* Re: incoming
2020-10-16 2:40 incoming Andrew Morton
@ 2020-10-16 3:03 ` Andrew Morton
2020-10-16 3:04 ` [patch 001/156] device-dax/kmem: fix resource release Andrew Morton
` (165 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:03 UTC (permalink / raw)
To: Linus Torvalds, mm-commits, linux-mm
And... I forgot to set in-reply-to :(
Shall resend, omitting linux-mm.
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 001/156] device-dax/kmem: fix resource release
2020-10-16 2:40 incoming Andrew Morton
2020-10-16 3:03 ` incoming Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 002/156] powerpc/mm: add DEBUG_VM WARN for pmd_clear Andrew Morton
` (164 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, Brice.Goglin, dan.j.williams, dave.hansen, dave.jiang,
david, ira.weiny, joao.m.martins, Jonathan.Cameron, justin.he,
mm-commits, pasha.tatashin, torvalds, vishal.l.verma
From: Dan Williams <dan.j.williams@intel.com>
Subject: device-dax/kmem: fix resource release
The conversion to request_mem_region() is broken because it assumes that
the range is marked busy prior to release. However, due to the way that
the kmem driver manipulates the IORESOURCE_BUSY flag (clears it to let
{add,remove}_memory() handle busy) it requires a manual release_resource()
to perform cleanup.
Given that the actual 'struct resource *' needs to be recalled, not just
the range, add that tracking to the kmem driver-data.
Link: https://lkml.kernel.org/r/160272252925.3136502.17220638073995895400.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: 0513bd5bb114 ("device-dax/kmem: replace release_resource() with release_mem_region()")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reported-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/dax/kmem.c | 48 ++++++++++++++++++++++++++++++-------------
1 file changed, 34 insertions(+), 14 deletions(-)
--- a/drivers/dax/kmem.c~device-dax-kmem-fix-resource-release
+++ a/drivers/dax/kmem.c
@@ -35,11 +35,17 @@ static int dax_kmem_range(struct dev_dax
return 0;
}
+struct dax_kmem_data {
+ const char *res_name;
+ struct resource *res[];
+};
+
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
{
struct device *dev = &dev_dax->dev;
+ struct dax_kmem_data *data;
+ int rc = -ENOMEM;
int i, mapped = 0;
- char *res_name;
int numa_node;
/*
@@ -55,14 +61,17 @@ static int dev_dax_kmem_probe(struct dev
return -EINVAL;
}
- res_name = kstrdup(dev_name(dev), GFP_KERNEL);
- if (!res_name)
+ data = kzalloc(sizeof(*data) + sizeof(struct resource *) * dev_dax->nr_range, GFP_KERNEL);
+ if (!data)
return -ENOMEM;
+ data->res_name = kstrdup(dev_name(dev), GFP_KERNEL);
+ if (!data->res_name)
+ goto err_res_name;
+
for (i = 0; i < dev_dax->nr_range; i++) {
struct resource *res;
struct range range;
- int rc;
rc = dax_kmem_range(dev_dax, i, &range);
if (rc) {
@@ -72,7 +81,7 @@ static int dev_dax_kmem_probe(struct dev
}
/* Region is permanently reserved if hotremove fails. */
- res = request_mem_region(range.start, range_len(&range), res_name);
+ res = request_mem_region(range.start, range_len(&range), data->res_name);
if (!res) {
dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve region\n",
i, range.start, range.end);
@@ -82,9 +91,10 @@ static int dev_dax_kmem_probe(struct dev
*/
if (mapped)
continue;
- kfree(res_name);
- return -EBUSY;
+ rc = -EBUSY;
+ goto err_request_mem;
}
+ data->res[i] = res;
/*
* Set flags appropriate for System RAM. Leave ..._BUSY clear
@@ -104,18 +114,25 @@ static int dev_dax_kmem_probe(struct dev
if (rc) {
dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
i, range.start, range.end);
- release_mem_region(range.start, range_len(&range));
+ release_resource(res);
+ kfree(res);
+ data->res[i] = NULL;
if (mapped)
continue;
- kfree(res_name);
- return rc;
+ goto err_request_mem;
}
mapped++;
}
- dev_set_drvdata(dev, res_name);
+ dev_set_drvdata(dev, data);
return 0;
+
+err_request_mem:
+ kfree(data->res_name);
+err_res_name:
+ kfree(data);
+ return rc;
}
#ifdef CONFIG_MEMORY_HOTREMOVE
@@ -123,7 +140,7 @@ static int dev_dax_kmem_remove(struct de
{
int i, success = 0;
struct device *dev = &dev_dax->dev;
- const char *res_name = dev_get_drvdata(dev);
+ struct dax_kmem_data *data = dev_get_drvdata(dev);
/*
* We have one shot for removing memory, if some memory blocks were not
@@ -142,7 +159,9 @@ static int dev_dax_kmem_remove(struct de
rc = remove_memory(dev_dax->target_node, range.start,
range_len(&range));
if (rc == 0) {
- release_mem_region(range.start, range_len(&range));
+ release_resource(data->res[i]);
+ kfree(data->res[i]);
+ data->res[i] = NULL;
success++;
continue;
}
@@ -153,7 +172,8 @@ static int dev_dax_kmem_remove(struct de
}
if (success >= dev_dax->nr_range) {
- kfree(res_name);
+ kfree(data->res_name);
+ kfree(data);
dev_set_drvdata(dev, NULL);
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 002/156] powerpc/mm: add DEBUG_VM WARN for pmd_clear
2020-10-16 2:40 incoming Andrew Morton
2020-10-16 3:03 ` incoming Andrew Morton
2020-10-16 3:04 ` [patch 001/156] device-dax/kmem: fix resource release Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 003/156] powerpc/mm: move setting pte specific flags to pfn_pte Andrew Morton
` (163 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: powerpc/mm: add DEBUG_VM WARN for pmd_clear
Patch series "mm/debug_vm_pgtable fixes", v4.
This patch series includes fixes for debug_vm_pgtable test code so that
they follow page table updates rules correctly. The first two patches
introduce changes w.r.t ppc64.
Hugetlb test is disabled on ppc64 because that needs larger change to satisfy
page table update rules.
These tests are broken w.r.t page table update rules and results in kernel
crash as below.
[ 21.083519] kernel BUG at arch/powerpc/mm/pgtable.c:304!
cpu 0x0: Vector: 700 (Program Check) at [c000000c6d1e76c0]
pc: c00000000009a5ec: assert_pte_locked+0x14c/0x380
lr: c0000000005eeeec: pte_update+0x11c/0x190
sp: c000000c6d1e7950
msr: 8000000002029033
current = 0xc000000c6d172c80
paca = 0xc000000003ba0000 irqmask: 0x03 irq_happened: 0x01
pid = 1, comm = swapper/0
kernel BUG at arch/powerpc/mm/pgtable.c:304!
[link register ] c0000000005eeeec pte_update+0x11c/0x190
[c000000c6d1e7950] 0000000000000001 (unreliable)
[c000000c6d1e79b0] c0000000005eee14 pte_update+0x44/0x190
[c000000c6d1e7a10] c000000001a2ca9c pte_advanced_tests+0x160/0x3d8
[c000000c6d1e7ab0] c000000001a2d4fc debug_vm_pgtable+0x7e8/0x1338
[c000000c6d1e7ba0] c0000000000116ec do_one_initcall+0xac/0x5f0
[c000000c6d1e7c80] c0000000019e4fac kernel_init_freeable+0x4dc/0x5a4
[c000000c6d1e7db0] c000000000012474 kernel_init+0x24/0x160
[c000000c6d1e7e20] c00000000000cbd0 ret_from_kernel_thread+0x5c/0x6c
With DEBUG_VM disabled
[ 20.530152] BUG: Kernel NULL pointer dereference on read at 0x00000000
[ 20.530183] Faulting instruction address: 0xc0000000000df330
cpu 0x33: Vector: 380 (Data SLB Access) at [c000000c6d19f700]
pc: c0000000000df330: memset+0x68/0x104
lr: c00000000009f6d8: hash__pmdp_huge_get_and_clear+0xe8/0x1b0
sp: c000000c6d19f990
msr: 8000000002009033
dar: 0
current = 0xc000000c6d177480
paca = 0xc00000001ec4f400 irqmask: 0x03 irq_happened: 0x01
pid = 1, comm = swapper/0
[link register ] c00000000009f6d8 hash__pmdp_huge_get_and_clear+0xe8/0x1b0
[c000000c6d19f990] c00000000009f748 hash__pmdp_huge_get_and_clear+0x158/0x1b0 (unreliable)
[c000000c6d19fa10] c0000000019ebf30 pmd_advanced_tests+0x1f0/0x378
[c000000c6d19fab0] c0000000019ed088 debug_vm_pgtable+0x79c/0x1244
[c000000c6d19fba0] c0000000000116ec do_one_initcall+0xac/0x5f0
[c000000c6d19fc80] c0000000019a4fac kernel_init_freeable+0x4dc/0x5a4
[c000000c6d19fdb0] c000000000012474 kernel_init+0x24/0x160
[c000000c6d19fe20] c00000000000cbd0 ret_from_kernel_thread+0x5c/0x6c
This patch (of 13):
With the hash page table, the kernel should not use pmd_clear for clearing
huge pte entries. Add a DEBUG_VM WARN to catch the wrong usage.
Link: https://lkml.kernel.org/r/20200902114222.181353-1-aneesh.kumar@linux.ibm.com
Link: https://lkml.kernel.org/r/20200902114222.181353-2-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/powerpc/include/asm/book3s/64/pgtable.h | 14 ++++++++++++++
1 file changed, 14 insertions(+)
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h~powerpc-mm-add-debug_vm-warn-for-pmd_clear
+++ a/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -866,6 +866,13 @@ static inline bool pte_ci(pte_t pte)
static inline void pmd_clear(pmd_t *pmdp)
{
+ if (IS_ENABLED(CONFIG_DEBUG_VM) && !radix_enabled()) {
+ /*
+ * Don't use this if we can possibly have a hash page table
+ * entry mapping this.
+ */
+ WARN_ON((pmd_val(*pmdp) & (H_PAGE_HASHPTE | _PAGE_PTE)) == (H_PAGE_HASHPTE | _PAGE_PTE));
+ }
*pmdp = __pmd(0);
}
@@ -914,6 +921,13 @@ static inline int pmd_bad(pmd_t pmd)
static inline void pud_clear(pud_t *pudp)
{
+ if (IS_ENABLED(CONFIG_DEBUG_VM) && !radix_enabled()) {
+ /*
+ * Don't use this if we can possibly have a hash page table
+ * entry mapping this.
+ */
+ WARN_ON((pud_val(*pudp) & (H_PAGE_HASHPTE | _PAGE_PTE)) == (H_PAGE_HASHPTE | _PAGE_PTE));
+ }
*pudp = __pud(0);
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 003/156] powerpc/mm: move setting pte specific flags to pfn_pte
2020-10-16 2:40 incoming Andrew Morton
` (2 preceding siblings ...)
