From: Dmitry Safonov <dima@arista.com>
To: linux-kernel@vger.kernel.org
Cc: Dmitry Safonov <0x7f454c46@gmail.com>,
Dmitry Safonov <dima@arista.com>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Andrew Morton <akpm@linux-foundation.org>,
Andy Lutomirski <luto@kernel.org>, Arnd Bergmann <arnd@arndb.de>,
Borislav Petkov <bp@alien8.de>,
Catalin Marinas <catalin.marinas@arm.com>,
Christophe Leroy <christophe.leroy@csgroup.eu>,
Guo Ren <guoren@kernel.org>, "H. Peter Anvin" <hpa@zytor.com>,
Ingo Molnar <mingo@redhat.com>, Oleg Nesterov <oleg@redhat.com>,
Russell King <linux@armlinux.org.uk>,
Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
Thomas Gleixner <tglx@linutronix.de>,
Vincenzo Frascino <vincenzo.frascino@arm.com>,
Will Deacon <will@kernel.org>,
x86@kernel.org, linux-mips@vger.kernel.org
Subject: [PATCH v3 16/23] mm: Add vdso_base in mm_struct
Date: Fri, 11 Jun 2021 19:02:35 +0100 [thread overview]
Message-ID: <20210611180242.711399-17-dima@arista.com> (raw)
In-Reply-To: <20210611180242.711399-1-dima@arista.com>
Instead of having every architecture to define vdso_base/vdso_addr etc,
provide a generic mechanism to track vdso_base for landing in userspace.
It'll minimize per-architecture difference, the number of callbacks to
provide.
Originally, it started from thread [1] where the need for .close()
callback on vm_special_mapping was pointed, this generic code besides
removing duplicated .mremap() callbacks provides a cheaper way to
support munmap() on vdso mappings without introducing .close() callbacks
for every architecture (which would bring even more code duplication).
[1]: https://lore.kernel.org/linux-arch/CAJwJo6ZANqYkSHbQ+3b+Fi_VT80MtrzEV5yreQAWx-L8j8x2zA@mail.gmail.com/
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: linux-mips@vger.kernel.org
Signed-off-by: Dmitry Safonov <dima@arista.com>
---
arch/Kconfig | 3 +++
arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 3 ++-
fs/aio.c | 3 ++-
include/linux/mm.h | 3 ++-
include/linux/mm_types.h | 17 +++++++++++++++++
kernel/fork.c | 1 +
mm/mmap.c | 19 ++++++++++++++++++-
mm/mremap.c | 2 +-
8 files changed, 46 insertions(+), 5 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index c45b770d3579..0e648a1ae412 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1235,6 +1235,9 @@ config HAVE_SPARSE_SYSCALL_NR
config ARCH_HAS_VDSO_DATA
bool
+config ARCH_HAS_VDSO_BASE
+ bool
+
config HAVE_STATIC_CALL
bool
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 05a89e33fde2..5ab191855816 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -1458,7 +1458,8 @@ static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
return 0;
}
-static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
+static int pseudo_lock_dev_mremap(struct vm_area_struct *old_vma,
+ struct vm_area_struct *new_vma)
{
/* Not supported */
return -EINVAL;
diff --git a/fs/aio.c b/fs/aio.c
index 76ce0cc3ee4e..0b27e9300d0f 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -323,7 +323,8 @@ static void aio_free_ring(struct kioctx *ctx)
}
}
-static int aio_ring_mremap(struct vm_area_struct *vma)
+static int aio_ring_mremap(struct vm_area_struct *old_vma,
+ struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct mm_struct *mm = vma->vm_mm;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c274f75efcf9..6ef91b337f9d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -589,7 +589,8 @@ struct vm_operations_struct {
void (*close)(struct vm_area_struct * area);
/* Called any time before splitting to check if it's allowed */
int (*may_split)(struct vm_area_struct *area, unsigned long addr);
- int (*mremap)(struct vm_area_struct *area);
+ int (*mremap)(struct vm_area_struct *old_vma,
+ struct vm_area_struct *new_vma);
/*
* Called by mprotect() to make driver-specific permission
* checks before mprotect() is finalised. The VMA must not
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e9c5f2051f08..49ad34410132 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -497,6 +497,16 @@ struct mm_struct {
/* Architecture-specific MM context */
mm_context_t context;
+#ifdef CONFIG_ARCH_HAS_VDSO_BASE
+ /*
+ * Address of special mapping VMA to land after processing
+ * a signal. Reads are unprotected: if a thread unmaps or
+ * mremaps the mapping while another thread is processing
+ * a signal, it can segfault while landing.
