Hello
With sincerity of purpose I wish to communicate with you seeking your
acceptance towards investing in your country under your Management as
my foreign investor/business partner.
I'm Mrs. Aisha Al-Gaddafi, the only biological Daughter of the late
Libyan President (Late Colonel Muammar Gaddafi) I'm a single Mother
and a widow with three Children, presently residing herein Oman the
Southeastern coast of the Arabian Peninsula in Western Asia. I have
investment funds worth Twenty Seven Million Five Hundred Thousand
United State Dollars ($27.500.000.00 ) which I want to entrust to you
for the investment project in your country.
I am willing to negotiate an investment/business profit sharing ratio
with you based on the future investment earning profits. If you are
willing to handle this project kindly reply urgently to enable me to
provide you more information about the investment funds.
Best Regards
Mrs. Aisha Al-Gaddafi.
The LLCC block has several banks each with a different base address
and holes in between. So it is not a correct approach to cover these
banks with a single offset/size. Instead, the individual bank's base
address needs to be specified in devicetree with the exact size.
While at it, let's also fix the size of the llcc_broadcast_base to cover
the whole region.
Also, let's get rid of reg-names property as it is not needed anymore.
The driver is expected to parse the reg field based on index to get the
addresses of each LLCC banks.
Cc: <stable(a)vger.kernel.org> # 5.13
Fixes: 0392968dbe09 ("arm64: dts: qcom: sc7280: Add device tree node for LLCC")
Reported-by: Parikshit Pareek <quic_ppareek(a)quicinc.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam(a)linaro.org>
---
arch/arm64/boot/dts/qcom/sc7280.dtsi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi
index 0adf13399e64..90e11cbbaf88 100644
--- a/arch/arm64/boot/dts/qcom/sc7280.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi
@@ -3579,8 +3579,8 @@ gem_noc: interconnect@9100000 {
system-cache-controller@9200000 {
compatible = "qcom,sc7280-llcc";
- reg = <0 0x09200000 0 0xd0000>, <0 0x09600000 0 0x50000>;
- reg-names = "llcc_base", "llcc_broadcast_base";
+ reg = <0 0x09200000 0 0x58000>, <0 0x09280000 0 0x58000>,
+ <0 0x09600000 0 0x58000>;
interrupts = <GIC_SPI 582 IRQ_TYPE_LEVEL_HIGH>;
};
--
2.25.1
Since commit 07ec77a1d4e8 ("sched: Allow task CPU affinity to be
restricted on asymmetric systems"), the setting and clearing of
user_cpus_ptr are done under pi_lock for arm64 architecture. However,
dup_user_cpus_ptr() accesses user_cpus_ptr without any lock
protection. When racing with the clearing of user_cpus_ptr in
__set_cpus_allowed_ptr_locked(), it can lead to user-after-free and
double-free in arm64 kernel.
Commit 8f9ea86fdf99 ("sched: Always preserve the user requested
cpumask") fixes this problem as user_cpus_ptr, once set, will never
be cleared in a task's lifetime. However, this bug was re-introduced
in commit 851a723e45d1 ("sched: Always clear user_cpus_ptr in
do_set_cpus_allowed()") which allows the clearing of user_cpus_ptr in
do_set_cpus_allowed(). This time, it will affect all arches.
Fix this bug by always clearing the user_cpus_ptr of the newly
cloned/forked task before the copying process starts and check the
user_cpus_ptr state of the source task under pi_lock.
Note to stable, this patch won't be applicable to stable releases.
Just copy the new dup_user_cpus_ptr() function over.
Fixes: 07ec77a1d4e8 ("sched: Allow task CPU affinity to be restricted on asymmetric systems")
Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()")
CC: stable(a)vger.kernel.org
Reported-by: David Wang 王标 <wangbiao3(a)xiaomi.com>
Signed-off-by: Waiman Long <longman(a)redhat.com>
---
kernel/sched/core.c | 32 ++++++++++++++++++++++++++++----
1 file changed, 28 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8df51b08bb38..f2b75faaf71a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2624,19 +2624,43 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
int node)
{
+ cpumask_t *user_mask;
unsigned long flags;
+ /*
+ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
+ * may differ by now due to racing.
