February 2025 - Linux-stable-mirror

[PATCH 0/2] Some fixes for Goodix Berlin touchscreen driver

by Luca Weiss

One is a simple comment fix, and the second one fixes a discrepancy between dt-bindings and driver, aligning the driver to match dt-bindings. Signed-off-by: Luca Weiss <luca.weiss(a)fairphone.com> --- Luca Weiss (2): Input: goodix-berlin - fix comment referencing wrong regulator Input: goodix-berlin - fix vddio regulator references drivers/input/touchscreen/goodix_berlin_core.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) --- base-commit: 8155b4ef3466f0e289e8fcc9e6e62f3f4dceeac2 change-id: 20250103-goodix-berlin-fixes-0f776d90caa7 Best regards, -- Luca Weiss <luca.weiss(a)fairphone.com>

3 months, 3 weeks

3
4
0 0

+ nfs-fix-nfs_release_folio-to-not-deadlock-via-kcompactd-writeback.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: NFS: fix nfs_release_folio() to not deadlock via kcompactd writeback has been added to the -mm mm-hotfixes-unstable branch. Its filename is nfs-fix-nfs_release_folio-to-not-deadlock-via-kcompactd-writeback.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Mike Snitzer <snitzer(a)kernel.org> Subject: NFS: fix nfs_release_folio() to not deadlock via kcompactd writeback Date: Mon, 24 Feb 2025 21:20:02 -0500 Add PF_KCOMPACTD flag and current_is_kcompactd() helper to check for it so nfs_release_folio() can skip calling nfs_wb_folio() from kcompactd. Otherwise NFS can deadlock waiting for kcompactd enduced writeback which recurses back to NFS (which triggers writeback to NFSD via NFS loopback mount on the same host, NFSD blocks waiting for XFS's call to __filemap_get_folio): 6070.550357] INFO: task kcompactd0:58 blocked for more than 4435 seconds. {--- [58] "kcompactd0" [<0>] folio_wait_bit+0xe8/0x200 [<0>] folio_wait_writeback+0x2b/0x80 [<0>] nfs_wb_folio+0x80/0x1b0 [nfs] [<0>] nfs_release_folio+0x68/0x130 [nfs] [<0>] split_huge_page_to_list_to_order+0x362/0x840 [<0>] migrate_pages_batch+0x43d/0xb90 [<0>] migrate_pages_sync+0x9a/0x240 [<0>] migrate_pages+0x93c/0x9f0 [<0>] compact_zone+0x8e2/0x1030 [<0>] compact_node+0xdb/0x120 [<0>] kcompactd+0x121/0x2e0 [<0>] kthread+0xcf/0x100 [<0>] ret_from_fork+0x31/0x40 [<0>] ret_from_fork_asm+0x1a/0x30 ---} Link: https://lkml.kernel.org/r/20250225022002.26141-1-snitzer@kernel.org Fixes: 96780ca55e3cb ("NFS: fix up nfs_release_folio() to try to release the page") Signed-off-by: Mike Snitzer <snitzer(a)kernel.org> Cc: Anna Schumaker <anna.schumaker(a)oracle.com> Cc: Trond Myklebust <trond.myklebust(a)hammerspace.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/nfs/file.c | 3 ++- include/linux/compaction.h | 5 +++++ include/linux/sched.h | 2 +- mm/compaction.c | 3 +++ 4 files changed, 11 insertions(+), 2 deletions(-) --- a/fs/nfs/file.c~nfs-fix-nfs_release_folio-to-not-deadlock-via-kcompactd-writeback +++ a/fs/nfs/file.c @@ -29,6 +29,7 @@ #include <linux/pagemap.h> #include <linux/gfp.h> #include <linux/swap.h> +#include <linux/compaction.h> #include <linux/uaccess.h> #include <linux/filelock.h> @@ -457,7 +458,7 @@ static bool nfs_release_folio(struct fol /* If the private flag is set, then the folio is not freeable */ if (folio_test_private(folio)) { if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL || - current_is_kswapd()) + current_is_kswapd() || current_is_kcompactd()) return false; if (nfs_wb_folio(folio->mapping->host, folio) < 0) return false; --- a/include/linux/compaction.h~nfs-fix-nfs_release_folio-to-not-deadlock-via-kcompactd-writeback +++ a/include/linux/compaction.h @@ -80,6 +80,11 @@ static inline unsigned long compact_gap( return 2UL << order; } +static inline int current_is_kcompactd(void) +{ + return current->flags & PF_KCOMPACTD; +} + #ifdef CONFIG_COMPACTION extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); --- a/include/linux/sched.h~nfs-fix-nfs_release_folio-to-not-deadlock-via-kcompactd-writeback +++ a/include/linux/sched.h @@ -1701,7 +1701,7 @@ extern struct pid *cad_pid; #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF__HOLE__00010000 0x00010000 +#define PF_KCOMPACTD 0x00010000 /* I am kcompactd */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ --- a/mm/compaction.c~nfs-fix-nfs_release_folio-to-not-deadlock-via-kcompactd-writeback +++ a/mm/compaction.c @@ -3181,6 +3181,7 @@ static int kcompactd(void *p) long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC); long timeout = default_timeout; + tsk->flags |= PF_KCOMPACTD; set_freezable(); pgdat->kcompactd_max_order = 0; @@ -3237,6 +3238,8 @@ static int kcompactd(void *p) pgdat->proactive_compact_trigger = false; } + tsk->flags &= ~PF_KCOMPACTD; + return 0; } _ Patches currently in -mm which might be from snitzer(a)kernel.org are nfs-fix-nfs_release_folio-to-not-deadlock-via-kcompactd-writeback.patch

