October 2024 - Linux-stable-mirror

[PATCH v2] nfsd: fix race between laundromat and free_stateid

by Olga Kornievskaia

There is a race between laundromat handling of revoked delegations and a client sending free_stateid operation. Laundromat thread finds that delegation has expired and needs to be revoked so it marks the delegation stid revoked and it puts it on a reaper list but then it unlock the state lock and the actual delegation revocation happens without the lock. Once the stid is marked revoked a racing free_stateid processing thread does the following (1) it calls list_del_init() which removes it from the reaper list and (2) frees the delegation stid structure. The laundromat thread ends up not calling the revoke_delegation() function for this particular delegation but that means it will no release the lock lease that exists on the file. Now, a new open for this file comes in and ends up finding that lease list isn't empty and calls nfsd_breaker_owns_lease() which ends up trying to derefence a freed delegation stateid. Leading to the followint use-after-free KASAN warning: kernel: ================================================================== kernel: BUG: KASAN: slab-use-after-free in nfsd_breaker_owns_lease+0x140/0x160 [nfsd] kernel: Read of size 8 at addr ffff0000e73cd0c8 by task nfsd/6205 kernel: kernel: CPU: 2 UID: 0 PID: 6205 Comm: nfsd Kdump: loaded Not tainted 6.11.0-rc7+ #9 kernel: Hardware name: Apple Inc. Apple Virtualization Generic Platform, BIOS 2069.0.0.0.0 08/03/2024 kernel: Call trace: kernel: dump_backtrace+0x98/0x120 kernel: show_stack+0x1c/0x30 kernel: dump_stack_lvl+0x80/0xe8 kernel: print_address_description.constprop.0+0x84/0x390 kernel: print_report+0xa4/0x268 kernel: kasan_report+0xb4/0xf8 kernel: __asan_report_load8_noabort+0x1c/0x28 kernel: nfsd_breaker_owns_lease+0x140/0x160 [nfsd] kernel: leases_conflict+0x68/0x370 kernel: __break_lease+0x204/0xc38 kernel: nfsd_open_break_lease+0x8c/0xf0 [nfsd] kernel: nfsd_file_do_acquire+0xb3c/0x11d0 [nfsd] kernel: nfsd_file_acquire_opened+0x84/0x110 [nfsd] kernel: nfs4_get_vfs_file+0x634/0x958 [nfsd] kernel: nfsd4_process_open2+0xa40/0x1a40 [nfsd] kernel: nfsd4_open+0xa08/0xe80 [nfsd] kernel: nfsd4_proc_compound+0xb8c/0x2130 [nfsd] kernel: nfsd_dispatch+0x22c/0x718 [nfsd] kernel: svc_process_common+0x8e8/0x1960 [sunrpc] kernel: svc_process+0x3d4/0x7e0 [sunrpc] kernel: svc_handle_xprt+0x828/0xe10 [sunrpc] kernel: svc_recv+0x2cc/0x6a8 [sunrpc] kernel: nfsd+0x270/0x400 [nfsd] kernel: kthread+0x288/0x310 kernel: ret_from_fork+0x10/0x20 This patch proposes a fix that's based on adding 2 new additional stid's sc_status values that help coordinate between the laundromat and other operations (nfsd4_free_stateid() and nfsd4_delegreturn()). First to make sure, that once the stid is marked revoked, it is not removed by the nfsd4_free_stateid(), the laundromat take a reference on the stateid. Then, coordinating whether the stid has been put on the cl_revoked list or we are processing FREE_STATEID and need to make sure to remove it from the list, each check that state and act accordingly. If laundromat has added to the cl_revoke list before the arrival of FREE_STATEID, then nfsd4_free_stateid() knows to remove it from the list. If nfsd4_free_stateid() finds that operations arrived before laundromat has placed it on cl_revoke list, it marks the state freed and then laundromat will no longer add it to the list. Also, for nfsd4_delegreturn() when looking for the specified stid, we need to access stid that are marked removed or freeable, it means the laundromat has started processing it but hasn't finished and this delegreturn needs to return nfserr_deleg_revoked and not nfserr_bad_stateid. The latter will not trigger a FREE_STATEID and the lack of it will leave this stid on the cl_revoked list indefinitely. Fixes: 2d4a532d385f ("nfsd: ensure that clp->cl_revoked list is protected by clp->cl_lock") CC: stable(a)vger.kernel.org Signed-off-by: Olga Kornievskaia <okorniev(a)redhat.com> --- fs/nfsd/nfs4state.c | 15 ++++++++++++--- fs/nfsd/state.h | 2 ++ 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index ac1859c7cc9d..cb989802e896 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1370,10 +1370,16 @@ static void revoke_delegation(struct nfs4_delegation *dp) if (dp->dl_stid.sc_status & (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED)) { spin_lock(&clp->cl_lock); - refcount_inc(&dp->dl_stid.sc_count); + if (dp->dl_stid.sc_status & SC_STATUS_FREED) { + list_del_init(&dp->dl_recall_lru); + spin_unlock(&clp->cl_lock); + goto out; + } list_add(&dp->dl_recall_lru, &clp->cl_revoked); + dp->dl_stid.sc_status |= SC_STATUS_FREEABLE; spin_unlock(&clp->cl_lock); } +out: destroy_unhashed_deleg(dp); } @@ -6545,6 +6551,7 @@ nfs4_laundromat(struct nfsd_net *nn) dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (!state_expired(&lt, dp->dl_time)) break; + refcount_inc(&dp->dl_stid.sc_count); unhash_delegation_locked(dp, SC_STATUS_REVOKED); list_add(&dp->dl_recall_lru, &reaplist); } @@ -7156,7 +7163,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (s->sc_status & SC_STATUS_REVOKED) { spin_unlock(&s->sc_lock); dp = delegstateid(s); - list_del_init(&dp->dl_recall_lru); + if (s->sc_status & SC_STATUS_FREEABLE) + list_del_init(&dp->dl_recall_lru); + s->sc_status |= SC_STATUS_FREED; spin_unlock(&cl->cl_lock); nfs4_put_stid(s); ret = nfs_ok; @@ -7486,7 +7495,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) return status; - status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, 0, &s, nn); + status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, SC_STATUS_REVOKED|SC_STATUS_FREEABLE, &s, nn); if (status) goto out; dp = delegstateid(s); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 79c743c01a47..35b3564c065f 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -114,6 +114,8 @@ struct nfs4_stid { /* For a deleg stateid kept around only to process free_stateid's: */ #define SC_STATUS_REVOKED BIT(1) #define SC_STATUS_ADMIN_REVOKED BIT(2) +#define SC_STATUS_FREEABLE BIT(3) +#define SC_STATUS_FREED BIT(4) unsigned short sc_status; struct list_head sc_cp_list; -- 2.43.5