+ */
+ dst->user_cpus_ptr = NULL;
+
+ /*
+ * This check is racy and losing the race is a valid situation.
+ * It is not worth the extra overhead of taking the pi_lock on
+ * every fork/clone.
+ */
if (!src->user_cpus_ptr)
return 0;
- dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
- if (!dst->user_cpus_ptr)
+ user_mask = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
+ if (!user_mask)
return -ENOMEM;
- /* Use pi_lock to protect content of user_cpus_ptr */
+ /*
+ * Use pi_lock to protect content of user_cpus_ptr
+ *
+ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
+ * do_set_cpus_allowed().
+ */
raw_spin_lock_irqsave(&src->pi_lock, flags);
- cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ if (src->user_cpus_ptr) {
+ swap(dst->user_cpus_ptr, user_mask);
+ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ }
raw_spin_unlock_irqrestore(&src->pi_lock, flags);
+
+ if (unlikely(user_mask))
+ kfree(user_mask);
+
return 0;
}
--
2.31.1
From: Baolin Wang <baolin.wang(a)linux.alibaba.com>
[ Upstream commit fac35ba763ed07ba93154c95ffc0c4a55023707f ]
On some architectures (like ARM64), it can support CONT-PTE/PMD size
hugetlb, which means it can support not only PMD/PUD size hugetlb (2M and
1G), but also CONT-PTE/PMD size(64K and 32M) if a 4K page size specified.
So when looking up a CONT-PTE size hugetlb page by follow_page(), it will
use pte_offset_map_lock() to get the pte entry lock for the CONT-PTE size
hugetlb in follow_page_pte(). However this pte entry lock is incorrect
for the CONT-PTE size hugetlb, since we should use huge_pte_lock() to get
the correct lock, which is mm->page_table_lock.
That means the pte entry of the CONT-PTE size hugetlb under current pte
lock is unstable in follow_page_pte(), we can continue to migrate or
poison the pte entry of the CONT-PTE size hugetlb, which can cause some
potential race issues, even though they are under the 'pte lock'.
For example, suppose thread A is trying to look up a CONT-PTE size hugetlb
page by move_pages() syscall under the lock, however antoher thread B can
migrate the CONT-PTE hugetlb page at the same time, which will cause
thread A to get an incorrect page, if thread A also wants to do page
migration, then data inconsistency error occurs.
Moreover we have the same issue for CONT-PMD size hugetlb in
follow_huge_pmd().
To fix above issues, rename the follow_huge_pmd() as follow_huge_pmd_pte()
to handle PMD and PTE level size hugetlb, which uses huge_pte_lock() to
get the correct pte entry lock to make the pte entry stable.
Mike said:
Support for CONT_PMD/_PTE was added with bb9dd3df8ee9 ("arm64: hugetlb:
refactor find_num_contig()"). Patch series "Support for contiguous pte
hugepages", v4. However, I do not believe these code paths were
executed until migration support was added with 5480280d3f2d ("arm64/mm:
enable HugeTLB migration for contiguous bit HugeTLB pages") I would go
with 5480280d3f2d for the Fixes: targe.
