From 7b69729046a4c58f4cb457184e5ac4aaa179bff4 Mon Sep 17 00:00:00 2001 From: Haoxiang Li Date: Wed, 24 Jun 2026 14:19:10 +0800 Subject: [PATCH 01/56] KVM: s390: pci: Fix GISC refcount leak on AIF enable failure kvm_s390_gisc_register() registers the guest ISC before pinning the guest interrupt forwarding pages and allocating the AISB bit. If any of the later setup steps fails, the function unwinds the pinned pages and other local state, but does not unregister the GISC reference. Add the missing kvm_s390_gisc_unregister() to the error unwind path. Fixes: 3c5a1b6f0a18 ("KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding") Cc: stable@vger.kernel.org Signed-off-by: Haoxiang Li Reviewed-by: Matthew Rosato Tested-by: Matthew Rosato Acked-by: Claudio Imbrenda Reviewed-by: Christian Borntraeger Signed-off-by: Claudio Imbrenda Message-ID: <20260624061910.2794734-1-haoxiang_li2024@163.com> Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 5b075c38998e..686113be0530 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -328,6 +328,7 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, unpin1: unpin_user_page(aibv_page); out: + kvm_s390_gisc_unregister(kvm, fib->fmt0.isc); return rc; } From 866d03de6def89c386cdfd457b28a1f566e02565 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Thu, 2 Jul 2026 17:23:59 +0200 Subject: [PATCH 02/56] KVM: s390: vsie: Avoid potential deadlock with real spaces The natural lock ordering is mmu_lock -> children_lock, but in gmap_create_shadow() the reverse order is used when handling shadowing of real address spaces. Convert the inner locking of kvm->mmu_lock to a trylock; return -EAGAIN if the lock is busy, and let the caller try again. This path is not expected to happen in real-life scenarios, so its performance is not important. Fixes: a2c17f9270cc ("KVM: s390: New gmap code") Signed-off-by: Claudio Imbrenda Reviewed-by: Christian Borntraeger Signed-off-by: Christian Borntraeger --- arch/s390/kvm/gmap.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c index 298fbaecec28..8abb4f55b306 100644 --- a/arch/s390/kvm/gmap.c +++ b/arch/s390/kvm/gmap.c @@ -1374,8 +1374,13 @@ struct gmap *gmap_create_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *pare /* Only allow one real-space gmap shadow. */ list_for_each_entry(sg, &parent->children, list) { if (sg->guest_asce.r) { - scoped_guard(write_lock, &parent->kvm->mmu_lock) + if (write_trylock(&parent->kvm->mmu_lock)) { gmap_unshadow(sg); + write_unlock(&parent->kvm->mmu_lock); + } else { + gmap_put(new); + return ERR_PTR(-EAGAIN); + } break; } } From 4d4a21e38f1b87a76b3e63d4f837ff4e9b52d5a6 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Thu, 2 Jul 2026 17:24:05 +0200 Subject: [PATCH 03/56] KVM: s390: Fix dat_crste_walk_range() early return If a walk entry handler for a lower level returns a value, dat_crste_walk_range() will not return immediately, but instead loop again and move to the next entry. This means that some entries are potentially skipped, and early return is ignored. Skipped entries might lead to all kinds of issues, given that the caller expects them to not be skipped. Early return is often used to interrupt a walk when a rescheduling is needed; if it is ignored it can lead to stalls. Fix by breaking from the loop immediately if the walk to a lower level returned non-zero. Fixes: 2db149a0a6c5 ("KVM: s390: KVM page table management functions: walks") Signed-off-by: Claudio Imbrenda Reviewed-by: Christian Borntraeger Signed-off-by: Christian Borntraeger --- arch/s390/kvm/dat.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index 5f1960ec982d..ed4259d17629 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -570,6 +570,8 @@ static long dat_crste_walk_range(gfn_t start, gfn_t end, struct crst_table *tabl else if (walk->ops->pte_entry) rc = dat_pte_walk_range(max(start, cur), min(end, next), dereference_pmd(crste.pmd), walk); + if (rc) + break; } } return rc; From 9489220fe0e69d2ca141e5062dd3ef3e2e55959f Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Thu, 2 Jul 2026 17:24:06 +0200 Subject: [PATCH 04/56] KVM: s390: Improve kvm_s390_vm_stop_migration() There is no need to clear cmma-dirty state if the VM is not using CMMA. Skip the CMMA-related code if CMMA is not in use. Fixes: 6cfd47f91f6a ("KVM: s390: Fix cmma dirty tracking") Fixes: 190df4a212a7 ("KVM: s390: CMMA tracking, ESSA emulation, migration mode") Signed-off-by: Claudio Imbrenda Reviewed-by: Christian Borntraeger Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 23c817595e28..150b5dd2170e 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1280,8 +1280,10 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm) * PGSTEs might have cmma_d set. */ WRITE_ONCE(kvm->arch.migration_mode, 0); - if (kvm->arch.use_cmma) - kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION); + if (!kvm->arch.use_cmma) + return 0; + + kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION); /* Clear cmma_d on all existing PGSTEs and set cmma_dirty_pages to 0. */ gmap_set_cmma_all_clean(kvm->arch.gmap); atomic64_set(&kvm->arch.cmma_dirty_pages, 0); From 3e3aa6da87d30a0064a17b836685cd43c90a3572 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Thu, 9 Jul 2026 09:54:04 -0400 Subject: [PATCH 05/56] KVM: s390: pci: Fix handling of AIF enable without AISB When a guest seeks to register IRQs without a summary bit specified, ensure that the associated GAITE then stores 0 for the guest AISB location instead of virt_to_phys(page_address(NULL)). Fixes: 3c5a1b6f0a18 ("KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding") Cc: stable@vger.kernel.org Reviewed-by: Farhan Ali Signed-off-by: Matthew Rosato Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 686113be0530..720bb58cabe2 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -300,9 +300,14 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, gaite->gisc = fib->fmt0.isc; gaite->count++; - gaite->aisbo = fib->fmt0.aisbo; - gaite->aisb = virt_to_phys(page_address(aisb_page) + (fib->fmt0.aisb & - ~PAGE_MASK)); + if (fib->fmt0.sum == 1) { + gaite->aisbo = fib->fmt0.aisbo; + gaite->aisb = virt_to_phys(page_address(aisb_page) + + (fib->fmt0.aisb & ~PAGE_MASK)); + } else { + gaite->aisbo = 0; + gaite->aisb = 0; + } aift->kzdev[zdev->aisb] = zdev->kzdev; spin_unlock_irq(&aift->gait_lock); From 8fa01be5a6149404adb82c0979a78f6347edd3ef Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 23 Jul 2026 15:14:04 -0700 Subject: [PATCH 06/56] KVM: s390: pci: Reject adapter interrupt forwarding if already enabled The MPCIFC instruction doesn't allow registering adapter interrupts without first unregistering. So reject any request to enable interrupt forwarding if its already enabled for the zPCI device. This also fixes overwriting and thus leaking resources when the ioctl is called multiple times for the same device. Fixes: 3c5a1b6f0a18 ("KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding") Cc: stable@vger.kernel.org Reviewed-by: Christian Borntraeger Reviewed-by: Matthew Rosato Signed-off-by: Farhan Ali Tested-by: Matthew Rosato Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 720bb58cabe2..d2a11cdf6941 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -237,6 +237,10 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, if (zdev->gisa == 0) return -EINVAL; + /* AIF already enabled for the device */ + if (zdev->kzdev->fib.fmt0.aibv != 0) + return -EINVAL; + kvm = zdev->kzdev->kvm; msi_vecs = min_t(unsigned int, fib->fmt0.noi, zdev->max_msi); From 36f6999ecde3976731a8bfc0b8e667da6f593069 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 23 Jul 2026 15:14:05 -0700 Subject: [PATCH 07/56] KVM: s390: pci: Fix memory accounting for pinned/unpinned pages The account_mem() and unaccount_mem() functions call get_uid() which increments the reference count of struct user_struct on every invocation. But we don't decrement the count by calling free_uid(). It also accounted/unaccounted the pages against the current->mm. But its possible the unaccount_mem() can be called from a different process context than the one that originally pinned the pages. Let's fix this by storing the pinning process user_struct and mm_struct when accounting for pinned pages, and subsequently free these resources when the pages are unpinned. Fixes: 3c5a1b6f0a18 ("KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding") Cc: stable@vger.kernel.org Reviewed-by: Christian Borntraeger Reviewed-by: Matthew Rosato Signed-off-by: Farhan Ali Tested-by: Matthew Rosato [borntraeger@linux.ibm.com: Fixed whitespace] Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 43 ++++++++++++++++++++++++++++++++----------- arch/s390/kvm/pci.h | 2 ++ 2 files changed, 34 insertions(+), 11 deletions(-) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index d2a11cdf6941..0741aed442bc 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -190,33 +190,54 @@ static int kvm_zpci_clear_airq(struct zpci_dev *zdev) return cc ? -EIO : 0; } -static inline void unaccount_mem(unsigned long nr_pages) +static inline void unaccount_mem(struct kvm_zdev *kzdev, unsigned long nr_pages) { - struct user_struct *user = get_uid(current_user()); + struct user_struct *user = kzdev->user_account; + struct mm_struct *mm_account = kzdev->mm_account; - if (user) + if (user) { atomic_long_sub(nr_pages, &user->locked_vm); - if (current->mm) - atomic64_sub(nr_pages, ¤t->mm->pinned_vm); + free_uid(user); + kzdev->user_account = NULL; + } + + if (mm_account) { + atomic64_sub(nr_pages, &mm_account->pinned_vm); + mmdrop(mm_account); + kzdev->mm_account = NULL; + } } -static inline int account_mem(unsigned long nr_pages) +static inline int account_mem(struct kvm_zdev *kzdev, unsigned long nr_pages) { struct user_struct *user = get_uid(current_user()); unsigned long page_limit, cur_pages, new_pages; + int rc = 0; page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; cur_pages = atomic_long_read(&user->locked_vm); do { new_pages = cur_pages + nr_pages; - if (new_pages > page_limit) - return -ENOMEM; + if (new_pages > page_limit) { + rc = -ENOMEM; + goto out; + } } while (!atomic_long_try_cmpxchg(&user->locked_vm, &cur_pages, new_pages)); - atomic64_add(nr_pages, ¤t->mm->pinned_vm); + if (current->mm) { + mmgrab(current->mm); + atomic64_add(nr_pages, ¤t->mm->pinned_vm); + } + + kzdev->user_account = user; + kzdev->mm_account = current->mm; return 0; + +out: + free_uid(user); + return rc; } static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, @@ -279,7 +300,7 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, } /* Account for pinned pages, roll back on failure */ - if (account_mem(pcount)) + if (account_mem(zdev->kzdev, pcount)) goto unpin2; /* AISB must be allocated before we can fill in GAITE */ @@ -400,7 +421,7 @@ static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force) pcount++; } if (pcount > 0) - unaccount_mem(pcount); + unaccount_mem(kzdev, pcount); out: mutex_unlock(&aift->aift_lock); diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index ff0972dd5e71..fdf8c7bf4ed0 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -22,6 +22,8 @@ struct kvm_zdev { struct kvm *kvm; struct zpci_fib fib; struct list_head entry; + struct user_struct *user_account; + struct mm_struct *mm_account; }; struct zpci_gaite { From f86842e4d6c482300f4567f492d512c9ccf5bc4f Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 23 Jul 2026 15:14:06 -0700 Subject: [PATCH 08/56] KVM: s390: pci: Fix missing error codes and memory unaccounting In kvm_s390_pci_aif_enable() two error paths failed to set an error code, causing the function to return 0 on failure. It also failed to rollback memory accounting on failure. Fix both by propagating an error code on failure and calling unaccount_mem() in the cleanup path. Fixes: 3c5a1b6f0a18 ("KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding") Cc: stable@vger.kernel.org Reviewed-by: Christian Borntraeger Reviewed-by: Matthew Rosato Signed-off-by: Farhan Ali Tested-by: Matthew Rosato Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 0741aed442bc..36eb30953bb5 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -300,14 +300,17 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, } /* Account for pinned pages, roll back on failure */ - if (account_mem(zdev->kzdev, pcount)) + rc = account_mem(zdev->kzdev, pcount); + if (rc) goto unpin2; /* AISB must be allocated before we can fill in GAITE */ mutex_lock(&aift->aift_lock); bit = airq_iv_alloc_bit(aift->sbv); - if (bit == -1UL) + if (bit == -1UL) { + rc = -ENOMEM; goto unlock; + } zdev->aisb = bit; /* store the summary bit number */ zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK | @@ -351,6 +354,8 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, return rc; unlock: + if (pcount > 0) + unaccount_mem(zdev->kzdev, pcount); mutex_unlock(&aift->aift_lock); unpin2: if (fib->fmt0.sum == 1) From 8bf09b9b7d3232806df95f409581f8a9fd99a3fa Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 23 Jul 2026 15:14:07 -0700 Subject: [PATCH 09/56] KVM: s390: pci: Fix NULL dereference on AIBV allocation failure The airq_iv_create() can return NULL on failure, but the return value was never checked. If it fails, zdev->aibv will be NULL and fail when dereferenced in kvm_zpci_set_airq(). Add a NULL check and free the previously allocated AISB bit and zdev->aisb on failure. Fixes: 3c5a1b6f0a18 ("KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding") Cc: stable@vger.kernel.org Reviewed-by: Christian Borntraeger Reviewed-by: Matthew Rosato Signed-off-by: Farhan Ali Tested-by: Matthew Rosato Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 36eb30953bb5..1eb127fc9f89 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -317,6 +317,11 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, AIRQ_IV_GUESTVEC, phys_to_virt(fib->fmt0.aibv)); + if (!zdev->aibv) { + rc = -ENOMEM; + goto free_aisb; + } + spin_lock_irq(&aift->gait_lock); gaite = aift->gait + zdev->aisb; @@ -353,6 +358,9 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, rc = kvm_zpci_set_airq(zdev); return rc; +free_aisb: + airq_iv_free_bit(aift->sbv, zdev->aisb); + zdev->aisb = 0; unlock: if (pcount > 0) unaccount_mem(zdev->kzdev, pcount); From 5580c9858f1e00f60191eb09c3add359836d60b6 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 23 Jul 2026 15:14:08 -0700 Subject: [PATCH 10/56] KVM: s390: pci: Fix resource leak on IRQ registration failure Currently if kvm_zpci_set_airq() fails, kvm_s390_pci_aif_enable() returns the error code but doesn't do any resource cleanup thus leaking resources. Fix this by cleaning up all the resources such as the GAITE, AIBV, AISB and unpinning any pinned pages. While at it, remove dead code that stored FIB values that were never referenced. As part of the cleanup, we are also holding the aift_lock a bit longer, as we hold the lock while executing the MPCIFC instruction. Though this is not strictly necessary, it means we don't have to drop and re-acquire in the error case. Fixes: 3c5a1b6f0a18 ("KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding") Cc: stable@vger.kernel.org Reviewed-by: Matthew Rosato Reviewed-by: Christian Borntraeger Signed-off-by: Farhan Ali Tested-by: Matthew Rosato Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 1eb127fc9f89..50f495bc8303 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -344,19 +344,32 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, aift->kzdev[zdev->aisb] = zdev->kzdev; spin_unlock_irq(&aift->gait_lock); - /* Update guest FIB for re-issue */ - fib->fmt0.aisbo = zdev->aisb & 63; - fib->fmt0.aisb = virt_to_phys(aift->sbv->vector) + (zdev->aisb / 64) * 8; - fib->fmt0.isc = gisc; - /* Save some guest fib values in the host for later use */ - zdev->kzdev->fib.fmt0.isc = fib->fmt0.isc; + zdev->kzdev->fib.fmt0.isc = gisc; zdev->kzdev->fib.fmt0.aibv = fib->fmt0.aibv; - mutex_unlock(&aift->aift_lock); /* Issue the clp to setup the irq now */ rc = kvm_zpci_set_airq(zdev); - return rc; + if (!rc) { + mutex_unlock(&aift->aift_lock); + return rc; + } + + /* Start cleanup */ + zdev->kzdev->fib.fmt0.isc = 0; + zdev->kzdev->fib.fmt0.aibv = 0; + + spin_lock_irq(&aift->gait_lock); + gaite->count--; + gaite->aisb = 0; + gaite->gisc = 0; + gaite->aisbo = 0; + gaite->gisa = 0; + aift->kzdev[zdev->aisb] = NULL; + spin_unlock_irq(&aift->gait_lock); + + airq_iv_release(zdev->aibv); + zdev->aibv = NULL; free_aisb: airq_iv_free_bit(aift->sbv, zdev->aisb); From 868d32ac72cba21c5c6d8a66a814b7c25a3a5c01 Mon Sep 17 00:00:00 2001 From: Farhan Ali Date: Thu, 23 Jul 2026 15:14:09 -0700 Subject: [PATCH 11/56] KVM: s390: pci: Validate AIBV and AISB before pinning guest pages The AIBV holds one bit per MSI-X vector for a given function. The size of the bit vector is derived from the NOI and the AIBVO. If the size of the AIBV exceeds a single page boundary, then reject the request as we cannot safely pin the guest AIBV. Similarly reject the request if the AISB address is not 8-byte aligned as the architecture requires doubleword alignment for the summary bit address. Since the AISBO can address up to 64 bits, the size of the AISB can only be 8 bytes for the function. This also ensures the AISB doesn't exceed a single page boundary. Fixes: 3c5a1b6f0a18 ("KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding") Cc: stable@vger.kernel.org Reviewed-by: Christian Borntraeger Reviewed-by: Matthew Rosato Signed-off-by: Farhan Ali Tested-by: Matthew Rosato Signed-off-by: Christian Borntraeger --- arch/s390/kvm/pci.