4 months, 2 weeks

3
2
0 0

[PATCH] resource,kexec: walk_system_ram_res_rev must retain resource flags

by Gregory Price

walk_system_ram_res_rev() erroneously discards resource flags when passing the information to the callback. This causes systems with IORESOURCE_SYSRAM_DRIVER_MANAGED memory to have these resources selected during kexec to store kexec buffers if that memory happens to be at placed above normal system ram. This leads to undefined behavior after reboot. If the kexec buffer is never touched, nothing happens. If the kexec buffer is touched, it could lead to a crash (like below) or undefined behavior. Tested on a system with CXL memory expanders with driver managed memory, TPM enabled, and CONFIG_IMA_KEXEC=y. Adding printk's showed the flags were being discarded and as a result the check for IORESOURCE_SYSRAM_DRIVER_MANAGED passes. find_next_iomem_res: name(System RAM (kmem)) start(10000000000) end(1034fffffff) flags(83000200) locate_mem_hole_top_down: start(10000000000) end(1034fffffff) flags(0) [.] BUG: unable to handle page fault for address: ffff89834ffff000 [.] #PF: supervisor read access in kernel mode [.] #PF: error_code(0x0000) - not-present page [.] PGD c04c8bf067 P4D c04c8bf067 PUD c04c8be067 PMD 0 [.] Oops: 0000 [#1] SMP [.] RIP: 0010:ima_restore_measurement_list+0x95/0x4b0 [.] RSP: 0018:ffffc900000d3a80 EFLAGS: 00010286 [.] RAX: 0000000000001000 RBX: 0000000000000000 RCX: ffff89834ffff000 [.] RDX: 0000000000000018 RSI: ffff89834ffff000 RDI: ffff89834ffff018 [.] RBP: ffffc900000d3ba0 R08: 0000000000000020 R09: ffff888132b8a900 [.] R10: 4000000000000000 R11: 000000003a616d69 R12: 0000000000000000 [.] R13: ffffffff8404ac28 R14: 0000000000000000 R15: ffff89834ffff000 [.] FS: 0000000000000000(0000) GS:ffff893d44640000(0000) knlGS:0000000000000000 [.] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [.] ata5: SATA link down (SStatus 0 SControl 300) [.] CR2: ffff89834ffff000 CR3: 000001034d00f001 CR4: 0000000000770ef0 [.] PKRU: 55555554 [.] Call Trace: [.] <TASK> [.] ? __die+0x78/0xc0 [.] ? page_fault_oops+0x2a8/0x3a0 [.] ? exc_page_fault+0x84/0x130 [.] ? asm_exc_page_fault+0x22/0x30 [.] ? ima_restore_measurement_list+0x95/0x4b0 [.] ? template_desc_init_fields+0x317/0x410 [.] ? crypto_alloc_tfm_node+0x9c/0xc0 [.] ? init_ima_lsm+0x30/0x30 [.] ima_load_kexec_buffer+0x72/0xa0 [.] ima_init+0x44/0xa0 [.] __initstub__kmod_ima__373_1201_init_ima7+0x1e/0xb0 [.] ? init_ima_lsm+0x30/0x30 [.] do_one_initcall+0xad/0x200 [.] ? idr_alloc_cyclic+0xaa/0x110 [.] ? new_slab+0x12c/0x420 [.] ? new_slab+0x12c/0x420 [.] ? number+0x12a/0x430 [.] ? sysvec_apic_timer_interrupt+0xa/0x80 [.] ? asm_sysvec_apic_timer_interrupt+0x16/0x20 [.] ? parse_args+0xd4/0x380 [.] ? parse_args+0x14b/0x380 [.] kernel_init_freeable+0x1c1/0x2b0 [.] ? rest_init+0xb0/0xb0 [.] kernel_init+0x16/0x1a0 [.] ret_from_fork+0x2f/0x40 [.] ? rest_init+0xb0/0xb0 [.] ret_from_fork_asm+0x11/0x20 [.] </TASK> Link: https://lore.kernel.org/all/20231114091658.228030-1-bhe@redhat.com/ Fixes: 7acf164b259d ("resource: add walk_system_ram_res_rev()") Cc: stable(a)vger.kernel.org Signed-off-by: Gregory Price <gourry(a)gourry.net> --- kernel/resource.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/kernel/resource.c b/kernel/resource.c index b730bd28b422..4101016e8b20 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -459,9 +459,7 @@ int walk_system_ram_res_rev(u64 start, u64 end, void *arg, rams_size += 16; } - rams[i].start = res.start; - rams[i++].end = res.end; - + rams[i++] = res; start = res.end + 1; } -- 2.43.0

