* [patch 01/10] mm/vmstat: protect per cpu variables with preempt disable on RT
2021-09-08 22:17 incoming Andrew Morton
@ 2021-09-08 22:17 ` Andrew Morton
2021-09-08 22:18 ` [patch 02/10] mm: migrate: introduce a local variable to get the number of pages Andrew Morton
` (8 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:17 UTC (permalink / raw)
To: akpm, hughd, linux-mm, mgorman, mingo, mm-commits, tglx,
torvalds, vbabka
From: Ingo Molnar <mingo@elte.hu>
Subject: mm/vmstat: protect per cpu variables with preempt disable on RT
Disable preemption on -RT for the vmstat code. On vanila the code runs in
IRQ-off regions while on -RT it may not when stats are updated under a
local_lock. "preempt_disable" ensures that the same resources is not
updated in parallel due to preemption.
This patch differs from the preempt-rt version where __count_vm_event and
__count_vm_events are also protected. The counters are explicitly
"allowed to be to be racy" so there is no need to protect them from
preemption. Only the accurate page stats that are updated by a
read-modify-write need protection. This patch also differs in that a
preempt_[en|dis]able_rt helper is not used. As vmstat is the only user of
the helper, it was suggested that it be open-coded in vmstat.c instead of
risking the helper being used in unnecessary contexts.
Link: https://lkml.kernel.org/r/20210805160019.1137-2-mgorman@techsingularity.net
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/vmstat.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 48 insertions(+)
--- a/mm/vmstat.c~mm-vmstat-protect-per-cpu-variables-with-preempt-disable-on-rt
+++ a/mm/vmstat.c
@@ -319,6 +319,16 @@ void __mod_zone_page_state(struct zone *
long x;
long t;
+ /*
+ * Accurate vmstat updates require a RMW. On !PREEMPT_RT kernels,
+ * atomicity is provided by IRQs being disabled -- either explicitly
+ * or via local_lock_irq. On PREEMPT_RT, local_lock_irq only disables
+ * CPU migrations and preemption potentially corrupts a counter so
+ * disable preemption.
+ */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
+
x = delta + __this_cpu_read(*p);
t = __this_cpu_read(pcp->stat_threshold);
@@ -328,6 +338,9 @@ void __mod_zone_page_state(struct zone *
x = 0;
}
__this_cpu_write(*p, x);
+
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
}
EXPORT_SYMBOL(__mod_zone_page_state);
@@ -350,6 +363,10 @@ void __mod_node_page_state(struct pglist
delta >>= PAGE_SHIFT;
}
+ /* See __mod_node_page_state */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
+
x = delta + __this_cpu_read(*p);
t = __this_cpu_read(pcp->stat_threshold);
@@ -359,6 +376,9 @@ void __mod_node_page_state(struct pglist
x = 0;
}
__this_cpu_write(*p, x);
+
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
}
EXPORT_SYMBOL(__mod_node_page_state);
@@ -391,6 +411,10 @@ void __inc_zone_state(struct zone *zone,
s8 __percpu *p = pcp->vm_stat_diff + item;
s8 v, t;
+ /* See __mod_node_page_state */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
+
v = __this_cpu_inc_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v > t)) {
@@ -399,6 +423,9 @@ void __inc_zone_state(struct zone *zone,
zone_page_state_add(v + overstep, zone, item);
__this_cpu_write(*p, -overstep);
}
+
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
}
void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
@@ -409,6 +436,10 @@ void __inc_node_state(struct pglist_data
VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+ /* See __mod_node_page_state */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
+
v = __this_cpu_inc_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v > t)) {
@@ -417,6 +448,9 @@ void __inc_node_state(struct pglist_data
node_page_state_add(v + overstep, pgdat, item);
__this_cpu_write(*p, -overstep);
}
+
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
}
void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
@@ -437,6 +471,10 @@ void __dec_zone_state(struct zone *zone,
s8 __percpu *p = pcp->vm_stat_diff + item;
s8 v, t;
+ /* See __mod_node_page_state */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
+
v = __this_cpu_dec_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v < - t)) {
@@ -445,6 +483,9 @@ void __dec_zone_state(struct zone *zone,
zone_page_state_add(v - overstep, zone, item);
__this_cpu_write(*p, overstep);
}
+
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
}
void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
@@ -455,6 +496,10 @@ void __dec_node_state(struct pglist_data
VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+ /* See __mod_node_page_state */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
+
v = __this_cpu_dec_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v < - t)) {
@@ -463,6 +508,9 @@ void __dec_node_state(struct pglist_data
node_page_state_add(v - overstep, pgdat, item);
__this_cpu_write(*p, overstep);
}
+
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
}
void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
_
^ permalink raw reply [flat|nested] 11+ messages in thread* [patch 02/10] mm: migrate: introduce a local variable to get the number of pages
2021-09-08 22:17 incoming Andrew Morton
2021-09-08 22:17 ` [patch 01/10] mm/vmstat: protect per cpu variables with preempt disable on RT Andrew Morton
@ 2021-09-08 22:18 ` Andrew Morton
2021-09-08 22:18 ` [patch 03/10] mm: migrate: fix the incorrect function name in comments Andrew Morton
` (7 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:18 UTC (permalink / raw)
To: akpm, apopple, baolin.wang, linux-mm, mm-commits, shy828301,
torvalds, willy
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Subject: mm: migrate: introduce a local variable to get the number of pages
Use thp_nr_pages() instead of compound_nr() to get the number of pages for
THP page, meanwhile introducing a local variable 'nr_pages' to avoid
getting the number of pages repeatedly.
Link: https://lkml.kernel.org/r/a8e331ac04392ee230c79186330fb05e86a2aa77.1629447552.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/migrate.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
--- a/mm/migrate.c~mm-migrate-introduce-a-local-variable-to-get-the-number-of-pages
+++ a/mm/migrate.c
@@ -2107,6 +2107,7 @@ out:
static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
{
int page_lru;
+ int nr_pages = thp_nr_pages(page);
VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page);
@@ -2115,7 +2116,7 @@ static int numamigrate_isolate_page(pg_d
return 0;
/* Avoid migrating to a node that is nearly full */
- if (!migrate_balanced_pgdat(pgdat, compound_nr(page)))
+ if (!migrate_balanced_pgdat(pgdat, nr_pages))
return 0;
if (isolate_lru_page(page))
@@ -2123,7 +2124,7 @@ static int numamigrate_isolate_page(pg_d
page_lru = page_is_file_lru(page);
mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru,
- thp_nr_pages(page));
+ nr_pages);
/*
* Isolating the page has taken another reference, so the
_
^ permalink raw reply [flat|nested] 11+ messages in thread* [patch 03/10] mm: migrate: fix the incorrect function name in comments
2021-09-08 22:17 incoming Andrew Morton
2021-09-08 22:17 ` [patch 01/10] mm/vmstat: protect per cpu variables with preempt disable on RT Andrew Morton
2021-09-08 22:18 ` [patch 02/10] mm: migrate: introduce a local variable to get the number of pages Andrew Morton
@ 2021-09-08 22:18 ` Andrew Morton
2021-09-08 22:18 ` [patch 04/10] mm: migrate: change to use bool type for 'page_was_mapped' Andrew Morton
` (6 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:18 UTC (permalink / raw)
To: akpm, apopple, baolin.wang, linux-mm, mm-commits, shy828301,
torvalds, willy
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Subject: mm: migrate: fix the incorrect function name in comments
since commit a98a2f0c8ce1 ("mm/rmap: split migration into its own
function"), the migration ptes establishment has been split into a
separate try_to_migrate() function, thus update the related comments.
Link: https://lkml.kernel.org/r/5b824bad6183259c916ae6cf42f81d14c6118b06.1629447552.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/migrate.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/migrate.c~mm-migrate-fix-the-incorrect-function-name-in-comments
+++ a/mm/migrate.c
@@ -1008,7 +1008,7 @@ static int __unmap_and_move(struct page
}
/*
- * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
+ * By try_to_migrate(), page->mapcount goes down to 0 here. In this case,
* we cannot notice that anon_vma is freed while we migrates a page.
* This get_anon_vma() delays freeing anon_vma pointer until the end
* of migration. File cache pages are no problem because of page_lock()
_
^ permalink raw reply [flat|nested] 11+ messages in thread* [patch 04/10] mm: migrate: change to use bool type for 'page_was_mapped'
2021-09-08 22:17 incoming Andrew Morton
` (2 preceding siblings ...)
2021-09-08 22:18 ` [patch 03/10] mm: migrate: fix the incorrect function name in comments Andrew Morton
@ 2021-09-08 22:18 ` Andrew Morton
2021-09-08 22:18 ` [patch 05/10] kexec: move locking into do_kexec_load Andrew Morton
` (5 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:18 UTC (permalink / raw)
To: akpm, apopple, baolin.wang, linux-mm, mm-commits, shy828301,
torvalds, willy
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Subject: mm: migrate: change to use bool type for 'page_was_mapped'
Change to use bool type for 'page_was_mapped' variable making it more
readable.
Link: https://lkml.kernel.org/r/ce1279df18d2c163998c403e0b5ec6d3f6f90f7a.1629447552.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/migrate.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/mm/migrate.c~mm-migrate-change-to-use-bool-type-for-page_was_mapped
+++ a/mm/migrate.c
@@ -960,7 +960,7 @@ static int __unmap_and_move(struct page
int force, enum migrate_mode mode)
{
int rc = -EAGAIN;
- int page_was_mapped = 0;
+ bool page_was_mapped = false;
struct anon_vma *anon_vma = NULL;
bool is_lru = !__PageMovable(page);
@@ -1063,7 +1063,7 @@ static int __unmap_and_move(struct page
VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
page);
try_to_migrate(page, 0);
- page_was_mapped = 1;
+ page_was_mapped = true;
}
if (!page_mapped(page))
_
^ permalink raw reply [flat|nested] 11+ messages in thread* [patch 05/10] kexec: move locking into do_kexec_load
2021-09-08 22:17 incoming Andrew Morton
` (3 preceding siblings ...)