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 50f495bc8303..50f5ec79600e 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -244,7 +244,7 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, bool assist) { struct page *pages[1], *aibv_page, *aisb_page = NULL; - unsigned int msi_vecs, idx; + unsigned int msi_vecs, idx, size; struct zpci_gaite *gaite; unsigned long hva, bit; struct kvm *kvm; @@ -271,6 +271,14 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, return gisc; /* Replace AIBV address */ + size = BITS_TO_LONGS(msi_vecs + fib->fmt0.aibvo) * sizeof(unsigned long); + npages = DIV_ROUND_UP((fib->fmt0.aibv & ~PAGE_MASK) + size, PAGE_SIZE); + /* AIBV cannot span more than 1 page */ + if (npages > 1) { + rc = -EINVAL; + goto out; + } + idx = srcu_read_lock(&kvm->srcu); hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aibv)); npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, pages); @@ -286,6 +294,12 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, /* Pin the guest AISB if one was specified */ if (fib->fmt0.sum == 1) { + /* AISB must be dword aligned */ + if (fib->fmt0.aisb & 0x7) { + rc = -EINVAL; + goto unpin1; + } + idx = srcu_read_lock(&kvm->srcu); hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aisb)); npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, From 9972befc3e34ff8b6847198c84f11bfc312dde40 Mon Sep 17 00:00:00 2001 From: Jaehoon Kim Date: Fri, 24 Jul 2026 08:39:43 -0500 Subject: [PATCH 12/56] KVM: s390: Fall back to short-term pinning in MAP ioctl FOLL_LONGTERM pinning fails for some memory types, such as file-backed guest memory. As a result, kvm_s390_adapter_map() returns -EINVAL and irqfd adapter registration fails even though interrupt delivery could still work via the existing non-atomic path. When FOLL_LONGTERM pinning fails, verify that the page is accessible using a short-term pin instead. If the short-term pin succeeds, unpin the page and add a map entry with pinned=false to preserve MAP/UNMAP symmetry. The non-atomic irqfd path already performs short-term pinning for interrupt delivery, so this restores the previous behavior for memory that cannot be pinned long-term. get_map_info() is updated to return NULL for unpinned entries so that the atomic irqfd fast path falls back to the non-atomic path. kvm_s390_adapter_unmap() and kvm_s390_unmap_all_adapters() skip dirty marking and unpin for unpinned entries. Update Documentation/virt/kvm/devices/s390_flic.rst to reflect the new MAP/UNMAP behavior. Fixes: c9a568838086 ("KVM: s390: Add map/unmap ioctl and clean mappings post-guest") Signed-off-by: Jaehoon Kim Reviewed-by: Douglas Freimuth Reviewed-by: Matthew Rosato Signed-off-by: Christian Borntraeger --- Documentation/virt/kvm/devices/s390_flic.rst | 15 +++++- arch/s390/include/asm/kvm_host.h | 5 ++ arch/s390/kvm/interrupt.c | 56 +++++++++++++++----- 3 files changed, 60 insertions(+), 16 deletions(-) diff --git a/Documentation/virt/kvm/devices/s390_flic.rst b/Documentation/virt/kvm/devices/s390_flic.rst index b784f8016748..983c858b444a 100644 --- a/Documentation/virt/kvm/devices/s390_flic.rst +++ b/Documentation/virt/kvm/devices/s390_flic.rst @@ -112,9 +112,20 @@ Groups: mask or unmask the adapter, as specified in mask KVM_S390_IO_ADAPTER_MAP - This is now a no-op. The mapping is purely done by the irq route. + Map an adapter indicator or summary page for long-term pinning so that + interrupt injection can be performed in atomic context. If long-term + pinning is not possible (e.g. file-backed memory), the page is verified + via a short-term pin and the ioctl returns success; interrupt injection + will use the non-atomic irqfd path with short-term pinning on each + interrupt. In Secure Execution mode this is a no-op and the ioctl + returns success. + KVM_S390_IO_ADAPTER_UNMAP - This is now a no-op. The mapping is purely done by the irq route. + Unmap a previously mapped adapter indicator or summary page and release + the long-term pin. If the page was not long-term pinned (e.g. file-backed + memory), the map entry is removed and success is returned; if no prior + map entry exists, -ENOENT is returned. In Secure Execution mode this is + a no-op and the ioctl returns success. KVM_DEV_FLIC_AISM modify the adapter-interruption-suppression mode for a given isc if the diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index eaa34c5bd3c1..c172f9b212d1 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -476,6 +476,11 @@ struct s390_map_info { __u64 guest_addr; __u64 addr; struct page *page; + /* + * True if the page is long-term pinned. False if long-term pinning + * failed and this entry exists only to preserve MAP/UNMAP symmetry. + */ + bool pinned; }; struct s390_io_adapter { diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 9e3e6b0d72ad..7514d9e2403c 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2520,8 +2520,22 @@ static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr) map->addr = host_addr; map->page = pin_map_page(kvm, host_addr, FOLL_LONGTERM); if (!map->page) { - ret = -EINVAL; - goto out; + /* + * Long-term pinning may fail for memory types such as file-backed + * memory. Verify that short-term pinning succeeds so that the + * non-atomic irqfd path can handle interrupt injection. + */ + map->page = pin_map_page(kvm, host_addr, 0); + if (!map->page) { + ret = -EINVAL; + goto out; + } + unpin_user_page(map->page); + map->page = NULL; + map->pinned = false; + /* Add an entry to preserve MAP/UNMAP symmetry. */ + } else { + map->pinned = true; } spin_lock_irqsave(&adapter->maps_lock, flags); if (adapter->nr_maps < MAX_S390_ADAPTER_MAPS) { @@ -2532,7 +2546,7 @@ static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr) ret = -EINVAL; } spin_unlock_irqrestore(&adapter->maps_lock, flags); - if (ret) + if (ret && map->page) unpin_user_page(map->page); out: if (ret) @@ -2546,6 +2560,7 @@ static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr) struct s390_map_info *map, *tmp, *map_to_free; struct page *map_page_to_put = NULL; u64 map_addr_to_mark = 0; + bool map_pinned = false; unsigned long flags; int found = 0, idx; @@ -2560,6 +2575,7 @@ static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr) list_del(&map->list); map_page_to_put = map->page; map_addr_to_mark = map->guest_addr; + map_pinned = map->pinned; map_to_free = map; break; } @@ -2568,11 +2584,18 @@ static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr) if (found) { kfree(map_to_free); - idx = srcu_read_lock(&kvm->srcu); - mark_page_dirty(kvm, map_addr_to_mark >> PAGE_SHIFT); - set_page_dirty_lock(map_page_to_put); - srcu_read_unlock(&kvm->srcu, idx); - unpin_user_page(map_page_to_put); + if (map_pinned) { + /* + * Only long-term pinned pages need to be marked dirty + * and released. Fallback entries exist only for + * MAP/UNMAP symmetry. + */ + idx = srcu_read_lock(&kvm->srcu); + mark_page_dirty(kvm, map_addr_to_mark >> PAGE_SHIFT); + set_page_dirty_lock(map_page_to_put); + srcu_read_unlock(&kvm->srcu, idx); + unpin_user_page(map_page_to_put); + } } return found ? 0 : -ENOENT; @@ -2598,11 +2621,13 @@ void kvm_s390_unmap_all_adapters(struct kvm *kvm) list_for_each_entry_safe(map, tmp, &local_list, list) { list_del(&map->list); - idx = srcu_read_lock(&kvm->srcu); - mark_page_dirty(kvm, map->guest_addr >> PAGE_SHIFT); - set_page_dirty_lock(map->page); - srcu_read_unlock(&kvm->srcu, idx); - unpin_user_page(map->page); + if (map->pinned) { + idx = srcu_read_lock(&kvm->srcu); + mark_page_dirty(kvm, map->guest_addr >> PAGE_SHIFT); + set_page_dirty_lock(map->page); + srcu_read_unlock(&kvm->srcu, idx); + unpin_user_page(map->page); + } kfree(map); } } @@ -2929,8 +2954,11 @@ static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter, return NULL; list_for_each_entry(map, &adapter->maps, list) { - if (map->addr == addr) + if (map->addr == addr) { + if (!map->pinned) + return NULL; return map; + } } return NULL; } From 74186c2968f8f756ac3226b545b598457c910c75 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:13 +0200 Subject: [PATCH 13/56] s390/vfio_ccw: Free all memory if cp_init() fails The routine cp_free() is called to unpin/free any memory once an I/O is completed successfully, or if cp_prefetch() fails. But if cp_init() fails, and cp->initialized is not enabled, the same routine cannot be used to free all the memory. An attempt to address this exists in ccwchain_handle_ccw(), where a single call to ccwchain_free() is made for the currently-processed CCW segment. But this will leak other segments (created as a result of a Transfer in Channel) that had been allocated as part of the same channel program. Address this by performing the cleanup outside of the recursive ccwchain_handle_ccw()/ccwchain_loop_tic() logic. Fixes: 8b515be512a2 ("vfio-ccw: Fix memory leak and don't call cp_free in cp_init") Cc: stable@vger.kernel.org Reviewed-by: Farhan Ali Reviewed-by: Matthew Rosato Signed-off-by: Eric Farman Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_cp.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 7561aa7d3e01..086d1b54bdb0 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -455,9 +455,6 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp) /* Loop for tics on this new chain. */ ret = ccwchain_loop_tic(chain, cp); - if (ret) - ccwchain_free(chain); - return ret; } @@ -486,6 +483,23 @@ static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp) return 0; } +static int ccwchain_build_ccws(dma32_t cda, struct channel_program *cp) +{ + struct ccwchain *chain, *temp; + int ret; + + ret = ccwchain_handle_ccw(cda, cp); + + if (ret) { + /* Cleanup if an error occurred */ + list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) { + ccwchain_free(chain); + } + } + + return ret; +} + static int ccwchain_fetch_tic(struct ccw1 *ccw, struct channel_program *cp) { @@ -735,7 +749,7 @@ int cp_init(struct channel_program *cp, union orb *orb) memcpy(&cp->orb, orb, sizeof(*orb)); /* Build a ccwchain for the first CCW segment */ - ret = ccwchain_handle_ccw(orb->cmd.cpa, cp); + ret = ccwchain_build_ccws(orb->cmd.cpa, cp); if (!ret) cp->initialized = true; From 5405c90d6a47b3014e74ee0618a162449abbbc93 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:14 +0200 Subject: [PATCH 14/56] s390/vfio_ccw: Limit the number of channel program segments The processing of channel programs, and the CCWs within them, is done recursively. As such, there is an arbitrary (but not architectural) limit to the number of CCWs that can exist in a single channel program. The vfio-ccw logic breaks these channel programs into segments whenever it encounters a Transfer-In-Channel (TIC) CCW, and the combined number of segments count towards the global limit. Impose an equivalent limit to the number of segments until such logic can be made non-recursive. Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces") Cc: stable@vger.kernel.org Reviewed-by: Matthew Rosato Signed-off-by: Eric Farman Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_cp.c | 6 ++++++ drivers/s390/cio/vfio_ccw_cp.h | 8 ++++++++ 2 files changed, 14 insertions(+) diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 086d1b54bdb0..1c2890d139c6 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -332,6 +332,7 @@ static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len) goto out_err; list_add_tail(&chain->next, &cp->ccwchain_list); + cp->ccwchain_count++; return chain; @@ -441,6 +442,10 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp) if (len < 0) return len; + /* Limit number of chains in a single channel program */ + if (cp->ccwchain_count >= CCWCHAIN_COUNT_MAX) + return -EINVAL; + /* Need alloc a new chain for this one. */ chain = ccwchain_alloc(cp, len); if (!chain) @@ -745,6 +750,7 @@ int cp_init(struct channel_program *cp, union orb *orb) vdev->dev, "Prefetching channel program even though prefetch not specified in ORB"); + cp->ccwchain_count = 0; INIT_LIST_HEAD(&cp->ccwchain_list); memcpy(&cp->orb, orb, sizeof(*orb)); diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h index fc31eb699807..a9b1d8dbc6f6 100644 --- a/drivers/s390/cio/vfio_ccw_cp.h +++ b/drivers/s390/cio/vfio_ccw_cp.h @@ -23,11 +23,18 @@ */ #define CCWCHAIN_LEN_MAX 256 +/* + * Maximum number of chains + */ +#define CCWCHAIN_COUNT_MAX 16 + /** * struct channel_program - manage information for channel program * @ccwchain_list: list head of ccwchains * @orb: orb for the currently processed ssch request * @initialized: whether this instance is actually initialized + * @guest_cp: copy of guest channel program + * @ccwchain_count: number of channel program segments (linked by TIC) * * @ccwchain_list is the head of a ccwchain list, that contents the * translated result of the guest channel program that pointed out by @@ -38,6 +45,7 @@ struct channel_program { union orb orb; bool initialized; struct ccw1 *guest_cp; + unsigned int ccwchain_count; }; int cp_init(struct channel_program *cp, union orb *orb); From a005b7f1a491ffda61bff0fd0f6548f8986fb977 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:15 +0200 Subject: [PATCH 15/56] s390/vfio_ccw: Fix out of bounds check on CCW array The routine ccwchain_calc_length() counts the number of channel command words (CCWs) that are chained together in a single channel program, and rejects anything larger than CCWCHAIN_LEN_MAX (256) CCWs. The loop itself is "do..while (count < 257)", and while the logic in is_cpa_within_range() correctly adjusts between the 0-index array of CCWs and the count of CCWs starting at 1, this means it would look at a possible 257th CCW before ending the loop and (correctly) returning an error. Fix this by restructuring the loop to break as soon as 256 CCWs (thus indexes 0-255) are examined, without looking at memory outside the range. Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces") Cc: stable@vger.kernel.org Reviewed-by: Matthew Rosato Signed-off-by: Eric Farman Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_cp.