4 months, 2 weeks

4
10
0 0

[RFC][PATCH] mm: Split locks in remap_file_pages()

by Roberto Sassu

From: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Commit ea7e2d5e49c0 ("mm: call the security_mmap_file() LSM hook in remap_file_pages()") fixed a security issue, it added an LSM check when trying to remap file pages, so that LSMs have the opportunity to evaluate such action like for other memory operations such as mmap() and mprotect(). However, that commit called security_mmap_file() inside the mmap_lock lock, while the other calls do it before taking the lock, after commit 8b3ec6814c83 ("take security_mmap_file() outside of ->mmap_sem"). This caused lock inversion issue with IMA which was taking the mmap_lock and i_mutex lock in the opposite way when the remap_file_pages() system call was called. Solve the issue by splitting the critical region in remap_file_pages() in two regions: the first takes a read lock of mmap_lock and retrieves the VMA and the file associated, and calculate the 'prot' and 'flags' variable; the second takes a write lock on mmap_lock, checks that the VMA flags and the VMA file descriptor are the same as the ones obtained in the first critical region (otherwise the system call fails), and calls do_mmap(). In between, after releasing the read lock and taking the write lock, call security_mmap_file(), and solve the lock inversion issue. Cc: stable(a)vger.kernel.org Fixes: ea7e2d5e49c0 ("mm: call the security_mmap_file() LSM hook in remap_file_pages()") Reported-by: syzbot+91ae49e1c1a2634d20c0(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-security-module/66f7b10e.050a0220.46d20.0036.… Reviewed-by: Roberto Sassu <roberto.sassu(a)huawei.com> (Calculate prot and flags earlier) Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> --- mm/mmap.c | 62 ++++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 45 insertions(+), 17 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 9c0fb43064b5..762944427e03 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1640,6 +1640,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long populate = 0; unsigned long ret = -EINVAL; struct file *file; + vm_flags_t vm_flags; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n", current->comm, current->pid); @@ -1656,12 +1657,53 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; - if (mmap_write_lock_killable(mm)) + if (mmap_read_lock_killable(mm)) + return -EINTR; + + vma = vma_lookup(mm, start); + + if (!vma || !(vma->vm_flags & VM_SHARED)) { + mmap_read_unlock(mm); + return -EINVAL; + } + + prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; + prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; + prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; + + flags &= MAP_NONBLOCK; + flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; + if (vma->vm_flags & VM_LOCKED) + flags |= MAP_LOCKED; + + /* Save vm_flags used to calculate prot and flags, and recheck later. */ + vm_flags = vma->vm_flags; + file = get_file(vma->vm_file); + + mmap_read_unlock(mm); + + ret = security_mmap_file(file, prot, flags); + if (ret) { + fput(file); + return ret; + } + + ret = -EINVAL; + + if (mmap_write_lock_killable(mm)) { + fput(file); return -EINTR; + } vma = vma_lookup(mm, start); - if (!vma || !(vma->vm_flags & VM_SHARED)) + if (!vma) + goto out; + + if (vma->vm_flags != vm_flags) + goto out; + + if (vma->vm_file != file) goto out; if (start + size > vma->vm_end) { @@ -1689,25 +1731,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, goto out; } - prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; - prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; - prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; - - flags &= MAP_NONBLOCK; - flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; - if (vma->vm_flags & VM_LOCKED) - flags |= MAP_LOCKED; - - file = get_file(vma->vm_file); - ret = security_mmap_file(vma->vm_file, prot, flags); - if (ret) - goto out_fput; ret = do_mmap(vma->vm_file, start, size, prot, flags, 0, pgoff, &populate, NULL); -out_fput: - fput(file); out: mmap_write_unlock(mm); + fput(file); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) -- 2.34.1

