCH_PAGE_TABLE_SYNC_MASK 0 @@ -1954,10 +1954,11 @@ static inline bool arch_has_pfn_modify_check(void) /* * Page Table Modification bits for pgtbl_mod_mask. * - * These are used by the p?d_alloc_track*() set of functions an in the generic - * vmalloc/ioremap code to track at which page-table levels entries have been - * modified. Based on that the code can better decide when vmalloc and ioremap - * mapping changes need to be synchronized to other page-tables in the system. + * These are used by the p?d_alloc_track*() and p*d_populate_kernel() + * functions in the generic vmalloc, ioremap and page table update code + * to track at which page-table levels entries have been modified. + * Based on that the code can better decide when page table changes need + * to be synchronized to other page-tables in the system. */ #define __PGTBL_PGD_MODIFIED 0 #define __PGTBL_P4D_MODIFIED 1 diff --git a/mm/kasan/init.c b/mm/kasan/init.c index ced6b29fcf76..8fce3370c84e 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -13,9 +13,9 @@ #include <linux/mm.h> #include <linux/pfn.h> #include <linux/slab.h> +#include <linux/pgalloc.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include "kasan.h" @@ -191,7 +191,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, pud_t *pud; pmd_t *pmd; - p4d_populate(&init_mm, p4d, + p4d_populate_kernel(addr, p4d, lm_alias(kasan_early_shadow_pud)); pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, @@ -212,7 +212,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, } else { p = early_alloc(PAGE_SIZE, NUMA_NO_NODE); pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } } zero_pud_populate(p4d, addr, next); @@ -251,10 +251,10 @@ int __ref kasan_populate_early_shadow(const void *shadow_start, * puds,pmds, so pgd_populate(), pud_populate() * is noops. */ - pgd_populate(&init_mm, pgd, + pgd_populate_kernel(addr, pgd, lm_alias(kasan_early_shadow_p4d)); p4d = p4d_offset(pgd, addr); - p4d_populate(&init_mm, p4d, + p4d_populate_kernel(addr, p4d, lm_alias(kasan_early_shadow_pud)); pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, @@ -273,7 +273,7 @@ int __ref kasan_populate_early_shadow(const void *shadow_start, if (!p) return -ENOMEM; } else { - pgd_populate(&init_mm, pgd, + pgd_populate_kernel(addr, pgd, early_alloc(PAGE_SIZE, NUMA_NO_NODE)); } } diff --git a/mm/percpu.c b/mm/percpu.c index d9cbaee92b60..a56f35dcc417 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3108,7 +3108,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK -#include <asm/pgalloc.h> +#include <linux/pgalloc.h> #ifndef P4D_TABLE_SIZE #define P4D_TABLE_SIZE PAGE_SIZE @@ -3134,13 +3134,13 @@ void __init __weak pcpu_populate_pte(unsigned long addr) if (pgd_none(*pgd)) { p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE); - pgd_populate(&init_mm, pgd, p4d); + pgd_populate_kernel(addr, pgd, p4d); } p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE); - p4d_populate(&init_mm, p4d, pud); + p4d_populate_kernel(addr, p4d, pud); } pud = pud_offset(p4d, addr); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 41aa0493eb03..dbd8daccade2 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -27,9 +27,9 @@ #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/sched.h> +#include <linux/pgalloc.h> #include <asm/dma.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "hugetlb_vmemmap.h" @@ -229,7 +229,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) if (!p) return NULL; pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } return p4d; } @@ -241,7 +241,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; - pgd_populate(&init_mm, pgd, p); + pgd_populate_kernel(addr, pgd, p); } return pgd; } -- 2.43.0

2 months, 1 week

6
15
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror August 2025