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 1c2890d139c6..af632f9d5453 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -377,11 +377,9 @@ static void ccwchain_cda_free(struct ccwchain *chain, int idx) static int ccwchain_calc_length(u64 iova, struct channel_program *cp) { struct ccw1 *ccw = cp->guest_cp; - int cnt = 0; - - do { - cnt++; + int cnt; + for (cnt = 1; cnt <= CCWCHAIN_LEN_MAX; cnt++, ccw++) { /* * We want to keep counting if the current CCW has the * command-chaining flag enabled, or if it is a TIC CCW @@ -391,15 +389,10 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp) * after the TIC, depending on the results of its operation. */ if (!ccw_is_chain(ccw) && !is_tic_within_range(ccw, iova, cnt)) - break; + return cnt; + } - ccw++; - } while (cnt < CCWCHAIN_LEN_MAX + 1); - - if (cnt == CCWCHAIN_LEN_MAX + 1) - cnt = -EINVAL; - - return cnt; + return -EINVAL; } static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp) From 565bef268d75bf7df665bce6923a88cd0eb74592 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:16 +0200 Subject: [PATCH 16/56] s390/vfio_ccw: Ensure first IDAW remains constant The first IDAW in a list does not need to be on a 2K/4K boundary like all others, and so is read separately to accurately calculate the size of the buffer needed to read the full IDAL. Verify that the address found in the first IDAW is unchanged between reads, to ensure a consistent set of IDAWs being worked with. Fixes: 01aa26c672c0 ("s390/cio: Combine direct and indirect CCW paths") Cc: stable@vger.kernel.org Reviewed-by: Matthew Rosato Signed-off-by: Eric Farman Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_cp.c | 16 ++++++++++++++++ drivers/s390/cio/vfio_ccw_cp.h | 2 ++ 2 files changed, 18 insertions(+) diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index af632f9d5453..6275794751cb 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -523,6 +523,7 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int &container_of(cp, struct vfio_ccw_private, cp)->vdev; dma64_t *idaws; dma32_t *idaws_f1; + u64 first_idaw; int idal_len = idaw_nr * sizeof(*idaws); int idaw_size = idal_is_2k(cp) ? PAGE_SIZE / 2 : PAGE_SIZE; int idaw_mask = ~(idaw_size - 1); @@ -539,6 +540,18 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int kfree(idaws); return ERR_PTR(ret); } + + idaws_f1 = (dma32_t *)idaws; + if (cp->orb.cmd.c64) + first_idaw = dma64_to_u64(idaws[0]); + else + first_idaw = dma32_to_u32(idaws_f1[0]); + + /* Unexpected mismatch from earlier read */ + if (first_idaw != cp->guest_iova) { + kfree(idaws); + return ERR_PTR(-EINVAL); + } } else { /* Fabricate an IDAL based off CCW data address */ if (cp->orb.cmd.c64) { @@ -604,6 +617,9 @@ static int ccw_count_idaws(struct ccw1 *ccw, iova = dma32_to_u32(ccw->cda); } + /* Save the read address for later */ + cp->guest_iova = iova; + /* Format-1 IDAWs operate on 2K each */ if (!cp->orb.cmd.c64) return idal_2k_nr_words((void *)iova, bytes); diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h index a9b1d8dbc6f6..9af98ff12d67 100644 --- a/drivers/s390/cio/vfio_ccw_cp.h +++ b/drivers/s390/cio/vfio_ccw_cp.h @@ -35,6 +35,7 @@ * @initialized: whether this instance is actually initialized * @guest_cp: copy of guest channel program * @ccwchain_count: number of channel program segments (linked by TIC) + * @guest_iova: first data address of a guest channel program * * @ccwchain_list is the head of a ccwchain list, that contents the * translated result of the guest channel program that pointed out by @@ -46,6 +47,7 @@ struct channel_program { bool initialized; struct ccw1 *guest_cp; unsigned int ccwchain_count; + u64 guest_iova; }; int cp_init(struct channel_program *cp, union orb *orb); From 4f6fdc6e1a7fbfa36b945af33c65a417948feac0 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:17 +0200 Subject: [PATCH 17/56] s390/vfio_ccw: Calculate idal length based on idaw type Sashiko pointed out that get_guest_idal() unconditionally calculates the length of the IDAL presuming everything is a Format-2 IDAW. The output of vfio-ccw is always Format-2, but the input can be either Format-1 (31-bit addresses) or Format-2 (64-bit addresses). As a result, the size of the guest IDAL may be incorrect and should be trimmed down. Reported-by: sashiko-bot Link: https://lore.kernel.org/r/20260720203400.7328E1F000E9@smtp.kernel.org/ Fixes: 1b676fe3d9d3 ("vfio/ccw: handle a guest Format-1 IDAL") Cc: stable@vger.kernel.org Reviewed-by: Matthew Rosato Signed-off-by: Eric Farman Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_cp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 6275794751cb..5ef082b8289a 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -233,6 +233,7 @@ static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len) } #define idal_is_2k(_cp) (!(_cp)->orb.cmd.c64 || (_cp)->orb.cmd.i2k) +#define get_idaw_size(_cp) ((_cp)->orb.cmd.c64 ? sizeof(u64) : sizeof(u32)) /* * Helpers to operate ccwchain. @@ -524,7 +525,7 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int dma64_t *idaws; dma32_t *idaws_f1; u64 first_idaw; - int idal_len = idaw_nr * sizeof(*idaws); + int idal_len = idaw_nr * get_idaw_size(cp); int idaw_size = idal_is_2k(cp) ? PAGE_SIZE / 2 : PAGE_SIZE; int idaw_mask = ~(idaw_size - 1); int i, ret; @@ -593,7 +594,7 @@ static int ccw_count_idaws(struct ccw1 *ccw, struct vfio_device *vdev = &container_of(cp, struct vfio_ccw_private, cp)->vdev; u64 iova; - int size = cp->orb.cmd.c64 ? sizeof(u64) : sizeof(u32); + int size = get_idaw_size(cp); int ret; int bytes = 1; From 9f5f9a78fedc45bc29d6a0a64e3a3472361afae5 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:18 +0200 Subject: [PATCH 18/56] s390/vfio_ccw: Ensure index for read/write regions are within range The introduction of the capability chain rightly clamped the region indexes to the range of the capabilities itself, but neglected to do so for the existing read/write regions which should also be enforced. Fixes: db8e5d17ac03 ("vfio-ccw: add capabilities chain") Cc: stable@vger.kernel.org Cc: Cornelia Huck Reviewed-by: Matthew Rosato Signed-off-by: Eric Farman Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_async.c | 16 ++++++++++++++++ drivers/s390/cio/vfio_ccw_chp.c | 15 +++++++++++++++ drivers/s390/cio/vfio_ccw_ops.c | 7 +++---- 3 files changed, 34 insertions(+), 4 deletions(-) diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c index 420d89ba7f83..4aff0b58fa5d 100644 --- a/drivers/s390/cio/vfio_ccw_async.c +++ b/drivers/s390/cio/vfio_ccw_async.c @@ -8,6 +8,7 @@ */ #include +#include #include "vfio_ccw_private.h" @@ -24,11 +25,20 @@ static ssize_t vfio_ccw_async_region_read(struct vfio_ccw_private *private, return -EINVAL; mutex_lock(&private->io_mutex); + + if (i >= private->num_regions) { + ret = -EINVAL; + goto out_unlock; + } + + i = array_index_nospec(i, private->num_regions); region = private->region[i].data; if (copy_to_user(buf, (void *)region + pos, count)) ret = -EFAULT; else ret = count; + +out_unlock: mutex_unlock(&private->io_mutex); return ret; } @@ -48,6 +58,12 @@ static ssize_t vfio_ccw_async_region_write(struct vfio_ccw_private *private, if (!mutex_trylock(&private->io_mutex)) return -EAGAIN; + if (i >= private->num_regions) { + ret = -EINVAL; + goto out_unlock; + } + + i = array_index_nospec(i, private->num_regions); region = private->region[i].data; if (copy_from_user((void *)region + pos, buf, count)) { ret = -EFAULT; diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c index 38c176cf6295..f3015132d4b5 100644 --- a/drivers/s390/cio/vfio_ccw_chp.c +++ b/drivers/s390/cio/vfio_ccw_chp.c @@ -9,6 +9,7 @@ */ #include +#include #include #include "vfio_ccw_private.h" @@ -26,6 +27,13 @@ static ssize_t vfio_ccw_schib_region_read(struct vfio_ccw_private *private, return -EINVAL; mutex_lock(&private->io_mutex); + + if (i >= private->num_regions) { + ret = -EINVAL; + goto out; + } + + i = array_index_nospec(i, private->num_regions); region = private->region[i].data; if (cio_update_schib(sch)) { @@ -97,6 +105,12 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private, list_del(&crw->next); mutex_lock(&private->io_mutex); + if (i >= private->num_regions) { + ret = -EINVAL; + goto out; + } + + i = array_index_nospec(i, private->num_regions); region = private->region[i].data; if (crw) @@ -109,6 +123,7 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private, region->crw = 0; +out: mutex_unlock(&private->io_mutex); kfree(crw); diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index 45ec722d25ea..032a1cdf4df7 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -243,6 +243,7 @@ static ssize_t vfio_ccw_mdev_read(struct vfio_device *vdev, return vfio_ccw_mdev_read_io_region(private, buf, count, ppos); default: index -= VFIO_CCW_NUM_REGIONS; + index = array_index_nospec(index, private->num_regions); return private->region[index].ops->read(private, buf, count, ppos); } @@ -295,6 +296,7 @@ static ssize_t vfio_ccw_mdev_write(struct vfio_device *vdev, return vfio_ccw_mdev_write_io_region(private, buf, count, ppos); default: index -= VFIO_CCW_NUM_REGIONS; + index = array_index_nospec(index, private->num_regions); return private->region[index].ops->write(private, buf, count, ppos); } @@ -338,11 +340,8 @@ static int vfio_ccw_mdev_ioctl_get_region_info(struct vfio_device *vdev, VFIO_CCW_NUM_REGIONS + private->num_regions) return -EINVAL; - info->index = array_index_nospec(info->index, - VFIO_CCW_NUM_REGIONS + - private->num_regions); - i = info->index - VFIO_CCW_NUM_REGIONS; + i = array_index_nospec(i, private->num_regions); info->offset = VFIO_CCW_INDEX_TO_OFFSET(info->index); info->size = private->region[i].size; From 79c60b2c61105368dcc8444eb45847e21734f7c4 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:19 +0200 Subject: [PATCH 19/56] s390/vfio_ccw: Cancel existing workqueues The initialization of the io_work and crw_work workqueues begs the question of whether they should be un-initialized. Add the corresponding cleanup tags in _release_dev to ensure work isn't dispatched after the private struct is free'd. Suggested-by: Matthew Rosato Fixes: e5f84dbaea59 ("vfio: ccw: return I/O results asynchronously") Fixes: 3f02cb2fd9d2 ("vfio-ccw: Wire up the CRW irq and CRW region") Cc: stable@vger.kernel.org Reviewed-by: Matthew Rosato Signed-off-by: Eric Farman Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_ops.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index 032a1cdf4df7..d361d1fde3a0 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -131,6 +131,13 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev) container_of(vdev, struct vfio_ccw_private, vdev); struct vfio_ccw_crw *crw, *temp; + /* + * Ensure these work items are fully drained, so none can + * fire after being released. + */ + cancel_work_sync(&private->io_work); + cancel_work_sync(&private->crw_work); + list_for_each_entry_safe(crw, temp, &private->crw, next) { list_del(&crw->next); kfree(crw); @@ -202,6 +209,14 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev) container_of(vdev, struct vfio_ccw_private, vdev); vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE); + + /* + * Ensure these work items are drained, in the event the + * device is re-opened instead of released. + */ + cancel_work_sync(&private->io_work); + cancel_work_sync(&private->crw_work); + vfio_ccw_unregister_dev_regions(private); } From 0c11f61a876ed6fcca53d442ed3f33ea8362a0f9 Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:20 +0200 Subject: [PATCH 20/56] s390/vfio_ccw: Move cp cleanup out of not operational The fsm_notoper() routine is called when the device has been lost, and is (by definition) no longer operational. Since this can happen asynchronously from the normal behavior of the driver, the cleanup may happen when holding other locks in the calling sequence (notably, the cio subchannel lock). Push the cleanup of the private->cp resources to a workqueue, where it can be done out from under that lock sequence and a future patch can safely manage the locking requirements. Fixes: 204b394a23ad ("vfio/ccw: Move FSM open/close to MDEV open/close") Cc: stable@vger.kernel.org Signed-off-by: Eric Farman Reviewed-by: Matthew Rosato Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_drv.c | 9 +++++++++ drivers/s390/cio/vfio_ccw_fsm.c | 3 +-- drivers/s390/cio/vfio_ccw_ops.c | 13 +++++++++++++ drivers/s390/cio/vfio_ccw_private.h | 3 +++ 4 files changed, 26 insertions(+), 2 deletions(-) diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 1a095085bc72..c197ad5ab580 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -125,6 +125,15 @@ void vfio_ccw_crw_todo(struct work_struct *work) eventfd_signal(private->crw_trigger); } +void vfio_ccw_notoper_todo(struct work_struct *work) +{ + struct vfio_ccw_private *private; + + private = container_of(work, struct vfio_ccw_private, notoper_work); + + cp_free(&private->cp); +} + /* * Css driver callbacks */ diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c index 4d7988ea47ef..4d47a3c7b9a0 100644 --- a/drivers/s390/cio/vfio_ccw_fsm.c +++ b/drivers/s390/cio/vfio_ccw_fsm.c @@ -170,8 +170,7 @@ static void fsm_notoper(struct vfio_ccw_private *private, css_sched_sch_todo(sch, SCH_TODO_UNREG); private->state = VFIO_CCW_STATE_NOT_OPER; - /* This is usually handled during CLOSE event */ - cp_free(&private->cp); + queue_work(vfio_ccw_work_q, &private->notoper_work); } /* diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index d361d1fde3a0..1df6d649565b 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -54,6 +54,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev) INIT_LIST_HEAD(&private->crw); INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo); INIT_WORK(&private->crw_work, vfio_ccw_crw_todo); + INIT_WORK(&private->notoper_work, vfio_ccw_notoper_todo); private->cp.guest_cp = kzalloc_objs(struct ccw1, CCWCHAIN_LEN_MAX); if (!private->cp.guest_cp) @@ -134,9 +135,16 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev) /* * Ensure these work items are fully drained, so none can * fire after being released. + * + * notoper_work should have nothing to do here, because only + * open devices could have channel_program resources in use + * and those would be released during close. Nevertheless, + * call flush here as well to be certain anything that was + * allocated is freed. */ cancel_work_sync(&private->io_work); cancel_work_sync(&private->crw_work); + flush_work(&private->notoper_work); list_for_each_entry_safe(crw, temp, &private->crw, next) { list_del(&crw->next); @@ -213,9 +221,14 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev) /* * Ensure these work items are drained, in the event the * device is re-opened instead of released. + * + * notoper_work needs to be given a chance to run if it + * is queued, so any memory associated with the channel + * program can be returned. */ cancel_work_sync(&private->io_work); cancel_work_sync(&private->crw_work); + flush_work(&private->notoper_work); vfio_ccw_unregister_dev_regions(private); } diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index 0501d4bbcdbd..e2256402b089 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -102,6 +102,7 @@ struct vfio_ccw_parent { * @req_trigger: eventfd ctx for signaling userspace to return device * @io_work: work for deferral process of I/O handling * @crw_work: work for deferral process of CRW handling + * @notoper_work: work for deferred processing in not-operational state */ struct vfio_ccw_private { struct vfio_device vdev; @@ -125,11 +126,13 @@ struct vfio_ccw_private { struct eventfd_ctx *req_trigger; struct work_struct io_work; struct work_struct crw_work; + struct work_struct notoper_work; } __aligned(8); int vfio_ccw_sch_quiesce(struct subchannel *sch); void vfio_ccw_sch_io_todo(struct work_struct *work); void vfio_ccw_crw_todo(struct work_struct *work); +void vfio_ccw_notoper_todo(struct work_struct *work); extern struct mdev_driver vfio_ccw_mdev_driver; From 34f4feff3e90bd09308fad0974e97113b23b812a Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:21 +0200 Subject: [PATCH 21/56] s390/vfio_ccw: Selectively expand io_mutex The io_mutex was defined to serialize the io_regions, but then has also sort of been associated with the I/O themselves because of the close relationship they share. With the handful of races that are possible, the choices are either to: A) expand the scope of io_mutex to close these remaining windows, or B) reduce the scope of io_mutex to just io_region, and introduce a new lock mechanism for the remaining I/O resources This patch implements A, since B brings with it a lot more interactions that would need to be tracked and kept in a correct hierarchy. It also takes advantage of the workqueue element for cp_free() that now gets called out of fsm_notoper(), which could be invoked out of an interrupt context and thus cannot acquire a mutex itself. Fixes: 4f76617378ee ("vfio-ccw: protect the I/O region") Cc: stable@vger.kernel.org Signed-off-by: Eric Farman Reviewed-by: Matthew Rosato Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_chp.c | 2 +- drivers/s390/cio/vfio_ccw_cp.c | 8 +++++++- drivers/s390/cio/vfio_ccw_drv.c | 6 ++++-- drivers/s390/cio/vfio_ccw_fsm.c | 5 +++++ drivers/s390/cio/vfio_ccw_private.h | 3 ++- 5 files changed, 19 insertions(+), 5 deletions(-) diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c index f3015132d4b5..9269b54f5cfd 100644 --- a/drivers/s390/cio/vfio_ccw_chp.c +++ b/drivers/s390/cio/vfio_ccw_chp.c @@ -98,13 +98,13 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private, if (pos + count > sizeof(*region)) return -EINVAL; + mutex_lock(&private->io_mutex); crw = list_first_entry_or_null(&private->crw, struct vfio_ccw_crw, next); if (crw) list_del(&crw->next); - mutex_lock(&private->io_mutex); if (i >= private->num_regions) { ret = -EINVAL; goto out; diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 5ef082b8289a..58722c4baa25 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -977,17 +977,23 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw) */ bool cp_iova_pinned(struct channel_program *cp, u64 iova, u64 length) { + struct vfio_ccw_private *private = + container_of(cp, struct vfio_ccw_private, cp); struct ccwchain *chain; int i; if (!cp->initialized) return false; + mutex_lock(&private->io_mutex); list_for_each_entry(chain, &cp->ccwchain_list, next) { for (i = 0; i < chain->ch_len; i++) - if (page_array_iova_pinned(&chain->ch_pa[i], iova, length)) + if (page_array_iova_pinned(&chain->ch_pa[i], iova, length)) { + mutex_unlock(&private->io_mutex); return true; + } } + mutex_unlock(&private->io_mutex); return false; } diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index c197ad5ab580..757ff5b2556e 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -91,6 +91,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work) is_final = !