3 months, 3 weeks

1
0
0 0

+ nfs-fix-nfs_release_folio-to-not-call-nfs_wb_folio-from-kcompactd.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: NFS: fix nfs_release_folio() to not call nfs_wb_folio() from kcompactd has been added to the -mm mm-hotfixes-unstable branch. Its filename is nfs-fix-nfs_release_folio-to-not-call-nfs_wb_folio-from-kcompactd.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Mike Snitzer <snitzer(a)kernel.org> Subject: NFS: fix nfs_release_folio() to not call nfs_wb_folio() from kcompactd Date: Mon, 24 Feb 2025 19:33:01 -0500 Add PF_KCOMPACTD flag and current_is_kcompactd() helper to check for it so nfs_release_folio() can skip calling nfs_wb_folio() from kcompactd. Otherwise NFS can deadlock waiting for kcompactd induced writeback which recurses back to NFS (which triggers writeback to NFSD via NFS loopback mount on the same host, NFSD blocks waiting for XFS's call to __filemap_get_folio): 6070.550357] INFO: task kcompactd0:58 blocked for more than 4435 seconds. {--- [58] "kcompactd0" [<0>] folio_wait_bit+0xe8/0x200 [<0>] folio_wait_writeback+0x2b/0x80 [<0>] nfs_wb_folio+0x80/0x1b0 [nfs] [<0>] nfs_release_folio+0x68/0x130 [nfs] [<0>] split_huge_page_to_list_to_order+0x362/0x840 [<0>] migrate_pages_batch+0x43d/0xb90 [<0>] migrate_pages_sync+0x9a/0x240 [<0>] migrate_pages+0x93c/0x9f0 [<0>] compact_zone+0x8e2/0x1030 [<0>] compact_node+0xdb/0x120 [<0>] kcompactd+0x121/0x2e0 [<0>] kthread+0xcf/0x100 [<0>] ret_from_fork+0x31/0x40 [<0>] ret_from_fork_asm+0x1a/0x30 ---} Link: https://lkml.kernel.org/r/20250225003301.25693-1-snitzer@kernel.org Fixes: 96780ca55e3cb ("NFS: fix up nfs_release_folio() to try to release the page") Signed-off-by: Mike Snitzer <snitzer(a)kernel.org> Cc: Anna Schumaker <anna.schumaker(a)oracle.com> Cc: Trond Myklebust <trond.myklebust(a)hammerspace.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/nfs/file.c | 3 ++- include/linux/compaction.h | 5 +++++ include/linux/sched.h | 2 +- mm/compaction.c | 3 +++ 4 files changed, 11 insertions(+), 2 deletions(-) --- a/fs/nfs/file.c~nfs-fix-nfs_release_folio-to-not-call-nfs_wb_folio-from-kcompactd +++ a/fs/nfs/file.c @@ -29,6 +29,7 @@ #include <linux/pagemap.h> #include <linux/gfp.h> #include <linux/swap.h> +#include <linux/compaction.h> #include <linux/uaccess.h> #include <linux/filelock.h> @@ -457,7 +458,7 @@ static bool nfs_release_folio(struct fol /* If the private flag is set, then the folio is not freeable */ if (folio_test_private(folio)) { if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL || - current_is_kswapd()) + current_is_kswapd() || current_is_kcompactd()) return false; if (nfs_wb_folio(folio->mapping->host, folio) < 0) return false; --- a/include/linux/compaction.h~nfs-fix-nfs_release_folio-to-not-call-nfs_wb_folio-from-kcompactd +++ a/include/linux/compaction.h @@ -80,6 +80,11 @@ static inline unsigned long compact_gap( return 2UL << order; } +static inline int current_is_kcompactd(void) +{ + return current->flags & PF_KCOMPACTD; +} + #ifdef CONFIG_COMPACTION extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); --- a/include/linux/sched.h~nfs-fix-nfs_release_folio-to-not-call-nfs_wb_folio-from-kcompactd +++ a/include/linux/sched.h @@ -1701,7 +1701,7 @@ extern struct pid *cad_pid; #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF__HOLE__00010000 0x00010000 +#define PF_KCOMPACTD 0x00010000 /* I am kcompactd */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ --- a/mm/compaction.c~nfs-fix-nfs_release_folio-to-not-call-nfs_wb_folio-from-kcompactd +++ a/mm/compaction.c @@ -3181,6 +3181,7 @@ static int kcompactd(void *p) long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC); long timeout = default_timeout; + tsk->flags | PF_KCOMPACTD; set_freezable(); pgdat->kcompactd_max_order = 0; @@ -3237,6 +3238,8 @@ static int kcompactd(void *p) pgdat->proactive_compact_trigger = false; } + tsk->flags &= ~PF_KCOMPACTD; + return 0; } _ Patches currently in -mm which might be from snitzer(a)kernel.org are nfs-fix-nfs_release_folio-to-not-call-nfs_wb_folio-from-kcompactd.patch

