s390 KVM PCI backports for 6.6
Subsystems (3)
v3 cover s390 KVM PCI backports for 6.6
Hi,
This patchset backports the failed commits to stable-6.6. I have resolved the merge conflicts and tested them on s390.
Thanks
Farhan
ChangeLog
---------
v2 -> v3
- Fix an error in patch 1 to remove in loop read.
- Add missing aisb calculation fix
v1 -> v2
- Resolve conflicts on latest 6.6 tree
Farhan Ali (3):
KVM: s390: pci: Fix memory accounting for pinned/unpinned pages
KVM: s390: pci: Fix missing error codes and memory unaccounting
KVM: s390: pci: Fix resource leak on IRQ registration failure
Matthew Rosato (1):
KVM: s390: pci: Fix aisb calculation
arch/s390/kvm/pci.c | 86 ++++++++++++++++++++++++++++++++------------- arch/s390/kvm/pci.h | 2 ++ 2 files changed, 64 insertions(+), 24 deletions(-)
Signature · 1 line
2.43.0
PATCH v3 1/4 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.
--- arch/s390/kvm/pci.c | 48 ++++++++++++++++++++++++++++++++------------- arch/s390/kvm/pci.h | 2 ++ 2 files changed, 36 insertions(+), 14 deletions(-)
arch/s390/kvm/pci.c +34 -14
@@ -191,34 +191,54 @@ 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 { - cur_pages =atomic_long_read (&user->locked_vm); new_pages = cur_pages + nr_pages; -if (new_pages > page_limit) -return -ENOMEM ; - }while (atomic_long_cmpxchg (&user->locked_vm, cur_pages, - new_pages) != cur_pages); +if (new_pages > page_limit) { + rc = -ENOMEM ; + goto out; + } + }while (!atomic_long_try_cmpxchg (&user->locked_vm, &cur_pages, new_pages)); + +if (current->mm) { +mmgrab (current->mm); +atomic64_add (nr_pages, ¤t->mm->pinned_vm); + } -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,
@@ -295,7 +315,7 @@ 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 */
@@ -424,7 +444,7 @@ 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);
arch/s390/kvm/pci.h +2 -0
@@ -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 {
Signature · 1 line
2.43.0
PATCH v3 2/4 KVM: s390: pci: Fix missing error codes and memory unaccounting
In reply to Farhan AliIn 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.
--- arch/s390/kvm/pci.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
arch/s390/kvm/pci.c +7 -2
@@ -315,14 +315,17 @@ 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 |
@@ -374,6 +377,8 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,airq_iv_free_bit (aift->sbv, zdev->aisb); zdev->aisb =0 ; unlock: +if (pcount >0 ) +unaccount_mem (zdev->kzdev, pcount);mutex_unlock (&aift->aift_lock); unpin2:if (fib->fmt0.sum ==1 )
Signature · 1 line
2.43.0
PATCH v3 3/4 KVM: s390: pci: Fix resource leak on IRQ registration failure
In reply to Farhan AliCurrently 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.
--- arch/s390/kvm/pci.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-)
arch/s390/kvm/pci.c +21 -8
@@ -359,19 +359,32 @@ 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);
Signature · 1 line
2.43.0
PATCH v3 4/4 KVM: s390: pci: Fix aisb calculation
In reply to Farhan AliFrom: Matthew Rosato <[email protected]>
The current implementation of aisb calculation will erroneously index via an unsigned long * as well as multiply by 8B for every 64-bits in the offset; only one or the other is required. This throws off aisb calculations once the number of devices exceeds 64, and can result in out-of-bounds access as well as failure to indicate summary bits associated with those devices in guests.
Fix this by converting to a physical address before applying the offset, as is already done in arch/s390/pci/pci_irq.c.
--- arch/s390/kvm/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/s390/kvm/pci.c +1 -1
@@ -167,7 +167,7 @@ static int kvm_zpci_set_airq(struct zpci_dev *zdev) fib.fmt0.noi =airq_iv_end (zdev->aibv); fib.fmt0.aibv =virt_to_phys (zdev->aibv->vector); fib.fmt0.aibvo =0 ; - fib.fmt0.aisb =virt_to_phys (aift->sbv->vector + (zdev->aisb /64 ) *8 ); + fib.fmt0.aisb =virt_to_phys (aift->sbv->vector) + (zdev->aisb /64 ) *8 ; fib.fmt0.aisbo = zdev->aisb &63 ; fib.gd = zdev->gisa;
Signature · 1 line
2.43.0
Quoted 2 lines
This patchset backports the failed commits to stable-6.6. I have resolved the merge conflicts and tested them on s390.
Queued the series for 6.6, thanks.
Signature · 2 lines
Thanks, Sasha