4 months, 2 weeks

3
4
0 0

[PATCH v3] comedi: Flush partial mappings in error case

by Jann Horn

If some remap_pfn_range() calls succeeded before one failed, we still have buffer pages mapped into the userspace page tables when we drop the buffer reference with comedi_buf_map_put(bm). The userspace mappings are only cleaned up later in the mmap error path. Fix it by explicitly flushing all mappings in our VMA on the error path. See commit 79a61cc3fc04 ("mm: avoid leaving partial pfn mappings around in error case"). Cc: stable(a)vger.kernel.org Fixes: ed9eccbe8970 ("Staging: add comedi core") Signed-off-by: Jann Horn <jannh(a)google.com> --- Note: compile-tested only; I don't actually have comedi hardware, and I don't know anything about comedi. --- Changes in v3: - gate zapping ptes on CONFIG_MMU (Intel kernel test robot) - Link to v2: https://lore.kernel.org/r/20241015-comedi-tlb-v2-1-cafb0e27dd9a@google.com Changes in v2: - only do the zapping in the pfnmap path (Ian Abbott) - use zap_vma_ptes() instead of zap_page_range_single() (Ian Abbott) - Link to v1: https://lore.kernel.org/r/20241014-comedi-tlb-v1-1-4b699144b438@google.com --- drivers/comedi/comedi_fops.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index 1b481731df96..b9df9b19d4bd 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -2407,6 +2407,18 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma) start += PAGE_SIZE; } + +#ifdef CONFIG_MMU + /* + * Leaving behind a partial mapping of a buffer we're about to + * drop is unsafe, see remap_pfn_range_notrack(). + * We need to zap the range here ourselves instead of relying + * on the automatic zapping in remap_pfn_range() because we call + * remap_pfn_range() in a loop. + */ + if (retval) + zap_vma_ptes(vma, vma->vm_start, size); +#endif } if (retval == 0) { --- base-commit: 6485cf5ea253d40d507cd71253c9568c5470cd27 change-id: 20241014-comedi-tlb-400246505961 -- Jann Horn <jannh(a)google.com>

4 months, 2 weeks

2
2
0 0

[PATCH RESEND] vdpa: solidrun: Fix UB bug with devres

by Philipp Stanner

In psnet_open_pf_bar() and snet_open_vf_bar() a string later passed to pcim_iomap_regions() is placed on the stack. Neither pcim_iomap_regions() nor the functions it calls copy that string. Should the string later ever be used, this, consequently, causes undefined behavior since the stack frame will by then have disappeared. Fix the bug by allocating the strings on the heap through devm_kasprintf(). Cc: stable(a)vger.kernel.org # v6.3 Fixes: 51a8f9d7f587 ("virtio: vdpa: new SolidNET DPU driver.") Reported-by: Christophe JAILLET <christophe.jaillet(a)wanadoo.fr> Closes: https://lore.kernel.org/all/74e9109a-ac59-49e2-9b1d-d825c9c9f891@wanadoo.fr/ Suggested-by: Andy Shevchenko <andy(a)kernel.org> Signed-off-by: Philipp Stanner <pstanner(a)redhat.com> --- drivers/vdpa/solidrun/snet_main.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index 99428a04068d..c8b74980dbd1 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -555,7 +555,7 @@ static const struct vdpa_config_ops snet_config_ops = { static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) { - char name[50]; + char *name; int ret, i, mask = 0; /* We don't know which BAR will be used to communicate.. * We will map every bar with len > 0. @@ -573,7 +573,10 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) return -ENODEV; } - snprintf(name, sizeof(name), "psnet[%s]-bars", pci_name(pdev)); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev)); + if (!name) + return -ENOMEM; + ret = pcim_iomap_regions(pdev, mask, name); if (ret) { SNET_ERR(pdev, "Failed to request and map PCI BARs\n"); @@ -590,10 +593,13 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) static int snet_open_vf_bar(struct pci_dev *pdev, struct snet *snet) { - char name[50]; + char *name; int ret; - snprintf(name, sizeof(name), "snet[%s]-bar", pci_name(pdev)); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "snet[%s]-bars", pci_name(pdev)); + if (!name) + return -ENOMEM; + /* Request and map BAR */ ret = pcim_iomap_regions(pdev, BIT(snet->psnet->cfg.vf_bar), name); if (ret) { -- 2.46.1