2021-09-08 22:18 ` [patch 04/10] mm: migrate: change to use bool type for 'page_was_mapped' Andrew Morton
@ 2021-09-08 22:18 ` Andrew Morton
2021-09-08 22:18 ` [patch 06/10] kexec: avoid compat_alloc_user_space Andrew Morton
` (4 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:18 UTC (permalink / raw)
To: akpm, arnd, benh, borntraeger, bp, catalin.marinas, davem,
deller, ebiederm, feng.tang, gor, hca, hch, hch, hpa,
James.Bottomley, linux-mm, mingo, mm-commits, mpe, paulus, tglx,
torvalds, tsbogend, viro, will
From: Arnd Bergmann <arnd@arndb.de>
Subject: kexec: move locking into do_kexec_load
Patch series "compat: remove compat_alloc_user_space", v5.
Going through compat_alloc_user_space() to convert indirect system call
arguments tends to add complexity compared to handling the native and
compat logic in the same code.
This patch (of 6):
The locking is the same between the native and compat version of
sys_kexec_load(), so it can be done in the common implementation to reduce
duplication.
Link: https://lkml.kernel.org/r/20210727144859.4150043-1-arnd@kernel.org
Link: https://lkml.kernel.org/r/20210727144859.4150043-2-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Co-developed-by: Eric Biederman <ebiederm@xmission.com>
Co-developed-by: Christoph Hellwig <hch@infradead.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/kexec.c | 44 ++++++++++++++++----------------------------
1 file changed, 16 insertions(+), 28 deletions(-)
--- a/kernel/kexec.c~kexec-move-locking-into-do_kexec_load
+++ a/kernel/kexec.c
@@ -110,6 +110,17 @@ static int do_kexec_load(unsigned long e
unsigned long i;
int ret;
+ /*
+ * Because we write directly to the reserved memory region when loading
+ * crash kernels we need a mutex here to prevent multiple crash kernels
+ * from attempting to load simultaneously, and to prevent a crash kernel
+ * from loading over the top of a in use crash kernel.
+ *
+ * KISS: always take the mutex.
+ */
+ if (!mutex_trylock(&kexec_mutex))
+ return -EBUSY;
+
if (flags & KEXEC_ON_CRASH) {
dest_image = &kexec_crash_image;
if (kexec_crash_image)
@@ -121,7 +132,8 @@ static int do_kexec_load(unsigned long e
if (nr_segments == 0) {
/* Uninstall image */
kimage_free(xchg(dest_image, NULL));
- return 0;
+ ret = 0;
+ goto out_unlock;
}
if (flags & KEXEC_ON_CRASH) {
/*
@@ -134,7 +146,7 @@ static int do_kexec_load(unsigned long e
ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags);
if (ret)
- return ret;
+ goto out_unlock;
if (flags & KEXEC_PRESERVE_CONTEXT)
image->preserve_context = 1;
@@ -171,6 +183,8 @@ out:
arch_kexec_protect_crashkres();
kimage_free(image);
+out_unlock:
+ mutex_unlock(&kexec_mutex);
return ret;
}
@@ -247,21 +261,8 @@ SYSCALL_DEFINE4(kexec_load, unsigned lon
((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT))
return -EINVAL;
- /* Because we write directly to the reserved memory
- * region when loading crash kernels we need a mutex here to
- * prevent multiple crash kernels from attempting to load
- * simultaneously, and to prevent a crash kernel from loading
- * over the top of a in use crash kernel.
- *
- * KISS: always take the mutex.
- */
- if (!mutex_trylock(&kexec_mutex))
- return -EBUSY;
-
result = do_kexec_load(entry, nr_segments, segments, flags);
- mutex_unlock(&kexec_mutex);
-
return result;
}
@@ -301,21 +302,8 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compa
return -EFAULT;
}
- /* Because we write directly to the reserved memory
- * region when loading crash kernels we need a mutex here to
- * prevent multiple crash kernels from attempting to load
- * simultaneously, and to prevent a crash kernel from loading
- * over the top of a in use crash kernel.
- *
- * KISS: always take the mutex.
- */
- if (!mutex_trylock(&kexec_mutex))
- return -EBUSY;
-
result = do_kexec_load(entry, nr_segments, ksegments, flags);
- mutex_unlock(&kexec_mutex);
-
return result;
}
#endif
_
^ permalink raw reply [flat|nested] 11+ messages in thread* [patch 06/10] kexec: avoid compat_alloc_user_space
2021-09-08 22:17 incoming Andrew Morton
` (4 preceding siblings ...)
2021-09-08 22:18 ` [patch 05/10] kexec: move locking into do_kexec_load Andrew Morton
@ 2021-09-08 22:18 ` Andrew Morton
2021-09-08 22:18 ` [patch 07/10] mm: simplify compat_sys_move_pages Andrew Morton
` (3 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:18 UTC (permalink / raw)
To: akpm, arnd, benh, borntraeger, bp, catalin.marinas, davem,
deller, ebiederm, feng.tang, gor, hca, hch, hch, hpa,
James.Bottomley, linux-mm, mingo, mm-commits, mpe, paulus, tglx,
torvalds, tsbogend, viro, will
From: Arnd Bergmann <arnd@arndb.de>
Subject: kexec: avoid compat_alloc_user_space
kimage_alloc_init() expects a __user pointer, so compat_sys_kexec_load()
uses compat_alloc_user_space() to convert the layout and put it back onto
the user space caller stack.
Moving the user space access into the syscall handler directly actually
makes the code simpler, as the conversion for compat mode can now be done
on kernel memory.
Link: https://lkml.kernel.org/r/20210727144859.4150043-3-arnd@kernel.org
Link: https://lore.kernel.org/lkml/YPbtsU4GX6PL7%2F42@infradead.org/
Link: https://lore.kernel.org/lkml/m1y2cbzmnw.fsf@fess.ebiederm.org/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Co-developed-by: Eric Biederman <ebiederm@xmission.com>
Co-developed-by: Christoph Hellwig <hch@infradead.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/kexec.c | 61 +++++++++++++++++++----------------------------
1 file changed, 25 insertions(+), 36 deletions(-)
--- a/kernel/kexec.c~kexec-avoid-compat_alloc_user_space
+++ a/kernel/kexec.c
@@ -19,26 +19,9 @@
#include "kexec_internal.h"
-static int copy_user_segment_list(struct kimage *image,
- unsigned long nr_segments,
- struct kexec_segment __user *segments)
-{
- int ret;
- size_t segment_bytes;
-
- /* Read in the segments */
- image->nr_segments = nr_segments;
- segment_bytes = nr_segments * sizeof(*segments);
- ret = copy_from_user(image->segment, segments, segment_bytes);
- if (ret)
- ret = -EFAULT;
-
- return ret;
-}
-
static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
unsigned long nr_segments,
- struct kexec_segment __user *segments,
+ struct kexec_segment *segments,
unsigned long flags)
{
int ret;
@@ -58,10 +41,8 @@ static int kimage_alloc_init(struct kima
return -ENOMEM;
image->start = entry;
-
- ret = copy_user_segment_list(image, nr_segments, segments);
- if (ret)
- goto out_free_image;
+ image->nr_segments = nr_segments;
+ memcpy(image->segment, segments, nr_segments * sizeof(*segments));
if (kexec_on_panic) {
/* Enable special crash kernel control page alloc policy. */
@@ -104,7 +85,7 @@ out_free_image:
}
static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
- struct kexec_segment __user *segments, unsigned long flags)
+ struct kexec_segment *segments, unsigned long flags)
{
struct kimage **dest_image, *image;
unsigned long i;
@@ -250,7 +231,8 @@ static inline int kexec_load_check(unsig
SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
struct kexec_segment __user *, segments, unsigned long, flags)
{
- int result;
+ struct kexec_segment *ksegments;
+ unsigned long result;
result = kexec_load_check(nr_segments, flags);
if (result)
@@ -261,7 +243,12 @@ SYSCALL_DEFINE4(kexec_load, unsigned lon
((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT))
return -EINVAL;
- result = do_kexec_load(entry, nr_segments, segments, flags);
+ ksegments = memdup_user(segments, nr_segments * sizeof(ksegments[0]));
+ if (IS_ERR(ksegments))
+ return PTR_ERR(ksegments);
+
+ result = do_kexec_load(entry, nr_segments, ksegments, flags);
+ kfree(ksegments);
return result;
}
@@ -273,7 +260,7 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compa
compat_ulong_t, flags)
{
struct compat_kexec_segment in;
- struct kexec_segment out, __user *ksegments;
+ struct kexec_segment *ksegments;
unsigned long i, result;
result = kexec_load_check(nr_segments, flags);
@@ -286,24 +273,26 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compa
if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT)
return -EINVAL;
- ksegments = compat_alloc_user_space(nr_segments * sizeof(out));
+ ksegments = kmalloc_array(nr_segments, sizeof(ksegments[0]),
+ GFP_KERNEL);
+ if (!ksegments)
+ return -ENOMEM;
+
for (i = 0; i < nr_segments; i++) {
result = copy_from_user(&in, &segments[i], sizeof(in));
if (result)
- return -EFAULT;
+ goto fail;
- out.buf = compat_ptr(in.buf);
- out.bufsz = in.bufsz;
- out.mem = in.mem;
- out.memsz = in.memsz;
-
- result = copy_to_user(&ksegments[i], &out, sizeof(out));
- if (result)
- return -EFAULT;
+ ksegments[i].buf = compat_ptr(in.buf);
+ ksegments[i].bufsz = in.bufsz;
+ ksegments[i].mem = in.mem;
+ ksegments[i].memsz = in.memsz;
}
result = do_kexec_load(entry, nr_segments, ksegments, flags);
+fail:
+ kfree(ksegments);
return result;
}
#endif
_
^ permalink raw reply [flat|nested] 11+ messages in thread* [patch 07/10] mm: simplify compat_sys_move_pages
2021-09-08 22:17 incoming Andrew Morton
` (5 preceding siblings ...)