2020-10-16 3:04 ` [patch 002/156] powerpc/mm: add DEBUG_VM WARN for pmd_clear Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 004/156] mm/debug_vm_pgtable/ppc64: avoid setting top bits in radom value Andrew Morton
` (162 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: powerpc/mm: move setting pte specific flags to pfn_pte
powerpc used to set the pte specific flags in set_pte_at(). This is
different from other architectures. To be consistent with other
architecture update pfn_pte to set _PAGE_PTE on ppc64. Also, drop now
unused pte_mkpte.
We add a VM_WARN_ON() to catch the usage of calling set_pte_at() without
setting _PAGE_PTE bit. We will remove that after a few releases.
With respect to huge pmd entries, pmd_mkhuge() takes care of adding the
_PAGE_PTE bit.
[akpm@linux-foundation.org: whitespace fix, per Christophe]
Link: https://lkml.kernel.org/r/20200902114222.181353-3-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/powerpc/include/asm/book3s/64/pgtable.h | 15 +++++++++------
arch/powerpc/include/asm/nohash/pgtable.h | 5 -----
arch/powerpc/mm/pgtable.c | 5 -----
3 files changed, 9 insertions(+), 16 deletions(-)
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h~powerpc-mm-move-setting-pte-specific-flags-to-pfn_pte
+++ a/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -615,7 +615,7 @@ static inline pte_t pfn_pte(unsigned lon
VM_BUG_ON(pfn >> (64 - PAGE_SHIFT));
VM_BUG_ON((pfn << PAGE_SHIFT) & ~PTE_RPN_MASK);
- return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot));
+ return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE);
}
static inline unsigned long pte_pfn(pte_t pte)
@@ -651,11 +651,6 @@ static inline pte_t pte_mkexec(pte_t pte
return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_EXEC));
}
-static inline pte_t pte_mkpte(pte_t pte)
-{
- return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PTE));
-}
-
static inline pte_t pte_mkwrite(pte_t pte)
{
/*
@@ -819,6 +814,14 @@ static inline int pte_none(pte_t pte)
static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte, int percpu)
{
+
+ VM_WARN_ON(!(pte_raw(pte) & cpu_to_be64(_PAGE_PTE)));
+ /*
+ * Keep the _PAGE_PTE added till we are sure we handle _PAGE_PTE
+ * in all the callers.
+ */
+ pte = __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PTE));
+
if (radix_enabled())
return radix__set_pte_at(mm, addr, ptep, pte, percpu);
return hash__set_pte_at(mm, addr, ptep, pte, percpu);
--- a/arch/powerpc/include/asm/nohash/pgtable.h~powerpc-mm-move-setting-pte-specific-flags-to-pfn_pte
+++ a/arch/powerpc/include/asm/nohash/pgtable.h
@@ -140,11 +140,6 @@ static inline pte_t pte_mkold(pte_t pte)
return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
}
-static inline pte_t pte_mkpte(pte_t pte)
-{
- return pte;
-}
-
static inline pte_t pte_mkspecial(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_SPECIAL);
--- a/arch/powerpc/mm/pgtable.c~powerpc-mm-move-setting-pte-specific-flags-to-pfn_pte
+++ a/arch/powerpc/mm/pgtable.c
@@ -184,9 +184,6 @@ void set_pte_at(struct mm_struct *mm, un
*/
VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
- /* Add the pte bit when trying to set a pte */
- pte = pte_mkpte(pte);
-
/* Note: mm->context.id might not yet have been assigned as
* this context might not have been activated yet when this
* is called.
@@ -275,8 +272,6 @@ void set_huge_pte_at(struct mm_struct *m
*/
VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
- pte = pte_mkpte(pte);
-
pte = set_pte_filter(pte);
val = pte_val(pte);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 004/156] mm/debug_vm_pgtable/ppc64: avoid setting top bits in radom value
2020-10-16 2:40 incoming Andrew Morton
` (3 preceding siblings ...)
2020-10-16 3:04 ` [patch 003/156] powerpc/mm: move setting pte specific flags to pfn_pte Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 005/156] mm/debug_vm_pgtables/hugevmap: use the arch helper to identify huge vmap support Andrew Morton
` (161 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable/ppc64: avoid setting top bits in radom value
ppc64 use bit 62 to indicate a pte entry (_PAGE_PTE). Avoid setting that
bit in random value.
Link: https://lkml.kernel.org/r/20200902114222.181353-4-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-ppc64-avoid-setting-top-bits-in-radom-value
+++ a/mm/debug_vm_pgtable.c
@@ -44,10 +44,17 @@
* entry type. But these bits might affect the ability to clear entries with
* pxx_clear() because of how dynamic page table folding works on s390. So
* while loading up the entries do not change the lower 4 bits. It does not
- * have affect any other platform.
+ * have affect any other platform. Also avoid the 62nd bit on ppc64 that is
+ * used to mark a pte entry.
*/
-#define S390_MASK_BITS 4
-#define RANDOM_ORVALUE GENMASK(BITS_PER_LONG - 1, S390_MASK_BITS)
+#define S390_SKIP_MASK GENMASK(3, 0)
+#if __BITS_PER_LONG == 64
+#define PPC64_SKIP_MASK GENMASK(62, 62)
+#else
+#define PPC64_SKIP_MASK 0x0
+#endif
+#define ARCH_SKIP_MASK (S390_SKIP_MASK | PPC64_SKIP_MASK)
+#define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK)
#define RANDOM_NZVALUE GENMASK(7, 0)
static void __init pte_basic_tests(unsigned long pfn, pgprot_t prot)
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 005/156] mm/debug_vm_pgtables/hugevmap: use the arch helper to identify huge vmap support.
2020-10-16 2:40 incoming Andrew Morton
` (4 preceding siblings ...)
2020-10-16 3:04 ` [patch 004/156] mm/debug_vm_pgtable/ppc64: avoid setting top bits in radom value Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 006/156] mm/debug_vm_pgtable/savedwrite: enable savedwrite test with CONFIG_NUMA_BALANCING Andrew Morton
` (160 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtables/hugevmap: use the arch helper to identify huge vmap support.
ppc64 supports huge vmap only with radix translation. Hence use arch
helper to determine the huge vmap support.
Link: https://lkml.kernel.org/r/20200902114222.181353-5-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtables-hugevmap-use-the-arch-helper-to-identify-huge-vmap-support
+++ a/mm/debug_vm_pgtable.c
@@ -28,6 +28,7 @@
#include <linux/swapops.h>
#include <linux/start_kernel.h>
#include <linux/sched/mm.h>
+#include <linux/io.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
@@ -206,11 +207,12 @@ static void __init pmd_leaf_tests(unsign
WARN_ON(!pmd_leaf(pmd));
}
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot)
{
pmd_t pmd;
- if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
+ if (!arch_ioremap_pmd_supported())
return;
pr_debug("Validating PMD huge\n");
@@ -224,6 +226,9 @@ static void __init pmd_huge_tests(pmd_t
pmd = READ_ONCE(*pmdp);
WARN_ON(!pmd_none(pmd));
}
+#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) { }
+#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot)
{
@@ -320,11 +325,12 @@ static void __init pud_leaf_tests(unsign
WARN_ON(!pud_leaf(pud));
}
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot)
{
pud_t pud;
- if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
+ if (!arch_ioremap_pud_supported())
return;
pr_debug("Validating PUD huge\n");
@@ -338,6 +344,10 @@ static void __init pud_huge_tests(pud_t
pud = READ_ONCE(*pudp);
WARN_ON(!pud_none(pud));
}
+#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) { }
+#endif /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+
#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot) { }
static void __init pud_advanced_tests(struct mm_struct *mm,
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 006/156] mm/debug_vm_pgtable/savedwrite: enable savedwrite test with CONFIG_NUMA_BALANCING
2020-10-16 2:40 incoming Andrew Morton
` (5 preceding siblings ...)
2020-10-16 3:04 ` [patch 005/156] mm/debug_vm_pgtables/hugevmap: use the arch helper to identify huge vmap support Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 007/156] mm/debug_vm_pgtable/THP: mark the pte entry huge before using set_pmd/pud_at Andrew Morton
` (159 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable/savedwrite: enable savedwrite test with CONFIG_NUMA_BALANCING
Saved write support was added to track the write bit of a pte after
marking the pte protnone. This was done so that AUTONUMA can convert a
write pte to protnone and still track the old write bit. When converting
it back we set the pte write bit correctly thereby avoiding a write fault
again. Hence enable the test only when CONFIG_NUMA_BALANCING is enabled
and use protnone protflags.
Link: https://lkml.kernel.org/r/20200902114222.181353-6-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-savedwrite-enable-savedwrite-test-with-config_numa_balancing
+++ a/mm/debug_vm_pgtable.c
@@ -119,10 +119,14 @@ static void __init pte_savedwrite_tests(
{
pte_t pte = pfn_pte(pfn, prot);
+ if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
+ return;
+
pr_debug("Validating PTE saved write\n");
WARN_ON(!pte_savedwrite(pte_mk_savedwrite(pte_clear_savedwrite(pte))));
WARN_ON(pte_savedwrite(pte_clear_savedwrite(pte_mk_savedwrite(pte))));
}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void __init pmd_basic_tests(unsigned long pfn, pgprot_t prot)
{
@@ -234,6 +238,9 @@ static void __init pmd_savedwrite_tests(
{
pmd_t pmd = pfn_pmd(pfn, prot);
+ if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
+ return;
+
pr_debug("Validating PMD saved write\n");
WARN_ON(!pmd_savedwrite(pmd_mk_savedwrite(pmd_clear_savedwrite(pmd))));
WARN_ON(pmd_savedwrite(pmd_clear_savedwrite(pmd_mk_savedwrite(pmd))));
@@ -1019,8 +1026,8 @@ static int __init debug_vm_pgtable(void)
pmd_huge_tests(pmdp, pmd_aligned, prot);
pud_huge_tests(pudp, pud_aligned, prot);
- pte_savedwrite_tests(pte_aligned, prot);
- pmd_savedwrite_tests(pmd_aligned, prot);
+ pte_savedwrite_tests(pte_aligned, protnone);
+ pmd_savedwrite_tests(pmd_aligned, protnone);
pte_unmap_unlock(ptep, ptl);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 007/156] mm/debug_vm_pgtable/THP: mark the pte entry huge before using set_pmd/pud_at
2020-10-16 2:40 incoming Andrew Morton
` (6 preceding siblings ...)