4 months, 2 weeks

5
7
0 0

FAILED: patch "[PATCH] KVM: s390: gaccess: Check if guest address is in memslot" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-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-4.19.y git checkout FETCH_HEAD git cherry-pick -x e8061f06185be0a06a73760d6526b8b0feadfe52 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101827-implosion-twilight-c8e1@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e8061f06185be0a06a73760d6526b8b0feadfe52 Mon Sep 17 00:00:00 2001 From: Nico Boehr <nrb(a)linux.ibm.com> Date: Tue, 17 Sep 2024 17:18:33 +0200 Subject: [PATCH] KVM: s390: gaccess: Check if guest address is in memslot Previously, access_guest_page() did not check whether the given guest address is inside of a memslot. This is not a problem, since kvm_write_guest_page/kvm_read_guest_page return -EFAULT in this case. However, -EFAULT is also returned when copy_to/from_user fails. When emulating a guest instruction, the address being outside a memslot usually means that an addressing exception should be injected into the guest. Failure in copy_to/from_user however indicates that something is wrong in userspace and hence should be handled there. To be able to distinguish these two cases, return PGM_ADDRESSING in access_guest_page() when the guest address is outside guest memory. In access_guest_real(), populate vcpu->arch.pgm.code such that kvm_s390_inject_prog_cond() can be used in the caller for injecting into the guest (if applicable). Since this adds a new return value to access_guest_page(), we need to make sure that other callers are not confused by the new positive return value. There are the following users of access_guest_page(): - access_guest_with_key() does the checking itself (in guest_range_to_gpas()), so this case should never happen. Even if, the handling is set up properly. - access_guest_real() just passes the return code to its callers, which are: - read_guest_real() - see below - write_guest_real() - see below There are the following users of read_guest_real(): - ar_translation() in gaccess.c which already returns PGM_* - setup_apcb10(), setup_apcb00(), setup_apcb11() in vsie.c which always return -EFAULT on read_guest_read() nonzero return - no change - shadow_crycb(), handle_stfle() always present this as validity, this could be handled better but doesn't change current behaviour - no change There are the following users of write_guest_real(): - kvm_s390_store_status_unloaded() always returns -EFAULT on write_guest_real() failure. Fixes: 2293897805c2 ("KVM: s390: add architecture compliant guest access functions") Cc: stable(a)vger.kernel.org Signed-off-by: Nico Boehr <nrb(a)linux.ibm.com> Reviewed-by: Heiko Carstens <hca(a)linux.ibm.com> Link: https://lore.kernel.org/r/20240917151904.74314-2-nrb@linux.ibm.com Acked-by: Janosch Frank <frankja(a)linux.ibm.com> Signed-off-by: Heiko Carstens <hca(a)linux.ibm.com> diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index e65f597e3044..a688351f4ab5 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -828,6 +828,8 @@ static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa, const gfn_t gfn = gpa_to_gfn(gpa); int rc; + if (!gfn_to_memslot(kvm, gfn)) + return PGM_ADDRESSING; if (mode == GACC_STORE) rc = kvm_write_guest_page(kvm, gfn, data, offset, len); else @@ -985,6 +987,8 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, gra += fragment_len; data += fragment_len; } + if (rc > 0) + vcpu->arch.pgm.code = rc; return rc; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index b320d12aa049..3fde45a151f2 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -405,11 +405,12 @@ int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, * @len: number of bytes to copy * * Copy @len bytes from @data (kernel space) to @gra (guest real address). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest low address and key protection are not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying from @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to guest memory. */ @@ -428,11 +429,12 @@ int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, * @len: number of bytes to copy * * Copy @len bytes from @gra (guest real address) to @data (kernel space). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest key protection is not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying to @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to kernel space. */

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] KVM: s390: gaccess: Check if guest address is in memslot" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-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-5.4.y git checkout FETCH_HEAD git cherry-pick -x e8061f06185be0a06a73760d6526b8b0feadfe52 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101826-gracious-singer-816f@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e8061f06185be0a06a73760d6526b8b0feadfe52 Mon Sep 17 00:00:00 2001 From: Nico Boehr <nrb(a)linux.ibm.com> Date: Tue, 17 Sep 2024 17:18:33 +0200 Subject: [PATCH] KVM: s390: gaccess: Check if guest address is in memslot Previously, access_guest_page() did not check whether the given guest address is inside of a memslot. This is not a problem, since kvm_write_guest_page/kvm_read_guest_page return -EFAULT in this case. However, -EFAULT is also returned when copy_to/from_user fails. When emulating a guest instruction, the address being outside a memslot usually means that an addressing exception should be injected into the guest. Failure in copy_to/from_user however indicates that something is wrong in userspace and hence should be handled there. To be able to distinguish these two cases, return PGM_ADDRESSING in access_guest_page() when the guest address is outside guest memory. In access_guest_real(), populate vcpu->arch.pgm.code such that kvm_s390_inject_prog_cond() can be used in the caller for injecting into the guest (if applicable). Since this adds a new return value to access_guest_page(), we need to make sure that other callers are not confused by the new positive return value. There are the following users of access_guest_page(): - access_guest_with_key() does the checking itself (in guest_range_to_gpas()), so this case should never happen. Even if, the handling is set up properly. - access_guest_real() just passes the return code to its callers, which are: - read_guest_real() - see below - write_guest_real() - see below There are the following users of read_guest_real(): - ar_translation() in gaccess.c which already returns PGM_* - setup_apcb10(), setup_apcb00(), setup_apcb11() in vsie.c which always return -EFAULT on read_guest_read() nonzero return - no change - shadow_crycb(), handle_stfle() always present this as validity, this could be handled better but doesn't change current behaviour - no change There are the following users of write_guest_real(): - kvm_s390_store_status_unloaded() always returns -EFAULT on write_guest_real() failure. Fixes: 2293897805c2 ("KVM: s390: add architecture compliant guest access functions") Cc: stable(a)vger.kernel.org Signed-off-by: Nico Boehr <nrb(a)linux.ibm.com> Reviewed-by: Heiko Carstens <hca(a)linux.ibm.com> Link: https://lore.kernel.org/r/20240917151904.74314-2-nrb@linux.ibm.com Acked-by: Janosch Frank <frankja(a)linux.ibm.com> Signed-off-by: Heiko Carstens <hca(a)linux.ibm.com> diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index e65f597e3044..a688351f4ab5 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -828,6 +828,8 @@ static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa, const gfn_t gfn = gpa_to_gfn(gpa); int rc; + if (!gfn_to_memslot(kvm, gfn)) + return PGM_ADDRESSING; if (mode == GACC_STORE) rc = kvm_write_guest_page(kvm, gfn, data, offset, len); else @@ -985,6 +987,8 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, gra += fragment_len; data += fragment_len; } + if (rc > 0) + vcpu->arch.pgm.code = rc; return rc; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index b320d12aa049..3fde45a151f2 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -405,11 +405,12 @@ int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, * @len: number of bytes to copy * * Copy @len bytes from @data (kernel space) to @gra (guest real address). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest low address and key protection are not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying from @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to guest memory. */ @@ -428,11 +429,12 @@ int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, * @len: number of bytes to copy * * Copy @len bytes from @gra (guest real address) to @data (kernel space). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest key protection is not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying to @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to kernel space. */