(scsw_actl(&irb->scsw) & (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT)); + mutex_lock(&private->io_mutex); if (scsw_is_solicited(&irb->scsw)) { cp_update_scsw(&private->cp, &irb->scsw); if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) { @@ -98,9 +99,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work) cp_is_finished = true; } } - mutex_lock(&private->io_mutex); memcpy(private->io_region->irb_area, irb, sizeof(*irb)); - mutex_unlock(&private->io_mutex); /* * Reset to IDLE only if processing of a channel program @@ -110,6 +109,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work) */ if (cp_is_finished) private->state = VFIO_CCW_STATE_IDLE; + mutex_unlock(&private->io_mutex); if (private->io_trigger) eventfd_signal(private->io_trigger); @@ -131,7 +131,9 @@ void vfio_ccw_notoper_todo(struct work_struct *work) private = container_of(work, struct vfio_ccw_private, notoper_work); + mutex_lock(&private->io_mutex); cp_free(&private->cp); + mutex_unlock(&private->io_mutex); } /* diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c index 4d47a3c7b9a0..5fd94e9d5c61 100644 --- a/drivers/s390/cio/vfio_ccw_fsm.c +++ b/drivers/s390/cio/vfio_ccw_fsm.c @@ -170,6 +170,7 @@ static void fsm_notoper(struct vfio_ccw_private *private, css_sched_sch_todo(sch, SCH_TODO_UNREG); private->state = VFIO_CCW_STATE_NOT_OPER; + /* This routine could be called from IRQ context, so defer */ queue_work(vfio_ccw_work_q, &private->notoper_work); } @@ -409,7 +410,11 @@ static void fsm_close(struct vfio_ccw_private *private, private->state = VFIO_CCW_STATE_STANDBY; spin_unlock_irq(&sch->lock); + + mutex_lock(&private->io_mutex); cp_free(&private->cp); + mutex_unlock(&private->io_mutex); + return; err_unlock: diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index e2256402b089..739121116ab6 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -88,7 +88,8 @@ struct vfio_ccw_parent { * @state: internal state of the device * @completion: synchronization helper of the I/O completion * @io_region: MMIO region to input/output I/O arguments/results - * @io_mutex: protect against concurrent update of I/O regions + * @io_mutex: protect against concurrent update of I/O resources + * and @cp lifecycle * @region: additional regions for other subchannel operations * @cmd_region: MMIO region for asynchronous I/O commands other than START * @schib_region: MMIO region for SCHIB information From 16b0798024c0e9117e395829ddbbe70981c79d9c Mon Sep 17 00:00:00 2001 From: Eric Farman Date: Tue, 28 Jul 2026 05:30:22 +0200 Subject: [PATCH 22/56] s390/vfio_ccw: Implement a crw lock Unlike the channel_program struct, which covers synchronous I/O submissions and asynchronous interrupts, the CRW region relies exclusively on asynchronous events coming from hardware. Implement a lock to manage the list of those payloads, to ensure they are read cohesively. Fixes: 3f02cb2fd9d2 ("vfio-ccw: Wire up the CRW irq and CRW region") Cc: stable@vger.kernel.org Reviewed-by: Matthew Rosato Reviewed-by: Farhan Ali Signed-off-by: Eric Farman Signed-off-by: Christian Borntraeger --- drivers/s390/cio/vfio_ccw_chp.c | 26 ++++++++++++++++---------- drivers/s390/cio/vfio_ccw_drv.c | 6 ++++++ drivers/s390/cio/vfio_ccw_ops.c | 4 ++++ drivers/s390/cio/vfio_ccw_private.h | 4 ++++ 4 files changed, 30 insertions(+), 10 deletions(-) diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c index 9269b54f5cfd..7708eb4d6de0 100644 --- a/drivers/s390/cio/vfio_ccw_chp.c +++ b/drivers/s390/cio/vfio_ccw_chp.c @@ -93,18 +93,13 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private, loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK; struct ccw_crw_region *region; struct vfio_ccw_crw *crw; + unsigned long flags; int ret; if (pos + count > sizeof(*region)) return -EINVAL; mutex_lock(&private->io_mutex); - crw = list_first_entry_or_null(&private->crw, - struct vfio_ccw_crw, next); - - if (crw) - list_del(&crw->next); - if (i >= private->num_regions) { ret = -EINVAL; goto out; @@ -113,6 +108,16 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private, i = array_index_nospec(i, private->num_regions); region = private->region[i].data; + spin_lock_irqsave(&private->crw_lock, flags); + crw = list_first_entry_or_null(&private->crw, + struct vfio_ccw_crw, next); + + if (crw) + list_del(&crw->next); + + /* Drop CRW lock while copying to userspace */ + spin_unlock_irqrestore(&private->crw_lock, flags); + if (crw) memcpy(®ion->crw, &crw->crw, sizeof(region->crw)); @@ -122,15 +127,16 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private, ret = count; region->crw = 0; - -out: - mutex_unlock(&private->io_mutex); - kfree(crw); /* Notify the guest if more CRWs are on our queue */ + spin_lock_irqsave(&private->crw_lock, flags); if (!list_empty(&private->crw) && private->crw_trigger) eventfd_signal(private->crw_trigger); + spin_unlock_irqrestore(&private->crw_lock, flags); + +out: + mutex_unlock(&private->io_mutex); return ret; } diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 757ff5b2556e..ab6b518cc353 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -118,11 +118,14 @@ void vfio_ccw_sch_io_todo(struct work_struct *work) void vfio_ccw_crw_todo(struct work_struct *work) { struct vfio_ccw_private *private; + unsigned long flags; private = container_of(work, struct vfio_ccw_private, crw_work); + spin_lock_irqsave(&private->crw_lock, flags); if (!list_empty(&private->crw) && private->crw_trigger) eventfd_signal(private->crw_trigger); + spin_unlock_irqrestore(&private->crw_lock, flags); } void vfio_ccw_notoper_todo(struct work_struct *work) @@ -286,6 +289,7 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private, unsigned int rsid) { struct vfio_ccw_crw *crw; + unsigned long flags; /* * If unable to allocate a CRW, just drop the event and @@ -303,7 +307,9 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private, crw->crw.erc = erc; crw->crw.rsid = rsid; + spin_lock_irqsave(&private->crw_lock, flags); list_add_tail(&crw->next, &private->crw); + spin_unlock_irqrestore(&private->crw_lock, flags); queue_work(vfio_ccw_work_q, &private->crw_work); } diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index 1df6d649565b..5ce91285c7d5 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -55,6 +55,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev) INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo); INIT_WORK(&private->crw_work, vfio_ccw_crw_todo); INIT_WORK(&private->notoper_work, vfio_ccw_notoper_todo); + spin_lock_init(&private->crw_lock); private->cp.guest_cp = kzalloc_objs(struct ccw1, CCWCHAIN_LEN_MAX); if (!private->cp.guest_cp) @@ -131,6 +132,7 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev) struct vfio_ccw_private *private = container_of(vdev, struct vfio_ccw_private, vdev); struct vfio_ccw_crw *crw, *temp; + unsigned long flags; /* * Ensure these work items are fully drained, so none can @@ -146,10 +148,12 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev) cancel_work_sync(&private->crw_work); flush_work(&private->notoper_work); + spin_lock_irqsave(&private->crw_lock, flags); list_for_each_entry_safe(crw, temp, &private->crw, next) { list_del(&crw->next); kfree(crw); } + spin_unlock_irqrestore(&private->crw_lock, flags); kmem_cache_free(vfio_ccw_crw_region, private->crw_region); kmem_cache_free(vfio_ccw_schib_region, private->schib_region); diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index 739121116ab6..3bd0171d38d0 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -98,6 +98,8 @@ struct vfio_ccw_parent { * @cp: channel program for the current I/O operation * @irb: irb info received from interrupt * @scsw: scsw info + * @crw_lock: serialization of CRW list information + * @crw: list of Channel Report Word elements * @io_trigger: eventfd ctx for signaling userspace I/O results * @crw_trigger: eventfd ctx for signaling userspace CRW information * @req_trigger: eventfd ctx for signaling userspace to return device @@ -120,6 +122,8 @@ struct vfio_ccw_private { struct channel_program cp; struct irb irb; union scsw scsw; + + spinlock_t crw_lock; struct list_head crw; struct eventfd_ctx *io_trigger; From 496e0f706b8ad7831bf7189ff9deb8701d2ebc2b Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:28 +0200 Subject: [PATCH 23/56] KVM: s390: Fix unlikely NULL gmap dereference When creating a new vCPU, kvm_vm_ioctl_create_vcpu() will call kvm_arch_vcpu_postcreate() after the file descriptor for the new vCPU has been created. The new file descriptor has not been returned yet, but a malicious userspace program could try to guess it. If a malicious userspace program manages to start the newly created vCPU before kvm_arch_vcpu_postcreate() is called, __vcpu_run() will try to dereference vcpu->arch.gmap and trigger a NULL pointer dereference. Fix this by adding a new field to struct kvm_vcpu_arch to keep track of the initialization status of the vCPU. Refuse to run a vCPU that is not fully initialized. Fixes: dafd032a15f8 ("KVM: s390: move vcpu specific initalization to a later point") Fixes: e38c884df921 ("KVM: s390: Switch to new gmap") Reviewed-by: Steffen Eiden Reviewed-by: Janosch Frank Reviewed-by: Christian Borntraeger Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-2-imbrenda@linux.ibm.com> --- arch/s390/include/asm/kvm_host.h | 1 + arch/s390/kvm/kvm-s390.c | 11 +++++++++++ 2 files changed, 12 insertions(+) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index c172f9b212d1..b4182ca4435f 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -440,6 +440,7 @@ struct kvm_vcpu_arch { bool skey_enabled; /* Indicator if the access registers have been loaded from guest */ bool acrs_loaded; + bool initialized; struct kvm_s390_pv_vcpu pv; union diag318_info diag318_info; struct kvm_s390_mmu_cache *mc; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 150b5dd2170e..f86b4b0b356f 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3613,6 +3613,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) if (test_kvm_facility(vcpu->kvm, 74) || vcpu->kvm->arch.user_instr0 || vcpu->kvm->arch.user_operexec) vcpu->arch.sie_block->ictl |= ICTL_OPEREXC; + + /* Pairs with smp_load_acquire() in kvm_arch_vcpu_ioctl_run() and kvm_arch_vcpu_ioctl() */ + smp_store_release(&vcpu->arch.initialized, true); } static bool kvm_has_pckmo_subfunc(struct kvm *kvm, unsigned long nr) @@ -5039,6 +5042,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->kvm_dirty_regs & ~KVM_SYNC_S390_VALID_FIELDS) return -EINVAL; + /* Pairs with smp_store_release() in kvm_arch_vcpu_postcreate() */ + if (!smp_load_acquire(&vcpu->arch.initialized)) + return -EINVAL; + vcpu_load(vcpu); if (guestdbg_exit_pending(vcpu)) { @@ -5523,6 +5530,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, long r; u16 rc, rrc; + /* Pairs with smp_store_release() in kvm_arch_vcpu_postcreate() */ + if (!smp_load_acquire(&vcpu->arch.initialized)) + return -EINVAL; + vcpu_load(vcpu); switch (ioctl) { From f8e370058e9e1396fea1a8d11906fa92ec9bad88 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:29 +0200 Subject: [PATCH 24/56] KVM: s390: Do not free SCA if it was not allocated If VM creation fails early in kvm_arch_init_vm(), the cleanup code tries to free up the SCA, even though the address is 0. Due to using free_pages_exact(), only the first page is skipped, accidentally freeing pages 1, 2, and 3. Fix by checking whether the pointer is NULL before attempting to free the SCA in sca_dispose(). Fixes: e72753ed1267 ("KVM: s390: Use ESCA instead of BSCA at VM init") Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-3-imbrenda@linux.ibm.com> Reviewed-by: Christian Borntraeger Reviewed-by: Janosch Frank --- arch/s390/kvm/kvm-s390.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f86b4b0b356f..1b3290a5ad1a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3247,7 +3247,8 @@ static void kvm_s390_crypto_init(struct kvm *kvm) static void sca_dispose(struct kvm *kvm) { - free_pages_exact(kvm->arch.sca, sizeof(*kvm->arch.sca)); + if (kvm->arch.sca) + free_pages_exact(kvm->arch.sca, sizeof(*kvm->arch.sca)); kvm->arch.sca = NULL; } From b050f741fd0d636f2daab72b74aeccea97abdb5f Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:30 +0200 Subject: [PATCH 25/56] KVM: s390: Fix kvm_s390_vcpu_unsetup_cmma() In some cases kvm_s390_vcpu_unsetup_cmma() can be called with a 0 cbrlo; in such cases, if running with V != R, free_page() will attempt to free physical page 0. Fix by freeing cbrlo only if it's non-zero. Fixes: b31605c12f4e ("KVM: s390: make cmma usage conditionally") Fixes: 29b40f105ec8 ("KVM: s390: protvirt: Add initial vm and cpu lifecycle handling") Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-4-imbrenda@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 1b3290a5ad1a..9be27db0a21e 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3678,7 +3678,8 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu) void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu) { - free_page((unsigned long)phys_to_virt(vcpu->arch.sie_block->cbrlo)); + if (vcpu->arch.sie_block->cbrlo) + free_page((unsigned long)phys_to_virt(vcpu->arch.sie_block->cbrlo)); vcpu->arch.sie_block->cbrlo = 0; } From a0496b40a4ab346052aaa59a5163c10224dda01f Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:31 +0200 Subject: [PATCH 26/56] KVM: s390: Fix overclearing ESCA in case of error If an attempt is made to create a vCPU with an already existing ID, the duplicated vCPU will be destroyed. When destroying a vCPU, its ESCA entry will be cleared. In the above scenario, the spurious duplicate vCPU is destroyed, but the ESCA entry corresponding to the original vCPU is cleared. Fix by skipping clearing the ESCA entry if the vCPU creation was not successful, i.e. if the vcpu->arch.initialized is still zero. Reviewed-by: Janosch Frank Signed-off-by: Claudio Imbrenda Fixes: abf4a71ed95f ("KVM: s390: Unlink vcpu on destroy - v2") [ Added Fixes tag while picking -- Claudio ] Message-ID: <20260803124040.126471-5-imbrenda@linux.ibm.com> --- arch/s390/kvm/interrupt.c | 2 +- arch/s390/kvm/kvm-s390.