2020-10-16 3:04 ` [patch 006/156] mm/debug_vm_pgtable/savedwrite: enable savedwrite test with CONFIG_NUMA_BALANCING Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 008/156] mm/debug_vm_pgtable/set_pte/pmd/pud: don't use set_*_at to update an existing pte entry Andrew Morton
` (158 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable/THP: mark the pte entry huge before using set_pmd/pud_at
kernel expects entries to be marked huge before we use
set_pmd_at()/set_pud_at().
Link: https://lkml.kernel.org/r/20200902114222.181353-7-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 20 +++++++++++---------
1 file changed, 11 insertions(+), 9 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-thp-mark-the-pte-entry-huge-before-using-set_pmd-pud_at
+++ a/mm/debug_vm_pgtable.c
@@ -155,7 +155,7 @@ static void __init pmd_advanced_tests(st
unsigned long pfn, unsigned long vaddr,
pgprot_t prot)
{
- pmd_t pmd = pfn_pmd(pfn, prot);
+ pmd_t pmd;
if (!has_transparent_hugepage())
return;
@@ -164,19 +164,19 @@ static void __init pmd_advanced_tests(st
/* Align the address wrt HPAGE_PMD_SIZE */
vaddr = (vaddr & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE;
- pmd = pfn_pmd(pfn, prot);
+ pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
set_pmd_at(mm, vaddr, pmdp, pmd);
pmdp_set_wrprotect(mm, vaddr, pmdp);
pmd = READ_ONCE(*pmdp);
WARN_ON(pmd_write(pmd));
- pmd = pfn_pmd(pfn, prot);
+ pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
set_pmd_at(mm, vaddr, pmdp, pmd);
pmdp_huge_get_and_clear(mm, vaddr, pmdp);
pmd = READ_ONCE(*pmdp);
WARN_ON(!pmd_none(pmd));
- pmd = pfn_pmd(pfn, prot);
+ pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
pmd = pmd_wrprotect(pmd);
pmd = pmd_mkclean(pmd);
set_pmd_at(mm, vaddr, pmdp, pmd);
@@ -236,7 +236,7 @@ static void __init pmd_huge_tests(pmd_t
static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot)
{
- pmd_t pmd = pfn_pmd(pfn, prot);
+ pmd_t pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
return;
@@ -276,7 +276,7 @@ static void __init pud_advanced_tests(st
unsigned long pfn, unsigned long vaddr,
pgprot_t prot)
{
- pud_t pud = pfn_pud(pfn, prot);
+ pud_t pud;
if (!has_transparent_hugepage())
return;
@@ -285,25 +285,27 @@ static void __init pud_advanced_tests(st
/* Align the address wrt HPAGE_PUD_SIZE */
vaddr = (vaddr & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE;
+ pud = pud_mkhuge(pfn_pud(pfn, prot));
set_pud_at(mm, vaddr, pudp, pud);
pudp_set_wrprotect(mm, vaddr, pudp);
pud = READ_ONCE(*pudp);
WARN_ON(pud_write(pud));
#ifndef __PAGETABLE_PMD_FOLDED
- pud = pfn_pud(pfn, prot);
+ pud = pud_mkhuge(pfn_pud(pfn, prot));
set_pud_at(mm, vaddr, pudp, pud);
pudp_huge_get_and_clear(mm, vaddr, pudp);
pud = READ_ONCE(*pudp);
WARN_ON(!pud_none(pud));
- pud = pfn_pud(pfn, prot);
+ pud = pud_mkhuge(pfn_pud(pfn, prot));
set_pud_at(mm, vaddr, pudp, pud);
pudp_huge_get_and_clear_full(mm, vaddr, pudp, 1);
pud = READ_ONCE(*pudp);
WARN_ON(!pud_none(pud));
#endif /* __PAGETABLE_PMD_FOLDED */
- pud = pfn_pud(pfn, prot);
+
+ pud = pud_mkhuge(pfn_pud(pfn, prot));
pud = pud_wrprotect(pud);
pud = pud_mkclean(pud);
set_pud_at(mm, vaddr, pudp, pud);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 008/156] mm/debug_vm_pgtable/set_pte/pmd/pud: don't use set_*_at to update an existing pte entry
2020-10-16 2:40 incoming Andrew Morton
` (7 preceding siblings ...)
2020-10-16 3:04 ` [patch 007/156] mm/debug_vm_pgtable/THP: mark the pte entry huge before using set_pmd/pud_at Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 009/156] mm/debug_vm_pgtable/locks: move non page table modifying test together Andrew Morton
` (157 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable/set_pte/pmd/pud: don't use set_*_at to update an existing pte entry
set_pte_at() should not be used to set a pte entry at locations that
already holds a valid pte entry. Architectures like ppc64 don't do TLB
invalidate in set_pte_at() and hence expect it to be used to set locations
that are not a valid PTE.
Link: https://lkml.kernel.org/r/20200902114222.181353-8-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 35 +++++++++++++++--------------------
1 file changed, 15 insertions(+), 20 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-set_pte-pmd-pud-dont-use-set__at-to-update-an-existing-pte-entry
+++ a/mm/debug_vm_pgtable.c
@@ -79,15 +79,18 @@ static void __init pte_advanced_tests(st
{
pte_t pte = pfn_pte(pfn, prot);
+ /*
+ * Architectures optimize set_pte_at by avoiding TLB flush.
+ * This requires set_pte_at to be not used to update an
+ * existing pte entry. Clear pte before we do set_pte_at
+ */
+
pr_debug("Validating PTE advanced\n");
pte = pfn_pte(pfn, prot);
set_pte_at(mm, vaddr, ptep, pte);
ptep_set_wrprotect(mm, vaddr, ptep);
pte = ptep_get(ptep);
WARN_ON(pte_write(pte));
-
- pte = pfn_pte(pfn, prot);
- set_pte_at(mm, vaddr, ptep, pte);
ptep_get_and_clear(mm, vaddr, ptep);
pte = ptep_get(ptep);
WARN_ON(!pte_none(pte));
@@ -101,13 +104,11 @@ static void __init pte_advanced_tests(st
ptep_set_access_flags(vma, vaddr, ptep, pte, 1);
pte = ptep_get(ptep);
WARN_ON(!(pte_write(pte) && pte_dirty(pte)));
-
- pte = pfn_pte(pfn, prot);
- set_pte_at(mm, vaddr, ptep, pte);
ptep_get_and_clear_full(mm, vaddr, ptep, 1);
pte = ptep_get(ptep);
WARN_ON(!pte_none(pte));
+ pte = pfn_pte(pfn, prot);
pte = pte_mkyoung(pte);
set_pte_at(mm, vaddr, ptep, pte);
ptep_test_and_clear_young(vma, vaddr, ptep);
@@ -169,9 +170,6 @@ static void __init pmd_advanced_tests(st
pmdp_set_wrprotect(mm, vaddr, pmdp);
pmd = READ_ONCE(*pmdp);
WARN_ON(pmd_write(pmd));
-
- pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
- set_pmd_at(mm, vaddr, pmdp, pmd);
pmdp_huge_get_and_clear(mm, vaddr, pmdp);
pmd = READ_ONCE(*pmdp);
WARN_ON(!pmd_none(pmd));
@@ -185,13 +183,11 @@ static void __init pmd_advanced_tests(st
pmdp_set_access_flags(vma, vaddr, pmdp, pmd, 1);
pmd = READ_ONCE(*pmdp);
WARN_ON(!(pmd_write(pmd) && pmd_dirty(pmd)));
-
- pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
- set_pmd_at(mm, vaddr, pmdp, pmd);
pmdp_huge_get_and_clear_full(vma, vaddr, pmdp, 1);
pmd = READ_ONCE(*pmdp);
WARN_ON(!pmd_none(pmd));
+ pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
pmd = pmd_mkyoung(pmd);
set_pmd_at(mm, vaddr, pmdp, pmd);
pmdp_test_and_clear_young(vma, vaddr, pmdp);
@@ -292,17 +288,9 @@ static void __init pud_advanced_tests(st
WARN_ON(pud_write(pud));
#ifndef __PAGETABLE_PMD_FOLDED
- pud = pud_mkhuge(pfn_pud(pfn, prot));
- set_pud_at(mm, vaddr, pudp, pud);
pudp_huge_get_and_clear(mm, vaddr, pudp);
pud = READ_ONCE(*pudp);
WARN_ON(!pud_none(pud));
-
- pud = pud_mkhuge(pfn_pud(pfn, prot));
- set_pud_at(mm, vaddr, pudp, pud);
- pudp_huge_get_and_clear_full(mm, vaddr, pudp, 1);
- pud = READ_ONCE(*pudp);
- WARN_ON(!pud_none(pud));
#endif /* __PAGETABLE_PMD_FOLDED */
pud = pud_mkhuge(pfn_pud(pfn, prot));
@@ -315,6 +303,13 @@ static void __init pud_advanced_tests(st
pud = READ_ONCE(*pudp);
WARN_ON(!(pud_write(pud) && pud_dirty(pud)));
+#ifndef __PAGETABLE_PMD_FOLDED
+ pudp_huge_get_and_clear_full(mm, vaddr, pudp, 1);
+ pud = READ_ONCE(*pudp);
+ WARN_ON(!pud_none(pud));
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+ pud = pud_mkhuge(pfn_pud(pfn, prot));
pud = pud_mkyoung(pud);
set_pud_at(mm, vaddr, pudp, pud);
pudp_test_and_clear_young(vma, vaddr, pudp);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 009/156] mm/debug_vm_pgtable/locks: move non page table modifying test together
2020-10-16 2:40 incoming Andrew Morton
` (8 preceding siblings ...)