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] KVM: s390: gaccess: Check if guest address is in memslot" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-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-5.10.y git checkout FETCH_HEAD git cherry-pick -x e8061f06185be0a06a73760d6526b8b0feadfe52 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101824-departure-oversight-aa1e@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e8061f06185be0a06a73760d6526b8b0feadfe52 Mon Sep 17 00:00:00 2001 From: Nico Boehr <nrb(a)linux.ibm.com> Date: Tue, 17 Sep 2024 17:18:33 +0200 Subject: [PATCH] KVM: s390: gaccess: Check if guest address is in memslot Previously, access_guest_page() did not check whether the given guest address is inside of a memslot. This is not a problem, since kvm_write_guest_page/kvm_read_guest_page return -EFAULT in this case. However, -EFAULT is also returned when copy_to/from_user fails. When emulating a guest instruction, the address being outside a memslot usually means that an addressing exception should be injected into the guest. Failure in copy_to/from_user however indicates that something is wrong in userspace and hence should be handled there. To be able to distinguish these two cases, return PGM_ADDRESSING in access_guest_page() when the guest address is outside guest memory. In access_guest_real(), populate vcpu->arch.pgm.code such that kvm_s390_inject_prog_cond() can be used in the caller for injecting into the guest (if applicable). Since this adds a new return value to access_guest_page(), we need to make sure that other callers are not confused by the new positive return value. There are the following users of access_guest_page(): - access_guest_with_key() does the checking itself (in guest_range_to_gpas()), so this case should never happen. Even if, the handling is set up properly. - access_guest_real() just passes the return code to its callers, which are: - read_guest_real() - see below - write_guest_real() - see below There are the following users of read_guest_real(): - ar_translation() in gaccess.c which already returns PGM_* - setup_apcb10(), setup_apcb00(), setup_apcb11() in vsie.c which always return -EFAULT on read_guest_read() nonzero return - no change - shadow_crycb(), handle_stfle() always present this as validity, this could be handled better but doesn't change current behaviour - no change There are the following users of write_guest_real(): - kvm_s390_store_status_unloaded() always returns -EFAULT on write_guest_real() failure. Fixes: 2293897805c2 ("KVM: s390: add architecture compliant guest access functions") Cc: stable(a)vger.kernel.org Signed-off-by: Nico Boehr <nrb(a)linux.ibm.com> Reviewed-by: Heiko Carstens <hca(a)linux.ibm.com> Link: https://lore.kernel.org/r/20240917151904.74314-2-nrb@linux.ibm.com Acked-by: Janosch Frank <frankja(a)linux.ibm.com> Signed-off-by: Heiko Carstens <hca(a)linux.ibm.com> diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index e65f597e3044..a688351f4ab5 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -828,6 +828,8 @@ static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa, const gfn_t gfn = gpa_to_gfn(gpa); int rc; + if (!gfn_to_memslot(kvm, gfn)) + return PGM_ADDRESSING; if (mode == GACC_STORE) rc = kvm_write_guest_page(kvm, gfn, data, offset, len); else @@ -985,6 +987,8 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, gra += fragment_len; data += fragment_len; } + if (rc > 0) + vcpu->arch.pgm.code = rc; return rc; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index b320d12aa049..3fde45a151f2 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -405,11 +405,12 @@ int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, * @len: number of bytes to copy * * Copy @len bytes from @data (kernel space) to @gra (guest real address). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest low address and key protection are not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying from @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to guest memory. */ @@ -428,11 +429,12 @@ int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, * @len: number of bytes to copy * * Copy @len bytes from @gra (guest real address) to @data (kernel space). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest key protection is not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying to @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to kernel space. */