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 7514d9e2403c..bb4e72466043 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -86,7 +86,7 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl; - if (!kvm_s390_use_sca_entries()) + if (!kvm_s390_use_sca_entries() || !vcpu->arch.initialized) return; kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 9be27db0a21e..5b2727d7dfd1 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3462,7 +3462,7 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu) { struct esca_block *sca = vcpu->kvm->arch.sca; - if (!kvm_s390_use_sca_entries()) + if (!kvm_s390_use_sca_entries() || !vcpu->arch.initialized) return; clear_bit_inv(vcpu->vcpu_id, (unsigned long *)sca->mcn); From d301ade41831e746783bdb697fae3afba47841ba Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:32 +0200 Subject: [PATCH 27/56] KVM: s390: ucontrol: Fix sca_clear_ext_call() When cleaning up a UCONTROL VM, sca_clear_ext_call() will touch memory outside of the allocated ESCA block, and UCONTROL VMs don't even use ESCA. Fix by not touching ESCA for UCONTROL VMs, and fence the KVM_S390_INTERRUPT ioctl altogether. Add extra checks in sca_ext_call_pending() and sca_inject_ext_call() to make sure UCONTROL VMs won't touch ESCA. Fencing does not cause regressions with userspace, since UCONTROL VMs never used KVM_S390_INTERRUPT ioctls. Fixes: 7d43bafcff17 ("KVM: s390: Make provisions for ESCA utilization") Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-6-imbrenda@linux.ibm.com> --- arch/s390/kvm/interrupt.c | 19 ++++++++++++++----- arch/s390/kvm/kvm-s390.c | 5 +++++ 2 files changed, 19 insertions(+), 5 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index bb4e72466043..8f24bcd1a6d3 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -45,13 +45,16 @@ static struct kvm_s390_gib *gib; static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id) { struct esca_block *sca = vcpu->kvm->arch.sca; - union esca_sigp_ctrl sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl; + union esca_sigp_ctrl sigp_ctrl; if (!kvm_s390_test_cpuflags(vcpu, CPUSTAT_ECALL_PEND)) return 0; + if (kvm_is_ucontrol(vcpu->kvm)) + return 0; BUG_ON(!kvm_s390_use_sca_entries()); + sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl; if (src_id) *src_id = sigp_ctrl.scn; @@ -60,13 +63,16 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id) static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) { - struct esca_block *sca = vcpu->kvm->arch.sca; - union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl; union esca_sigp_ctrl old_val, new_val = {.scn = src_id, .c = 1}; + struct esca_block *sca = vcpu->kvm->arch.sca; + union esca_sigp_ctrl *sigp_ctrl; int expect, rc; BUG_ON(!kvm_s390_use_sca_entries()); + if (kvm_is_ucontrol(vcpu->kvm)) + return -EINVAL; + sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl; old_val = READ_ONCE(*sigp_ctrl); old_val.c = 0; @@ -84,10 +90,13 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) static void sca_clear_ext_call(struct kvm_vcpu *vcpu) { struct esca_block *sca = vcpu->kvm->arch.sca; - union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl; + union esca_sigp_ctrl *sigp_ctrl; - if (!kvm_s390_use_sca_entries() || !vcpu->arch.initialized) + if (!kvm_s390_use_sca_entries() || !vcpu->arch.initialized || kvm_is_ucontrol(vcpu->kvm)) return; + + /* Initialize after the above check, to prevent going out of bounds */ + sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl; kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND); WRITE_ONCE(sigp_ctrl->value, 0); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5b2727d7dfd1..21574f57be72 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2934,6 +2934,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; + r = -EINVAL; + if (kvm_is_ucontrol(kvm)) + break; r = -EFAULT; if (copy_from_user(&s390int, argp, sizeof(s390int))) break; @@ -5456,6 +5459,8 @@ long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, struct kvm_s390_interrupt s390int; struct kvm_s390_irq s390irq = {}; + if (kvm_is_ucontrol(vcpu->kvm)) + return -EINVAL; if (copy_from_user(&s390int, argp, sizeof(s390int))) return -EFAULT; if (s390int_to_s390irq(&s390int, &s390irq)) From d699986f11bf854bddecd6b1bfdf53e05ef945d6 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:33 +0200 Subject: [PATCH 28/56] KVM: s390: Fix leaking of PGM_ADDRESSING to userspace If kvm_s390_set_cmma_bits() is asked to set CMMA values outside of a memslot, PGM_ADDRESSING (5) is returned, instead of a negative error value. Same issue with kvm_s390_{g,s}et_skeys(), kvm_s390_keyop(), and dat_reset_reference_bit(). Fix by returning -EFAULT whenever the return value would be > 0, which is consistent with the behaviour before the gmap rewrite. Fixes: e38c884df921 ("KVM: s390: Switch to new gmap") Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-7-imbrenda@linux.ibm.com> --- arch/s390/kvm/dat.c | 16 ++++++++++------ arch/s390/kvm/dat.h | 2 +- arch/s390/kvm/kvm-s390.c | 16 ++++++++-------- arch/s390/kvm/priv.c | 5 +++-- 4 files changed, 22 insertions(+), 17 deletions(-) diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index ed4259d17629..171b61959908 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -755,13 +755,15 @@ int dat_cond_set_storage_key(struct kvm_s390_mmu_cache *mmc, union asce asce, gf return rc; } -int dat_reset_reference_bit(union asce asce, gfn_t gfn) +int dat_reset_reference_bit(union asce asce, gfn_t gfn, union skey *skey) { union pgste pgste, old; union crste *crstep; union pte *ptep; int rc; + skey->skey = 0; + rc = dat_entry_walk(NULL, gfn, asce, DAT_WALK_ANY, TABLE_TYPE_PAGE_TABLE, &crstep, &ptep); if (rc) return rc; @@ -771,21 +773,23 @@ int dat_reset_reference_bit(union asce asce, gfn_t gfn) if (!crste.h.fc || !crste.s.fc1.pr) return 0; - return page_reset_referenced(large_crste_to_phys(*crstep, gfn)); + skey->skey = page_reset_referenced(large_crste_to_phys(*crstep, gfn)) << 1; + return 0; } old = pgste_get_lock(ptep); pgste = old; if (!ptep->h.i) { - rc = page_reset_referenced(pte_origin(*ptep)); - pgste.hr = rc >> 1; + skey->skey = page_reset_referenced(pte_origin(*ptep)) << 1; + pgste.hr = skey->r; } - rc |= (pgste.gr << 1) | pgste.gc; + skey->r |= pgste.gr; + skey->c |= pgste.gc; pgste.gr = 0; dat_update_ptep_sd(old, pgste, ptep); pgste_set_unlock(ptep, pgste); - return rc; + return 0; } static long dat_reset_skeys_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_walk *walk) diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h index fad605305e05..141ee7b9f019 100644 --- a/arch/s390/kvm/dat.h +++ b/arch/s390/kvm/dat.h @@ -537,7 +537,7 @@ int dat_set_storage_key(struct kvm_s390_mmu_cache *mc, union asce asce, gfn_t gf union skey skey, bool nq); int dat_cond_set_storage_key(struct kvm_s390_mmu_cache *mmc, union asce asce, gfn_t gfn, union skey skey, union skey *oldkey, bool nq, bool mr, bool mc); -int dat_reset_reference_bit(union asce asce, gfn_t gfn); +int dat_reset_reference_bit(union asce asce, gfn_t gfn, union skey *skey); long dat_reset_skeys(union asce asce, gfn_t start); unsigned long dat_get_ptval(struct page_table *table, struct ptval_param param); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 21574f57be72..e162efaa35b8 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -571,7 +571,7 @@ static int kvm_s390_keyop(struct kvm_s390_mmu_cache *mc, struct kvm *kvm, int op switch (op) { case KVM_S390_KEYOP_SSKE: r = dat_cond_set_storage_key(mc, asce, gfn, skey, &skey, 0, 0, 0); - if (r >= 0) + if (r == 0 || r == 1) return skey.skey; break; case KVM_S390_KEYOP_ISKE: @@ -580,14 +580,14 @@ static int kvm_s390_keyop(struct kvm_s390_mmu_cache *mc, struct kvm *kvm, int op return skey.skey; break; case KVM_S390_KEYOP_RRBE: - r = dat_reset_reference_bit(asce, gfn); - if (r > 0) - return r << 1; + r = dat_reset_reference_bit(asce, gfn, &skey); + if (!r) + return skey.skey; break; default: return -EINVAL; } - return r; + return r > 0 ? -EFAULT : r; } /* Section: device related */ @@ -2214,7 +2214,7 @@ static int kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) } kvfree(keys); - return r; + return r <= 0 ? r : -EFAULT; } static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) @@ -2276,7 +2276,7 @@ static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) kvm_s390_free_mmu_cache(mc); out: kvfree(keys); - return r; + return r <= 0 ? r : -EFAULT; } /* @@ -2386,7 +2386,7 @@ static int kvm_s390_set_cmma_bits(struct kvm *kvm, set_bit(GMAP_FLAG_USES_CMM, &kvm->arch.gmap->flags); - return r; + return r <= 0 ? r : -EFAULT; } /** diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index ad0ddc433a73..ea5a99537346 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -289,6 +289,7 @@ static int handle_iske(struct kvm_vcpu *vcpu) static int handle_rrbe(struct kvm_vcpu *vcpu) { unsigned long gaddr; + union skey skey; int reg1, reg2; int rc; @@ -307,12 +308,12 @@ static int handle_rrbe(struct kvm_vcpu *vcpu) gaddr = kvm_s390_logical_to_effective(vcpu, gaddr); gaddr = kvm_s390_real_to_abs(vcpu, gaddr); scoped_guard(read_lock, &vcpu->kvm->mmu_lock) - rc = dat_reset_reference_bit(vcpu->arch.gmap->asce, gpa_to_gfn(gaddr)); + rc = dat_reset_reference_bit(vcpu->arch.gmap->asce, gpa_to_gfn(gaddr), &skey); if (rc > 0) return kvm_s390_inject_program_int(vcpu, rc); if (rc < 0) return rc; - kvm_s390_set_psw_cc(vcpu, rc); + kvm_s390_set_psw_cc(vcpu, (skey.skey >> 1) & 3); return 0; } From 4db7207052874f13dec1e9be384cca279c6693e8 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:34 +0200 Subject: [PATCH 29/56] KVM: s390: Fix race in __do_essa() An unlikely race between __do_essa() and kvm_s390_vm_start_migration(), kvm_s390_vm_stop_migration(), or dat_get_cmma() was possible. Fix by locking kvm->slots_arch_lock. Since this is not a hot path, the overhead of an additional mutex is negligible. Fixes: e38c884df921 ("KVM: s390: Switch to new gmap") Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-8-imbrenda@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 20 ++++++++++---------- arch/s390/kvm/priv.c | 5 +++-- 2 files changed, 13 insertions(+), 12 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index e162efaa35b8..e5c5e9f61cb2 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1219,8 +1219,8 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) /* * Must be called with kvm->srcu held to avoid races on memslots, and with - * kvm->slots_lock to avoid races with ourselves, kvm_s390_vm_stop_migration(), - * and kvm_s390_get_cmma_bits(). + * kvm->slots_arch_lock to avoid races with ourselves, + * kvm_s390_vm_stop_migration(), and kvm_s390_get_cmma_bits(). */ static int kvm_s390_vm_start_migration(struct kvm *kvm) { @@ -1265,7 +1265,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) } /* - * Must be called with kvm->slots_lock to avoid races with ourselves, + * Must be called with kvm->slots_arch_lock to avoid races with ourselves, * kvm_s390_vm_start_migration() and kvm_s390_get_cmma_bits(). */ static int kvm_s390_vm_stop_migration(struct kvm *kvm) @@ -1300,7 +1300,9 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm, { int res = -ENXIO; - mutex_lock(&kvm->slots_lock); + guard(srcu)(&kvm->srcu); + guard(mutex)(&kvm->slots_arch_lock); + switch (attr->attr) { case KVM_S390_VM_MIGRATION_START: res = kvm_s390_vm_start_migration(kvm); @@ -1311,7 +1313,6 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm, default: break; } - mutex_unlock(&kvm->slots_lock); return res; } @@ -3001,9 +3002,8 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) r = -EFAULT; if (copy_from_user(&args, argp, sizeof(args))) break; - mutex_lock(&kvm->slots_lock); - r = kvm_s390_get_cmma_bits(kvm, &args); - mutex_unlock(&kvm->slots_lock); + scoped_guard(mutex, &kvm->slots_arch_lock) + r = kvm_s390_get_cmma_bits(kvm, &args); if (!r) { r = copy_to_user(argp, &args, sizeof(args)); if (r) @@ -3017,9 +3017,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) r = -EFAULT; if (copy_from_user(&args, argp, sizeof(args))) break; - mutex_lock(&kvm->slots_lock); + mutex_lock(&kvm->slots_arch_lock); r = kvm_s390_set_cmma_bits(kvm, &args); - mutex_unlock(&kvm->slots_lock); + mutex_unlock(&kvm->slots_arch_lock); break; } case KVM_S390_PV_COMMAND: { diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index ea5a99537346..b1ba24c346ef 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -1261,8 +1261,9 @@ static int handle_essa(struct kvm_vcpu *vcpu) /* Retry the ESSA instruction */ kvm_s390_retry_instr(vcpu); } else { - scoped_guard(read_lock, &vcpu->kvm->mmu_lock) - i = __do_essa(vcpu, orc); + scoped_guard(mutex, &vcpu->kvm->slots_arch_lock) + scoped_guard(read_lock, &vcpu->kvm->mmu_lock) + i = __do_essa(vcpu, orc); if (i < 0) return i; /* Account for the possible extra cbrl entry */ From ec215346270512db60478e45e8dff2de950225aa Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:35 +0200 Subject: [PATCH 30/56] KVM: s390: cmma: Fix dirty tracking when removing memslot When a memslot is removed, all ptes that mapped the slot are cleared or even deallocated. If this happens while the system is in migration mode, and if cmma-dirty pages are removed, the cmma-dirty counter will not reflect reality. Fix by appropriately decrementing the cmma-dirty counter when removing a memslot. Opportunistically improve kvm_arch_commit_memory_region() to use __free() for the struct kvm_s390_mmu_cache. Fixes: e38c884df921 ("KVM: s390: Switch to new gmap") Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-9-imbrenda@linux.ibm.com> --- arch/s390/kvm/dat.c | 7 ++++++- arch/s390/kvm/kvm-s390.c | 25 +++++++++++++++++++++++-- 2 files changed, 29 insertions(+), 3 deletions(-) diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index 171b61959908..3f2d6e8902d7 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -850,6 +850,7 @@ static long _dat_slot_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_wal struct slot_priv *p = walk->priv; union crste dummy = { .val = p->token }; union pte new_pte, pte = READ_ONCE(*ptep); + union pgste pgste; new_pte = _PTE_TOK(dummy.tok.type, dummy.tok.par); @@ -857,7 +858,11 @@ static long _dat_slot_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_wal if (pte.val == new_pte.val) return 0; - dat_ptep_xchg(ptep, new_pte, gfn, walk->asce, false); + pgste = pgste_get_lock(ptep); + pgste = __dat_ptep_xchg(ptep, pgste, new_pte, gfn, walk->asce, false); + pgste.cmma_d = 0; + pgste_set_unlock(ptep, pgste); + return 0; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index e5c5e9f61cb2..ba811f0673d1 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -5812,14 +5812,30 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, return 0; } +static long cmma_d_count_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_walk *walk) +{ + union pgste pgste; + + pgste = pgste_get_lock(ptep); + if (pgste.cmma_d) { + pgste.cmma_d = 0; + atomic64_dec(walk->priv); + } + pgste_set_unlock(ptep, pgste); + return 0; +} + void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - struct kvm_s390_mmu_cache *mc = NULL; + const struct dat_walk_ops ops = { .pte_entry = cmma_d_count_pte, }; + struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL; int rc = 0; + guard(mutex)(&kvm->slots_arch_lock); + if (change == KVM_MR_FLAGS_ONLY) return; @@ -5830,6 +5846,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, } scoped_guard(write_lock, &kvm->mmu_lock) { + if (kvm->arch.migration_mode && kvm->arch.use_cmma && old) { + _dat_walk_gfn_range(old->base_gfn, old->base_gfn + old->npages, + kvm->arch.gmap->asce, &ops, DAT_WALK_IGN_HOLES, + &kvm->arch.cmma_dirty_pages); + } + switch (change) { case KVM_MR_DELETE: rc = dat_delete_slot(mc, kvm->arch.gmap->asce, old->base_gfn, old->npages); @@ -5851,7 +5873,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, out: if (rc) pr_warn("failed to commit memory region\n"); - kvm_s390_free_mmu_cache(mc); return; } From dab62d218754e00a22aff45d2b0116c5ee30cbd2 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:36 +0200 Subject: [PATCH 31/56] KVM: s390: ucontrol: Add missing locking around gmap_remove_child() gmap_remove_child() needs to be called while holding the children_lock of the parent gmap. This was not the case in the error handling path of kvm_arch_vcpu_create() for UCONTROL guests. Fix by adding the missing lock. Fixes: e38c884df921 ("KVM: s390: Switch