If find_linux_pte fails, IRQs will not be restored. This is unlikely
to happen in practice since it would have been reported as hanging
hosts, but it should of course be fixed anyway.
Cc: stable(a)vger.kernel.org
Reported-by: Sean Christopherson <seanjc(a)google.com>
Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com>
---
arch/powerpc/kvm/e500_mmu_host.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index e5a145b578a4..6824e8139801 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -479,7 +479,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
if (pte_present(pte)) {
wimg = (pte_val(pte) >> PTE_WIMGE_SHIFT) &
MAS2_WIMGE_MASK;
- local_irq_restore(flags);
} else {
local_irq_restore(flags);
pr_err_ratelimited("%s: pte not present: gfn %lx,pfn %lx\n",
@@ -488,8 +487,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
goto out;
}
}
+ local_irq_restore(flags);
+
writable = kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg);
-
kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
ref, gvaddr, stlbe);
--
2.47.1
In case of possible unpredictably large arguments passed to
rose_setsockopt() and multiplied by extra values on top of that,
integer overflows may occur.
Do the safest minimum and fix these issues by checking the
contents of 'opt' and returning -EINVAL if they are too large. Also,
switch to unsigned int and remove useless check for negative 'opt'
in ROSE_IDLE case.
Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable(a)vger.kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich(a)fintech.ru>
---
net/rose/af_rose.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 59050caab65c..72c65d938a15 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -397,15 +397,15 @@ static int rose_setsockopt(struct socket *sock, int level, int optname,
{
struct sock *sk = sock->sk;
struct rose_sock *rose = rose_sk(sk);
- int opt;
+ unsigned int opt;
if (level != SOL_ROSE)
return -ENOPROTOOPT;
- if (optlen < sizeof(int))
+ if (optlen < sizeof(unsigned int))
return -EINVAL;
- if (copy_from_sockptr(&opt, optval, sizeof(int)))
+ if (copy_from_sockptr(&opt, optval, sizeof(unsigned int)))
return -EFAULT;
switch (optname) {
@@ -414,31 +414,31 @@ static int rose_setsockopt(struct socket *sock, int level, int optname,
return 0;
case ROSE_T1:
- if (opt < 1)
+ if (opt < 1 || opt > UINT_MAX / HZ)
return -EINVAL;
rose->t1 = opt * HZ;
return 0;
case ROSE_T2:
- if (opt < 1)
+ if (opt < 1 || opt > UINT_MAX / HZ)
return -EINVAL;
rose->t2 = opt * HZ;
return 0;
case ROSE_T3:
- if (opt < 1)
+ if (opt < 1 || opt > UINT_MAX / HZ)
return -EINVAL;
rose->t3 = opt * HZ;
return 0;
case ROSE_HOLDBACK:
- if (opt < 1)
+ if (opt < 1 || opt > UINT_MAX / HZ)
return -EINVAL;
rose->hb = opt * HZ;
return 0;
case ROSE_IDLE:
- if (opt < 0)
+ if (opt > UINT_MAX / (60 * HZ))
return -EINVAL;
rose->idle = opt * 60 * HZ;
return 0;
pci-legacy systems are not using logic_pio to managed PIO
allocations, thus the generic pci_address_to_pio won't work
when PCI_IOBASE is defined.
Override the function to use architecture implementation to
fix the problem.
Cc: stable(a)vger.kernel.org
Fixes: 4bfb53e7d317 ("mips: add <asm-generic/io.h> including")
Reported-by: Mateusz Jończyk <mat.jonczyk(a)o2.pl>
Closes: https://lore.kernel.org/r/99f75c66-4c2d-45dc-a808-b5ba440c7551@app.fastmail…
Signed-off-by: Jiaxun Yang <jiaxun.yang(a)flygoat.com>
---
This is a quick fix for fixes tree and stable backporting.
In long term, we should get logic_pio accept fixed mapping,
and make PCI core code aware of platforms not using vmap
for PCI_IOBASE.