+ */
+ void __user *vdso_base;
+#endif
+#define UNMAPPED_VDSO_BASE TASK_SIZE_MAX
unsigned long flags; /* Must use atomic bitops to access */
@@ -598,6 +608,13 @@ static inline void init_tlb_flush_pending(struct mm_struct *mm)
atomic_set(&mm->tlb_flush_pending, 0);
}
+static inline void init_vdso_base(struct mm_struct *mm)
+{
+#ifdef CONFIG_ARCH_HAS_VDSO_BASE
+ mm->vdso_base = (void __user *)UNMAPPED_VDSO_BASE;
+#endif
+}
+
static inline void inc_tlb_flush_pending(struct mm_struct *mm)
{
atomic_inc(&mm->tlb_flush_pending);
diff --git a/kernel/fork.c b/kernel/fork.c
index dc06afd725cb..eb4ad74d042e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1082,6 +1082,7 @@ struct mm_struct *mm_alloc(void)
return NULL;
memset(mm, 0, sizeof(*mm));
+ init_vdso_base(mm);
return mm_init(mm, current, current_user_ns());
}
diff --git a/mm/mmap.c b/mm/mmap.c
index 4f0d62409b1c..5d1ffce51119 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3381,11 +3381,25 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
static vm_fault_t special_mapping_fault(struct vm_fault *vmf);
+static void update_vdso_base(struct vm_area_struct *old_vma,
+ unsigned long new_addr)
+{
+#ifdef CONFIG_ARCH_HAS_VDSO_BASE
+ struct mm_struct *mm = old_vma->vm_mm;
+
+ if (WARN_ON_ONCE(!mm))
+ return;
+ if (old_vma->vm_start == (unsigned long)mm->vdso_base)
+ mm->vdso_base = (void __user *)new_addr;
+#endif
+}
+
/*
* Having a close hook prevents vma merging regardless of flags.
*/
static void special_mapping_close(struct vm_area_struct *vma)
{
+ update_vdso_base(vma, UNMAPPED_VDSO_BASE);
}
static const char *special_mapping_name(struct vm_area_struct *vma)
@@ -3393,7 +3407,8 @@ static const char *special_mapping_name(struct vm_area_struct *vma)
return ((struct vm_special_mapping *)vma->vm_private_data)->name;
}
-static int special_mapping_mremap(struct vm_area_struct *new_vma)
+static int special_mapping_mremap(struct vm_area_struct *old_vma,
+ struct vm_area_struct *new_vma)
{
struct vm_special_mapping *sm = new_vma->vm_private_data;
@@ -3403,6 +3418,8 @@ static int special_mapping_mremap(struct vm_area_struct *new_vma)
if (sm->mremap)
sm->mremap(sm, new_vma);
+ update_vdso_base(old_vma, new_vma->vm_start);
+
return 0;
}
diff --git a/mm/mremap.c b/mm/mremap.c
index 47c255b60150..d28ba49d607c 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -545,7 +545,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
if (moved_len < old_len) {
err = -ENOMEM;
} else if (vma->vm_ops && vma->vm_ops->mremap) {
- err = vma->vm_ops->mremap(new_vma);
+ err = vma->vm_ops->mremap(vma, new_vma);
}
if (unlikely(err)) {
--
2.31.1
next prev parent reply other threads:[~2021-06-11 18:03 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-11 18:02 [PATCH v3 00/23] Add generic vdso_base tracking Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 01/23] x86/elf: Check in_x32_syscall() in compat_arch_setup_additional_pages() Dmitry Safonov
2021-06-19 20:41 ` Thomas Gleixner
2021-06-21 20:59 ` Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 02/23] elf: Move arch_setup_additional_pages() to generic elf.h Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 03/23] arm/elf: Remove needless ifdef CONFIG_MMU Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 04/23] arm64: Use in_compat_task() in arch_setup_additional_pages() Dmitry Safonov