2020-10-16 3:04 ` [patch 008/156] mm/debug_vm_pgtable/set_pte/pmd/pud: don't use set_*_at to update an existing pte entry Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 010/156] mm/debug_vm_pgtable/locks: take correct page table lock Andrew Morton
` (156 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable/locks: move non page table modifying test together
This will help in adding proper locks in a later patch
Link: https://lkml.kernel.org/r/20200902114222.181353-9-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 51 +++++++++++++++++++++-------------------
1 file changed, 28 insertions(+), 23 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-locks-move-non-page-table-modifying-test-together
+++ a/mm/debug_vm_pgtable.c
@@ -986,7 +986,7 @@ static int __init debug_vm_pgtable(void)
p4dp = p4d_alloc(mm, pgdp, vaddr);
pudp = pud_alloc(mm, p4dp, vaddr);
pmdp = pmd_alloc(mm, pudp, vaddr);
- ptep = pte_alloc_map_lock(mm, pmdp, vaddr, &ptl);
+ ptep = pte_alloc_map(mm, pmdp, vaddr);
/*
* Save all the page table page addresses as the page table
@@ -1006,33 +1006,12 @@ static int __init debug_vm_pgtable(void)
p4d_basic_tests(p4d_aligned, prot);
pgd_basic_tests(pgd_aligned, prot);
- pte_clear_tests(mm, ptep, vaddr);
- pmd_clear_tests(mm, pmdp);
- pud_clear_tests(mm, pudp);
- p4d_clear_tests(mm, p4dp);
- pgd_clear_tests(mm, pgdp);
-
- pte_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
- pmd_advanced_tests(mm, vma, pmdp, pmd_aligned, vaddr, prot);
- pud_advanced_tests(mm, vma, pudp, pud_aligned, vaddr, prot);
- hugetlb_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
-
pmd_leaf_tests(pmd_aligned, prot);
pud_leaf_tests(pud_aligned, prot);
- pmd_huge_tests(pmdp, pmd_aligned, prot);
- pud_huge_tests(pudp, pud_aligned, prot);
-
pte_savedwrite_tests(pte_aligned, protnone);
pmd_savedwrite_tests(pmd_aligned, protnone);
- pte_unmap_unlock(ptep, ptl);
-
- pmd_populate_tests(mm, pmdp, saved_ptep);
- pud_populate_tests(mm, pudp, saved_pmdp);
- p4d_populate_tests(mm, p4dp, saved_pudp);
- pgd_populate_tests(mm, pgdp, saved_p4dp);
-
pte_special_tests(pte_aligned, prot);
pte_protnone_tests(pte_aligned, protnone);
pmd_protnone_tests(pmd_aligned, protnone);
@@ -1050,11 +1029,37 @@ static int __init debug_vm_pgtable(void)
pmd_swap_tests(pmd_aligned, prot);
swap_migration_tests();
- hugetlb_basic_tests(pte_aligned, prot);
pmd_thp_tests(pmd_aligned, prot);
pud_thp_tests(pud_aligned, prot);
+ hugetlb_basic_tests(pte_aligned, prot);
+
+ pte_clear_tests(mm, ptep, vaddr);
+ pmd_clear_tests(mm, pmdp);
+ pud_clear_tests(mm, pudp);
+ p4d_clear_tests(mm, p4dp);
+ pgd_clear_tests(mm, pgdp);
+
+ ptl = pte_lockptr(mm, pmdp);
+ spin_lock(ptl);
+
+ pte_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
+ pmd_advanced_tests(mm, vma, pmdp, pmd_aligned, vaddr, prot);
+ pud_advanced_tests(mm, vma, pudp, pud_aligned, vaddr, prot);
+ hugetlb_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
+
+
+ pmd_huge_tests(pmdp, pmd_aligned, prot);
+ pud_huge_tests(pudp, pud_aligned, prot);
+
+ pte_unmap_unlock(ptep, ptl);
+
+ pmd_populate_tests(mm, pmdp, saved_ptep);
+ pud_populate_tests(mm, pudp, saved_pmdp);
+ p4d_populate_tests(mm, p4dp, saved_pudp);
+ pgd_populate_tests(mm, pgdp, saved_p4dp);
+
p4d_free(mm, saved_p4dp);
pud_free(mm, saved_pudp);
pmd_free(mm, saved_pmdp);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 010/156] mm/debug_vm_pgtable/locks: take correct page table lock
2020-10-16 2:40 incoming Andrew Morton
` (9 preceding siblings ...)
2020-10-16 3:04 ` [patch 009/156] mm/debug_vm_pgtable/locks: move non page table modifying test together Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 011/156] mm/debug_vm_pgtable/thp: use page table depost/withdraw with THP Andrew Morton
` (155 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable/locks: take correct page table lock
Make sure we call pte accessors with correct lock held.
Link: https://lkml.kernel.org/r/20200902114222.181353-10-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 35 ++++++++++++++++++++++-------------
1 file changed, 22 insertions(+), 13 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-locks-take-correct-page-table-lock
+++ a/mm/debug_vm_pgtable.c
@@ -1035,30 +1035,39 @@ static int __init debug_vm_pgtable(void)
hugetlb_basic_tests(pte_aligned, prot);
- pte_clear_tests(mm, ptep, vaddr);
- pmd_clear_tests(mm, pmdp);
- pud_clear_tests(mm, pudp);
- p4d_clear_tests(mm, p4dp);
- pgd_clear_tests(mm, pgdp);
+ /*
+ * Page table modifying tests. They need to hold
+ * proper page table lock.
+ */
ptl = pte_lockptr(mm, pmdp);
spin_lock(ptl);
-
+ pte_clear_tests(mm, ptep, vaddr);
pte_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
- pmd_advanced_tests(mm, vma, pmdp, pmd_aligned, vaddr, prot);
- pud_advanced_tests(mm, vma, pudp, pud_aligned, vaddr, prot);
- hugetlb_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
-
+ pte_unmap_unlock(ptep, ptl);
+ ptl = pmd_lock(mm, pmdp);
+ pmd_clear_tests(mm, pmdp);
+ pmd_advanced_tests(mm, vma, pmdp, pmd_aligned, vaddr, prot);
pmd_huge_tests(pmdp, pmd_aligned, prot);
+ pmd_populate_tests(mm, pmdp, saved_ptep);
+ spin_unlock(ptl);
+
+ ptl = pud_lock(mm, pudp);
+ pud_clear_tests(mm, pudp);
+ pud_advanced_tests(mm, vma, pudp, pud_aligned, vaddr, prot);
pud_huge_tests(pudp, pud_aligned, prot);
+ pud_populate_tests(mm, pudp, saved_pmdp);
+ spin_unlock(ptl);
- pte_unmap_unlock(ptep, ptl);
+ hugetlb_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
- pmd_populate_tests(mm, pmdp, saved_ptep);
- pud_populate_tests(mm, pudp, saved_pmdp);
+ spin_lock(&mm->page_table_lock);
+ p4d_clear_tests(mm, p4dp);
+ pgd_clear_tests(mm, pgdp);
p4d_populate_tests(mm, p4dp, saved_pudp);
pgd_populate_tests(mm, pgdp, saved_p4dp);
+ spin_unlock(&mm->page_table_lock);
p4d_free(mm, saved_p4dp);
pud_free(mm, saved_pudp);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 011/156] mm/debug_vm_pgtable/thp: use page table depost/withdraw with THP
2020-10-16 2:40 incoming Andrew Morton
` (10 preceding siblings ...)
2020-10-16 3:04 ` [patch 010/156] mm/debug_vm_pgtable/locks: take correct page table lock Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:04 ` [patch 012/156] mm/debug_vm_pgtable/pmd_clear: don't use pmd/pud_clear on pte entries Andrew Morton
` (154 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable/thp: use page table depost/withdraw with THP
Architectures like ppc64 use deposited page table while updating the huge
pte entries.
Link: https://lkml.kernel.org/r/20200902114222.181353-11-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-thp-use-page-table-depost-withdraw-with-thp
+++ a/mm/debug_vm_pgtable.c
@@ -154,7 +154,7 @@ static void __init pmd_basic_tests(unsig
static void __init pmd_advanced_tests(struct mm_struct *mm,
struct vm_area_struct *vma, pmd_t *pmdp,
unsigned long pfn, unsigned long vaddr,
- pgprot_t prot)
+ pgprot_t prot, pgtable_t pgtable)
{
pmd_t pmd;
@@ -165,6 +165,8 @@ static void __init pmd_advanced_tests(st
/* Align the address wrt HPAGE_PMD_SIZE */
vaddr = (vaddr & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE;
+ pgtable_trans_huge_deposit(mm, pmdp, pgtable);
+
pmd = pmd_mkhuge(pfn_pmd(pfn, prot));
set_pmd_at(mm, vaddr, pmdp, pmd);
pmdp_set_wrprotect(mm, vaddr, pmdp);
@@ -193,6 +195,8 @@ static void __init pmd_advanced_tests(st
pmdp_test_and_clear_young(vma, vaddr, pmdp);
pmd = READ_ONCE(*pmdp);
WARN_ON(pmd_young(pmd));
+
+ pgtable = pgtable_trans_huge_withdraw(mm, pmdp);
}
static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot)
@@ -371,7 +375,7 @@ static void __init pud_basic_tests(unsig
static void __init pmd_advanced_tests(struct mm_struct *mm,
struct vm_area_struct *vma, pmd_t *pmdp,
unsigned long pfn, unsigned long vaddr,
- pgprot_t prot)
+ pgprot_t prot, pgtable_t pgtable)
{
}
static void __init pud_advanced_tests(struct mm_struct *mm,
@@ -1048,7 +1052,7 @@ static int __init debug_vm_pgtable(void)
ptl = pmd_lock(mm, pmdp);
pmd_clear_tests(mm, pmdp);
- pmd_advanced_tests(mm, vma, pmdp, pmd_aligned, vaddr, prot);
+ pmd_advanced_tests(mm, vma, pmdp, pmd_aligned, vaddr, prot, saved_ptep);
pmd_huge_tests(pmdp, pmd_aligned, prot);
pmd_populate_tests(mm, pmdp, saved_ptep);
spin_unlock(ptl);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 012/156] mm/debug_vm_pgtable/pmd_clear: don't use pmd/pud_clear on pte entries
2020-10-16 2:40 incoming Andrew Morton
` (11 preceding siblings ...)
2020-10-16 3:04 ` [patch 011/156] mm/debug_vm_pgtable/thp: use page table depost/withdraw with THP Andrew Morton
@ 2020-10-16 3:04 ` Andrew Morton
2020-10-16 3:05 ` [patch 013/156] mm/debug_vm_pgtable/hugetlb: disable hugetlb test on ppc64 Andrew Morton
` (153 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:04 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable/pmd_clear: don't use pmd/pud_clear on pte entries
pmd_clear() should not be used to clear pmd level pte entries.
Link: https://lkml.kernel.org/r/20200902114222.181353-12-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-pmd_clear-dont-use-pmd-pud_clear-on-pte-entries
+++ a/mm/debug_vm_pgtable.c
@@ -196,6 +196,8 @@ static void __init pmd_advanced_tests(st
pmd = READ_ONCE(*pmdp);
WARN_ON(pmd_young(pmd));
+ /* Clear the pte entries */
+ pmdp_huge_get_and_clear(mm, vaddr, pmdp);
pgtable = pgtable_trans_huge_withdraw(mm, pmdp);
}
@@ -319,6 +321,8 @@ static void __init pud_advanced_tests(st
pudp_test_and_clear_young(vma, vaddr, pudp);
pud = READ_ONCE(*pudp);
WARN_ON(pud_young(pud));
+
+ pudp_huge_get_and_clear(mm, vaddr, pudp);
}
static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot)
@@ -442,8 +446,6 @@ static void __init pud_populate_tests(st
* This entry points to next level page table page.
* Hence this must not qualify as pud_bad().
*/
- pmd_clear(pmdp);
- pud_clear(pudp);
pud_populate(mm, pudp, pmdp);
pud = READ_ONCE(*pudp);
WARN_ON(pud_bad(pud));
@@ -575,7 +577,6 @@ static void __init pmd_populate_tests(st
* This entry points to next level page table page.
* Hence this must not qualify as pmd_bad().