2021-09-08 22:18 ` [patch 06/10] kexec: avoid compat_alloc_user_space Andrew Morton
@ 2021-09-08 22:18 ` Andrew Morton
2021-09-08 22:18 ` [patch 08/10] mm: simplify compat numa syscalls Andrew Morton
` (2 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:18 UTC (permalink / raw)
To: akpm, arnd, benh, borntraeger, bp, catalin.marinas, davem,
deller, ebiederm, feng.tang, gor, hca, hch, hch, hpa,
James.Bottomley, linux-mm, mingo, mm-commits, mpe, paulus, tglx,
torvalds, tsbogend, viro, will
From: Arnd Bergmann <arnd@arndb.de>
Subject: mm: simplify compat_sys_move_pages
The compat move_pages() implementation uses compat_alloc_user_space() for
converting the pointer array. Moving the compat handling into the
function itself is a bit simpler and lets us avoid the
compat_alloc_user_space() call.
Link: https://lkml.kernel.org/r/20210727144859.4150043-4-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/migrate.c | 45 ++++++++++++++++++++++++++++++---------------
1 file changed, 30 insertions(+), 15 deletions(-)
--- a/mm/migrate.c~mm-simplify-compat_sys_move_pages
+++ a/mm/migrate.c
@@ -1900,6 +1900,23 @@ set_status:
mmap_read_unlock(mm);
}
+static int get_compat_pages_array(const void __user *chunk_pages[],
+ const void __user * __user *pages,
+ unsigned long chunk_nr)
+{
+ compat_uptr_t __user *pages32 = (compat_uptr_t __user *)pages;
+ compat_uptr_t p;
+ int i;
+
+ for (i = 0; i < chunk_nr; i++) {
+ if (get_user(p, pages32 + i))
+ return -EFAULT;
+ chunk_pages[i] = compat_ptr(p);
+ }
+
+ return 0;
+}
+
/*
* Determine the nodes of a user array of pages and store it in
* a user array of status.
@@ -1919,8 +1936,15 @@ static int do_pages_stat(struct mm_struc
if (chunk_nr > DO_PAGES_STAT_CHUNK_NR)
chunk_nr = DO_PAGES_STAT_CHUNK_NR;
- if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages)))
- break;
+ if (in_compat_syscall()) {
+ if (get_compat_pages_array(chunk_pages, pages,
+ chunk_nr))
+ break;
+ } else {
+ if (copy_from_user(chunk_pages, pages,
+ chunk_nr * sizeof(*chunk_pages)))
+ break;
+ }
do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status);
@@ -2025,23 +2049,14 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid,
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
- compat_uptr_t __user *, pages32,
+ compat_uptr_t __user *, pages,
const int __user *, nodes,
int __user *, status,
int, flags)
{
- const void __user * __user *pages;
- int i;
-
- pages = compat_alloc_user_space(nr_pages * sizeof(void *));
- for (i = 0; i < nr_pages; i++) {
- compat_uptr_t p;
-
- if (get_user(p, pages32 + i) ||
- put_user(compat_ptr(p), pages + i))
- return -EFAULT;
- }
- return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
+ return kernel_move_pages(pid, nr_pages,
+ (const void __user *__user *)pages,
+ nodes, status, flags);
}
#endif /* CONFIG_COMPAT */
_
^ permalink raw reply [flat|nested] 11+ messages in thread* [patch 08/10] mm: simplify compat numa syscalls
2021-09-08 22:17 incoming Andrew Morton
` (6 preceding siblings ...)
2021-09-08 22:18 ` [patch 07/10] mm: simplify compat_sys_move_pages Andrew Morton
@ 2021-09-08 22:18 ` Andrew Morton
2021-09-08 22:18 ` [patch 09/10] compat: remove some compat entry points Andrew Morton
2021-09-08 22:18 ` [patch 10/10] arch: remove compat_alloc_user_space Andrew Morton
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:18 UTC (permalink / raw)
To: akpm, arnd, benh, borntraeger, bp, catalin.marinas, davem,
deller, ebiederm, feng.tang, gor, hca, hch, hch, hpa,
James.Bottomley, linux-mm, mingo, mm-commits, mpe, paulus, tglx,
torvalds, tsbogend, viro, will
From: Arnd Bergmann <arnd@arndb.de>
Subject: mm: simplify compat numa syscalls
The compat implementations for mbind, get_mempolicy, set_mempolicy and
migrate_pages are just there to handle the subtly different layout of
bitmaps on 32-bit hosts.
The compat implementation however lacks some of the checks that are
present in the native one, in particular for checking that the extra bits
are all zero when user space has a larger mask size than the kernel.
Worse, those extra bits do not get cleared when copying in or out of the
kernel, which can lead to incorrect data as well.
Unify the implementation to handle the compat bitmap layout directly in
the get_nodes() and copy_nodes_to_user() helpers. Splitting out the
get_bitmap() helper from get_nodes() also helps readability of the native
case.
On x86, two additional problems are addressed by this: compat tasks can
pass a bitmap at the end of a mapping, causing a fault when reading across
the page boundary for a 64-bit word. x32 tasks might also run into
problems with get_mempolicy corrupting data when an odd number of 32-bit
words gets passed.
On parisc the migrate_pages() system call apparently had the wrong calling
convention, as big-endian architectures expect the words inside of a
bitmap to be swapped. This is not a problem though since parisc has no
NUMA support.
[arnd@arndb.de: fix mempolicy crash]
Link: https://lkml.kernel.org/r/20210730143417.3700653-1-arnd@kernel.org
Link: https://lore.kernel.org/lkml/YQPLG20V3dmOfq3a@osiris/
Link: https://lkml.kernel.org/r/20210727144859.4150043-5-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/compat.h | 17 +--
mm/mempolicy.c | 176 ++++++++++++---------------------------
2 files changed, 64 insertions(+), 129 deletions(-)
--- a/include/linux/compat.h~mm-simplify-compat-numa-syscalls
+++ a/include/linux/compat.h
@@ -395,14 +395,6 @@ struct compat_kexec_segment;
struct compat_mq_attr;
struct compat_msgbuf;
-#define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t))
-
-#define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG)
-
-long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
- unsigned long bitmap_size);
-long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
- unsigned long bitmap_size);
void copy_siginfo_to_external32(struct compat_siginfo *to,
const struct kernel_siginfo *from);
int copy_siginfo_from_user32(kernel_siginfo_t *to,
@@ -976,6 +968,15 @@ static inline bool in_compat_syscall(voi
#endif /* CONFIG_COMPAT */
+#define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t))
+
+#define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG)
+
+long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
+ unsigned long bitmap_size);
+long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
+ unsigned long bitmap_size);
+
/*
* Some legacy ABIs like the i386 one use less than natural alignment for 64-bit
* types, and will need special compat treatment for that. Most architectures
--- a/mm/mempolicy.c~mm-simplify-compat-numa-syscalls
+++ a/mm/mempolicy.c
@@ -1362,16 +1362,33 @@ mpol_out:
/*
* User space interface with variable sized bitmaps for nodelists.
*/
+static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask,
+ unsigned long maxnode)
+{
+ unsigned long nlongs = BITS_TO_LONGS(maxnode);
+ int ret;
+
+ if (in_compat_syscall())
+ ret = compat_get_bitmap(mask,
+ (const compat_ulong_t __user *)nmask,
+ maxnode);
+ else
+ ret = copy_from_user(mask, nmask,
+ nlongs * sizeof(unsigned long));
+
+ if (ret)
+ return -EFAULT;
+
+ if (maxnode % BITS_PER_LONG)
+ mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1;
+
+ return 0;
+}
/* Copy a node mask from user space. */
static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
unsigned long maxnode)
{
- unsigned long k;
- unsigned long t;
- unsigned long nlongs;
- unsigned long endmask;
-
--maxnode;
nodes_clear(*nodes);
if (maxnode == 0 || !nmask)
@@ -1379,49 +1396,29 @@ static int get_nodes(nodemask_t *nodes,
if (maxnode > PAGE_SIZE*BITS_PER_BYTE)
return -EINVAL;
- nlongs = BITS_TO_LONGS(maxnode);
- if ((maxnode % BITS_PER_LONG) == 0)
- endmask = ~0UL;
- else
- endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;
-
/*
* When the user specified more nodes than supported just check
- * if the non supported part is all zero.
- *
- * If maxnode have more longs than MAX_NUMNODES, check
- * the bits in that area first. And then go through to
- * check the rest bits which equal or bigger than MAX_NUMNODES.
- * Otherwise, just check bits [MAX_NUMNODES, maxnode).
+ * if the non supported part is all zero, one word at a time,
+ * starting at the end.