---
arch/mips/pci/pci-legacy.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c
index ec2567f8efd83bff7b106cbbd9ec7a6de0308c4c..66898fd182dc1fec1d1e9ae4c908873d59777182 100644
--- a/arch/mips/pci/pci-legacy.c
+++ b/arch/mips/pci/pci-legacy.c
@@ -29,6 +29,14 @@ static LIST_HEAD(controllers);
static int pci_initialized;
+unsigned long pci_address_to_pio(phys_addr_t address)
+{
+ if (address > IO_SPACE_LIMIT)
+ return (unsigned long)-1;
+
+ return (unsigned long) address;
+}
+
/*
* We need to avoid collisions with `mirrored' VGA ports
* and other strange ISA hardware, so we always want the
---
base-commit: dab2734f8e9ecba609d66d1dd087a392a7774c04
change-id: 20250114-malta-io-fixes-85e14b1b9f8b
Best regards,
--
Jiaxun Yang <jiaxun.yang(a)flygoat.com>
The comparison function cmpworker() violates the C standard's
requirements for qsort() comparison functions, which mandate symmetry
and transitivity:
Symmetry: If x < y, then y > x.
Transitivity: If x < y and y < z, then x < z.
In its current implementation, cmpworker() incorrectly returns 0 when
w1->tid < w2->tid, which breaks both symmetry and transitivity. This
violation causes undefined behavior, potentially leading to issues such
as memory corruption in glibc [1].
Fix the issue by returning -1 when w1->tid < w2->tid, ensuring
compliance with the C standard and preventing undefined behavior.
Link: https://www.qualys.com/2024/01/30/qsort.txt [1]
Fixes: 121dd9ea0116 ("perf bench: Add epoll parallel epoll_wait benchmark")
Cc: stable(a)vger.kernel.org
Signed-off-by: Kuan-Wei Chiu <visitorckw(a)gmail.com>
---
Changes in v3:
- Perform a full comparison for clarity, as suggested by James.
tools/perf/bench/epoll-wait.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index ef5c4257844d..20fe4f72b4af 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -420,7 +420,12 @@ static int cmpworker(const void *p1, const void *p2)
struct worker *w1 = (struct worker *) p1;
struct worker *w2 = (struct worker *) p2;
- return w1->tid > w2->tid;
+
+ if (w1->tid > w2->tid)
+ return 1;
+ if (w1->tid < w2->tid)
+ return -1;
+ return 0;
}
int bench_epoll_wait(int argc, const char **argv)
--
2.34.1
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 9322d1915f9d976ee48c09d800fbd5169bc2ddcc
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012050-motor-prevalent-e802@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 9322d1915f9d976ee48c09d800fbd5169bc2ddcc Mon Sep 17 00:00:00 2001
From: Joe Hattori <joe(a)pf.is.s.u-tokyo.ac.jp>
Date: Sun, 15 Dec 2024 12:39:45 +0900
Subject: [PATCH] irqchip: Plug a OF node reference leak in
platform_irqchip_probe()
platform_irqchip_probe() leaks a OF node when irq_init_cb() fails. Fix it
by declaring par_np with the __free(device_node) cleanup construct.
This bug was found by an experimental static analysis tool that I am
developing.
Fixes: f8410e626569 ("irqchip: Add IRQCHIP_PLATFORM_DRIVER_BEGIN/END and IRQCHIP_MATCH helper macros")
Signed-off-by: Joe Hattori <joe(a)pf.is.s.u-tokyo.ac.jp>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/all/20241215033945.3414223-1-joe@pf.is.s.u-tokyo.ac…
diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c
index 1eeb0d0156ce..0ee7b6b71f5f 100644
--- a/drivers/irqchip/irqchip.c
+++ b/drivers/irqchip/irqchip.c
@@ -35,11 +35,10 @@ void __init irqchip_init(void)
int platform_irqchip_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
- struct device_node *par_np = of_irq_find_parent(np);
+ struct device_node *par_np __free(device_node) = of_irq_find_parent(np);
of_irq_init_cb_t irq_init_cb = of_device_get_match_data(&pdev->dev);
if (!irq_init_cb) {
- of_node_put(par_np);
return -EINVAL;
}
@@ -55,7 +54,6 @@ int platform_irqchip_probe(struct platform_device *pdev)
* interrupt controller can check for specific domains as necessary.