3 months, 3 weeks

2
1
0 0

[PATCH v2 RESEND] phy: Fix error handling in tegra_xusb_port_init

by Ma Ke

If device_add() fails, do not use device_unregister() for error handling. device_unregister() consists two functions: device_del() and put_device(). device_unregister() should only be called after device_add() succeeded because device_del() undoes what device_add() does if successful. Change device_unregister() to put_device() call before returning from the function. As comment of device_add() says, 'if device_add() succeeds, you should call device_del() when you want to get rid of it. If device_add() has not succeeded, use only put_device() to drop the reference count'. Found by code review. Cc: stable(a)vger.kernel.org Fixes: 53d2a715c240 ("phy: Add Tegra XUSB pad controller support") Signed-off-by: Ma Ke <make24(a)iscas.ac.cn> --- Changes in v2: - modified the bug description as suggestions. --- drivers/phy/tegra/xusb.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 79d4814d758d..c89df95aa6ca 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -548,16 +548,16 @@ static int tegra_xusb_port_init(struct tegra_xusb_port *port, err = dev_set_name(&port->dev, "%s-%u", name, index); if (err < 0) - goto unregister; + goto put_device; err = device_add(&port->dev); if (err < 0) - goto unregister; + goto put_device; return 0; -unregister: - device_unregister(&port->dev); +put_device: + put_device(&port->dev); return err; } -- 2.25.1

3 months, 3 weeks

1
0
0 0

[PATCH v5 RESEND] [ARM] fix reference leak in locomo_init_one_child()

by Ma Ke

Once device_register() failed, we should call put_device() to decrement reference count for cleanup. Or it could cause memory leak. As comment of device_register() says, 'NOTE: _Never_ directly free @dev after calling this function, even if it returned an error! Always use put_device() to give up the reference initialized in this function instead.' Found by code review. Cc: stable(a)vger.kernel.org Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Ma Ke <make24(a)iscas.ac.cn> --- Changes in v5: - modified the bug description as suggestions; Changes in v4: - deleted the redundant initialization; Changes in v3: - modified the patch as suggestions; Changes in v2: - modified the patch as suggestions. --- arch/arm/common/locomo.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c index cb6ef449b987..45106066a17f 100644 --- a/arch/arm/common/locomo.c +++ b/arch/arm/common/locomo.c @@ -223,10 +223,8 @@ locomo_init_one_child(struct locomo *lchip, struct locomo_dev_info *info) int ret; dev = kzalloc(sizeof(struct locomo_dev), GFP_KERNEL); - if (!dev) { - ret = -ENOMEM; - goto out; - } + if (!dev) + return -ENOMEM; /* * If the parent device has a DMA mask associated with it, @@ -254,10 +252,9 @@ locomo_init_one_child(struct locomo *lchip, struct locomo_dev_info *info) NO_IRQ : lchip->irq_base + info->irq[0]; ret = device_register(&dev->dev); - if (ret) { - out: - kfree(dev); - } + if (ret) + put_device(&dev->dev); + return ret; } -- 2.25.1