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] KVM: s390: gaccess: Check if guest address is in memslot" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-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-5.15.y git checkout FETCH_HEAD git cherry-pick -x e8061f06185be0a06a73760d6526b8b0feadfe52 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101823-tractor-twitter-a318@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e8061f06185be0a06a73760d6526b8b0feadfe52 Mon Sep 17 00:00:00 2001 From: Nico Boehr <nrb(a)linux.ibm.com> Date: Tue, 17 Sep 2024 17:18:33 +0200 Subject: [PATCH] KVM: s390: gaccess: Check if guest address is in memslot Previously, access_guest_page() did not check whether the given guest address is inside of a memslot. This is not a problem, since kvm_write_guest_page/kvm_read_guest_page return -EFAULT in this case. However, -EFAULT is also returned when copy_to/from_user fails. When emulating a guest instruction, the address being outside a memslot usually means that an addressing exception should be injected into the guest. Failure in copy_to/from_user however indicates that something is wrong in userspace and hence should be handled there. To be able to distinguish these two cases, return PGM_ADDRESSING in access_guest_page() when the guest address is outside guest memory. In access_guest_real(), populate vcpu->arch.pgm.code such that kvm_s390_inject_prog_cond() can be used in the caller for injecting into the guest (if applicable). Since this adds a new return value to access_guest_page(), we need to make sure that other callers are not confused by the new positive return value. There are the following users of access_guest_page(): - access_guest_with_key() does the checking itself (in guest_range_to_gpas()), so this case should never happen. Even if, the handling is set up properly. - access_guest_real() just passes the return code to its callers, which are: - read_guest_real() - see below - write_guest_real() - see below There are the following users of read_guest_real(): - ar_translation() in gaccess.c which already returns PGM_* - setup_apcb10(), setup_apcb00(), setup_apcb11() in vsie.c which always return -EFAULT on read_guest_read() nonzero return - no change - shadow_crycb(), handle_stfle() always present this as validity, this could be handled better but doesn't change current behaviour - no change There are the following users of write_guest_real(): - kvm_s390_store_status_unloaded() always returns -EFAULT on write_guest_real() failure. Fixes: 2293897805c2 ("KVM: s390: add architecture compliant guest access functions") Cc: stable(a)vger.kernel.org Signed-off-by: Nico Boehr <nrb(a)linux.ibm.com> Reviewed-by: Heiko Carstens <hca(a)linux.ibm.com> Link: https://lore.kernel.org/r/20240917151904.74314-2-nrb@linux.ibm.com Acked-by: Janosch Frank <frankja(a)linux.ibm.com> Signed-off-by: Heiko Carstens <hca(a)linux.ibm.com> diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index e65f597e3044..a688351f4ab5 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -828,6 +828,8 @@ static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa, const gfn_t gfn = gpa_to_gfn(gpa); int rc; + if (!gfn_to_memslot(kvm, gfn)) + return PGM_ADDRESSING; if (mode == GACC_STORE) rc = kvm_write_guest_page(kvm, gfn, data, offset, len); else @@ -985,6 +987,8 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, gra += fragment_len; data += fragment_len; } + if (rc > 0) + vcpu->arch.pgm.code = rc; return rc; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index b320d12aa049..3fde45a151f2 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -405,11 +405,12 @@ int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, * @len: number of bytes to copy * * Copy @len bytes from @data (kernel space) to @gra (guest real address). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest low address and key protection are not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying from @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to guest memory. */ @@ -428,11 +429,12 @@ int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, * @len: number of bytes to copy * * Copy @len bytes from @gra (guest real address) to @data (kernel space). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest key protection is not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying to @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to kernel space. */