2021-06-15 10:21 ` Will Deacon
2021-06-11 18:02 ` [PATCH v3 05/23] x86: Remove compat_arch_setup_additional_pages() Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 06/23] elf: " Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 07/23] vdso: Set mm->context.vdso only on success of _install_special_mapping() Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 08/23] elf/vdso: Modify arch_setup_additional_pages() parameters Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 09/23] elf: Use sysinfo_ehdr in ARCH_DLINFO() Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 10/23] arm/vdso: Remove vdso pointer from mm->context Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 11/23] s390/vdso: Remove vdso_base " Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 12/23] sparc/vdso: Remove vdso " Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 13/23] mm/mmap: Make vm_special_mapping::mremap return void Dmitry Safonov
2021-06-17 7:20 ` Christophe Leroy
2021-06-21 21:12 ` Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 14/23] x86/signal: Land on &frame->retcode when vdso isn't mapped Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 15/23] x86/signal: Check if vdso_image_32 is mapped before trying to land on it Dmitry Safonov
2021-06-11 18:02 ` Dmitry Safonov [this message]
2021-06-11 18:02 ` [PATCH v3 17/23] x86/vdso: Migrate to generic vdso_base Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 18/23] arm/vdso: " Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 19/23] arm64/vdso: Migrate compat signals " Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 20/23] arm64/vdso: Migrate native " Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 21/23] mips/vdso: Migrate " Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 22/23] powerpc/vdso: Migrate native signals " Dmitry Safonov
2021-06-15 12:52 ` Michael Ellerman
2021-06-17 6:30 ` Christophe Leroy
2021-06-17 6:36 ` Christophe Leroy
2021-06-17 7:34 ` Christophe Leroy
2021-06-21 21:22 ` Dmitry Safonov
2021-06-11 18:02 ` [PATCH v3 23/23] x86/vdso/selftest: Add a test for unmapping vDSO Dmitry Safonov
2021-06-11 18:21 ` Shuah Khan
2021-06-11 18:37 ` Dmitry Safonov
2021-06-11 18:43 ` Shuah Khan
2021-06-17 9:13 ` [PATCH v3 00/23] Add generic vdso_base tracking Christophe Leroy
2021-06-21 21:57 ` Dmitry Safonov
2022-03-09 15:41 ` Christophe Leroy
2022-03-10 21:17 ` Dmitry Safonov
2022-08-19 9:17 ` Christophe Leroy
2022-08-23 19:13 ` Dmitry Safonov
2023-10-11 10:28 ` Christophe Leroy
2023-10-11 23:20 ` H. Peter Anvin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210611180242.711399-17-dima@arista.com \
--to=dima@arista.com \
--cc=0x7f454c46@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=bp@alien8.de \
--cc=catalin.marinas@arm.com \
--cc=christophe.leroy@csgroup.eu \
--cc=guoren@kernel.org \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mips@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=oleg@redhat.com \
--cc=tglx@linutronix.de \
--cc=tsbogend@alpha.franken.de \
--cc=vincenzo.frascino@arm.com \
--cc=viro@zeniv.linux.org.uk \
--cc=will@kernel.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).