*/
- pmd_clear(pmdp);
pmd_populate(mm, pmdp, pgtable);
pmd = READ_ONCE(*pmdp);
WARN_ON(pmd_bad(pmd));
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 013/156] mm/debug_vm_pgtable/hugetlb: disable hugetlb test on ppc64
2020-10-16 2:40 incoming Andrew Morton
` (12 preceding siblings ...)
2020-10-16 3:04 ` [patch 012/156] mm/debug_vm_pgtable/pmd_clear: don't use pmd/pud_clear on pte entries Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 014/156] mm/debug_vm_pgtable: avoid none pte in pte_clear_test Andrew Morton
` (152 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, christophe.leroy,
mm-commits, mpe, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable/hugetlb: disable hugetlb test on ppc64
The seems to be missing quite a lot of details w.r.t allocating the
correct pgtable_t page (huge_pte_alloc()), holding the right lock
(huge_pte_lock()) etc. The vma used is also not a hugetlb VMA.
ppc64 do have runtime checks within CONFIG_DEBUG_VM for most of these.
Hence disable the test on ppc64.
[anshuman.khandual@arm.com: drop hugetlb_advanced_tests()]
Link: https://lore.kernel.org/lkml/289c3fdb-1394-c1af-bdc4-5542907089dc@linux.ibm.com/#t
Link: https://lkml.kernel.org/r/1600914446-21890-1-git-send-email-anshuman.khandual@arm.com
Link: https://lkml.kernel.org/r/20200902114222.181353-13-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 51 ----------------------------------------
1 file changed, 51 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-hugetlb-disable-hugetlb-test-on-ppc64
+++ a/mm/debug_vm_pgtable.c
@@ -810,57 +810,8 @@ static void __init hugetlb_basic_tests(u
WARN_ON(!pte_huge(pte_mkhuge(pte)));
#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
}
-
-static void __init hugetlb_advanced_tests(struct mm_struct *mm,
- struct vm_area_struct *vma,
- pte_t *ptep, unsigned long pfn,
- unsigned long vaddr, pgprot_t prot)
-{
- struct page *page = pfn_to_page(pfn);
- pte_t pte = ptep_get(ptep);
- unsigned long paddr = __pfn_to_phys(pfn) & PMD_MASK;
-
- pr_debug("Validating HugeTLB advanced\n");
- pte = pte_mkhuge(mk_pte(pfn_to_page(PHYS_PFN(paddr)), prot));
- set_huge_pte_at(mm, vaddr, ptep, pte);
- barrier();
- WARN_ON(!pte_same(pte, huge_ptep_get(ptep)));
- huge_pte_clear(mm, vaddr, ptep, PMD_SIZE);
- pte = huge_ptep_get(ptep);
- WARN_ON(!huge_pte_none(pte));
-
- pte = mk_huge_pte(page, prot);
- set_huge_pte_at(mm, vaddr, ptep, pte);
- barrier();
- huge_ptep_set_wrprotect(mm, vaddr, ptep);
- pte = huge_ptep_get(ptep);
- WARN_ON(huge_pte_write(pte));
-
- pte = mk_huge_pte(page, prot);
- set_huge_pte_at(mm, vaddr, ptep, pte);
- barrier();
- huge_ptep_get_and_clear(mm, vaddr, ptep);
- pte = huge_ptep_get(ptep);
- WARN_ON(!huge_pte_none(pte));
-
- pte = mk_huge_pte(page, prot);
- pte = huge_pte_wrprotect(pte);
- set_huge_pte_at(mm, vaddr, ptep, pte);
- barrier();
- pte = huge_pte_mkwrite(pte);
- pte = huge_pte_mkdirty(pte);
- huge_ptep_set_access_flags(vma, vaddr, ptep, pte, 1);
- pte = huge_ptep_get(ptep);
- WARN_ON(!(huge_pte_write(pte) && huge_pte_dirty(pte)));
-}
#else /* !CONFIG_HUGETLB_PAGE */
static void __init hugetlb_basic_tests(unsigned long pfn, pgprot_t prot) { }
-static void __init hugetlb_advanced_tests(struct mm_struct *mm,
- struct vm_area_struct *vma,
- pte_t *ptep, unsigned long pfn,
- unsigned long vaddr, pgprot_t prot)
-{
-}
#endif /* CONFIG_HUGETLB_PAGE */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -1065,8 +1016,6 @@ static int __init debug_vm_pgtable(void)
pud_populate_tests(mm, pudp, saved_pmdp);
spin_unlock(ptl);
- hugetlb_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
-
spin_lock(&mm->page_table_lock);
p4d_clear_tests(mm, p4dp);
pgd_clear_tests(mm, pgdp);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 014/156] mm/debug_vm_pgtable: avoid none pte in pte_clear_test
2020-10-16 2:40 incoming Andrew Morton
` (13 preceding siblings ...)
2020-10-16 3:05 ` [patch 013/156] mm/debug_vm_pgtable/hugetlb: disable hugetlb test on ppc64 Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 015/156] mm/debug_vm_pgtable: avoid doing memory allocation with pgtable_t mapped Andrew Morton
` (151 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, aneesh.kumar, anshuman.khandual, aou, christophe.leroy,
linux, mm-commits, mpe, natechancellor, palmer, paul.walmsley,
torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable: avoid none pte in pte_clear_test
pte_clear_tests operate on an existing pte entry. Make sure that is not a
none pte entry.
[aneesh.kumar@linux.ibm.com: avoid kernel crash with riscv]
Link: https://lkml.kernel.org/r/20201015033206.140550-1-aneesh.kumar@linux.ibm.com
Link: https://lkml.kernel.org/r/20200902114222.181353-14-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-avoid-none-pte-in-pte_clear_test
+++ a/mm/debug_vm_pgtable.c
@@ -542,12 +542,15 @@ static void __init pgd_populate_tests(st
#endif /* PAGETABLE_P4D_FOLDED */
static void __init pte_clear_tests(struct mm_struct *mm, pte_t *ptep,
- unsigned long vaddr)
+ unsigned long pfn, unsigned long vaddr,
+ pgprot_t prot)
{
- pte_t pte = ptep_get(ptep);
+ pte_t pte = pfn_pte(pfn, prot);
pr_debug("Validating PTE clear\n");
+#ifndef CONFIG_RISCV
pte = __pte(pte_val(pte) | RANDOM_ORVALUE);
+#endif
set_pte_at(mm, vaddr, ptep, pte);
barrier();
pte_clear(mm, vaddr, ptep);
@@ -998,7 +1001,7 @@ static int __init debug_vm_pgtable(void)
ptl = pte_lockptr(mm, pmdp);
spin_lock(ptl);
- pte_clear_tests(mm, ptep, vaddr);
+ pte_clear_tests(mm, ptep, pte_aligned, vaddr, prot);
pte_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
pte_unmap_unlock(ptep, ptl);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 015/156] mm/debug_vm_pgtable: avoid doing memory allocation with pgtable_t mapped.
2020-10-16 2:40 incoming Andrew Morton
` (14 preceding siblings ...)
2020-10-16 3:05 ` [patch 014/156] mm/debug_vm_pgtable: avoid none pte in pte_clear_test Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 016/156] XArray: add xa_get_order Andrew Morton
` (150 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, aneesh.kumar, lkp, mm-commits, torvalds
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: mm/debug_vm_pgtable: avoid doing memory allocation with pgtable_t mapped.
With highmem, pte_alloc_map() keep the level4 page table mapped using
kmap_atomic(). Avoid doing new memory allocation with page table mapped
like above.
[ 9.409233] BUG: sleeping function called from invalid context at mm/page_alloc.c:4822
[ 9.410557] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper
[ 9.411932] no locks held by swapper/1.
[ 9.412595] CPU: 0 PID: 1 Comm: swapper Not tainted 5.9.0-rc3-00323-gc50eb1ed654b5 #2
[ 9.413824] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
[ 9.415207] Call Trace:
[ 9.415651] ? ___might_sleep.cold+0xa7/0xcc
[ 9.416367] ? __alloc_pages_nodemask+0x14c/0x5b0
[ 9.417055] ? swap_migration_tests+0x50/0x293
[ 9.417704] ? debug_vm_pgtable+0x4bc/0x708
[ 9.418287] ? swap_migration_tests+0x293/0x293
[ 9.418911] ? do_one_initcall+0x82/0x3cb
[ 9.419465] ? parse_args+0x1bd/0x280
[ 9.419983] ? rcu_read_lock_sched_held+0x36/0x60
[ 9.420673] ? trace_initcall_level+0x1f/0xf3
[ 9.421279] ? trace_initcall_level+0xbd/0xf3
[ 9.421881] ? do_basic_setup+0x9d/0xdd
[ 9.422410] ? do_basic_setup+0xc3/0xdd
[ 9.422938] ? kernel_init_freeable+0x72/0xa3
[ 9.423539] ? rest_init+0x134/0x134
[ 9.424055] ? kernel_init+0x5/0x12c
[ 9.424574] ? ret_from_fork+0x19/0x30
Link: https://lkml.kernel.org/r/20200913110327.645310-1-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/debug_vm_pgtable.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
--- a/mm/debug_vm_pgtable.c~mm-debug_vm_pgtable-avoid-doing-memory-allocation-with-pgtable_t-mapped
+++ a/mm/debug_vm_pgtable.c
@@ -945,7 +945,13 @@ static int __init debug_vm_pgtable(void)
p4dp = p4d_alloc(mm, pgdp, vaddr);
pudp = pud_alloc(mm, p4dp, vaddr);
pmdp = pmd_alloc(mm, pudp, vaddr);
- ptep = pte_alloc_map(mm, pmdp, vaddr);
+ /*
+ * Allocate pgtable_t
+ */
+ if (pte_alloc(mm, pmdp)) {
+ pr_err("pgtable allocation failed\n");
+ return 1;
+ }
/*
* Save all the page table page addresses as the page table
@@ -999,8 +1005,7 @@ static int __init debug_vm_pgtable(void)
* proper page table lock.
*/
- ptl = pte_lockptr(mm, pmdp);
- spin_lock(ptl);
+ ptep = pte_offset_map_lock(mm, pmdp, vaddr, &ptl);
pte_clear_tests(mm, ptep, pte_aligned, vaddr, prot);
pte_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot);
pte_unmap_unlock(ptep, ptl);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 016/156] XArray: add xa_get_order
2020-10-16 2:40 incoming Andrew Morton
` (15 preceding siblings ...)
2020-10-16 3:05 ` [patch 015/156] mm/debug_vm_pgtable: avoid doing memory allocation with pgtable_t mapped Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 017/156] XArray: add xas_split Andrew Morton
` (149 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, cai, kirill, mm-commits, songliubraving, torvalds, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: XArray: add xa_get_order
Patch series "Fix read-only THP for non-tmpfs filesystems".