to new gmap") Reviewed-by: Steffen Eiden Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-10-imbrenda@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ba811f0673d1..2741ca323ede 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3875,7 +3875,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) out_ucontrol_uninit: if (kvm_is_ucontrol(vcpu->kvm)) { + spin_lock(&vcpu->kvm->arch.gmap->children_lock); gmap_remove_child(vcpu->arch.gmap); + spin_unlock(&vcpu->kvm->arch.gmap->children_lock); vcpu->arch.gmap = gmap_put(vcpu->arch.gmap); } out_free_sie_block: From e4d678900a1ae66112812fe4d2aff16044ca37f2 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:37 +0200 Subject: [PATCH 32/56] KVM: s390: Free the mmu cache when kvm_arch_vcpu_create() fails The mmu cache is the first thing that is allocated in kvm_arch_vcpu_create(), but in case of failure it was not freed. Fix by freeing the mmu cache in case of failure. Refactor kvm_arch_vcpu_create() to use scope-based cleanup instead of gotos. Fixes: e38c884df921 ("KVM: s390: Switch to new gmap") Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-11-imbrenda@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 40 ++++++++++++++++++---------------------- 1 file changed, 18 insertions(+), 22 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 2741ca323ede..9b8a35e7dc82 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3800,21 +3800,21 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) return 0; } +DEFINE_FREE(sie_page, struct sie_page *, if (_T) free_page((unsigned long)(_T))) + int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { - struct sie_page *sie_page; + struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL; + struct sie_page *sie_page __free(sie_page) = NULL; int rc; BUILD_BUG_ON(sizeof(struct sie_page) != 4096); - vcpu->arch.mc = kvm_s390_new_mmu_cache(); - if (!vcpu->arch.mc) + mc = kvm_s390_new_mmu_cache(); + if (!mc) return -ENOMEM; sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL_ACCOUNT); - if (!sie_page) { - kvm_s390_free_mmu_cache(vcpu->arch.mc); - vcpu->arch.mc = NULL; + if (!sie_page) return -ENOMEM; - } vcpu->arch.sie_block = &sie_page->sie_block; vcpu->arch.sie_block->itdba = virt_to_phys(&sie_page->itdb); @@ -3856,10 +3856,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; if (kvm_is_ucontrol(vcpu->kvm)) { - rc = -ENOMEM; vcpu->arch.gmap = gmap_new_child(vcpu->kvm->arch.gmap, -1UL); if (!vcpu->arch.gmap) - goto out_free_sie_block; + return -ENOMEM; } VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%p, sie block at 0x%p", @@ -3867,22 +3866,19 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block); rc = kvm_s390_vcpu_setup(vcpu); - if (rc) - goto out_ucontrol_uninit; + if (rc) { + if (kvm_is_ucontrol(vcpu->kvm)) { + scoped_guard(spinlock, &vcpu->kvm->arch.gmap->children_lock) + gmap_remove_child(vcpu->arch.gmap); + vcpu->arch.gmap = gmap_put(vcpu->arch.gmap); + } + return rc; + } + vcpu->arch.mc = no_free_ptr(mc); + sie_page = NULL; kvm_s390_update_topology_change_report(vcpu->kvm, 1); return 0; - -out_ucontrol_uninit: - if (kvm_is_ucontrol(vcpu->kvm)) { - spin_lock(&vcpu->kvm->arch.gmap->children_lock); - gmap_remove_child(vcpu->arch.gmap); - spin_unlock(&vcpu->kvm->arch.gmap->children_lock); - vcpu->arch.gmap = gmap_put(vcpu->arch.gmap); - } -out_free_sie_block: - free_page((unsigned long)(vcpu->arch.sie_block)); - return rc; } int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) From 216c5289dd66d9cde6b42cbe68ee8dec5669678a Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:38 +0200 Subject: [PATCH 33/56] KVM: s390: Return -EINTR if a signal is pending while faulting-in If a fatal signal is pending while trying to fault-in a page, return -EINTR instead of -EAGAIN. Also fix unpack_one() to handle -EINTR properly. Fixes: e907ae530133 ("KVM: s390: Add helper functions for fault handling") Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-12-imbrenda@linux.ibm.com> --- arch/s390/kvm/faultin.c | 6 +++--- arch/s390/kvm/pv.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/s390/kvm/faultin.c b/arch/s390/kvm/faultin.c index fee80047bd94..3cc45f7f5b2d 100644 --- a/arch/s390/kvm/faultin.c +++ b/arch/s390/kvm/faultin.c @@ -91,9 +91,9 @@ int kvm_s390_faultin_gfn(struct kvm_vcpu *vcpu, struct kvm *kvm, struct guest_fa /* Access outside memory, addressing exception. */ if (is_noslot_pfn(f->pfn)) return PGM_ADDRESSING; - /* Signal pending: try again. */ - if (f->pfn == KVM_PFN_ERR_SIGPENDING) - return -EAGAIN; + /* Fatal signal pending: bail out. */ + if (is_sigpending_pfn(f->pfn)) + return -EINTR; /* Check if it's read-only memory; don't try to actually handle that case. */ if (f->pfn == KVM_PFN_ERR_RO_FAULT) return -EOPNOTSUPP; diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 1beacc841ca8..dc204b521052 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -809,7 +809,7 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak, return -EAGAIN; } - if (ret && ret != -EAGAIN) + if (ret && ret != -EAGAIN && ret != -EINTR) KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x", uvcb.gaddr, *rc, *rrc); return ret; From 9187a9186d0ac7b260b07917aabc672a80d37c3c Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:39 +0200 Subject: [PATCH 34/56] KVM: s390: Fix ordering when adding to SCA When adding a new vCPU to the SCA area, the validity bit in the MCN was set before the pointer to the state description, potentially allowing for a race. Fix by setting the pointer before setting the bit. Fixes: 14542a0a54c5 ("KVM: S390: Remove sca_lock") Reviewed-by: Steffen Eiden Reviewed-by: Janosch Frank Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-13-imbrenda@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 9b8a35e7dc82..518a69c55e85 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3485,8 +3485,8 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu) if (!kvm_s390_use_sca_entries()) return; + WRITE_ONCE(sca->cpu[vcpu->vcpu_id].sda, virt_to_phys(vcpu->arch.sie_block)); set_bit_inv(vcpu->vcpu_id, (unsigned long *)sca->mcn); - sca->cpu[vcpu->vcpu_id].sda = virt_to_phys(vcpu->arch.sie_block); } static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id) From feadc5e84dcb53422a437556c35af9efd9826fd5 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Mon, 3 Aug 2026 14:40:40 +0200 Subject: [PATCH 35/56] KVM: s390: Fix cleanup in kvm_s390_pv_create_cpu() If creating a protected vCPU in kvm_s390_pv_create_cpu() fails, kvm_s390_pv_destroy_cpu() was called, which checks whether the vCPU has a PV handle and exits doing nothing otherwise. At that point, due to not having created the protected vCPU, the PV handle will not be set, and kvm_s390_pv_destroy_cpu() will do nothing, thus leaking the allocated memory. Fix by factoring out the code to free and reset a PV vCPU; call it from kvm_s390_pv_destroy_cpu() and kvm_s390_pv_create_cpu(). Opportunistically fix the return value of kvm_s390_pv_destroy_cpu() in case of errors: return -EIO instead if EIO. Fixes: d4074324b07a ("KVM: s390: pv: avoid double free of sida page") Reviewed-by: Steffen Eiden Reviewed-by: Janosch Frank Signed-off-by: Claudio Imbrenda Message-ID: <20260803124040.126471-14-imbrenda@linux.ibm.com> --- arch/s390/kvm/pv.c | 41 +++++++++++++++++++++-------------------- 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index dc204b521052..b02e0159d3cd 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -244,6 +244,24 @@ static void kvm_s390_clear_pv_state(struct kvm *kvm) kvm->arch.pv.stor_var = NULL; } +static void kvm_s390_pv_dispose_cpu(struct kvm_vcpu *vcpu, bool free_stor_base) +{ + if (free_stor_base) + free_pages(vcpu->arch.pv.stor_base, get_order(uv_info.guest_cpu_stor_len)); + free_page((unsigned long)sida_addr(vcpu->arch.sie_block)); + vcpu->arch.sie_block->pv_handle_cpu = 0; + vcpu->arch.sie_block->pv_handle_config = 0; + memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv)); + vcpu->arch.sie_block->sdf = 0; + /* + * The sidad field (for sdf == 2) is now the gbea field (for sdf == 0). + * Use the reset value of gbea to avoid leaking the kernel pointer of + * the just freed sida. + */ + vcpu->arch.sie_block->gbea = 1; + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); +} + int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) { int cc; @@ -258,24 +276,9 @@ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", *rc, *rrc); /* Intended memory leak for something that should never happen. */ - if (!cc) - free_pages(vcpu->arch.pv.stor_base, - get_order(uv_info.guest_cpu_stor_len)); + kvm_s390_pv_dispose_cpu(vcpu, !cc); - free_page((unsigned long)sida_addr(vcpu->arch.sie_block)); - vcpu->arch.sie_block->pv_handle_cpu = 0; - vcpu->arch.sie_block->pv_handle_config = 0; - memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv)); - vcpu->arch.sie_block->sdf = 0; - /* - * The sidad field (for sdf == 2) is now the gbea field (for sdf == 0). - * Use the reset value of gbea to avoid leaking the kernel pointer of - * the just freed sida. - */ - vcpu->arch.sie_block->gbea = 1; - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - - return cc ? EIO : 0; + return cc ? -EIO : 0; } int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) @@ -319,9 +322,7 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) uvcb.header.rrc); if (cc) { - u16 dummy; - - kvm_s390_pv_destroy_cpu(vcpu, &dummy, &dummy); + kvm_s390_pv_dispose_cpu(vcpu, true); return -EIO; } From b98014e98e0842b498506d9b3060bf1707ed0739 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 5 Aug 2026 13:04:48 +0200 Subject: [PATCH 36/56] KVM: s390: Remove user triggerable WARN_ON pin_map_page() fails legitimately whenever the userspace mapping behind the adapter route has gone away, e.g. when the VMM unmaps that memory. As this can happen without a kernel programming error, remove the WARN_ON. Fixes: 1e95e3bc6b05 ("KVM: s390: Enable adapter_indicators_set to use mapped pages") Cc: Douglas Freimuth Cc: Matthew Rosato Signed-off-by: Christian Borntraeger Reviewed-by: Matthew Rosato Reviewed-by: Douglas Freimuth Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260805110455.7200-2-borntraeger@linux.ibm.com> --- arch/s390/kvm/interrupt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 8f24bcd1a6d3..23f0e0821474 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3013,7 +3013,7 @@ static int adapter_indicators_set(struct kvm *kvm, if (!summary_info) { spin_unlock_irqrestore(&adapter->maps_lock, flags); summary_page = pin_map_page(kvm, adapter_int->summary_addr, 0); - if (WARN_ON_ONCE(!summary_page)) + if (!summary_page) return -1; idx = srcu_read_lock(&kvm->srcu); map = page_address(summary_page); From 4e2c7f7cbc27418f9a290399b986c1b85ff93b90 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 5 Aug 2026 13:04:49 +0200 Subject: [PATCH 37/56] KVM: s390: Zero initialize data structures for inject_pfault_token __kvm_inject_pfault_token() only sets .type and .u.ext.ext_params2 of the on-stack struct kvm_s390_irq but the full ext substructure is copied into the cpu local variable on inject. ext_params and pad contain stale stack values. Interrupt delivery only uses ext_params2, so nothing leaks to the guest, but a host user can use the migration ioctls to get to the data. Fix by zero-initializing the irq struct. Do the same for the inti data structure. Fixes: 383d0b050106 ("KVM: s390: handle pending local interrupts via bitmap") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Matthew Rosato Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260805110455.7200-3-borntraeger@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 518a69c55e85..611dcb534210 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4474,8 +4474,8 @@ int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clo static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token, unsigned long token) { - struct kvm_s390_interrupt inti; - struct kvm_s390_irq irq; + struct kvm_s390_interrupt inti = {}; + struct kvm_s390_irq irq = {}; struct kvm_s390_interrupt_info *inti_mem = NULL; int ret = 0; From b239410c7653ff6781d4cf1d63cfc52a1bb71788 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 5 Aug 2026 13:04:50 +0200 Subject: [PATCH 38/56] KVM: s390: Zero initialize irq in reinject_machine_check kvm_s390_reinject_machine_check() fills cr14, mcic, ext_damage_code and failing_storage_address of the on-stack struct kvm_s390_irq, but struct kvm_s390_mchk_info also has a pad word and a 16 byte fixed_logout array. struct mcck_volatile_info carries no logout data, so there is nothing to copy there and both stay whatever was on the stack. __inject_mchk() then memcpy()s fixed_logout into the vcpu local interrupt state unconditionally. This will reach the guest during deliver and userspace during migration. Reflecting zeroes is the correct behaviour here, as KVM has no logout data for a reinjected machine check. This needs a host machine check while the cpu is in SIE so not trivial to trigger. Fixes: 4d62fcc0b692 ("KVM: s390: Inject machine check into the guest") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Matthew Rosato Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260805110455.7200-4-borntraeger@linux.ibm.com> --- arch/s390/kvm/interrupt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 23f0e0821474..009d6a845d59 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3109,7 +3109,7 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu, struct mcck_volatile_info *mcck_info) { struct kvm_s390_interrupt_info inti; - struct kvm_s390_irq irq; + struct kvm_s390_irq irq = {}; struct kvm_s390_mchk_info *mchk; union mci mci; __u64 cr14 = 0; /* upper bits are not used */ From 121ea1de927c8b9bfdf53c31cad27b86d5de0293 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 5 Aug 2026 13:04:51 +0200 Subject: [PATCH 39/56] KVM: s390: Fix memory leak in guest debug handling bp_data is freed only for the error case by kfree(bp_data). Every successful KVM_SET_GUEST_DEBUG will leak bp_data. Fixes: 27291e2165b6 ("KVM: s390: hardware support for guest debugging") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Matthew Rosato Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260805110455.7200-5-borntraeger@linux.ibm.com> --- arch/s390/kvm/guestdbg.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 69835e1d4f20..4c02dbebb2eb 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -267,6 +267,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, vcpu->arch.guestdbg.hw_bp_info = bp_info; vcpu->arch.guestdbg.nr_hw_wp = nr_wp; vcpu->arch.guestdbg.hw_wp_info = wp_info; + kfree(bp_data); return 0; error: kfree(bp_data); From aa9c8e8baf1e765fa65b93212522c636f25d846f Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 5 Aug 2026 13:04:52 +0200 Subject: [PATCH 40/56] KVM: s390: Fix old_data leak in guest debug error path __import_wp_info() allocates a per-watchpoint old_data buffer to back up the original guest memory contents. If a later watchpoint of the same KVM_SET_GUEST_DEBUG request fails to import, kvm_s390_import_bp_data() jumps to the error label, which frees the wp_info array but not the old_data buffers of the entries that were imported successfully. Up to MAX_BP_COUNT - 1 buffers of up to MAX_WP_SIZE bytes are leaked per failed request, and the request can be repeated. Create error handling for cleaning up all created old_data memory areas. Fixes: 27291e2165b6 ("KVM: s390: hardware support for guest debugging") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Matthew Rosato Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260805110455.7200-6-borntraeger@linux.ibm.com> --- arch/s390/kvm/guestdbg.