3 months, 3 weeks

1
0
0 0

[PATCH v2] Bluetooth: Add check for mgmt_alloc_skb() in mgmt_remote_name()

by Haoxiang Li

Add check for the return value of mgmt_alloc_skb() in mgmt_remote_name() to prevent null pointer dereference. Fixes: ba17bb62ce41 ("Bluetooth: Fix skb allocation in mgmt_remote_name() & mgmt_device_connected()") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <haoxiang_li2024(a)163.com> --- Changes in v2: - modify the title description. --- net/bluetooth/mgmt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index f53304cb09db..3e0f88cd975c 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -10413,6 +10413,8 @@ void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, skb = mgmt_alloc_skb(hdev, MGMT_EV_DEVICE_FOUND, sizeof(*ev) + (name ? eir_precalc_len(name_len) : 0)); + if (!skb) + return; ev = skb_put(skb, sizeof(*ev)); bacpy(&ev->addr.bdaddr, bdaddr); -- 2.25.1

3 months, 3 weeks

2
1
0 0

[PATCH] dlm: fix lkb timeout scanning lookup

by Alexander Aring

If a lkb is timed out when dlm_scan_timeout() kicks in and removes a timed out lkb from ls->ls_timeout list the next iteration can end in timeout the same lkb again that shouldn't happen. Since commit dc1acd5c9469 ("dlm: replace usage of found with dedicated list iterator variable") we don't set the lkb variable before the inner lookup loop to NULL. The outer loop will not stop and checks if there was a successful lookup with the lkb pointer of the last iteration that wasn't set to NULL. To stop this behavior we use the old condition "!do_cancel && !do_warn" which signals if there was a successful lookup and the lkb variable should be set with the lkb that was looked up to be timed out. If the condition is false there is no timed out lkb in ls->ls_timeout and the outer loop stops. Cc: stable(a)vger.kernel.org Reported-by: Marc Smith <msmith626(a)gmail.com> Fixes: dc1acd5c9469 ("dlm: replace usage of found with dedicated list iterator variable") Signed-off-by: Alexander Aring <aahringo(a)redhat.com> --- fs/dlm/lock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 226822f49d30..1ff842be5891 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1919,7 +1919,7 @@ void dlm_scan_timeout(struct dlm_ls *ls) } mutex_unlock(&ls->ls_timeout_mutex); - if (!lkb) + if (!do_cancel && !do_warn) break; r = lkb->lkb_resource; -- 2.43.0

3 months, 3 weeks

1
0
0 0

[PATCH] perf: Add RCU read lock protection to perf_iterate_ctx()

by Breno Leitao

The perf_iterate_ctx() function performs RCU list traversal but currently lacks RCU read lock protection. This causes lockdep warnings when running perf probe with unshare(1) under CONFIG_PROVE_RCU_LIST=y: WARNING: suspicious RCU usage kernel/events/core.c:8168 RCU-list traversed in non-reader section!! Call Trace: lockdep_rcu_suspicious ? perf_event_addr_filters_apply perf_iterate_ctx perf_event_exec begin_new_exec ? load_elf_phdrs load_elf_binary ? lock_acquire ? find_held_lock ? bprm_execve bprm_execve do_execveat_common.isra.0 __x64_sys_execve do_syscall_64 entry_SYSCALL_64_after_hwframe This protection was previously present but was removed in commit bd2756811766 ("perf: Rewrite core context handling"). Add back the necessary rcu_read_lock()/rcu_read_unlock() pair around perf_iterate_ctx() call in perf_event_exec(). CC: stable(a)vger.kernel.org Fixes: bd2756811766 ("perf: Rewrite core context handling") Signed-off-by: Breno Leitao <leitao(a)debian.org> --- kernel/events/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index 065f9188b44a0d8ee66cc76314ae247dbe45cb57..e2adb06f8d81307b2762375474bee1c9e8a74598 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8277,7 +8277,9 @@ void perf_event_exec(void) perf_event_enable_on_exec(ctx); perf_event_remove_on_exec(ctx); + rcu_read_lock(); perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true); + rcu_read_unlock(); perf_unpin_context(ctx); put_ctx(ctx); --- base-commit: dbb0aea70ce4b85915a52d7adf9af57bd80f330a change-id: 20250117-fix_perf_rcu-2ff93190950a Best regards, -- Breno Leitao <leitao(a)debian.org>