*/
- if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
- for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
- if (get_user(t, nmask + k))
- return -EFAULT;
- if (k == nlongs - 1) {
- if (t & endmask)
- return -EINVAL;
- } else if (t)
- return -EINVAL;
- }
- nlongs = BITS_TO_LONGS(MAX_NUMNODES);
- endmask = ~0UL;
- }
-
- if (maxnode > MAX_NUMNODES && MAX_NUMNODES % BITS_PER_LONG != 0) {
- unsigned long valid_mask = endmask;
+ while (maxnode > MAX_NUMNODES) {
+ unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG);
+ unsigned long t;
- valid_mask &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1);
- if (get_user(t, nmask + nlongs - 1))
+ if (get_bitmap(&t, &nmask[maxnode / BITS_PER_LONG], bits))
return -EFAULT;
- if (t & valid_mask)
+
+ if (maxnode - bits >= MAX_NUMNODES) {
+ maxnode -= bits;
+ } else {
+ maxnode = MAX_NUMNODES;
+ t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1);
+ }
+ if (t)
return -EINVAL;
}
- if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long)))
- return -EFAULT;
- nodes_addr(*nodes)[nlongs-1] &= endmask;
- return 0;
+ return get_bitmap(nodes_addr(*nodes), nmask, maxnode);
}
/* Copy a kernel node mask to user space */
@@ -1430,6 +1427,10 @@ static int copy_nodes_to_user(unsigned l
{
unsigned long copy = ALIGN(maxnode-1, 64) / 8;
unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long);
+ bool compat = in_compat_syscall();
+
+ if (compat)
+ nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t);
if (copy > nbytes) {
if (copy > PAGE_SIZE)
@@ -1437,7 +1438,13 @@ static int copy_nodes_to_user(unsigned l
if (clear_user((char __user *)mask + nbytes, copy - nbytes))
return -EFAULT;
copy = nbytes;
+ maxnode = nr_node_ids;
}
+
+ if (compat)
+ return compat_put_bitmap((compat_ulong_t __user *)mask,
+ nodes_addr(*nodes), maxnode);
+
return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
}
@@ -1649,72 +1656,22 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, in
compat_ulong_t, maxnode,
compat_ulong_t, addr, compat_ulong_t, flags)
{
- long err;
- unsigned long __user *nm = NULL;
- unsigned long nr_bits, alloc_size;
- DECLARE_BITMAP(bm, MAX_NUMNODES);
-
- nr_bits = min_t(unsigned long, maxnode-1, nr_node_ids);
- alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
-
- if (nmask)
- nm = compat_alloc_user_space(alloc_size);
-
- err = kernel_get_mempolicy(policy, nm, nr_bits+1, addr, flags);
-
- if (!err && nmask) {
- unsigned long copy_size;
- copy_size = min_t(unsigned long, sizeof(bm), alloc_size);
- err = copy_from_user(bm, nm, copy_size);
- /* ensure entire bitmap is zeroed */
- err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8);
- err |= compat_put_bitmap(nmask, bm, nr_bits);
- }
-
- return err;
+ return kernel_get_mempolicy(policy, (unsigned long __user *)nmask,
+ maxnode, addr, flags);
}
COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode)
{
- unsigned long __user *nm = NULL;
- unsigned long nr_bits, alloc_size;
- DECLARE_BITMAP(bm, MAX_NUMNODES);
-
- nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
- alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
-
- if (nmask) {
- if (compat_get_bitmap(bm, nmask, nr_bits))
- return -EFAULT;
- nm = compat_alloc_user_space(alloc_size);
- if (copy_to_user(nm, bm, alloc_size))
- return -EFAULT;
- }
-
- return kernel_set_mempolicy(mode, nm, nr_bits+1);
+ return kernel_set_mempolicy(mode, (unsigned long __user *)nmask, maxnode);
}
COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
compat_ulong_t, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode, compat_ulong_t, flags)
{
- unsigned long __user *nm = NULL;
- unsigned long nr_bits, alloc_size;
- nodemask_t bm;
-
- nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
- alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
-
- if (nmask) {
- if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits))
- return -EFAULT;
- nm = compat_alloc_user_space(alloc_size);
- if (copy_to_user(nm, nodes_addr(bm), alloc_size))
- return -EFAULT;
- }
-
- return kernel_mbind(start, len, mode, nm, nr_bits+1, flags);
+ return kernel_mbind(start, len, mode, (unsigned long __user *)nmask,
+ maxnode, flags);
}
COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid,
@@ -1722,32 +1679,9 @@ COMPAT_SYSCALL_DEFINE4(migrate_pages, co
const compat_ulong_t __user *, old_nodes,
const compat_ulong_t __user *, new_nodes)
{
- unsigned long __user *old = NULL;
- unsigned long __user *new = NULL;
- nodemask_t tmp_mask;
- unsigned long nr_bits;
- unsigned long size;
-
- nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES);
- size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
- if (old_nodes) {
- if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits))
- return -EFAULT;
- old = compat_alloc_user_space(new_nodes ? size * 2 : size);
- if (new_nodes)
- new = old + size / sizeof(unsigned long);
- if (copy_to_user(old, nodes_addr(tmp_mask), size))
- return -EFAULT;
- }
- if (new_nodes) {
- if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits))
- return -EFAULT;
- if (new == NULL)
- new = compat_alloc_user_space(size);
- if (copy_to_user(new, nodes_addr(tmp_mask), size))
- return -EFAULT;
- }
- return kernel_migrate_pages(pid, nr_bits + 1, old, new);
+ return kernel_migrate_pages(pid, maxnode,
+ (const unsigned long __user *)old_nodes,
+ (const unsigned long __user *)new_nodes);
}
#endif /* CONFIG_COMPAT */
_
^ permalink raw reply [flat|nested] 11+ messages in thread* [patch 09/10] compat: remove some compat entry points
2021-09-08 22:17 incoming Andrew Morton
` (7 preceding siblings ...)
2021-09-08 22:18 ` [patch 08/10] mm: simplify compat numa syscalls Andrew Morton
@ 2021-09-08 22:18 ` Andrew Morton
2021-09-08 22:18 ` [patch 10/10] arch: remove compat_alloc_user_space Andrew Morton
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:18 UTC (permalink / raw)
To: akpm, arnd, benh, borntraeger, bp, catalin.marinas, davem,
deller, ebiederm, feng.tang, gor, hca, hch, hch, hpa,
James.Bottomley, linux-mm, mingo, mm-commits, mpe, paulus, tglx,
torvalds, tsbogend, viro, will
From: Arnd Bergmann <arnd@arndb.de>
Subject: compat: remove some compat entry points
These are all handled correctly when calling the native system call entry
point, so remove the special cases.
Link: https://lkml.kernel.org/r/20210727144859.4150043-6-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/arm64/include/asm/unistd32.h | 10 ++---
arch/mips/kernel/syscalls/syscall_n32.tbl | 10 ++---
arch/mips/kernel/syscalls/syscall_o32.tbl | 10 ++---
arch/parisc/kernel/syscalls/syscall.tbl | 8 ++--
arch/powerpc/kernel/syscalls/syscall.tbl | 10 ++---
arch/s390/kernel/syscalls/syscall.tbl | 10 ++---
arch/sparc/kernel/syscalls/syscall.tbl | 10 ++---
arch/x86/entry/syscalls/syscall_32.tbl | 4 +-
arch/x86/entry/syscalls/syscall_64.tbl | 2 -
include/linux/compat.h | 20 ----------
include/uapi/asm-generic/unistd.h | 10 ++---
kernel/sys_ni.c | 5 --
mm/mempolicy.c | 37 --------------------
mm/migrate.c | 13 -------
14 files changed, 42 insertions(+), 117 deletions(-)
--- a/arch/arm64/include/asm/unistd32.h~compat-remove-some-compat-entry-points
+++ a/arch/arm64/include/asm/unistd32.h
@@ -649,11 +649,11 @@ __SYSCALL(__NR_inotify_add_watch, sys_in
#define __NR_inotify_rm_watch 318
__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
#define __NR_mbind 319
-__SYSCALL(__NR_mbind, compat_sys_mbind)
+__SYSCALL(__NR_mbind, sys_mbind)
#define __NR_get_mempolicy 320
-__SYSCALL(__NR_get_mempolicy, compat_sys_get_mempolicy)
+__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
#define __NR_set_mempolicy 321
-__SYSCALL(__NR_set_mempolicy, compat_sys_set_mempolicy)
+__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
#define __NR_openat 322
__SYSCALL(__NR_openat, compat_sys_openat)
#define __NR_mkdirat 323
@@ -699,7 +699,7 @@ __SYSCALL(__NR_tee, sys_tee)
#define __NR_vmsplice 343
__SYSCALL(__NR_vmsplice, sys_vmsplice)
#define __NR_move_pages 344
-__SYSCALL(__NR_move_pages, compat_sys_move_pages)
+__SYSCALL(__NR_move_pages, sys_move_pages)
#define __NR_getcpu 345
__SYSCALL(__NR_getcpu, sys_getcpu)
#define __NR_epoll_pwait 346
@@ -811,7 +811,7 @@ __SYSCALL(__NR_rseq, sys_rseq)
#define __NR_io_pgetevents 399
__SYSCALL(__NR_io_pgetevents, compat_sys_io_pgetevents)
#define __NR_migrate_pages 400
-__SYSCALL(__NR_migrate_pages, compat_sys_migrate_pages)
+__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
#define __NR_kexec_file_load 401