As described more verbosely in the [3/3] changelog, we can inadvertently
put an order-0 page in the page cache which occupies 512 consecutive
entries. Users are running into this if they enable the
READ_ONLY_THP_FOR_FS config option; see
https://bugzilla.kernel.org/show_bug.cgi?id=206569 and Qian Cai has also
reported it here:
https://lore.kernel.org/lkml/20200616013309.GB815@lca.pw/
This is a rather intrusive way of fixing the problem, but has the
advantage that I've actually been testing it with the THP patches, which
means that it sees far more use than it does upstream -- indeed, Song has
been entirely unable to reproduce it. It also has the advantage that it
removes a few patches from my gargantuan backlog of THP patches.
This patch (of 3):
This function returns the order of the entry at the index. We need this
because there isn't space in the shadow entry to encode its order.
[akpm@linux-foundation.org: export xa_get_order to modules]
Link: https://lkml.kernel.org/r/20200903183029.14930-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200903183029.14930-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Qian Cai <cai@lca.pw>
Cc: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/xarray.h | 9 ++++++++
lib/test_xarray.c | 21 ++++++++++++++++++++
lib/xarray.c | 40 +++++++++++++++++++++++++++++++++++++++
3 files changed, 70 insertions(+)
--- a/include/linux/xarray.h~xarray-add-xa_get_order
+++ a/include/linux/xarray.h
@@ -1505,6 +1505,15 @@ void xas_pause(struct xa_state *);
void xas_create_range(struct xa_state *);
+#ifdef CONFIG_XARRAY_MULTI
+int xa_get_order(struct xarray *, unsigned long index);
+#else
+static inline int xa_get_order(struct xarray *xa, unsigned long index)
+{
+ return 0;
+}
+#endif
+
/**
* xas_reload() - Refetch an entry from the xarray.
* @xas: XArray operation state.
--- a/lib/test_xarray.c~xarray-add-xa_get_order
+++ a/lib/test_xarray.c
@@ -1649,6 +1649,26 @@ static noinline void check_account(struc
#endif
}
+static noinline void check_get_order(struct xarray *xa)
+{
+ unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1;
+ unsigned int order;
+ unsigned long i, j;
+
+ for (i = 0; i < 3; i++)
+ XA_BUG_ON(xa, xa_get_order(xa, i) != 0);
+
+ for (order = 0; order < max_order; order++) {
+ for (i = 0; i < 10; i++) {
+ xa_store_order(xa, i << order, order,
+ xa_mk_index(i << order), GFP_KERNEL);
+ for (j = i << order; j < (i + 1) << order; j++)
+ XA_BUG_ON(xa, xa_get_order(xa, j) != order);
+ xa_erase(xa, i << order);
+ }
+ }
+}
+
static noinline void check_destroy(struct xarray *xa)
{
unsigned long index;
@@ -1697,6 +1717,7 @@ static int xarray_checks(void)
check_reserve(&array);
check_reserve(&xa0);
check_multi_store(&array);
+ check_get_order(&array);
check_xa_alloc();
check_find(&array);
check_find_entry(&array);
--- a/lib/xarray.c~xarray-add-xa_get_order
+++ a/lib/xarray.c
@@ -1592,6 +1592,46 @@ unlock:
return xas_result(&xas, NULL);
}
EXPORT_SYMBOL(xa_store_range);
+
+/**
+ * xa_get_order() - Get the order of an entry.
+ * @xa: XArray.
+ * @index: Index of the entry.
+ *
+ * Return: A number between 0 and 63 indicating the order of the entry.
+ */
+int xa_get_order(struct xarray *xa, unsigned long index)
+{
+ XA_STATE(xas, xa, index);
+ void *entry;
+ int order = 0;
+
+ rcu_read_lock();
+ entry = xas_load(&xas);
+
+ if (!entry)
+ goto unlock;
+
+ if (!xas.xa_node)
+ goto unlock;
+
+ for (;;) {
+ unsigned int slot = xas.xa_offset + (1 << order);
+
+ if (slot >= XA_CHUNK_SIZE)
+ break;
+ if (!xa_is_sibling(xas.xa_node->slots[slot]))
+ break;
+ order++;
+ }
+
+ order += xas.xa_node->shift;
+unlock:
+ rcu_read_unlock();
+
+ return order;
+}
+EXPORT_SYMBOL(xa_get_order);
#endif /* CONFIG_XARRAY_MULTI */
/**
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 017/156] XArray: add xas_split
2020-10-16 2:40 incoming Andrew Morton
` (16 preceding siblings ...)
2020-10-16 3:05 ` [patch 016/156] XArray: add xa_get_order Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 018/156] mm/filemap: fix storing to a THP shadow entry Andrew Morton
` (148 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, cai, kirill, mm-commits, songliubraving, torvalds, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: XArray: add xas_split
In order to use multi-index entries for huge pages in the page cache, we
need to be able to split a multi-index entry (eg if a file is truncated in
the middle of a huge page entry). This version does not support splitting
more than one level of the tree at a time. This is an acceptable
limitation for the page cache as we do not expect to support order-12
pages in the near future.
[akpm@linux-foundation.org: export xas_split_alloc() to modules]
[willy@infradead.org: fix xarray split]
Link: https://lkml.kernel.org/r/20200910175450.GV6583@casper.infradead.org
[willy@infradead.org: fix xarray]
Link: https://lkml.kernel.org/r/20201001233943.GW20115@casper.infradead.org
Link: https://lkml.kernel.org/r/20200903183029.14930-3-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Qian Cai <cai@lca.pw>
Cc: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
Documentation/core-api/xarray.rst | 14 +-
include/linux/xarray.h | 13 ++
lib/test_xarray.c | 44 +++++++
lib/xarray.c | 168 ++++++++++++++++++++++++++--
4 files changed, 224 insertions(+), 15 deletions(-)
--- a/Documentation/core-api/xarray.rst~xarray-add-xas_split
+++ a/Documentation/core-api/xarray.rst
@@ -475,13 +475,15 @@ or iterations will move the index to the
Each entry will only be returned once, no matter how many indices it
occupies.
-Using xas_next() or xas_prev() with a multi-index xa_state
-is not supported. Using either of these functions on a multi-index entry
-will reveal sibling entries; these should be skipped over by the caller.
+Using xas_next() or xas_prev() with a multi-index xa_state is not
+supported. Using either of these functions on a multi-index entry will
+reveal sibling entries; these should be skipped over by the caller.
-Storing ``NULL`` into any index of a multi-index entry will set the entry
-at every index to ``NULL`` and dissolve the tie. Splitting a multi-index
-entry into entries occupying smaller ranges is not yet supported.
+Storing ``NULL`` into any index of a multi-index entry will set the
+entry at every index to ``NULL`` and dissolve the tie. A multi-index
+entry can be split into entries occupying smaller ranges by calling
+xas_split_alloc() without the xa_lock held, followed by taking the lock
+and calling xas_split().
Functions and structures
========================
--- a/include/linux/xarray.h~xarray-add-xas_split
+++ a/include/linux/xarray.h
@@ -1507,11 +1507,24 @@ void xas_create_range(struct xa_state *)
#ifdef CONFIG_XARRAY_MULTI
int xa_get_order(struct xarray *, unsigned long index);
+void xas_split(struct xa_state *, void *entry, unsigned int order);
+void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t);
#else
static inline int xa_get_order(struct xarray *xa, unsigned long index)
{
return 0;
}
+
+static inline void xas_split(struct xa_state *xas, void *entry,
+ unsigned int order)
+{
+ xas_store(xas, entry);
+}
+
+static inline void xas_split_alloc(struct xa_state *xas, void *entry,
+ unsigned int order, gfp_t gfp)
+{
+}
#endif
/**
--- a/lib/test_xarray.c~xarray-add-xas_split
+++ a/lib/test_xarray.c
@@ -1503,6 +1503,49 @@ static noinline void check_store_range(s
}
}
+#ifdef CONFIG_XARRAY_MULTI
+static void check_split_1(struct xarray *xa, unsigned long index,
+ unsigned int order)
+{
+ XA_STATE(xas, xa, index);
+ void *entry;
+ unsigned int i = 0;
+
+ xa_store_order(xa, index, order, xa, GFP_KERNEL);
+
+ xas_split_alloc(&xas, xa, order, GFP_KERNEL);
+ xas_lock(&xas);
+ xas_split(&xas, xa, order);
+ xas_unlock(&xas);
+
+ xa_for_each(xa, index, entry) {
+ XA_BUG_ON(xa, entry != xa);
+ i++;
+ }
+ XA_BUG_ON(xa, i != 1 << order);
+
+ xa_set_mark(xa, index, XA_MARK_0);
+ XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0));
+
+ xa_destroy(xa);
+}
+
+static noinline void check_split(struct xarray *xa)
+{
+ unsigned int order;
+
+ XA_BUG_ON(xa, !xa_empty(xa));
+
+ for (order = 1; order < 2 * XA_CHUNK_SHIFT; order++) {
+ check_split_1(xa, 0, order);
+ check_split_1(xa, 1UL << order, order);
+ check_split_1(xa, 3UL << order, order);
+ }
+}
+#else
+static void check_split(struct xarray *xa) { }
+#endif
+
static void check_align_1(struct xarray *xa, char *name)
{
int i;
@@ -1729,6 +1772,7 @@ static int xarray_checks(void)
check_store_range(&array);
check_store_iter(&array);
check_align(&xa0);
+ check_split(&array);
check_workingset(&array, 0);
check_workingset(&array, 64);
--- a/lib/xarray.c~xarray-add-xas_split
+++ a/lib/xarray.c
@@ -266,13 +266,14 @@ static void xa_node_free(struct xa_node
*/
static void xas_destroy(struct xa_state *xas)
{
- struct xa_node *node = xas->xa_alloc;
+ struct xa_node *next, *node = xas->xa_alloc;
- if (!node)
- return;
- XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
- kmem_cache_free(radix_tree_node_cachep, node);
- xas->xa_alloc = NULL;
+ while (node) {
+ XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+ next = rcu_dereference_raw(node->parent);
+ radix_tree_node_rcu_free(&node->rcu_head);
+ xas->xa_alloc = node = next;
+ }
}
/**
@@ -304,6 +305,7 @@ bool xas_nomem(struct xa_state *xas, gfp
xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
if (!xas->xa_alloc)
return false;
+ xas->xa_alloc->parent = NULL;
XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
xas->xa_node = XAS_RESTART;
return true;
@@ -339,6 +341,7 @@ static bool __xas_nomem(struct xa_state
}
if (!xas->xa_alloc)
return false;
+ xas->xa_alloc->parent = NULL;
XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
xas->xa_node = XAS_RESTART;
return true;
@@ -403,7 +406,7 @@ static unsigned long xas_size(const stru
/*
* Use this to calculate the maximum index that will need to be created
* in order to add the entry described by @xas. Because we cannot store a
- * multiple-index entry at index 0, the calculation is a little more complex
+ * multi-index entry at index 0, the calculation is a little more complex
* than you might expect.
