[PATCH v2 stable 6.6 0/3] s390 KVM PCI backports for 6.6

[PATCH v2 stable 6.6 0/3] s390 KVM PCI backports for 6.6

[Farhan Ali]

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
---------
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

 arch/s390/kvm/pci.c | 83 +++++++++++++++++++++++++++++++++------------
 arch/s390/kvm/pci.h |  2 ++
 2 files changed, 63 insertions(+), 22 deletions(-)

-- 
2.43.0

[PATCH v2 1/3] 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>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
[borntraeger@linux.ibm.com: Fixed whitespace]
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
(cherry picked from commit 36f6999ecde3976731a8bfc0b8e667da6f593069)
[alifm@linux.ibm.com: Resolve merge conflict]
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 arch/s390/kvm/pci.c | 47 ++++++++++++++++++++++++++++++++-------------
 arch/s390/kvm/pci.h |  2 ++
 2 files changed, 36 insertions(+), 13 deletions(-)

diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index 17fedfc7bb99..54a7a2f38c69 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -191,34 +191,55 @@ 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 {
 		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, &current->mm->pinned_vm);
+	}
 
-	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,
@@ -295,7 +316,7 @@ 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 +445,7 @@ 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

[PATCH v2 2/3] 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>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
(cherry picked from commit f86842e4d6c482300f4567f492d512c9ccf5bc4f)
[alifm@linux.ibm.com: Resolve merge conflict]
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 54a7a2f38c69..56a19c00d3b7 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -316,14 +316,17 @@ 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 |
@@ -375,6 +378,8 @@ 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)
-- 
2.43.0

[PATCH v2 3/3] 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
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 <mjrosato@linux.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
(cherry picked from commit 5580c9858f1e00f60191eb09c3add359836d60b6)
[alifm@linux.ibm.com: Resolved merge conflict]
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 56a19c00d3b7..930c5141f2f8 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -360,19 +360,32 @@ 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 v2 stable 6.12 0/3] s390 KVM PCI backports for 6.12

[Farhan Ali]

Hi,

This patchset backports the failed commits to stable-6.12. I have resolved
the merge conflicts and tested them on s390.

Thanks
Farhan

ChangeLog
---------
v1 -> v2
   - Resolve conflicts on latest 6.12 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

 arch/s390/kvm/pci.c | 83 +++++++++++++++++++++++++++++++++------------
 arch/s390/kvm/pci.h |  2 ++
 2 files changed, 63 insertions(+), 22 deletions(-)

-- 
2.43.0

[PATCH v2 1/3] 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>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
[borntraeger@linux.ibm.com: Fixed whitespace]
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
(cherry picked from commit 36f6999ecde3976731a8bfc0b8e667da6f593069)
[alifm@linux.ibm.com: Resolve merge conflict]
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
---
 arch/s390/kvm/pci.c | 47 ++++++++++++++++++++++++++++++++-------------
 arch/s390/kvm/pci.h |  2 ++
 2 files changed, 36 insertions(+), 13 deletions(-)

diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index 17fedfc7bb99..54a7a2f38c69 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -191,34 +191,55 @@ 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 {
 		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, &current->mm->pinned_vm);
+	}
 
-	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,
@@ -295,7 +316,7 @@ 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 +445,7 @@ 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