__SYSCALL(__NR_kexec_file_load, sys_kexec_file_load)
/* 402 is unused */
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl~compat-remove-some-compat-entry-points
+++ a/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -239,9 +239,9 @@
228 n32 clock_nanosleep sys_clock_nanosleep_time32
229 n32 tgkill sys_tgkill
230 n32 utimes sys_utimes_time32
-231 n32 mbind compat_sys_mbind
-232 n32 get_mempolicy compat_sys_get_mempolicy
-233 n32 set_mempolicy compat_sys_set_mempolicy
+231 n32 mbind sys_mbind
+232 n32 get_mempolicy sys_get_mempolicy
+233 n32 set_mempolicy sys_set_mempolicy
234 n32 mq_open compat_sys_mq_open
235 n32 mq_unlink sys_mq_unlink
236 n32 mq_timedsend sys_mq_timedsend_time32
@@ -258,7 +258,7 @@
247 n32 inotify_init sys_inotify_init
248 n32 inotify_add_watch sys_inotify_add_watch
249 n32 inotify_rm_watch sys_inotify_rm_watch
-250 n32 migrate_pages compat_sys_migrate_pages
+250 n32 migrate_pages sys_migrate_pages
251 n32 openat sys_openat
252 n32 mkdirat sys_mkdirat
253 n32 mknodat sys_mknodat
@@ -279,7 +279,7 @@
268 n32 sync_file_range sys_sync_file_range
269 n32 tee sys_tee
270 n32 vmsplice sys_vmsplice
-271 n32 move_pages compat_sys_move_pages
+271 n32 move_pages sys_move_pages
272 n32 set_robust_list compat_sys_set_robust_list
273 n32 get_robust_list compat_sys_get_robust_list
274 n32 kexec_load compat_sys_kexec_load
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl~compat-remove-some-compat-entry-points
+++ a/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -279,9 +279,9 @@
265 o32 clock_nanosleep sys_clock_nanosleep_time32
266 o32 tgkill sys_tgkill
267 o32 utimes sys_utimes_time32
-268 o32 mbind sys_mbind compat_sys_mbind
-269 o32 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
-270 o32 set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy
+268 o32 mbind sys_mbind
+269 o32 get_mempolicy sys_get_mempolicy
+270 o32 set_mempolicy sys_set_mempolicy
271 o32 mq_open sys_mq_open compat_sys_mq_open
272 o32 mq_unlink sys_mq_unlink
273 o32 mq_timedsend sys_mq_timedsend_time32
@@ -298,7 +298,7 @@
284 o32 inotify_init sys_inotify_init
285 o32 inotify_add_watch sys_inotify_add_watch
286 o32 inotify_rm_watch sys_inotify_rm_watch
-287 o32 migrate_pages sys_migrate_pages compat_sys_migrate_pages
+287 o32 migrate_pages sys_migrate_pages
288 o32 openat sys_openat compat_sys_openat
289 o32 mkdirat sys_mkdirat
290 o32 mknodat sys_mknodat
@@ -319,7 +319,7 @@
305 o32 sync_file_range sys_sync_file_range sys32_sync_file_range
306 o32 tee sys_tee
307 o32 vmsplice sys_vmsplice
-308 o32 move_pages sys_move_pages compat_sys_move_pages
+308 o32 move_pages sys_move_pages
309 o32 set_robust_list sys_set_robust_list compat_sys_set_robust_list
310 o32 get_robust_list sys_get_robust_list compat_sys_get_robust_list
311 o32 kexec_load sys_kexec_load compat_sys_kexec_load
--- a/arch/parisc/kernel/syscalls/syscall.tbl~compat-remove-some-compat-entry-points
+++ a/arch/parisc/kernel/syscalls/syscall.tbl
@@ -292,9 +292,9 @@
258 32 clock_nanosleep sys_clock_nanosleep_time32
258 64 clock_nanosleep sys_clock_nanosleep
259 common tgkill sys_tgkill
-260 common mbind sys_mbind compat_sys_mbind
-261 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
-262 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy
+260 common mbind sys_mbind
+261 common get_mempolicy sys_get_mempolicy
+262 common set_mempolicy sys_set_mempolicy
# 263 was vserver
264 common add_key sys_add_key
265 common request_key sys_request_key
@@ -331,7 +331,7 @@
292 64 sync_file_range sys_sync_file_range
293 common tee sys_tee
294 common vmsplice sys_vmsplice
-295 common move_pages sys_move_pages compat_sys_move_pages
+295 common move_pages sys_move_pages
296 common getcpu sys_getcpu
297 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait
298 common statfs64 sys_statfs64 compat_sys_statfs64
--- a/arch/powerpc/kernel/syscalls/syscall.tbl~compat-remove-some-compat-entry-points
+++ a/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -330,10 +330,10 @@
256 64 sys_debug_setcontext sys_ni_syscall
256 spu sys_debug_setcontext sys_ni_syscall
# 257 reserved for vserver
-258 nospu migrate_pages sys_migrate_pages compat_sys_migrate_pages
-259 nospu mbind sys_mbind compat_sys_mbind
-260 nospu get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
-261 nospu set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy
+258 nospu migrate_pages sys_migrate_pages
+259 nospu mbind sys_mbind
+260 nospu get_mempolicy sys_get_mempolicy
+261 nospu set_mempolicy sys_set_mempolicy
262 nospu mq_open sys_mq_open compat_sys_mq_open
263 nospu mq_unlink sys_mq_unlink
264 32 mq_timedsend sys_mq_timedsend_time32
@@ -381,7 +381,7 @@
298 common faccessat sys_faccessat
299 common get_robust_list sys_get_robust_list compat_sys_get_robust_list
300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list
-301 common move_pages sys_move_pages compat_sys_move_pages
+301 common move_pages sys_move_pages
302 common getcpu sys_getcpu
303 nospu epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait
304 32 utimensat sys_utimensat_time32
--- a/arch/s390/kernel/syscalls/syscall.tbl~compat-remove-some-compat-entry-points
+++ a/arch/s390/kernel/syscalls/syscall.tbl
@@ -274,9 +274,9 @@
265 common statfs64 sys_statfs64 compat_sys_statfs64
266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
267 common remap_file_pages sys_remap_file_pages sys_remap_file_pages
-268 common mbind sys_mbind compat_sys_mbind
-269 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
-270 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy
+268 common mbind sys_mbind sys_mbind
+269 common get_mempolicy sys_get_mempolicy sys_get_mempolicy
+270 common set_mempolicy sys_set_mempolicy sys_set_mempolicy
271 common mq_open sys_mq_open compat_sys_mq_open
272 common mq_unlink sys_mq_unlink sys_mq_unlink
273 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32
@@ -293,7 +293,7 @@
284 common inotify_init sys_inotify_init sys_inotify_init
285 common inotify_add_watch sys_inotify_add_watch sys_inotify_add_watch
286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch
-287 common migrate_pages sys_migrate_pages compat_sys_migrate_pages
+287 common migrate_pages sys_migrate_pages sys_migrate_pages
288 common openat sys_openat compat_sys_openat
289 common mkdirat sys_mkdirat sys_mkdirat
290 common mknodat sys_mknodat sys_mknodat
@@ -317,7 +317,7 @@
307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range
308 common tee sys_tee sys_tee
309 common vmsplice sys_vmsplice sys_vmsplice
-310 common move_pages sys_move_pages compat_sys_move_pages
+310 common move_pages sys_move_pages sys_move_pages
311 common getcpu sys_getcpu sys_getcpu
312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait
313 common utimes sys_utimes sys_utimes_time32
--- a/arch/sparc/kernel/syscalls/syscall.tbl~compat-remove-some-compat-entry-points
+++ a/arch/sparc/kernel/syscalls/syscall.tbl
@@ -365,12 +365,12 @@
299 common unshare sys_unshare
300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list
301 common get_robust_list sys_get_robust_list compat_sys_get_robust_list
-302 common migrate_pages sys_migrate_pages compat_sys_migrate_pages
-303 common mbind sys_mbind compat_sys_mbind
-304 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
-305 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy
+302 common migrate_pages sys_migrate_pages
+303 common mbind sys_mbind
+304 common get_mempolicy sys_get_mempolicy
+305 common set_mempolicy sys_set_mempolicy
306 common kexec_load sys_kexec_load compat_sys_kexec_load
-307 common move_pages sys_move_pages compat_sys_move_pages
+307 common move_pages sys_move_pages
308 common getcpu sys_getcpu
309 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait
310 32 utimensat sys_utimensat_time32
--- a/arch/x86/entry/syscalls/syscall_32.tbl~compat-remove-some-compat-entry-points
+++ a/arch/x86/entry/syscalls/syscall_32.tbl
@@ -286,7 +286,7 @@
272 i386 fadvise64_64 sys_ia32_fadvise64_64
273 i386 vserver
274 i386 mbind sys_mbind
-275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
+275 i386 get_mempolicy sys_get_mempolicy
276 i386 set_mempolicy sys_set_mempolicy
277 i386 mq_open sys_mq_open compat_sys_mq_open
278 i386 mq_unlink sys_mq_unlink
@@ -328,7 +328,7 @@
314 i386 sync_file_range sys_ia32_sync_file_range
315 i386 tee sys_tee
316 i386 vmsplice sys_vmsplice
-317 i386 move_pages sys_move_pages compat_sys_move_pages
+317 i386 move_pages sys_move_pages
