[PATCH v5 1/6] KVM: s390: pci: Reject adapter interrupt forwarding if already enabled

[PATCH v5 1/6] KVM: s390: pci: Reject adapter interrupt forwarding if already enabled

[Farhan Ali]

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 <borntraeger@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 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);
 
-- 
2.43.0

[PATCH v5 2/6] KVM: s390: pci: Fix memory accounting for pinned/unpinned pages

[Farhan Ali]

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 <borntraeger@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 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..44c00e5e32c5 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, &current->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, &current->mm->pinned_vm);
+	if (current->mm) {
+		mmgrab(current->mm);
+		atomic64_add(nr_pages, &current->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 {
-- 
2.43.0

Re: [PATCH v5 2/6] KVM: s390: pci: Fix memory accounting for pinned/unpinned pages

[Matthew Rosato]

On 7/23/26 2:34 PM, Farhan Ali wrote:
> 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 <borntraeger@linux.ibm.com>
> Signed-off-by: Farhan Ali <alifm@linux.ibm.com>

Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>

With one note below:


>  
>  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;
>  

Sashiko marked a failure to unaccount on error paths after this point as
a regression, but it's a pre-existing issue AND resolved with patch 3 of
this series.

>  	/* 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 {

[PATCH v5 3/6] KVM: s390: pci: Fix missing error codes and memory unaccounting

[Farhan Ali]

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 <borntraeger@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 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 44c00e5e32c5..f58d7ec0bc7e 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)
-- 
2.43.0

[PATCH v5 4/6] KVM: s390: pci: Fix NULL dereference on AIBV allocation failure

[Farhan Ali]

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 <borntraeger@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 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 f58d7ec0bc7e..602534e3cc10 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);
-- 
2.43.0

[PATCH v5 5/6] KVM: s390: pci: Fix resource leak on IRQ registration failure

[Farhan Ali]

Currently if kvm_zpci_set_airq() fails, kvm_s390_pci_aif_enable() returns
an 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 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 <mjrosato@linux.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 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 602534e3cc10..ca8ef76bcf6b 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);
-- 
2.43.0

[PATCH v5 6/6] KVM: s390: pci: Validate AIBV and AISB before pinning guest pages

[Farhan Ali]

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 <borntraeger@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 arch/s390/kvm/pci.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index ca8ef76bcf6b..25185d04ca28 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 +271,15 @@ 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) * sizeof(unsigned long);
+	size += (fib->fmt0.aibvo / 8);
+	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 +295,12 @@ 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,
-- 
2.43.0