4 months, 2 weeks

1
0
0 0

[PATCH 5.10] gfs2: Fix potential glock use-after-free on unmount

by He Zhe

From: Andreas Gruenbacher <agruenba(a)redhat.com> commit 0636b34b44589b142700ac137b5f69802cfe2e37 upstream. When a DLM lockspace is released and there ares still locks in that lockspace, DLM will unlock those locks automatically. Commit fb6791d100d1b started exploiting this behavior to speed up filesystem unmount: gfs2 would simply free glocks it didn't want to unlock and then release the lockspace. This didn't take the bast callbacks for asynchronous lock contention notifications into account, which remain active until until a lock is unlocked or its lockspace is released. To prevent those callbacks from accessing deallocated objects, put the glocks that should not be unlocked on the sd_dead_glocks list, release the lockspace, and only then free those glocks. As an additional measure, ignore unexpected ast and bast callbacks if the receiving glock is dead. Fixes: fb6791d100d1b ("GFS2: skip dlm_unlock calls in unmount") Signed-off-by: Andreas Gruenbacher <agruenba(a)redhat.com> Cc: David Teigland <teigland(a)redhat.com> CVE: CVE-2024-38570 [Zhe: sd_glock_wait in gfs2_glock_free_later is not renamed to sd_kill_wait yet. So still use sd_glock_wait in gfs2_glock_free_later in this case.] Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- fs/gfs2/glock.c | 35 ++++++++++++++++++++++++++++++++--- fs/gfs2/glock.h | 1 + fs/gfs2/incore.h | 1 + fs/gfs2/lock_dlm.c | 13 +++++++++++-- fs/gfs2/ops_fstype.c | 1 + fs/gfs2/super.c | 3 --- 6 files changed, 46 insertions(+), 8 deletions(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index b0f01a8e3776..11206d810344 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -159,19 +159,46 @@ static bool glock_blocked_by_withdraw(struct gfs2_glock *gl) return true; } -void gfs2_glock_free(struct gfs2_glock *gl) +static void __gfs2_glock_free(struct gfs2_glock *gl) { - struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - gfs2_glock_assert_withdraw(gl, atomic_read(&gl->gl_revokes) == 0); rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms); smp_mb(); wake_up_glock(gl); call_rcu(&gl->gl_rcu, gfs2_glock_dealloc); +} + +void gfs2_glock_free(struct gfs2_glock *gl) { + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + __gfs2_glock_free(gl); if (atomic_dec_and_test(&sdp->sd_glock_disposal)) wake_up(&sdp->sd_glock_wait); } +void gfs2_glock_free_later(struct gfs2_glock *gl) { + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + spin_lock(&lru_lock); + list_add(&gl->gl_lru, &sdp->sd_dead_glocks); + spin_unlock(&lru_lock); + if (atomic_dec_and_test(&sdp->sd_glock_disposal)) + wake_up(&sdp->sd_glock_wait); +} + +static void gfs2_free_dead_glocks(struct gfs2_sbd *sdp) +{ + struct list_head *list = &sdp->sd_dead_glocks; + + while(!list_empty(list)) { + struct gfs2_glock *gl; + + gl = list_first_entry(list, struct gfs2_glock, gl_lru); + list_del_init(&gl->gl_lru); + __gfs2_glock_free(gl); + } +} + /** * gfs2_glock_hold() - increment reference count on glock * @gl: The glock to hold @@ -2016,6 +2043,8 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp) wait_event_timeout(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0, HZ * 600); + gfs2_lm_unmount(sdp); + gfs2_free_dead_glocks(sdp); glock_hash_walk(dump_glock_func, sdp); } diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 53813364517b..b81b369e7485 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -253,6 +253,7 @@ extern void gfs2_glock_finish_truncate(struct gfs2_inode *ip); extern void gfs2_glock_thaw(struct gfs2_sbd *sdp); extern void gfs2_glock_add_to_lru(struct gfs2_glock *gl); extern void gfs2_glock_free(struct gfs2_glock *gl); +extern void gfs2_glock_free_later(struct gfs2_glock *gl); extern int __init gfs2_glock_init(void); extern void gfs2_glock_exit(void); diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index f8858d995b24..44cee9a4eef6 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -863,6 +863,7 @@ struct gfs2_sbd { struct gfs2_holder sd_freeze_gh; atomic_t sd_freeze_state; struct mutex sd_freeze_mutex; + struct list_head sd_dead_glocks; char sd_fsname[GFS2_FSNAME_LEN + 3 * sizeof(int) + 2]; char sd_table_name[GFS2_FSNAME_LEN]; diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 5564aa8b4592..9aad03f0dcdf 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -118,6 +118,11 @@ static void gdlm_ast(void *arg) struct gfs2_glock *gl = arg; unsigned ret = gl->gl_state; + /* If the glock is dead, we only react to a dlm_unlock() reply. */ + if (__lockref_is_dead(&gl->gl_lockref) && + gl->gl_lksb.sb_status != -DLM_EUNLOCK) + return; + gfs2_update_reply_times(gl); BUG_ON(gl->gl_lksb.sb_flags & DLM_SBF_DEMOTED); @@ -168,6 +173,9 @@ static void gdlm_bast(void *arg, int mode) { struct gfs2_glock *gl = arg; + if (__lockref_is_dead(&gl->gl_lockref)) + return; + switch (mode) { case DLM_LOCK_EX: gfs2_glock_cb(gl, LM_ST_UNLOCKED); @@ -286,6 +294,8 @@ static void gdlm_put_lock(struct gfs2_glock *gl) struct lm_lockstruct *ls = &sdp->sd_lockstruct; int error; + BUG_ON(!__lockref_is_dead(&gl->gl_lockref)); + if (gl->gl_lksb.sb_lkid == 0) { gfs2_glock_free(gl); return; @@ -305,7 +315,7 @@ static void gdlm_put_lock(struct gfs2_glock *gl) if (test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags) && !gl->gl_lksb.sb_lvbptr) { - gfs2_glock_free(gl); + gfs2_glock_free_later(gl); return; } @@ -315,7 +325,6 @@ static void gdlm_put_lock(struct gfs2_glock *gl) fs_err(sdp, "gdlm_unlock %x,%llx err=%d\n", gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number, error); - return; } } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 648f7336043f..4a8c070d14cf 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -141,6 +141,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) init_waitqueue_head(&sdp->sd_log_flush_wait); atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN); mutex_init(&sdp->sd_freeze_mutex); + INIT_LIST_HEAD(&sdp->sd_dead_glocks); return sdp; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 8cf4ef61cdc4..039d678b1689 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -662,10 +662,7 @@ static void gfs2_put_super(struct super_block *sb) gfs2_gl_hash_clear(sdp); truncate_inode_pages_final(&sdp->sd_aspace); gfs2_delete_debugfs_file(sdp); - /* Unmount the locking protocol */ - gfs2_lm_unmount(sdp); - /* At this point, we're through participating in the lockspace */ gfs2_sys_fs_del(sdp); free_sbd(sdp); } -- 2.25.1

4 months, 2 weeks

2
9
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2024