*/
if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY)) {
- of_node_put(par_np);
return -EPROBE_DEFER;
}
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 9322d1915f9d976ee48c09d800fbd5169bc2ddcc
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012049-connector-oxford-19f1@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 9322d1915f9d976ee48c09d800fbd5169bc2ddcc Mon Sep 17 00:00:00 2001
From: Joe Hattori <joe(a)pf.is.s.u-tokyo.ac.jp>
Date: Sun, 15 Dec 2024 12:39:45 +0900
Subject: [PATCH] irqchip: Plug a OF node reference leak in
platform_irqchip_probe()
platform_irqchip_probe() leaks a OF node when irq_init_cb() fails. Fix it
by declaring par_np with the __free(device_node) cleanup construct.
This bug was found by an experimental static analysis tool that I am
developing.
Fixes: f8410e626569 ("irqchip: Add IRQCHIP_PLATFORM_DRIVER_BEGIN/END and IRQCHIP_MATCH helper macros")
Signed-off-by: Joe Hattori <joe(a)pf.is.s.u-tokyo.ac.jp>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/all/20241215033945.3414223-1-joe@pf.is.s.u-tokyo.ac…
diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c
index 1eeb0d0156ce..0ee7b6b71f5f 100644
--- a/drivers/irqchip/irqchip.c
+++ b/drivers/irqchip/irqchip.c
@@ -35,11 +35,10 @@ void __init irqchip_init(void)
int platform_irqchip_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
- struct device_node *par_np = of_irq_find_parent(np);
+ struct device_node *par_np __free(device_node) = of_irq_find_parent(np);
of_irq_init_cb_t irq_init_cb = of_device_get_match_data(&pdev->dev);
if (!irq_init_cb) {
- of_node_put(par_np);
return -EINVAL;
}
@@ -55,7 +54,6 @@ int platform_irqchip_probe(struct platform_device *pdev)
* interrupt controller can check for specific domains as necessary.
*/
if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY)) {
- of_node_put(par_np);
return -EPROBE_DEFER;
}
The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 0cef0bb836e3cfe00f08f9606c72abd72fe78ca3
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012032-buffoon-cabbie-1e42@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 0cef0bb836e3cfe00f08f9606c72abd72fe78ca3 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts(a)arm.com>
Date: Tue, 7 Jan 2025 14:47:52 +0000
Subject: [PATCH] mm: clear uffd-wp PTE/PMD state on mremap()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When mremap()ing a memory region previously registered with userfaultfd as
write-protected but without UFFD_FEATURE_EVENT_REMAP, an inconsistency in
flag clearing leads to a mismatch between the vma flags (which have
uffd-wp cleared) and the pte/pmd flags (which do not have uffd-wp
cleared). This mismatch causes a subsequent mprotect(PROT_WRITE) to
trigger a warning in page_table_check_pte_flags() due to setting the pte
to writable while uffd-wp is still set.
Fix this by always explicitly clearing the uffd-wp pte/pmd flags on any
such mremap() so that the values are consistent with the existing clearing
of VM_UFFD_WP. Be careful to clear the logical flag regardless of its
physical form; a PTE bit, a swap PTE bit, or a PTE marker. Cover PTE,
huge PMD and hugetlb paths.
Link: https://lkml.kernel.org/r/20250107144755.1871363-2-ryan.roberts@arm.com
Co-developed-by: Mikołaj Lenczewski <miko.lenczewski(a)arm.com>
Signed-off-by: Mikołaj Lenczewski <miko.lenczewski(a)arm.com>
Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com>
Closes: https://lore.kernel.org/linux-mm/810b44a8-d2ae-4107-b665-5a42eae2d948@arm.c…
Fixes: 63b2d4174c4a ("userfaultfd: wp: add the writeprotect API to userfaultfd ioctl")
Cc: David Hildenbrand <david(a)redhat.com>
Cc: Jann Horn <jannh(a)google.com>
Cc: Liam R. Howlett <Liam.Howlett(a)Oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com>
Cc: Mark Rutland <mark.rutland(a)arm.com>
Cc: Muchun Song <muchun.song(a)linux.dev>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index cb40f1a1d081..75342022d144 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -247,6 +247,13 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
vma_is_shmem(vma);
}
+static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma)
+{
+ struct userfaultfd_ctx *uffd_ctx = vma->vm_userfaultfd_ctx.ctx;
+