318 i386 getcpu sys_getcpu
319 i386 epoll_pwait sys_epoll_pwait
320 i386 utimensat sys_utimensat_time32
--- a/arch/x86/entry/syscalls/syscall_64.tbl~compat-remove-some-compat-entry-points
+++ a/arch/x86/entry/syscalls/syscall_64.tbl
@@ -398,7 +398,7 @@
530 x32 set_robust_list compat_sys_set_robust_list
531 x32 get_robust_list compat_sys_get_robust_list
532 x32 vmsplice sys_vmsplice
-533 x32 move_pages compat_sys_move_pages
+533 x32 move_pages sys_move_pages
534 x32 preadv compat_sys_preadv64
535 x32 pwritev compat_sys_pwritev64
536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
--- a/include/linux/compat.h~compat-remove-some-compat-entry-points
+++ a/include/linux/compat.h
@@ -799,26 +799,6 @@ asmlinkage long compat_sys_execve(const
/* mm/fadvise.c: No generic prototype for fadvise64_64 */
/* mm/, CONFIG_MMU only */
-asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
- compat_ulong_t mode,
- compat_ulong_t __user *nmask,
- compat_ulong_t maxnode, compat_ulong_t flags);
-asmlinkage long compat_sys_get_mempolicy(int __user *policy,
- compat_ulong_t __user *nmask,
- compat_ulong_t maxnode,
- compat_ulong_t addr,
- compat_ulong_t flags);
-asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
- compat_ulong_t maxnode);
-asmlinkage long compat_sys_migrate_pages(compat_pid_t pid,
- compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes,
- const compat_ulong_t __user *new_nodes);
-asmlinkage long compat_sys_move_pages(pid_t pid, compat_ulong_t nr_pages,
- __u32 __user *pages,
- const int __user *nodes,
- int __user *status,
- int flags);
-
asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid,
compat_pid_t pid, int sig,
struct compat_siginfo __user *uinfo);
--- a/include/uapi/asm-generic/unistd.h~compat-remove-some-compat-entry-points
+++ a/include/uapi/asm-generic/unistd.h
@@ -673,15 +673,15 @@ __SYSCALL(__NR_madvise, sys_madvise)
#define __NR_remap_file_pages 234
__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
#define __NR_mbind 235
-__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind)
+__SYSCALL(__NR_mbind, sys_mbind)
#define __NR_get_mempolicy 236
-__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy)
+__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
#define __NR_set_mempolicy 237
-__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy)
+__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
#define __NR_migrate_pages 238
-__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages)
+__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
#define __NR_move_pages 239
-__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages)
+__SYSCALL(__NR_move_pages, sys_move_pages)
#endif
#define __NR_rt_tgsigqueueinfo 240
--- a/kernel/sys_ni.c~compat-remove-some-compat-entry-points
+++ a/kernel/sys_ni.c
@@ -292,15 +292,10 @@ COND_SYSCALL(process_madvise);
COND_SYSCALL(process_mrelease);
COND_SYSCALL(remap_file_pages);
COND_SYSCALL(mbind);
-COND_SYSCALL_COMPAT(mbind);
COND_SYSCALL(get_mempolicy);
-COND_SYSCALL_COMPAT(get_mempolicy);
COND_SYSCALL(set_mempolicy);
-COND_SYSCALL_COMPAT(set_mempolicy);
COND_SYSCALL(migrate_pages);
-COND_SYSCALL_COMPAT(migrate_pages);
COND_SYSCALL(move_pages);
-COND_SYSCALL_COMPAT(move_pages);
COND_SYSCALL(perf_event_open);
COND_SYSCALL(accept4);
--- a/mm/mempolicy.c~compat-remove-some-compat-entry-points
+++ a/mm/mempolicy.c
@@ -1649,43 +1649,6 @@ SYSCALL_DEFINE5(get_mempolicy, int __use
return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags);
}
-#ifdef CONFIG_COMPAT
-
-COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
- compat_ulong_t __user *, nmask,
- compat_ulong_t, maxnode,
- compat_ulong_t, addr, compat_ulong_t, flags)
-{
- return kernel_get_mempolicy(policy, (unsigned long __user *)nmask,
- maxnode, addr, flags);
-}
-
-COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
- compat_ulong_t, maxnode)
-{
- return kernel_set_mempolicy(mode, (unsigned long __user *)nmask, maxnode);
-}
-
-COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
- compat_ulong_t, mode, compat_ulong_t __user *, nmask,
- compat_ulong_t, maxnode, compat_ulong_t, flags)
-{
- return kernel_mbind(start, len, mode, (unsigned long __user *)nmask,
- maxnode, flags);
-}
-
-COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid,
- compat_ulong_t, maxnode,
- const compat_ulong_t __user *, old_nodes,
- const compat_ulong_t __user *, new_nodes)
-{
- return kernel_migrate_pages(pid, maxnode,
- (const unsigned long __user *)old_nodes,
- (const unsigned long __user *)new_nodes);
-}
-
-#endif /* CONFIG_COMPAT */
-
bool vma_migratable(struct vm_area_struct *vma)
{
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
--- a/mm/migrate.c~compat-remove-some-compat-entry-points
+++ a/mm/migrate.c
@@ -2047,19 +2047,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid,
return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
}
-#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
- compat_uptr_t __user *, pages,
- const int __user *, nodes,
- int __user *, status,
- int, flags)
-{
- return kernel_move_pages(pid, nr_pages,
- (const void __user *__user *)pages,
- nodes, status, flags);
-}
-#endif /* CONFIG_COMPAT */
-
#ifdef CONFIG_NUMA_BALANCING
/*
* Returns true if this is a safe migration target node for misplaced NUMA
_
^ permalink raw reply [flat|nested] 11+ messages in thread* [patch 10/10] arch: remove compat_alloc_user_space
2021-09-08 22:17 incoming Andrew Morton
` (8 preceding siblings ...)
2021-09-08 22:18 ` [patch 09/10] compat: remove some compat entry points Andrew Morton
@ 2021-09-08 22:18 ` Andrew Morton
9 siblings, 0 replies; 11+ messages in thread
From: Andrew Morton @ 2021-09-08 22:18 UTC (permalink / raw)
To: akpm, arnd, benh, borntraeger, bp, catalin.marinas, davem,
deller, ebiederm, feng.tang, gor, hca, hch, hch, hpa,
James.Bottomley, linux-mm, mingo, mm-commits, mpe, paulus, tglx,
torvalds, tsbogend, viro, will
From: Arnd Bergmann <arnd@arndb.de>
Subject: arch: remove compat_alloc_user_space
All users of compat_alloc_user_space() and copy_in_user() have been
removed from the kernel, only a few functions in sparc remain that can be
changed to calling arch_copy_in_user() instead.
Link: https://lkml.kernel.org/r/20210727144859.4150043-7-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/arm64/include/asm/compat.h | 5 -
arch/arm64/include/asm/uaccess.h | 11 ---
arch/arm64/lib/Makefile | 2
arch/arm64/lib/copy_in_user.S | 77 ----------------------
arch/mips/cavium-octeon/octeon-memcpy.S | 2
arch/mips/include/asm/compat.h | 8 --
arch/mips/include/asm/uaccess.h | 26 -------
arch/mips/lib/memcpy.S | 11 ---
arch/parisc/include/asm/compat.h | 6 -
arch/parisc/include/asm/uaccess.h | 2
arch/parisc/lib/memcpy.c | 9 --
arch/powerpc/include/asm/compat.h | 16 ----
arch/s390/include/asm/compat.h | 10 --
arch/s390/include/asm/uaccess.h | 3
arch/s390/lib/uaccess.c | 63 ------------------
arch/sparc/include/asm/compat.h | 19 -----
arch/sparc/kernel/process_64.c | 2
arch/sparc/kernel/signal32.c | 12 +--
arch/sparc/kernel/signal_64.c | 8 +-
arch/x86/include/asm/compat.h | 13 ---
arch/x86/include/asm/uaccess_64.h | 7 --
include/linux/compat.h | 2
include/linux/uaccess.h | 10 --
kernel/compat.c | 21 ------
24 files changed, 12 insertions(+), 333 deletions(-)
--- a/arch/arm64/include/asm/compat.h~arch-remove-compat_alloc_user_space
+++ a/arch/arm64/include/asm/compat.h
@@ -107,11 +107,6 @@ struct compat_statfs {
#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
#define COMPAT_MINSIGSTKSZ 2048
-static inline void __user *arch_compat_alloc_user_space(long len)
-{
- return (void __user *)compat_user_stack_pointer() - len;
-}
-
struct compat_ipc64_perm {
compat_key_t key;
__compat_uid32_t uid;
--- a/arch/arm64/include/asm/uaccess.h~arch-remove-compat_alloc_user_space
+++ a/arch/arm64/include/asm/uaccess.h
@@ -430,17 +430,6 @@ extern unsigned long __must_check __arch
__actu_ret; \
})
-extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n);
-#define raw_copy_in_user(to, from, n) \
-({ \
- unsigned long __aciu_ret; \
- uaccess_ttbr0_enable(); \
- __aciu_ret = __arch_copy_in_user(__uaccess_mask_ptr(to), \
- __uaccess_mask_ptr(from), (n)); \
- uaccess_ttbr0_disable(); \
- __aciu_ret; \
-})
-
#define INLINE_COPY_TO_USER
#define INLINE_COPY_FROM_USER
--- a/arch/arm64/lib/copy_in_user.S
+++ /dev/null
@@ -1,77 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copy from user space to user space
- *
- * Copyright (C) 2012 ARM Ltd.