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 4c02dbebb2eb..f7c94d54efbe 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -252,7 +252,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, ret = __import_wp_info(vcpu, &bp_data[i], &wp_info[nr_wp]); if (ret) - goto error; + goto error_wp; nr_wp++; break; case KVM_HW_BP: @@ -269,6 +269,10 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, vcpu->arch.guestdbg.hw_wp_info = wp_info; kfree(bp_data); return 0; + +error_wp: + while (nr_wp--) + kfree(wp_info[nr_wp].old_data); error: kfree(bp_data); kfree(wp_info); From a4e482def8533ebace517d9f67f1465841b1f982 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 5 Aug 2026 13:04:53 +0200 Subject: [PATCH 41/56] KVM: s390: Take srcu when importing watchpoint data __import_wp_info() backs up the original guest memory contents of a watchpoint with read_guest_abs(), which is kvm_read_guest() and therefore resolves the memslot via __kvm_memslots(). That requires kvm->srcu (or kvm->slots_lock) to be held, otherwise a concurrent memslot update can free the memslots array under us once its SRCU grace period has elapsed. As this is not fast path, following lock ordering (mutex first, then srcu) take the big hammer and hold the srcu for the full import. Fixes: 27291e2165b6 ("KVM: s390: hardware support for guest debugging") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260805110455.7200-7-borntraeger@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 611dcb534210..0a197e055cad 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4248,8 +4248,10 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, /* enforce guest PER */ kvm_s390_set_cpuflags(vcpu, CPUSTAT_P); - if (dbg->control & KVM_GUESTDBG_USE_HW_BP) - rc = kvm_s390_import_bp_data(vcpu, dbg); + if (dbg->control & KVM_GUESTDBG_USE_HW_BP) { + scoped_guard(srcu, &vcpu->kvm->srcu) + rc = kvm_s390_import_bp_data(vcpu, dbg); + } } else { kvm_s390_clear_cpuflags(vcpu, CPUSTAT_P); vcpu->arch.guestdbg.last_bp = 0; From e7f698b09d4a7c36b299acf680fc50fe868e2bcd Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 5 Aug 2026 13:04:54 +0200 Subject: [PATCH 42/56] KVM: s390: Free guest debug data on vcpu destroy kvm_s390_clear_bp_data() is only called from kvm_arch_vcpu_ioctl_set_guest_debug(), i.e. when user space changes or disables debugging. A vCPU that is destroyed while hardware breakpoints are still armed - the normal case when the VMM just exits or crashes - leaks hw_bp_info, hw_wp_info and all old_data buffers, since generic KVM frees the vCPU right after kvm_arch_vcpu_destroy(). That is bounded by MAX_BP_COUNT entries, so roughly 8 KiB per vCPU, but it is unbounded over VM lifetimes. The allocations are GFP_KERNEL_ACCOUNT, so the charge also outlives the exiting process and pins dying memcgs. Fix by clearing the debug data on vCPU destruction. Calling it unconditionally is fine: struct kvm_vcpu is zero allocated, so for a vCPU that never enabled debugging the counters are 0 and the pointers NULL. Fixes: 27291e2165b6 ("KVM: s390: hardware support for guest debugging") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Matthew Rosato Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260805110455.7200-8-borntraeger@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 0a197e055cad..095c9ba0aa5c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3410,6 +3410,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id); kvm_s390_clear_local_irqs(vcpu); kvm_clear_async_pf_completion_queue(vcpu); + kvm_s390_clear_bp_data(vcpu); if (!kvm_is_ucontrol(vcpu->kvm)) sca_del_vcpu(vcpu); kvm_s390_update_topology_change_report(vcpu->kvm, 1); From 4c07680a467e2f7697245bcd11691bffb2a6f0ed Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 5 Aug 2026 13:04:55 +0200 Subject: [PATCH 43/56] KVM: s390: Fix length check __import_wp_info() struct kvm_hw_breakpoint::len is a __u64 that is fully controlled by user space. This is then assigned to wp_info->len, which is an int. The bounds check is done on the truncated value while the allocation uses the untruncated one: wp_info->len = bp_data->len; [...] if (wp_info->len < 0 || wp_info->len > MAX_WP_SIZE) return -EINVAL; wp_info->old_data = kmalloc(bp_data->len, GFP_KERNEL_ACCOUNT); Use the validated value for the allocation as intended. Without this fix userspace can trigger >4GB allocations which will fail and result in a WARN due to MAX_PAGE_ORDER. Fixes: 27291e2165b6 ("KVM: s390: hardware support for guest debugging") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260805110455.7200-9-borntraeger@linux.ibm.com> --- arch/s390/kvm/guestdbg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index f7c94d54efbe..9a6149e310bb 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -184,7 +184,7 @@ static int __import_wp_info(struct kvm_vcpu *vcpu, if (wp_info->len < 0 || wp_info->len > MAX_WP_SIZE) return -EINVAL; - wp_info->old_data = kmalloc(bp_data->len, GFP_KERNEL_ACCOUNT); + wp_info->old_data = kmalloc(wp_info->len, GFP_KERNEL_ACCOUNT); if (!wp_info->old_data) return -ENOMEM; /* try to backup the original value */ From 4400270ec0348d05dc0439d8f0130853ce7f9e20 Mon Sep 17 00:00:00 2001 From: Anthony Krowiak Date: Thu, 6 Aug 2026 13:34:35 -0400 Subject: [PATCH 44/56] s390/vfio-ap: fix stale pqap_hook pointer on error in vfio_ap_mdev_set_kvm() In vfio_ap_mdev_set_kvm(), kvm->arch.crypto.pqap_hook is set to &matrix_mdev->pqap_hook before the update locks are acquired and the mdev list is checked for a conflicting assignment. If another mdev is already attached to the same KVM instance, the function returns -EPERM without restoring the hook pointer, leaving kvm->arch.crypto.pqap_hook pointing at the failing matrix_mdev instead of the mdev that legitimately owns the KVM. Since matrix_mdev->kvm is never set on this error path, vfio_ap_mdev_unset_kvm() will not clean up the hook when matrix_mdev is later closed. If matrix_mdev is subsequently freed, any PQAP instruction executed by the guest will dereference the stale pointer through pqap_hook_rwsem, resulting in a use-after-free. Since kvm->arch.crypto.pqap_hook is only set in the vfio_ap_mdev_set_kvm() function and is cleared in the vfio_ap_mdev_unset_kvm() function, a check for 'kvm->arch.crypto.pqap_hook != NULL' is all that is needed to determine whether it belongs to another mdev. This will alleviate the need to iterate the matrix_dev->mdev_list list to see if the kvm object is assigned to another mdev.This was introduced in v3 to alleviate the need to take the mdevs_lock while iterating the list; however, this did not prevent a potential race condition. The pqap_hook_rwsem(write) is now performed inside get_update_locks_for_kvm(), which is updated to acquire pqap_hook_rwsem(write) between kvm->lock and mdevs_lock. This ordering is consistent with the PQAP intercept path, which acquires pqap_hook_rwsem in read mode while srcu is held under vcpu->mutex, establishing the dependency: kvm->lock -> vcpu->mutex -> srcu -> pqap_hook_rwsem(read). The pqap_hook_rwsem is now released inside the release_update_locks_for_kvm(), which is updated to release pqap_hook_rwsem(write) between mdevs_lock and kvm->lock. Additionally, kvm_put_kvm() in vfio_ap_mdev_unset_kvm() is moved after release_update_locks_for_kvm(). Previously it was called while kvm->lock was held; if it were ever the last reference, kvm_destroy_vm() would run under kvm->lock, which would deadlock. Fixes: 86956e70761b3 ("s390/vfio-ap: replace open coded locks for VFIO_GROUP_NOTIFY_SET_KVM notification") Cc: stable@vger.kernel.org Co-developed-by: Matthew Rosato Signed-off-by: Matthew Rosato Signed-off-by: Anthony Krowiak Acked-by: Christian Borntraeger Signed-off-by: Claudio Imbrenda Message-ID: <20260806173435.105044-1-akrowiak@linux.ibm.com> --- drivers/s390/crypto/vfio_ap_ops.c | 45 ++++++++++++++----------------- 1 file changed, 20 insertions(+), 25 deletions(-) diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 44b3a1dcc1b3..99a0efd999ef 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -48,15 +48,19 @@ static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q); * 1. matrix_dev->guests_lock: required to use the KVM pointer to update a KVM * guest's APCB. * 2. kvm->lock: required to update a guest's APCB - * 3. matrix_dev->mdevs_lock: required to access data stored in a matrix_mdev + * 3. kvm->arch.crypto.pqap_hook_rwsem: required to update pqap_hook and + * serialize against PQAP intercepts + * 4. matrix_dev->mdevs_lock: required to access data stored in a matrix_mdev * - * Note: If @kvm is NULL, the KVM lock will not be taken. + * Note: If @kvm is NULL, the KVM lock and pqap_hook_rwsem will not be taken. */ static inline void get_update_locks_for_kvm(struct kvm *kvm) { mutex_lock(&matrix_dev->guests_lock); - if (kvm) + if (kvm) { mutex_lock(&kvm->lock); + down_write(&kvm->arch.crypto.pqap_hook_rwsem); + } mutex_lock(&matrix_dev->mdevs_lock); } @@ -68,16 +72,19 @@ static inline void get_update_locks_for_kvm(struct kvm *kvm) * * The proper unlocking order is: * 1. matrix_dev->mdevs_lock - * 2. kvm->lock - * 3. matrix_dev->guests_lock + * 2. kvm->arch.crypto.pqap_hook_rwsem + * 3. kvm->lock + * 4. matrix_dev->guests_lock * - * Note: If @kvm is NULL, the KVM lock will not be released. + * Note: If @kvm is NULL, the KVM lock and pqap_hook_rwsem will not be released. */ static inline void release_update_locks_for_kvm(struct kvm *kvm) { mutex_unlock(&matrix_dev->mdevs_lock); - if (kvm) + if (kvm) { + up_write(&kvm->arch.crypto.pqap_hook_rwsem); mutex_unlock(&kvm->lock); + } mutex_unlock(&matrix_dev->guests_lock); } @@ -1821,26 +1828,17 @@ static const struct attribute_group *vfio_ap_mdev_attr_groups[] = { static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, struct kvm *kvm) { - struct ap_matrix_mdev *m; - if (kvm->arch.crypto.crycbd) { - down_write(&kvm->arch.crypto.pqap_hook_rwsem); - kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook; - up_write(&kvm->arch.crypto.pqap_hook_rwsem); - get_update_locks_for_kvm(kvm); - - list_for_each_entry(m, &matrix_dev->mdev_list, node) { - if (m != matrix_mdev && m->kvm == kvm) { - release_update_locks_for_kvm(kvm); - return -EPERM; - } + if (kvm->arch.crypto.pqap_hook) { + release_update_locks_for_kvm(kvm); + return -EPERM; } + kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook; kvm_get_kvm(kvm); matrix_mdev->kvm = kvm; vfio_ap_mdev_update_guest_apcb(matrix_mdev); - release_update_locks_for_kvm(kvm); } @@ -1883,18 +1881,15 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) struct kvm *kvm = matrix_mdev->kvm; if (kvm && kvm->arch.crypto.crycbd) { - down_write(&kvm->arch.crypto.pqap_hook_rwsem); - kvm->arch.crypto.pqap_hook = NULL; - up_write(&kvm->arch.crypto.pqap_hook_rwsem); - get_update_locks_for_kvm(kvm); + kvm->arch.crypto.pqap_hook = NULL; kvm_arch_crypto_clear_masks(kvm); vfio_ap_mdev_reset_queues(matrix_mdev); - kvm_put_kvm(kvm); matrix_mdev->kvm = NULL; release_update_locks_for_kvm(kvm); + kvm_put_kvm(kvm); } } From 546dde823a36d7283dcf46127c2f3d093443860f Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 6 Aug 2026 16:58:35 +0200 Subject: [PATCH 45/56] KVM: s390: Fix memory corruption by not reinjecting CK machine checks Channel-subsystem damage machine checks are for the host channel subsystem. The guest channel subsystem is emulated in the userspace VMM. There is no point in forwarding such machine checks into the guest. This also simplifies the machine check reinjection and avoids kfree of a stack variable as reported by sashiko. There might be still machine checks that have the ck bit set with another bit (like instruction damage), mask out the CK bit in s390_backup_mcck_info(), like the CP and ED bits already are. Fixes: 4d62fcc0b692 ("KVM: s390: Inject machine check into the guest") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Acked-by: Heiko Carstens Acked-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260806145835.31818-1-borntraeger@linux.ibm.com> --- arch/s390/include/asm/nmi.h | 3 +++ arch/s390/kernel/nmi.c | 5 +---- arch/s390/kvm/interrupt.c | 24 ++++++++---------------- 3 files changed, 12 insertions(+), 20 deletions(-) diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h index 6454c1531854..7919b2b9ac9c 100644 --- a/arch/s390/include/asm/nmi.h +++ b/arch/s390/include/asm/nmi.h @@ -22,6 +22,7 @@ #define MCCK_CODE_SYSTEM_DAMAGE BIT(63) #define MCCK_CODE_EXT_DAMAGE BIT(63 - 5) #define MCCK_CODE_CP BIT(63 - 9) +#define MCCK_CODE_CK BIT(63 - 11) #define MCCK_CODE_STG_ERROR BIT(63 - 16) #define MCCK_CODE_STG_KEY_ERROR BIT(63 - 18) #define MCCK_CODE_STG_DEGRAD BIT(63 - 19) @@ -33,6 +34,8 @@ #define MCCK_CODE_FC_VALID BIT(63 - 43) #define MCCK_CODE_CPU_TIMER_VALID BIT(63 - 46) +#define MCCK_CODE_NO_GUEST (MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE | MCCK_CODE_CK) + #ifndef __ASSEMBLER__ union mci { diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index e17a59d4d5a4..17297a8b63d9 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -344,8 +344,7 @@ static void notrace s390_backup_mcck_info(struct pt_regs *regs) sie_page = container_of(sie_block, struct sie_page, sie_block); mcck_backup = &sie_page->mcck_info; - mcck_backup->mcic = get_lowcore()->mcck_interruption_code & - ~(MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE); + mcck_backup->mcic = get_lowcore()->mcck_interruption_code & ~MCCK_CODE_NO_GUEST; mcck_backup->ext_damage_code = get_lowcore()->external_damage_code; mcck_backup->failing_storage_address = get_lowcore()->failing_storage_address; } @@ -357,8 +356,6 @@ NOKPROBE_SYMBOL(s390_backup_mcck_info); #define ED_STP_ISLAND 6 /* External damage STP island check */ #define ED_STP_SYNC 7 /* External damage STP sync check */ -#define MCCK_CODE_NO_GUEST (MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE) - /* * machine check handler. */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 009d6a845d59..0d9fbe75dc66 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3108,9 +3108,7 @@ static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e, void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu, struct mcck_volatile_info *mcck_info) { - struct kvm_s390_interrupt_info inti; struct kvm_s390_irq irq = {}; - struct kvm_s390_mchk_info *mchk; union mci mci; __u64 cr14 = 0; /* upper bits are not used */ int rc; @@ -3129,20 +3127,14 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu, if (mci.w) cr14 |= CR14_WARNING_SUBMASK; - mchk = mci.ck ? &inti.mchk : &irq.u.mchk; - mchk->cr14 = cr14; - mchk->mcic = mcck_info->mcic; - mchk->ext_damage_code = mcck_info->ext_damage_code; - mchk->failing_storage_address = mcck_info->failing_storage_address; - if (mci.ck) { - /* Inject the floating machine check */ - inti.type = KVM_S390_MCHK; - rc = __inject_vm(vcpu->kvm, &inti); - } else { - /* Inject the machine check to specified vcpu */ - irq.type = KVM_S390_MCHK; - rc = kvm_s390_inject_vcpu(vcpu, &irq); - } + irq.u.mchk.cr14 = cr14; + irq.u.mchk.mcic = mcck_info->mcic; + irq.u.mchk.ext_damage_code = mcck_info->ext_damage_code; + irq.u.mchk.failing_storage_address = mcck_info->failing_storage_address; + + /* Inject the machine check to specified vcpu */ + irq.type = KVM_S390_MCHK; + rc = kvm_s390_inject_vcpu(vcpu, &irq); WARN_ON_ONCE(rc); } From da07a751efa4583385f9f0f47113549fe8871242 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 11 Aug 2026 17:37:35 +0200 Subject: [PATCH 46/56] KVM: s390: keyop: use mmu_lock to read gmap->asce Every other dat_* consumer in this file (kvm_s390_get_skeys, set_skeys, get_cmma_bits, set_cmma_bits, MEM_CLR_CMMA, kvm_s390_fixup_prefix, kvm_test_age_gfn, kvm_age_gfn) reads kvm->arch.gmap->asce *inside* the mmu_lock read-side. keyop is the only outlier. gmap->asce is mutated under write_lock(mmu_lock) by gmap_set_limit() and keyop might use a stale asce value for walking as KVM_S390_KEYOP and KVM_S390_VM_MEM_LIMIT_SIZE can run concurrently. This can result in memory corruption. Fixes: 0ee4ddc1647b ("KVM: s390: Storage key manipulation IOCTL") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260811153738.206885-2-borntraeger@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 095c9ba0aa5c..a3e55c613243 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -562,11 +562,12 @@ static void __kvm_s390_exit(void) static int kvm_s390_keyop(struct kvm_s390_mmu_cache *mc, struct kvm *kvm, int op, unsigned long addr, union skey skey) { - union asce asce = kvm->arch.gmap->asce; gfn_t gfn = gpa_to_gfn(addr); + union asce asce; int r; guard(read_lock)(&kvm->mmu_lock); + asce = kvm->arch.gmap->asce; switch (op) { case KVM_S390_KEYOP_SSKE: From 34d5b5b646c91cfb9338d7a12c955a70ffb8c66b Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 11 Aug 2026 17:37:36 +0200 Subject: [PATCH 47/56] KVM: s390: vsie: zero stale crypto bits When shadowing crypto access bits from a format0 apcb (crycb 0 or 1), the bits 64..255 are unchanged from whatever is in the vsie page in the crycb and thus in the apcb. This gives a nested guest potential access to a device no longer available. Zero out the remaining bits. Fixes: 6b79de4b056e ("KVM: s390: vsie: allow guest FORMAT-1 CRYCB on host FORMAT-2") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260811153738.206885-3-borntraeger@linux.ibm.com> --- arch/s390/kvm/vsie.