+ return uffd_ctx && (uffd_ctx->features & UFFD_FEATURE_EVENT_REMAP) == 0;
+}
+
extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
extern void dup_userfaultfd_complete(struct list_head *);
void dup_userfaultfd_fail(struct list_head *);
@@ -402,6 +409,11 @@ static inline bool userfaultfd_wp_async(struct vm_area_struct *vma)
return false;
}
+static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma)
+{
+ return false;
+}
+
#endif /* CONFIG_USERFAULTFD */
static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e53d83b3e5cf..db64116a4f84 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2206,6 +2206,16 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd)
return pmd;
}
+static pmd_t clear_uffd_wp_pmd(pmd_t pmd)
+{
+ if (pmd_present(pmd))
+ pmd = pmd_clear_uffd_wp(pmd);
+ else if (is_swap_pmd(pmd))
+ pmd = pmd_swp_clear_uffd_wp(pmd);
+
+ return pmd;
+}
+
bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
{
@@ -2244,6 +2254,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
}
pmd = move_soft_dirty_pmd(pmd);
+ if (vma_has_uffd_without_event_remap(vma))
+ pmd = clear_uffd_wp_pmd(pmd);
set_pmd_at(mm, new_addr, new_pmd, pmd);
if (force_flush)
flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c498874a7170..eaaec19caa7c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5402,6 +5402,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte,
unsigned long sz)
{
+ bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma);
struct hstate *h = hstate_vma(vma);
struct mm_struct *mm = vma->vm_mm;
spinlock_t *src_ptl, *dst_ptl;
@@ -5418,7 +5419,18 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
pte = huge_ptep_get_and_clear(mm, old_addr, src_pte);
- set_huge_pte_at(mm, new_addr, dst_pte, pte, sz);
+
+ if (need_clear_uffd_wp && pte_marker_uffd_wp(pte))
+ huge_pte_clear(mm, new_addr, dst_pte, sz);
+ else {
+ if (need_clear_uffd_wp) {
+ if (pte_present(pte))
+ pte = huge_pte_clear_uffd_wp(pte);
+ else if (is_swap_pte(pte))
+ pte = pte_swp_clear_uffd_wp(pte);
+ }
+ set_huge_pte_at(mm, new_addr, dst_pte, pte, sz);
+ }
if (src_ptl != dst_ptl)
spin_unlock(src_ptl);
diff --git a/mm/mremap.c b/mm/mremap.c
index 60473413836b..cff7f552f909 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -138,6 +138,7 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
struct vm_area_struct *new_vma, pmd_t *new_pmd,
unsigned long new_addr, bool need_rmap_locks)
{
+ bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma);
struct mm_struct *mm = vma->vm_mm;
pte_t *old_pte, *new_pte, pte;
pmd_t dummy_pmdval;
@@ -216,7 +217,18 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
force_flush = true;
pte = move_pte(pte, old_addr, new_addr);
pte = move_soft_dirty_pte(pte);
- set_pte_at(mm, new_addr, new_pte, pte);
+
+ if (need_clear_uffd_wp && pte_marker_uffd_wp(pte))
+ pte_clear(mm, new_addr, new_pte);
+ else {
+ if (need_clear_uffd_wp) {
+ if (pte_present(pte))
+ pte = pte_clear_uffd_wp(pte);
+ else if (is_swap_pte(pte))
+ pte = pte_swp_clear_uffd_wp(pte);
+ }
+ set_pte_at(mm, new_addr, new_pte, pte);
+ }
}
arch_leave_lazy_mmu_mode();
@@ -278,6 +290,15 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
if (WARN_ON_ONCE(!pmd_none(*new_pmd)))
return false;
+ /* If this pmd belongs to a uffd vma with remap events disabled, we need
+ * to ensure that the uffd-wp state is cleared from all pgtables. This
+ * means recursing into lower page tables in move_page_tables(), and we
+ * can reuse the existing code if we simply treat the entry as "not
+ * moved".
+ */
+ if (vma_has_uffd_without_event_remap(vma))
+ return false;
+
/*
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_lock prevents deadlock.
@@ -333,6 +354,15 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
if (WARN_ON_ONCE(!pud_none(*new_pud)))
return false;
+ /* If this pud belongs to a uffd vma with remap events disabled, we need
+ * to ensure that the uffd-wp state is cleared from all pgtables. This
+ * means recursing into lower page tables in move_page_tables(), and we
+ * can reuse the existing code if we simply treat the entry as "not
+ * moved".
+ */
+ if (vma_has_uffd_without_event_remap(vma))
+ return false;
+
/*
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_lock prevents deadlock.