- */
-
-#include <linux/linkage.h>
-
-#include <asm/asm-uaccess.h>
-#include <asm/assembler.h>
-#include <asm/cache.h>
-
-/*
- * Copy from user space to user space (alignment handled by the hardware)
- *
- * Parameters:
- * x0 - to
- * x1 - from
- * x2 - n
- * Returns:
- * x0 - bytes not copied
- */
- .macro ldrb1 reg, ptr, val
- user_ldst 9998f, ldtrb, \reg, \ptr, \val
- .endm
-
- .macro strb1 reg, ptr, val
- user_ldst 9998f, sttrb, \reg, \ptr, \val
- .endm
-
- .macro ldrh1 reg, ptr, val
- user_ldst 9997f, ldtrh, \reg, \ptr, \val
- .endm
-
- .macro strh1 reg, ptr, val
- user_ldst 9997f, sttrh, \reg, \ptr, \val
- .endm
-
- .macro ldr1 reg, ptr, val
- user_ldst 9997f, ldtr, \reg, \ptr, \val
- .endm
-
- .macro str1 reg, ptr, val
- user_ldst 9997f, sttr, \reg, \ptr, \val
- .endm
-
- .macro ldp1 reg1, reg2, ptr, val
- user_ldp 9997f, \reg1, \reg2, \ptr, \val
- .endm
-
- .macro stp1 reg1, reg2, ptr, val
- user_stp 9997f, \reg1, \reg2, \ptr, \val
- .endm
-
-end .req x5
-srcin .req x15
-SYM_FUNC_START(__arch_copy_in_user)
- add end, x0, x2
- mov srcin, x1
-#include "copy_template.S"
- mov x0, #0
- ret
-SYM_FUNC_END(__arch_copy_in_user)
-EXPORT_SYMBOL(__arch_copy_in_user)
-
- .section .fixup,"ax"
- .align 2
-9997: cmp dst, dstin
- b.ne 9998f
- // Before being absolutely sure we couldn't copy anything, try harder
-USER(9998f, ldtrb tmp1w, [srcin])
-USER(9998f, sttrb tmp1w, [dst])
- add dst, dst, #1
-9998: sub x0, end, dst // bytes not copied
- ret
- .previous
--- a/arch/arm64/lib/Makefile~arch-remove-compat_alloc_user_space
+++ a/arch/arm64/lib/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
lib-y := clear_user.o delay.o copy_from_user.o \
- copy_to_user.o copy_in_user.o copy_page.o \
+ copy_to_user.o copy_page.o \
clear_page.o csum.o insn.o memchr.o memcpy.o \
memset.o memcmp.o strcmp.o strncmp.o strlen.o \
strnlen.o strchr.o strrchr.o tishift.o
--- a/arch/mips/cavium-octeon/octeon-memcpy.S~arch-remove-compat_alloc_user_space
+++ a/arch/mips/cavium-octeon/octeon-memcpy.S
@@ -154,8 +154,6 @@ FEXPORT(__raw_copy_from_user)
EXPORT_SYMBOL(__raw_copy_from_user)
FEXPORT(__raw_copy_to_user)
EXPORT_SYMBOL(__raw_copy_to_user)
-FEXPORT(__raw_copy_in_user)
-EXPORT_SYMBOL(__raw_copy_in_user)
/*
* Note: dst & src may be unaligned, len may be 0
* Temps
--- a/arch/mips/include/asm/compat.h~arch-remove-compat_alloc_user_space
+++ a/arch/mips/include/asm/compat.h
@@ -96,14 +96,6 @@ struct compat_statfs {
#define COMPAT_OFF_T_MAX 0x7fffffff
-static inline void __user *arch_compat_alloc_user_space(long len)
-{
- struct pt_regs *regs = (struct pt_regs *)
- ((unsigned long) current_thread_info() + THREAD_SIZE - 32) - 1;
-
- return (void __user *) (regs->regs[29] - len);
-}
-
struct compat_ipc64_perm {
compat_key_t key;
__compat_uid32_t uid;
--- a/arch/mips/include/asm/uaccess.h~arch-remove-compat_alloc_user_space
+++ a/arch/mips/include/asm/uaccess.h
@@ -428,7 +428,6 @@ do { \
extern size_t __raw_copy_from_user(void *__to, const void *__from, size_t __n);
extern size_t __raw_copy_to_user(void *__to, const void *__from, size_t __n);
-extern size_t __raw_copy_in_user(void *__to, const void *__from, size_t __n);
static inline unsigned long
raw_copy_from_user(void *to, const void __user *from, unsigned long n)
@@ -480,31 +479,6 @@ raw_copy_to_user(void __user *to, const
#define INLINE_COPY_FROM_USER
#define INLINE_COPY_TO_USER
-static inline unsigned long
-raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- register void __user *__cu_to_r __asm__("$4");
- register const void __user *__cu_from_r __asm__("$5");
- register long __cu_len_r __asm__("$6");
-
- __cu_to_r = to;
- __cu_from_r = from;
- __cu_len_r = n;
-
- __asm__ __volatile__(
- ".set\tnoreorder\n\t"
- __MODULE_JAL(__raw_copy_in_user)
- ".set\tnoat\n\t"
- __UA_ADDU "\t$1, %1, %2\n\t"
- ".set\tat\n\t"
- ".set\treorder"
- : "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)
- :
- : "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",
- DADDI_SCRATCH, "memory");
- return __cu_len_r;
-}
-
extern __kernel_size_t __bzero(void __user *addr, __kernel_size_t size);
/*
--- a/arch/mips/lib/memcpy.S~arch-remove-compat_alloc_user_space
+++ a/arch/mips/lib/memcpy.S
@@ -666,8 +666,6 @@ FEXPORT(__raw_copy_from_user)
EXPORT_SYMBOL(__raw_copy_from_user)
FEXPORT(__raw_copy_to_user)
EXPORT_SYMBOL(__raw_copy_to_user)
-FEXPORT(__raw_copy_in_user)
-EXPORT_SYMBOL(__raw_copy_in_user)
#endif
/* Legacy Mode, user <-> user */
__BUILD_COPY_USER LEGACY_MODE USEROP USEROP
@@ -703,13 +701,4 @@ EXPORT_SYMBOL(__raw_copy_to_user)
__BUILD_COPY_USER EVA_MODE KERNELOP USEROP
END(__raw_copy_to_user)
-/*
- * __copy_in_user (EVA)
- */
-
-LEAF(__raw_copy_in_user)
-EXPORT_SYMBOL(__raw_copy_in_user)
-__BUILD_COPY_USER EVA_MODE USEROP USEROP
-END(__raw_copy_in_user)
-
#endif
--- a/arch/parisc/include/asm/compat.h~arch-remove-compat_alloc_user_space
+++ a/arch/parisc/include/asm/compat.h
@@ -163,12 +163,6 @@ struct compat_shmid64_ds {
#define COMPAT_ELF_NGREG 80
typedef compat_ulong_t compat_elf_gregset_t[COMPAT_ELF_NGREG];
-static __inline__ void __user *arch_compat_alloc_user_space(long len)
-{
- struct pt_regs *regs = ¤t->thread.regs;
- return (void __user *)regs->gr[30];
-}
-
static inline int __is_compat_task(struct task_struct *t)
{
return test_tsk_thread_flag(t, TIF_32BIT);
--- a/arch/parisc/include/asm/uaccess.h~arch-remove-compat_alloc_user_space
+++ a/arch/parisc/include/asm/uaccess.h
@@ -215,8 +215,6 @@ unsigned long __must_check raw_copy_to_u
unsigned long len);
unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src,
unsigned long len);
-unsigned long __must_check raw_copy_in_user(void __user *dst, const void __user *src,
- unsigned long len);
#define INLINE_COPY_TO_USER
#define INLINE_COPY_FROM_USER
--- a/arch/parisc/lib/memcpy.c~arch-remove-compat_alloc_user_space
+++ a/arch/parisc/lib/memcpy.c
@@ -38,14 +38,6 @@ unsigned long raw_copy_from_user(void *d
}
EXPORT_SYMBOL(raw_copy_from_user);
-unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long len)
-{
- mtsp(get_user_space(), 1);
- mtsp(get_user_space(), 2);
- return pa_memcpy((void __force *)dst, (void __force *)src, len);
-}
-
-
void * memcpy(void * dst,const void *src, size_t count)
{
mtsp(get_kernel_space(), 1);
@@ -54,7 +46,6 @@ void * memcpy(void * dst,const void *src
return dst;
}
-EXPORT_SYMBOL(raw_copy_in_user);
EXPORT_SYMBOL(memcpy);
bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
--- a/arch/powerpc/include/asm/compat.h~arch-remove-compat_alloc_user_space
+++ a/arch/powerpc/include/asm/compat.h
@@ -83,22 +83,6 @@ struct compat_statfs {
#define COMPAT_OFF_T_MAX 0x7fffffff
-static inline void __user *arch_compat_alloc_user_space(long len)
-{
- struct pt_regs *regs = current->thread.regs;
- unsigned long usp = regs->gpr[1];
-
- /*
- * We can't access below the stack pointer in the 32bit ABI and
- * can access 288 bytes in the 64bit big-endian ABI,
- * or 512 bytes with the new ELFv2 little-endian ABI.
- */
- if (!is_32bit_task())
- usp -= USER_REDZONE_SIZE;
-
- return (void __user *) (usp - len);
-}
-
/*
* ipc64_perm is actually 32/64bit clean but since the compat layer refers to
* it we may as well define it.
--- a/arch/s390/include/asm/compat.h~arch-remove-compat_alloc_user_space
+++ a/arch/s390/include/asm/compat.h
@@ -176,16 +176,6 @@ static inline int is_compat_task(void)
return test_thread_flag(TIF_31BIT);
}
-static inline void __user *arch_compat_alloc_user_space(long len)
-{
- unsigned long stack;
-
- stack = KSTK_ESP(current);
- if (is_compat_task())
- stack &= 0x7fffffffUL;
- return (void __user *) (stack - len);
-}
-
#endif
struct compat_ipc64_perm {
--- a/arch/s390/include/asm/uaccess.h~arch-remove-compat_alloc_user_space
+++ a/arch/s390/include/asm/uaccess.h
@@ -227,9 +227,6 @@ static inline int __get_user_fn(void *x,
__get_user(x, ptr); \
})
-unsigned long __must_check
-raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
-
/*
* Copy a null terminated string from userspace.