*/
static unsigned long xas_max(struct xa_state *xas)
@@ -946,6 +949,153 @@ void xas_init_marks(const struct xa_stat
}
EXPORT_SYMBOL_GPL(xas_init_marks);
+#ifdef CONFIG_XARRAY_MULTI
+static unsigned int node_get_marks(struct xa_node *node, unsigned int offset)
+{
+ unsigned int marks = 0;
+ xa_mark_t mark = XA_MARK_0;
+
+ for (;;) {
+ if (node_get_mark(node, offset, mark))
+ marks |= 1 << (__force unsigned int)mark;
+ if (mark == XA_MARK_MAX)
+ break;
+ mark_inc(mark);
+ }
+
+ return marks;
+}
+
+static void node_set_marks(struct xa_node *node, unsigned int offset,
+ struct xa_node *child, unsigned int marks)
+{
+ xa_mark_t mark = XA_MARK_0;
+
+ for (;;) {
+ if (marks & (1 << (__force unsigned int)mark)) {
+ node_set_mark(node, offset, mark);
+ if (child)
+ node_mark_all(child, mark);
+ }
+ if (mark == XA_MARK_MAX)
+ break;
+ mark_inc(mark);
+ }
+}
+
+/**
+ * xas_split_alloc() - Allocate memory for splitting an entry.
+ * @xas: XArray operation state.
+ * @entry: New entry which will be stored in the array.
+ * @order: New entry order.
+ * @gfp: Memory allocation flags.
+ *
+ * This function should be called before calling xas_split().
+ * If necessary, it will allocate new nodes (and fill them with @entry)
+ * to prepare for the upcoming split of an entry of @order size into
+ * entries of the order stored in the @xas.
+ *
+ * Context: May sleep if @gfp flags permit.
+ */
+void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order,
+ gfp_t gfp)
+{
+ unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+ unsigned int mask = xas->xa_sibs;
+
+ /* XXX: no support for splitting really large entries yet */
+ if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order))
+ goto nomem;
+ if (xas->xa_shift + XA_CHUNK_SHIFT > order)
+ return;
+
+ do {
+ unsigned int i;
+ void *sibling;
+ struct xa_node *node;
+
+ node = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+ if (!node)
+ goto nomem;
+ node->array = xas->xa;
+ for (i = 0; i < XA_CHUNK_SIZE; i++) {
+ if ((i & mask) == 0) {
+ RCU_INIT_POINTER(node->slots[i], entry);
+ sibling = xa_mk_sibling(0);
+ } else {
+ RCU_INIT_POINTER(node->slots[i], sibling);
+ }
+ }
+ RCU_INIT_POINTER(node->parent, xas->xa_alloc);
+ xas->xa_alloc = node;
+ } while (sibs-- > 0);
+
+ return;
+nomem:
+ xas_destroy(xas);
+ xas_set_err(xas, -ENOMEM);
+}
+EXPORT_SYMBOL_GPL(xas_split_alloc);
+
+/**
+ * xas_split() - Split a multi-index entry into smaller entries.
+ * @xas: XArray operation state.
+ * @entry: New entry to store in the array.
+ * @order: New entry order.
+ *
+ * The value in the entry is copied to all the replacement entries.
+ *
+ * Context: Any context. The caller should hold the xa_lock.
+ */
+void xas_split(struct xa_state *xas, void *entry, unsigned int order)
+{
+ unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+ unsigned int offset, marks;
+ struct xa_node *node;
+ void *curr = xas_load(xas);
+ int values = 0;
+
+ node = xas->xa_node;
+ if (xas_top(node))
+ return;
+
+ marks = node_get_marks(node, xas->xa_offset);
+
+ offset = xas->xa_offset + sibs;
+ do {
+ if (xas->xa_shift < node->shift) {
+ struct xa_node *child = xas->xa_alloc;
+
+ xas->xa_alloc = rcu_dereference_raw(child->parent);
+ child->shift = node->shift - XA_CHUNK_SHIFT;
+ child->offset = offset;
+ child->count = XA_CHUNK_SIZE;
+ child->nr_values = xa_is_value(entry) ?
+ XA_CHUNK_SIZE : 0;
+ RCU_INIT_POINTER(child->parent, node);
+ node_set_marks(node, offset, child, marks);
+ rcu_assign_pointer(node->slots[offset],
+ xa_mk_node(child));
+ if (xa_is_value(curr))
+ values--;
+ } else {
+ unsigned int canon = offset - xas->xa_sibs;
+
+ node_set_marks(node, canon, NULL, marks);
+ rcu_assign_pointer(node->slots[canon], entry);
+ while (offset > canon)
+ rcu_assign_pointer(node->slots[offset--],
+ xa_mk_sibling(canon));
+ values += (xa_is_value(entry) - xa_is_value(curr)) *
+ (xas->xa_sibs + 1);
+ }
+ } while (offset-- > xas->xa_offset);
+
+ node->nr_values += values;
+}
+EXPORT_SYMBOL_GPL(xas_split);
+#endif
+
/**
* xas_pause() - Pause a walk to drop a lock.
* @xas: XArray operation state.
@@ -1407,7 +1557,7 @@ EXPORT_SYMBOL(__xa_store);
* @gfp: Memory allocation flags.
*
* After this function returns, loads from this index will return @entry.
- * Storing into an existing multislot entry updates the entry of every index.
+ * Storing into an existing multi-index entry updates the entry of every index.
* The marks associated with @index are unaffected unless @entry is %NULL.
*
* Context: Any context. Takes and releases the xa_lock.
@@ -1549,7 +1699,7 @@ static void xas_set_range(struct xa_stat
*
* After this function returns, loads from any index between @first and @last,
* inclusive will return @entry.
- * Storing into an existing multislot entry updates the entry of every index.
+ * Storing into an existing multi-index entry updates the entry of every index.
* The marks associated with @index are unaffected unless @entry is %NULL.
*
* Context: Process context. Takes and releases the xa_lock. May sleep
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 018/156] mm/filemap: fix storing to a THP shadow entry
2020-10-16 2:40 incoming Andrew Morton
` (17 preceding siblings ...)
2020-10-16 3:05 ` [patch 017/156] XArray: add xas_split Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 019/156] mm/filemap: fix page cache removal for arbitrary sized THPs Andrew Morton
` (147 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, cai, kirill, mm-commits, songliubraving, torvalds, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/filemap: fix storing to a THP shadow entry
When a THP is removed from the page cache by reclaim, we replace it with a
shadow entry that occupies all slots of the XArray previously occupied by
the THP. If the user then accesses that page again, we only allocate a
single page, but storing it into the shadow entry replaces all entries
with that one page. That leads to bugs like
page dumped because: VM_BUG_ON_PAGE(page_to_pgoff(page) != offset)
------------[ cut here ]------------
kernel BUG at mm/filemap.c:2529!
https://bugzilla.kernel.org/show_bug.cgi?id=206569
This is hard to reproduce with mainline, but happens regularly with the
THP patchset (as so many more THPs are created). This solution is take
from the THP patchset. It splits the shadow entry into order-0 pieces at
the time that we bring a new page into cache.
Link: https://lkml.kernel.org/r/20200903183029.14930-4-willy@infradead.org
Fixes: 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS")
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/filemap.c | 42 +++++++++++++++++++++++++++++++-----------
1 file changed, 31 insertions(+), 11 deletions(-)
--- a/mm/filemap.c~mm-filemap-fix-storing-to-a-thp-shadow-entry
+++ a/mm/filemap.c
@@ -829,13 +829,12 @@ EXPORT_SYMBOL_GPL(replace_page_cache_pag
static int __add_to_page_cache_locked(struct page *page,
struct address_space *mapping,
- pgoff_t offset, gfp_t gfp_mask,
+ pgoff_t offset, gfp_t gfp,
void **shadowp)
{
XA_STATE(xas, &mapping->i_pages, offset);
int huge = PageHuge(page);
int error;
- void *old;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapBacked(page), page);
@@ -846,25 +845,46 @@ static int __add_to_page_cache_locked(st
page->index = offset;
if (!huge) {
- error = mem_cgroup_charge(page, current->mm, gfp_mask);
+ error = mem_cgroup_charge(page, current->mm, gfp);
if (error)
goto error;
}
+ gfp &= GFP_RECLAIM_MASK;
+
do {
+ unsigned int order = xa_get_order(xas.xa, xas.xa_index);
+ void *entry, *old = NULL;
+
+ if (order > thp_order(page))
+ xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
+ order, gfp);
xas_lock_irq(&xas);
- old = xas_load(&xas);
- if (old && !xa_is_value(old))
- xas_set_err(&xas, -EEXIST);
+ xas_for_each_conflict(&xas, entry) {
+ old = entry;
+ if (!xa_is_value(entry)) {
+ xas_set_err(&xas, -EEXIST);
+ goto unlock;
+ }
+ }
+
+ if (old) {
+ if (shadowp)
+ *shadowp = old;
+ /* entry may have been split before we acquired lock */
+ order = xa_get_order(xas.xa, xas.xa_index);
+ if (order > thp_order(page)) {
+ xas_split(&xas, old, order);
+ xas_reset(&xas);
+ }
+ }
+
xas_store(&xas, page);
if (xas_error(&xas))
goto unlock;
- if (xa_is_value(old)) {
+ if (old)
mapping->nrexceptional--;
- if (shadowp)
- *shadowp = old;
- }
mapping->nrpages++;
/* hugetlb pages do not participate in page cache accounting */
@@ -872,7 +892,7 @@ static int __add_to_page_cache_locked(st
__inc_lruvec_page_state(page, NR_FILE_PAGES);
unlock:
xas_unlock_irq(&xas);
- } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK));
+ } while (xas_nomem(&xas, gfp));
if (xas_error(&xas)) {
error = xas_error(&xas);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 019/156] mm/filemap: fix page cache removal for arbitrary sized THPs
2020-10-16 2:40 incoming Andrew Morton
` (18 preceding siblings ...)
2020-10-16 3:05 ` [patch 018/156] mm/filemap: fix storing to a THP shadow entry Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 020/156] mm/memory: remove page fault assumption of compound page size Andrew Morton
` (146 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill.shutemov, mm-commits, torvalds, willy, ying.huang
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/filemap: fix page cache removal for arbitrary sized THPs
Patch series "Remove assumptions of THP size".
There are a number of places in the VM which assume that a THP is a PMD in
size. That's true today, and remains true after this patch series, but
this is a prerequisite for switching to arbitrary-sized THPs.
thp_nr_pages() still returns either HPAGE_PMD_NR or 1, but will be changed
later.
This patch (of 11):
page_cache_free_page() assumes THPs are PMD_SIZE; fix that assumption.