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index eea24562e7db..0a7d8dfab6b7 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -173,6 +173,7 @@ static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s, sizeof(struct kvm_s390_apcb0))) return -EFAULT; + memset(apcb_s, 0, sizeof(*apcb_s)); apcb_s->apm[0] = apcb_h->apm[0] & tmp.apm[0]; apcb_s->aqm[0] = apcb_h->aqm[0] & tmp.aqm[0] & 0xffff000000000000UL; apcb_s->adm[0] = apcb_h->adm[0] & tmp.adm[0] & 0xffff000000000000UL; From 1e3c8e7b3465fb8a49d3623d2d0f449c0b5b48f3 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 11 Aug 2026 17:37:37 +0200 Subject: [PATCH 48/56] KVM: s390: pv: Fix rc/rrc offset for PVM_DUMP The rc/rrc value is copied to the cmd location of the cmd in the kvm_pv_cmd structure. Fix the offset. Fixes: 8aba09588d2a ("KVM: s390: Add CPU dump functionality") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260811153738.206885-4-borntraeger@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index a3e55c613243..ed4190128812 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -5736,7 +5736,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_s390_handle_pv_vcpu_dump(vcpu, &cmd); /* Always copy over UV rc / rrc data */ - if (copy_to_user((__u8 __user *)argp, &cmd.rc, + if (copy_to_user(argp + offsetof(struct kvm_pv_cmd, rc), &cmd.rc, sizeof(cmd.rc) + sizeof(cmd.rrc))) r = -EFAULT; break; From c44d36d8e6501c4934412d9014e5e02da9efdb8f Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 11 Aug 2026 17:37:38 +0200 Subject: [PATCH 49/56] KVM: s390: Restore sigset on error path kvm_sigset_activate() installs vcpu->sigset via sigprocmask() and stashes the caller's mask in current->real_blocked; only kvm_sigset_deactivate() restores it. For KVM_RUN on a STOPPED vcpu the error path will not restore the userspace mask. Re-arrange the error handling to also restore the signal mask. Fixes: 6352e4d2dd9a3 ("KVM: s390: implement KVM_(S|G)ET_MP_STATE for user space state control") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260811153738.206885-5-borntraeger@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ed4190128812..17aa38710170 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -5073,7 +5073,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) pr_err_ratelimited("can't run stopped vcpu %d\n", vcpu->vcpu_id); rc = -EINVAL; - goto out; + goto out_sigset; } kernel_fpu_begin(&fpu, KERNEL_FPC | KERNEL_VXR); @@ -5103,9 +5103,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) store_regs(vcpu); kernel_fpu_end(&fpu, KERNEL_FPC | KERNEL_VXR); + vcpu->stat.exit_userspace++; + +out_sigset: kvm_sigset_deactivate(vcpu); - vcpu->stat.exit_userspace++; out: vcpu_put(vcpu); return rc; From 88e22ffd1e46b95e40a6afabe486deb1d31a3ae1 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Wed, 12 Aug 2026 12:44:28 +0200 Subject: [PATCH 50/56] KVM: s390: Properly handle NULL pointer in dat_cond_set_storage_key() Some callers pass NULL as oldkey. Calling page_cond_set_storage_key() will cause that NULL pointer to get dereferenced. Fix by checking for NULL and assigning the pointer to a dummy local variable to avoid crashes. Fixes: 8e03e8316eb2 ("KVM: s390: KVM page table management functions: storage keys") Reviewed-by: Christian Borntraeger Reviewed-by: Christoph Schlameuss Signed-off-by: Claudio Imbrenda Message-ID: <20260812104436.109741-2-imbrenda@linux.ibm.com> --- arch/s390/kvm/dat.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index 3f2d6e8902d7..165c704fcf29 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -722,9 +722,12 @@ int dat_cond_set_storage_key(struct kvm_s390_mmu_cache *mmc, union asce asce, gf if (rc) return rc; - if (!ptep) + if (!ptep) { + if (!oldkey) + oldkey = &prev; return page_cond_set_storage_key(large_crste_to_phys(*crstep, gfn), skey, oldkey, nq, mr, mc); + } old = pgste_get_lock(ptep); pgste = old; From 062e44a9319f14b6f66a5e8accb98cfa873c7b0d Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Wed, 12 Aug 2026 12:44:29 +0200 Subject: [PATCH 51/56] KVM: s390: Use srcu in kvm_arch_vcpu_unlocked_ioctl() kvm_arch_vcpu_unlocked_ioctl() is called without further locks held, but kvm_s390_inject_vcpu(), which is called from there, needs either the kvm->srcu or the slots lock. Fix by taking the kvm->srcu in kvm_arch_vcpu_unlocked_ioctl(). Fixes: ba5c1e9b6cee ("KVM: s390: interrupt subsystem, cpu timer, waitpsw") Reviewed-by: Christian Borntraeger Reviewed-by: Christoph Schlameuss Signed-off-by: Claudio Imbrenda Message-ID: <20260812104436.109741-3-imbrenda@linux.ibm.com> --- arch/s390/kvm/kvm-s390.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 17aa38710170..91b975835457 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -5456,7 +5456,8 @@ long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, if (copy_from_user(&s390irq, argp, sizeof(s390irq))) return -EFAULT; - rc = kvm_s390_inject_vcpu(vcpu, &s390irq); + scoped_guard(srcu, &vcpu->kvm->srcu) + rc = kvm_s390_inject_vcpu(vcpu, &s390irq); break; } case KVM_S390_INTERRUPT: { @@ -5469,7 +5470,8 @@ long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, return -EFAULT; if (s390int_to_s390irq(&s390int, &s390irq)) return -EINVAL; - rc = kvm_s390_inject_vcpu(vcpu, &s390irq); + scoped_guard(srcu, &vcpu->kvm->srcu) + rc = kvm_s390_inject_vcpu(vcpu, &s390irq); break; } default: From ae50d472225895e0d2a2c176aedf907ec1342c07 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Wed, 12 Aug 2026 12:44:30 +0200 Subject: [PATCH 52/56] KVM: s390: Fix get_all_floating_irqs() When attempting to report all pending floating interrupt to userspace, the GISA IPM bits are atomically tested and cleared, and the corresponding interrupt description is written in the output buffer. If the output buffer is too small, an error is returned to userspace, but the GISA IPM bits are now lost. Moreover, the contract of KVM_DEV_FLIC_GET_ALL_IRQS, which is the only path to get_all_floating_irqs(), states that: > All interrupts remain pending, i.e. are not deleted from the list of > currently pending interrupts. Fix by non-destructively testing for the GISA IPM bits. Fixes: 24160af6cb28 ("KVM: s390: add GISA interrupts to FLIC ioctl interface") Reviewed-by: Christian Borntraeger Signed-off-by: Claudio Imbrenda Message-ID: <20260812104436.109741-4-imbrenda@linux.ibm.com> --- arch/s390/kvm/interrupt.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 0d9fbe75dc66..ca2f521092be 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -273,6 +273,11 @@ static inline int gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); } +static inline int gisa_test_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) +{ + return test_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *)gisa); +} + static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu) { unsigned long pending = vcpu->kvm->arch.float_int.pending_irqs | @@ -2242,7 +2247,7 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) ret = -ENOMEM; goto out_nolock; } - if (gisa_tac_ipm_gisc(gi->origin, i)) { + if (gisa_test_ipm_gisc(gi->origin, i)) { irq = (struct kvm_s390_irq *) &buf[n]; irq->type = KVM_S390_INT_IO(1, 0, 0, 0); irq->u.io.io_int_word = isc_to_int_word(i); From b5a941112fe46e4c30c93c0500efe641aef99840 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Wed, 12 Aug 2026 12:44:32 +0200 Subject: [PATCH 53/56] KVM: s390: Fix pgste_get_trylock_multiple() In case of failure, pgste_get_trylock_multiple() will attempt to unlock the locked PGSTEs based on whether the PCL is set. In some circumstances this can lead to unlocking PGSTEs that were locked by other threads. Fix by unlocking the amount of PGSTEs that were actually locked, ignoring the PCL bit in the array. Fixes: 94fd9b16cc67 ("KVM: s390: KVM page table management functions: lifecycle management") Reviewed-by: Christian Borntraeger Reviewed-by: Christoph Schlameuss Signed-off-by: Claudio Imbrenda Message-ID: <20260812104436.109741-6-imbrenda@linux.ibm.com> --- arch/s390/kvm/dat.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index 165c704fcf29..f4dd6f783417 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -923,11 +923,8 @@ static void pgste_set_unlock_multiple(union pte *first, int n, union pgste *pgst { int i; - for (i = 0; i < n; i++) { - if (!pgstes[i].pcl) - break; + for (i = 0; i < n; i++) pgste_set_unlock(first + i, pgstes[i]); - } } static bool pgste_get_trylock_multiple(union pte *first, int n, union pgste *pgstes) @@ -940,7 +937,7 @@ static bool pgste_get_trylock_multiple(union pte *first, int n, union pgste *pgs } if (i == n) return true; - pgste_set_unlock_multiple(first, n, pgstes); + pgste_set_unlock_multiple(first, i, pgstes); return false; } From d343407b728a80b74be3c24b59f15e60289ea527 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Wed, 12 Aug 2026 12:44:33 +0200 Subject: [PATCH 54/56] KVM: s390: Fix IRQ injection with SIGP Stop and Store Status When __inject_sigp_stop() is called for a Stop and Store Status operation, if the vCPU is running, the interrupt is marked as pending and the status is stored by the thread performing the KVM_RUN IOCTL. If the vCPU is already stopped, the status is stored immediately. Storing the status means writing into userspace, which might fault, and __inject_sigp_stop() is called from do_inject_vcpu() which in turn is always called holding a spinlock, which is obviously an issue. Fix this by returning -EWOULDBLOCK from __inject_sigp_stop(), and adding a bool flag to indicate whether a store status is needed. The callers of do_inject_vcpu() are modified to pass the pointer to the bool flag; whenever a Store Status operation is needed, the callers can now perform it outside the spinlock. Opportunistically refactor kvm_s390_set_irq_state() to use scoped_guard() and __free(). Fixes: 6cddd432e3da ("KVM: s390: handle stop irqs without action_bits") Signed-off-by: Claudio Imbrenda [ Added Fixes tag while picking -- Claudio ] Message-ID: <20260812104436.109741-7-imbrenda@linux.ibm.com> --- arch/s390/kvm/interrupt.c | 72 +++++++++++++++++++++------------------ 1 file changed, 39 insertions(+), 33 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index ca2f521092be..da740a378a8c 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1555,23 +1555,21 @@ static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) } #define KVM_S390_STOP_SUPP_FLAGS (KVM_S390_STOP_FLAG_STORE_STATUS) -static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq, bool *storestatus) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_stop_info *stop = &li->irq.stop; - int rc = 0; vcpu->stat.inject_stop_signal++; trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0); if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS) return -EINVAL; - if (is_vcpu_stopped(vcpu)) { - if (irq->u.stop.flags & KVM_S390_STOP_FLAG_STORE_STATUS) - rc = kvm_s390_store_status_unloaded(vcpu, - KVM_S390_STORE_STATUS_NOADDR); - return rc; + if (!(irq->u.stop.flags & KVM_S390_STOP_FLAG_STORE_STATUS)) + return 0; + *storestatus = true; + return -EWOULDBLOCK; } if (test_and_set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs)) @@ -2107,7 +2105,7 @@ void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu) spin_unlock(&li->lock); } -static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq, bool *storestatus) { int rc; @@ -2119,7 +2117,7 @@ static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) rc = __inject_set_prefix(vcpu, irq); break; case KVM_S390_SIGP_STOP: - rc = __inject_sigp_stop(vcpu, irq); + rc = __inject_sigp_stop(vcpu, irq, storestatus); break; case KVM_S390_RESTART: rc = __inject_sigp_restart(vcpu); @@ -2155,11 +2153,16 @@ static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + bool storestatus = false; int rc; spin_lock(&li->lock); - rc = do_inject_vcpu(vcpu, irq); + rc = do_inject_vcpu(vcpu, irq, &storestatus); spin_unlock(&li->lock); + + if (rc == -EWOULDBLOCK && storestatus) + rc = kvm_s390_store_status_unloaded(vcpu, KVM_S390_STORE_STATUS_NOADDR); + if (!rc) kvm_s390_vcpu_wakeup(vcpu); return rc; @@ -3194,7 +3197,8 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *irqstate, int len) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_irq *buf; + struct kvm_s390_irq *buf __free(kvfree) = NULL; + bool tmp, storestatus = false; int r = 0; int n; @@ -3202,32 +3206,34 @@ int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *irqstate, int len if (!buf) return -ENOMEM; - if (copy_from_user((void *) buf, irqstate, len)) { - r = -EFAULT; - goto out_free; + if (copy_from_user((void *)buf, irqstate, len)) + return -EFAULT; + + scoped_guard(spinlock, &li->lock) { + /* + * Don't allow setting the interrupt state + * when there are already interrupts pending + */ + if (li->pending_irqs) + return -EBUSY; + + for (n = 0; n < len / sizeof(*buf); n++) { + tmp = false; + r = do_inject_vcpu(vcpu, &buf[n], &tmp); + if (r == -EWOULDBLOCK && tmp) { + storestatus = true; + r = 0; + } + if (r) + break; + } } - /* - * Don't allow setting the interrupt state - * when there are already interrupts pending - */ - spin_lock(&li->lock); - if (li->pending_irqs) { - r = -EBUSY; - goto out_unlock; + if (storestatus) { + n = kvm_s390_store_status_unloaded(vcpu, KVM_S390_STORE_STATUS_NOADDR); + return r ? r : n; } - for (n = 0; n < len / sizeof(*buf); n++) { - r = do_inject_vcpu(vcpu, &buf[n]); - if (r) - break; - } - -out_unlock: - spin_unlock(&li->lock); -out_free: - vfree(buf); - return r; } From 6b1130e1b4715f5aab4768111c26bd718a14686a Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Wed, 12 Aug 2026 12:44:34 +0200 Subject: [PATCH 55/56] KVM: s390: Fix kvm_s390_clear_pv_state() kvm_s390_clear_pv_state() needs to also clear the dumping flag, to allow the protected VM to be started again (as non-protected, with all protected state safely destroyed) after a forced reboot while a protected dump was ongoing and not completed. Fixes: e40df9efd68a ("KVM: s390: pv: clear the state without memset") Reviewed-by: Christian Borntraeger Signed-off-by: Claudio Imbrenda Message-ID: <20260812104436.109741-8-imbrenda@linux.ibm.com> --- arch/s390/kvm/pv.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index b02e0159d3cd..98a9a57f71b9 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -242,6 +242,10 @@ static void kvm_s390_clear_pv_state(struct kvm *kvm) kvm->arch.pv.guest_len = 0; kvm->arch.pv.stor_base = 0; kvm->arch.pv.stor_var = NULL; + if (kvm->arch.pv.dumping) { + kvm_s390_vcpu_unblock_all(kvm); + kvm->arch.pv.dumping = false; + } } static void kvm_s390_pv_dispose_cpu(struct kvm_vcpu *vcpu, bool free_stor_base) From 30300ec2780efa6cb9ea0887d1b94506af9c4eea Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Wed, 12 Aug 2026 12:44:35 +0200 Subject: [PATCH 56/56] KVM: s390: Fix potential tiny kernel stack leak In some circumstances, one bit of kernel stack could have been leaked from dat_cond_set_storage_key(). Fix by clearing prev before use. Fixes: 8e03e8316eb2 ("KVM: s390: KVM page table management functions: storage keys") Reviewed-by: Christian Borntraeger Signed-off-by: Claudio Imbrenda Message-ID: <20260812104436.109741-9-imbrenda@linux.ibm.com> --- arch/s390/kvm/dat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index f4dd6f783417..f2ea013cb33e 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -737,6 +737,7 @@ int dat_cond_set_storage_key(struct kvm_s390_mmu_cache *mmc, union asce asce, gf pgste.fp = skey.fp; pgste.gc = skey.c; pgste.gr = skey.r; + prev.skey = 0; if (!ptep->h.i) { rc = page_cond_set_storage_key(pte_origin(*ptep), skey, &prev, nq, mr, mc);