*/
--- a/arch/s390/lib/uaccess.c~arch-remove-compat_alloc_user_space
+++ a/arch/s390/lib/uaccess.c
@@ -204,69 +204,6 @@ unsigned long raw_copy_to_user(void __us
}
EXPORT_SYMBOL(raw_copy_to_user);
-static inline unsigned long copy_in_user_mvcos(void __user *to, const void __user *from,
- unsigned long size)
-{
- unsigned long tmp1, tmp2;
-
- tmp1 = -4096UL;
- /* FIXME: copy with reduced length. */
- asm volatile(
- " lgr 0,%[spec]\n"
- "0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n"
- " jz 2f\n"
- "1: algr %0,%3\n"
- " slgr %1,%3\n"
- " slgr %2,%3\n"
- " j 0b\n"
- "2:slgr %0,%0\n"
- "3: \n"
- EX_TABLE(0b,3b)
- : "+a" (size), "+a" (to), "+a" (from), "+a" (tmp1), "=a" (tmp2)
- : [spec] "d" (0x810081UL)
- : "cc", "memory", "0");
- return size;
-}
-
-static inline unsigned long copy_in_user_mvc(void __user *to, const void __user *from,
- unsigned long size)
-{
- unsigned long tmp1;
-
- asm volatile(
- " sacf 256\n"
- " aghi %0,-1\n"
- " jo 5f\n"
- " bras %3,3f\n"
- "0: aghi %0,257\n"
- "1: mvc 0(1,%1),0(%2)\n"
- " la %1,1(%1)\n"
- " la %2,1(%2)\n"
- " aghi %0,-1\n"
- " jnz 1b\n"
- " j 5f\n"
- "2: mvc 0(256,%1),0(%2)\n"
- " la %1,256(%1)\n"
- " la %2,256(%2)\n"
- "3: aghi %0,-256\n"
- " jnm 2b\n"
- "4: ex %0,1b-0b(%3)\n"
- "5: slgr %0,%0\n"
- "6: sacf 768\n"
- EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
- : "+a" (size), "+a" (to), "+a" (from), "=a" (tmp1)
- : : "cc", "memory");
- return size;
-}
-
-unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- if (copy_with_mvcos())
- return copy_in_user_mvcos(to, from, n);
- return copy_in_user_mvc(to, from, n);
-}
-EXPORT_SYMBOL(raw_copy_in_user);
-
static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size)
{
unsigned long tmp1, tmp2;
--- a/arch/sparc/include/asm/compat.h~arch-remove-compat_alloc_user_space
+++ a/arch/sparc/include/asm/compat.h
@@ -116,25 +116,6 @@ struct compat_statfs {
#define COMPAT_OFF_T_MAX 0x7fffffff
-#ifdef CONFIG_COMPAT
-static inline void __user *arch_compat_alloc_user_space(long len)
-{
- struct pt_regs *regs = current_thread_info()->kregs;
- unsigned long usp = regs->u_regs[UREG_I6];
-
- if (test_thread_64bit_stack(usp))
- usp += STACK_BIAS;
-
- if (test_thread_flag(TIF_32BIT))
- usp &= 0xffffffffUL;
-
- usp -= len;
- usp &= ~0x7UL;
-
- return (void __user *) usp;
-}
-#endif
-
struct compat_ipc64_perm {
compat_key_t key;
__compat_uid32_t uid;
--- a/arch/sparc/kernel/process_64.c~arch-remove-compat_alloc_user_space
+++ a/arch/sparc/kernel/process_64.c
@@ -455,7 +455,7 @@ static unsigned long clone_stackframe(un
distance = fp - psp;
rval = (csp - distance);
- if (copy_in_user((void __user *) rval, (void __user *) psp, distance))
+ if (raw_copy_in_user((void __user *)rval, (void __user *)psp, distance))
rval = 0;
else if (!stack_64bit) {
if (put_user(((u32)csp),
--- a/arch/sparc/kernel/signal32.c~arch-remove-compat_alloc_user_space
+++ a/arch/sparc/kernel/signal32.c
@@ -435,9 +435,9 @@ static int setup_frame32(struct ksignal
(_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
if (!wsaved) {
- err |= copy_in_user((u32 __user *)sf,
- (u32 __user *)(regs->u_regs[UREG_FP]),
- sizeof(struct reg_window32));
+ err |= raw_copy_in_user((u32 __user *)sf,
+ (u32 __user *)(regs->u_regs[UREG_FP]),
+ sizeof(struct reg_window32));
} else {
struct reg_window *rp;
@@ -567,9 +567,9 @@ static int setup_rt_frame32(struct ksign
err |= put_compat_sigset(&sf->mask, oldset, sizeof(compat_sigset_t));
if (!wsaved) {
- err |= copy_in_user((u32 __user *)sf,
- (u32 __user *)(regs->u_regs[UREG_FP]),
- sizeof(struct reg_window32));
+ err |= raw_copy_in_user((u32 __user *)sf,
+ (u32 __user *)(regs->u_regs[UREG_FP]),
+ sizeof(struct reg_window32));
} else {
struct reg_window *rp;
--- a/arch/sparc/kernel/signal_64.c~arch-remove-compat_alloc_user_space
+++ a/arch/sparc/kernel/signal_64.c
@@ -406,10 +406,10 @@ setup_rt_frame(struct ksignal *ksig, str
err |= copy_to_user(&sf->mask, sigmask_to_save(), sizeof(sigset_t));
if (!wsaved) {
- err |= copy_in_user((u64 __user *)sf,
- (u64 __user *)(regs->u_regs[UREG_FP] +
- STACK_BIAS),
- sizeof(struct reg_window));
+ err |= raw_copy_in_user((u64 __user *)sf,
+ (u64 __user *)(regs->u_regs[UREG_FP] +
+ STACK_BIAS),
+ sizeof(struct reg_window));
} else {
struct reg_window *rp;
--- a/arch/x86/include/asm/compat.h~arch-remove-compat_alloc_user_space
+++ a/arch/x86/include/asm/compat.h
@@ -156,19 +156,6 @@ struct compat_shmid64_ds {
(!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT))
#endif
-static inline void __user *arch_compat_alloc_user_space(long len)
-{
- compat_uptr_t sp = task_pt_regs(current)->sp;
-
- /*
- * -128 for the x32 ABI redzone. For IA32, it is not strictly
- * necessary, but not harmful.
- */
- sp -= 128;
-
- return (void __user *)round_down(sp - len, 16);
-}
-
static inline bool in_x32_syscall(void)
{
#ifdef CONFIG_X86_X32_ABI
--- a/arch/x86/include/asm/uaccess_64.h~arch-remove-compat_alloc_user_space
+++ a/arch/x86/include/asm/uaccess_64.h
@@ -58,13 +58,6 @@ raw_copy_to_user(void __user *dst, const
return copy_user_generic((__force void *)dst, src, size);
}
-static __always_inline __must_check
-unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size)
-{
- return copy_user_generic((__force void *)dst,
- (__force void *)src, size);
-}
-
extern long __copy_user_nocache(void *dst, const void __user *src,
unsigned size, int zerorest);
--- a/include/linux/compat.h~arch-remove-compat_alloc_user_space
+++ a/include/linux/compat.h
@@ -511,8 +511,6 @@ extern long compat_arch_ptrace(struct ta
struct epoll_event; /* fortunately, this one is fixed-layout */
-extern void __user *compat_alloc_user_space(unsigned long len);
-
int compat_restore_altstack(const compat_stack_t __user *uss);
int __compat_save_altstack(compat_stack_t __user *, unsigned long);
#define unsafe_compat_save_altstack(uss, sp, label) do { \
--- a/include/linux/uaccess.h~arch-remove-compat_alloc_user_space
+++ a/include/linux/uaccess.h
@@ -200,16 +200,6 @@ copy_to_user(void __user *to, const void
n = _copy_to_user(to, from, n);
return n;
}
-#ifdef CONFIG_COMPAT
-static __always_inline unsigned long __must_check
-copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- might_fault();
- if (access_ok(to, n) && access_ok(from, n))
- n = raw_copy_in_user(to, from, n);
- return n;
-}
-#endif
#ifndef copy_mc_to_kernel
/*
--- a/kernel/compat.c~arch-remove-compat_alloc_user_space
+++ a/kernel/compat.c
@@ -269,24 +269,3 @@ get_compat_sigset(sigset_t *set, const c
return 0;
}
EXPORT_SYMBOL_GPL(get_compat_sigset);
-
-/*
- * Allocate user-space memory for the duration of a single system call,
- * in order to marshall parameters inside a compat thunk.
- */
-void __user *compat_alloc_user_space(unsigned long len)
-{
- void __user *ptr;
-
- /* If len would occupy more than half of the entire compat space... */
- if (unlikely(len > (((compat_uptr_t)~0) >> 1)))
- return NULL;
-
- ptr = arch_compat_alloc_user_space(len);
-
- if (unlikely(!access_ok(ptr, len)))
- return NULL;
-
- return ptr;
-}
-EXPORT_SYMBOL_GPL(compat_alloc_user_space);
_
^ permalink raw reply [flat|nested] 11+ messages in thread