Link: https://lkml.kernel.org/r/635f43bdd85ac2615a58405da82b4d33c6e5eb05.16620175…
Fixes: 5480280d3f2d ("arm64/mm: enable HugeTLB migration for contiguous bit HugeTLB pages")
Signed-off-by: Baolin Wang <baolin.wang(a)linux.alibaba.com>
Suggested-by: Mike Kravetz <mike.kravetz(a)oracle.com>
Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com>
Cc: David Hildenbrand <david(a)redhat.com>
Cc: Muchun Song <songmuchun(a)bytedance.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
[5.4: Fixup contextual diffs before pin_user_pages()]
Signed-off-by: Samuel Mendoza-Jonas <samjonas(a)amazon.com>
---
include/linux/hugetlb.h | 6 +++---
mm/gup.c | 13 ++++++++++++-
mm/hugetlb.c | 28 ++++++++++++++--------------
3 files changed, 29 insertions(+), 18 deletions(-)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index cef70d6e1657..c7507135c2a0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -127,8 +127,8 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
struct page *follow_huge_pd(struct vm_area_struct *vma,
unsigned long address, hugepd_t hpd,
int flags, int pdshift);
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
- pmd_t *pmd, int flags);
+struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address,
+ int flags);
struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
pud_t *pud, int flags);
struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
@@ -175,7 +175,7 @@ static inline void hugetlb_show_meminfo(void)
{
}
#define follow_huge_pd(vma, addr, hpd, flags, pdshift) NULL
-#define follow_huge_pmd(mm, addr, pmd, flags) NULL
+#define follow_huge_pmd_pte(vma, addr, flags) NULL
#define follow_huge_pud(mm, addr, pud, flags) NULL
#define follow_huge_pgd(mm, addr, pgd, flags) NULL
#define prepare_hugepage_range(file, addr, len) (-EINVAL)
diff --git a/mm/gup.c b/mm/gup.c
index 3ef769529548..98bd5e0a51c8 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -188,6 +188,17 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
spinlock_t *ptl;
pte_t *ptep, pte;
+ /*
+ * Considering PTE level hugetlb, like continuous-PTE hugetlb on
+ * ARM64 architecture.
+ */
+ if (is_vm_hugetlb_page(vma)) {
+ page = follow_huge_pmd_pte(vma, address, flags);
+ if (page)
+ return page;
+ return no_page_table(vma, flags);
+ }
+
retry:
if (unlikely(pmd_bad(*pmd)))
return no_page_table(vma, flags);
@@ -333,7 +344,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
if (pmd_none(pmdval))
return no_page_table(vma, flags);
if (pmd_huge(pmdval) && vma->vm_flags & VM_HUGETLB) {
- page = follow_huge_pmd(mm, address, pmd, flags);
+ page = follow_huge_pmd_pte(vma, address, flags);
if (page)
return page;
return no_page_table(vma, flags);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2126d78f053d..177dfd03af4e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5157,30 +5157,30 @@ follow_huge_pd(struct vm_area_struct *vma,
}
struct page * __weak
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
- pmd_t *pmd, int flags)
+follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags)
{
+ struct hstate *h = hstate_vma(vma);
+ struct mm_struct *mm = vma->vm_mm;
struct page *page = NULL;
spinlock_t *ptl;
- pte_t pte;
+ pte_t *ptep, pte;
+
retry:
- ptl = pmd_lockptr(mm, pmd);
- spin_lock(ptl);
- /*
- * make sure that the address range covered by this pmd is not
- * unmapped from other threads.
- */
- if (!pmd_huge(*pmd))
- goto out;
- pte = huge_ptep_get((pte_t *)pmd);
+ ptep = huge_pte_offset(mm, address, huge_page_size(h));
+ if (!ptep)
+ return NULL;
+
+ ptl = huge_pte_lock(h, mm, ptep);
+ pte = huge_ptep_get(ptep);
if (pte_present(pte)) {
- page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
+ page = pte_page(pte) +
+ ((address & ~huge_page_mask(h)) >> PAGE_SHIFT);
if (flags & FOLL_GET)
get_page(page);
} else {
if (is_hugetlb_entry_migration(pte)) {
spin_unlock(ptl);
- __migration_entry_wait(mm, (pte_t *)pmd, ptl);
+ __migration_entry_wait(mm, ptep, ptl);
goto retry;
}
/*
--
2.25.1