3 months, 3 weeks

3
2
0 0

[PATCH] iommu/vt-d: Remove device comparison in context_setup_pass_through_cb

by Jerry Snitselaar

Remove the device comparison check in context_setup_pass_through_cb. pci_for_each_dma_alias already makes a decision on whether the callback function should be called for a device. With the check in place it will fail to create context entries for aliases as it walks up to the root bus. Fixes: 2031c469f816 ("iommu/vt-d: Add support for static identity domain") Closes: https://lore.kernel.org/linux-iommu/82499eb6-00b7-4f83-879a-e97b4144f576@li… Cc: Joerg Roedel <joro(a)8bytes.org> Cc: Lu Baolu <baolu.lu(a)linux.intel.com> Cc: stable(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Signed-off-by: Jerry Snitselaar <jsnitsel(a)redhat.com> --- drivers/iommu/intel/iommu.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index cc46098f875b..4d8d4593c9c8 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4378,9 +4378,6 @@ static int context_setup_pass_through_cb(struct pci_dev *pdev, u16 alias, void * { struct device *dev = data; - if (dev != &pdev->dev) - return 0; - return context_setup_pass_through(dev, PCI_BUS_NUM(alias), alias & 0xff); } -- 2.44.0

3 months, 3 weeks

1
0
0 0

[PATCH AUTOSEL 6.12 01/28] bpf: unify VM_WRITE vs VM_MAYWRITE use in BPF map mmaping logic

by Sasha Levin

From: Andrii Nakryiko <andrii(a)kernel.org> [ Upstream commit 98671a0fd1f14e4a518ee06b19037c20014900eb ] For all BPF maps we ensure that VM_MAYWRITE is cleared when memory-mapping BPF map contents as initially read-only VMA. This is because in some cases BPF verifier relies on the underlying data to not be modified afterwards by user space, so once something is mapped read-only, it shouldn't be re-mmap'ed as read-write. As such, it's not necessary to check VM_MAYWRITE in bpf_map_mmap() and map->ops->map_mmap() callbacks: VM_WRITE should be consistently set for read-write mappings, and if VM_WRITE is not set, there is no way for user space to upgrade read-only mapping to read-write one. This patch cleans up this VM_WRITE vs VM_MAYWRITE handling within bpf_map_mmap(), which is an entry point for any BPF map mmap()-ing logic. We also drop unnecessary sanitization of VM_MAYWRITE in BPF ringbuf's map_mmap() callback implementation, as it is already performed by common code in bpf_map_mmap(). Note, though, that in bpf_map_mmap_{open,close}() callbacks we can't drop VM_MAYWRITE use, because it's possible (and is outside of subsystem's control) to have initially read-write memory mapping, which is subsequently dropped to read-only by user space through mprotect(). In such case, from BPF verifier POV it's read-write data throughout the lifetime of BPF map, and is counted as "active writer". But its VMAs will start out as VM_WRITE|VM_MAYWRITE, then mprotect() can change it to just VM_MAYWRITE (and no VM_WRITE), so when its finally munmap()'ed and bpf_map_mmap_close() is called, vm_flags will be just VM_MAYWRITE, but we still need to decrement active writer count with bpf_map_write_active_dec() as it's still considered to be a read-write mapping by the rest of BPF subsystem. Similar reasoning applies to bpf_map_mmap_open(), which is called whenever mmap(), munmap(), and/or mprotect() forces mm subsystem to split original VMA into multiple discontiguous VMAs. Memory-mapping handling is a bit tricky, yes. Cc: Jann Horn <jannh(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/r/20250129012246.1515826-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/bpf/ringbuf.c | 4 ---- kernel/bpf/syscall.c | 10 ++++++++-- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index e1cfe890e0be6..1499d8caa9a35 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -268,8 +268,6 @@ static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma /* allow writable mapping for the consumer_pos only */ if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) return -EPERM; - } else { - vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, @@ -289,8 +287,6 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma * position, and the ring buffer data itself. */ return -EPERM; - } else { - vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 368ae8d231d41..fa43f26ce0dac 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -966,15 +966,21 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; vm_flags_clear(vma, VM_MAYEXEC); + /* If mapping is read-only, then disallow potentially re-mapping with + * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing + * means that as far as BPF map's memory-mapped VMAs are concerned, + * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set, + * both should be set, so we can forget about VM_MAYWRITE and always + * check just VM_WRITE + */ if (!(vma->vm_flags & VM_WRITE)) - /* disallow re-mapping with PROT_WRITE */ vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); if (err) goto out; - if (vma->vm_flags & VM_MAYWRITE) + if (vma->vm_flags & VM_WRITE) bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); -- 2.39.5

3 months, 3 weeks

2
28
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2025