Link: https://lkml.kernel.org/r/20200908195539.25896-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200908195539.25896-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/filemap.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/filemap.c~mm-filemap-fix-page-cache-removal-for-arbitrary-sized-thps
+++ a/mm/filemap.c
@@ -249,7 +249,7 @@ static void page_cache_free_page(struct
freepage(page);
if (PageTransHuge(page) && !PageHuge(page)) {
- page_ref_sub(page, HPAGE_PMD_NR);
+ page_ref_sub(page, thp_nr_pages(page));
VM_BUG_ON_PAGE(page_count(page) <= 0, page);
} else {
put_page(page);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 020/156] mm/memory: remove page fault assumption of compound page size
2020-10-16 2:40 incoming Andrew Morton
` (19 preceding siblings ...)
2020-10-16 3:05 ` [patch 019/156] mm/filemap: fix page cache removal for arbitrary sized THPs Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 021/156] mm/page_owner: change split_page_owner to take a count Andrew Morton
` (145 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill.shutemov, mm-commits, torvalds, willy, ying.huang
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/memory: remove page fault assumption of compound page size
A compound page in the page cache will not necessarily be of PMD size,
so check explicitly.
[willy@infradead.org: fix remove page fault assumption of compound page size]
Link: https://lkml.kernel.org/r/20201001152259.14932-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200908195539.25896-3-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
--- a/mm/memory.c~mm-memory-remove-page-fault-assumption-of-compound-page-size
+++ a/mm/memory.c
@@ -3709,13 +3709,14 @@ static vm_fault_t do_set_pmd(struct vm_f
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
pmd_t entry;
int i;
- vm_fault_t ret;
+ vm_fault_t ret = VM_FAULT_FALLBACK;
if (!transhuge_vma_suitable(vma, haddr))
- return VM_FAULT_FALLBACK;
+ return ret;
- ret = VM_FAULT_FALLBACK;
page = compound_head(page);
+ if (compound_order(page) != HPAGE_PMD_ORDER)
+ return ret;
/*
* Archs like ppc64 need additonal space to store information
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 021/156] mm/page_owner: change split_page_owner to take a count
2020-10-16 2:40 incoming Andrew Morton
` (20 preceding siblings ...)
2020-10-16 3:05 ` [patch 020/156] mm/memory: remove page fault assumption of compound page size Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 022/156] mm/huge_memory: fix total_mapcount assumption of page size Andrew Morton
` (144 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill.shutemov, mm-commits, sjpark, torvalds, willy, ying.huang
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/page_owner: change split_page_owner to take a count
The implementation of split_page_owner() prefers a count rather than the
old order of the page. When we support a variable size THP, we won't
have the order at this point, but we will have the number of pages.
So change the interface to what the caller and callee would prefer.
Link: https://lkml.kernel.org/r/20200908195539.25896-4-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/page_owner.h | 6 +++---
mm/huge_memory.c | 2 +-
mm/page_owner.c | 4 ++--
3 files changed, 6 insertions(+), 6 deletions(-)
--- a/include/linux/page_owner.h~mm-page_owner-change-split_page_owner-to-take-a-count
+++ a/include/linux/page_owner.h
@@ -11,7 +11,7 @@ extern struct page_ext_operations page_o
extern void __reset_page_owner(struct page *page, unsigned int order);
extern void __set_page_owner(struct page *page,
unsigned int order, gfp_t gfp_mask);
-extern void __split_page_owner(struct page *page, unsigned int order);
+extern void __split_page_owner(struct page *page, unsigned int nr);
extern void __copy_page_owner(struct page *oldpage, struct page *newpage);
extern void __set_page_owner_migrate_reason(struct page *page, int reason);
extern void __dump_page_owner(struct page *page);
@@ -31,10 +31,10 @@ static inline void set_page_owner(struct
__set_page_owner(page, order, gfp_mask);
}
-static inline void split_page_owner(struct page *page, unsigned int order)
+static inline void split_page_owner(struct page *page, unsigned int nr)
{
if (static_branch_unlikely(&page_owner_inited))
- __split_page_owner(page, order);
+ __split_page_owner(page, nr);
}
static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
{
--- a/mm/huge_memory.c~mm-page_owner-change-split_page_owner-to-take-a-count
+++ a/mm/huge_memory.c
@@ -2454,7 +2454,7 @@ static void __split_huge_page(struct pag
ClearPageCompound(head);
- split_page_owner(head, HPAGE_PMD_ORDER);
+ split_page_owner(head, HPAGE_PMD_NR);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
--- a/mm/page_owner.c~mm-page_owner-change-split_page_owner-to-take-a-count
+++ a/mm/page_owner.c
@@ -204,7 +204,7 @@ void __set_page_owner_migrate_reason(str
page_owner->last_migrate_reason = reason;
}
-void __split_page_owner(struct page *page, unsigned int order)
+void __split_page_owner(struct page *page, unsigned int nr)
{
int i;
struct page_ext *page_ext = lookup_page_ext(page);
@@ -213,7 +213,7 @@ void __split_page_owner(struct page *pag
if (unlikely(!page_ext))
return;
- for (i = 0; i < (1 << order); i++) {
+ for (i = 0; i < nr; i++) {
page_owner = get_page_owner(page_ext);
page_owner->order = 0;
page_ext = page_ext_next(page_ext);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 022/156] mm/huge_memory: fix total_mapcount assumption of page size
2020-10-16 2:40 incoming Andrew Morton
` (21 preceding siblings ...)
2020-10-16 3:05 ` [patch 021/156] mm/page_owner: change split_page_owner to take a count Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 023/156] mm/huge_memory: fix split " Andrew Morton
` (143 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill, mm-commits, sjpark, torvalds, willy, ying.huang
From: "Kirill A. Shutemov" <kirill@shutemov.name>
Subject: mm/huge_memory: fix total_mapcount assumption of page size
File THPs may now be of arbitrary order.
Link: https://lkml.kernel.org/r/20200908195539.25896-5-willy@infradead.org
Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/huge_memory.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
--- a/mm/huge_memory.c~mm-huge_memory-fix-total_mapcount-assumption-of-page-size
+++ a/mm/huge_memory.c
@@ -2494,7 +2494,7 @@ static void __split_huge_page(struct pag
int total_mapcount(struct page *page)
{
- int i, compound, ret;
+ int i, compound, nr, ret;
VM_BUG_ON_PAGE(PageTail(page), page);
@@ -2502,16 +2502,17 @@ int total_mapcount(struct page *page)
return atomic_read(&page->_mapcount) + 1;
compound = compound_mapcount(page);
+ nr = compound_nr(page);
if (PageHuge(page))
return compound;
ret = compound;
- for (i = 0; i < HPAGE_PMD_NR; i++)
+ for (i = 0; i < nr; i++)
ret += atomic_read(&page[i]._mapcount) + 1;
/* File pages has compound_mapcount included in _mapcount */
if (!PageAnon(page))
- return ret - compound * HPAGE_PMD_NR;
+ return ret - compound * nr;
if (PageDoubleMap(page))
- ret -= HPAGE_PMD_NR;
+ ret -= nr;
return ret;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 023/156] mm/huge_memory: fix split assumption of page size
2020-10-16 2:40 incoming Andrew Morton
` (22 preceding siblings ...)
2020-10-16 3:05 ` [patch 022/156] mm/huge_memory: fix total_mapcount assumption of page size Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 024/156] mm/huge_memory: fix page_trans_huge_mapcount assumption of THP size Andrew Morton
` (142 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill, mm-commits, sjpark, torvalds, willy, ying.huang
From: "Kirill A. Shutemov" <kirill@shutemov.name>
Subject: mm/huge_memory: fix split assumption of page size
File THPs may now be of arbitrary size, and we can't rely on that size
after doing the split so remember the number of pages before we start the
split.
Link: https://lkml.kernel.org/r/20200908195539.25896-6-willy@infradead.org
Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/huge_memory.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
--- a/mm/huge_memory.c~mm-huge_memory-fix-split-assumption-of-page-size
+++ a/mm/huge_memory.c
@@ -2335,13 +2335,13 @@ static void unmap_page(struct page *page
VM_BUG_ON_PAGE(!unmap_success, page);
}
-static void remap_page(struct page *page)
+static void remap_page(struct page *page, unsigned int nr)
{
int i;
if (PageTransHuge(page)) {
remove_migration_ptes(page, page, true);
} else {
- for (i = 0; i < HPAGE_PMD_NR; i++)
+ for (i = 0; i < nr; i++)
remove_migration_ptes(page + i, page + i, true);
}
}
@@ -2419,6 +2419,7 @@ static void __split_huge_page(struct pag
struct lruvec *lruvec;
struct address_space *swap_cache = NULL;
unsigned long offset = 0;
+ unsigned int nr = thp_nr_pages(head);
int i;
lruvec = mem_cgroup_page_lruvec(head, pgdat);
@@ -2434,7 +2435,7 @@ static void __split_huge_page(struct pag
xa_lock(&swap_cache->i_pages);
}
- for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
+ for (i = nr - 1; i >= 1; i--) {
__split_huge_page_tail(head, i, lruvec, list);
/* Some pages can be beyond i_size: drop them from page cache */
if (head[i].index >= end) {
@@ -2454,7 +2455,7 @@ static void __split_huge_page(struct pag
ClearPageCompound(head);
- split_page_owner(head, HPAGE_PMD_NR);
+ split_page_owner(head, nr);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
@@ -2473,9 +2474,9 @@ static void __split_huge_page(struct pag
spin_unlock_irqrestore(&pgdat->lru_lock, flags);
- remap_page(head);
+ remap_page(head, nr);
- for (i = 0; i < HPAGE_PMD_NR; i++) {
+ for (i = 0; i < nr; i++) {
struct page *subpage = head + i;
if (subpage == page)
continue;
@@ -2729,7 +2730,7 @@ int split_huge_page_to_list(struct page
fail: if (mapping)
xa_unlock(&mapping->i_pages);
spin_unlock_irqrestore(&pgdata->lru_lock, flags);
- remap_page(head);
+ remap_page(head, thp_nr_pages(head));
ret = -EBUSY;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 024/156] mm/huge_memory: fix page_trans_huge_mapcount assumption of THP size
2020-10-16 2:40 incoming Andrew Morton
` (23 preceding siblings ...)
2020-10-16 3:05 ` [patch 023/156] mm/huge_memory: fix split " Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 025/156] mm/huge_memory: fix can_split_huge_page " Andrew Morton
` (141 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill.shutemov, mm-commits, sjpark, torvalds, willy, ying.huang
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/huge_memory: fix page_trans_huge_mapcount assumption of THP size
Ask the page what size it is instead of assuming it's PMD size.
Link: https://lkml.kernel.org/r/20200908195539.25896-7-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/huge_memory.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/mm/huge_memory.c~mm-huge_memory-fix-page_trans_huge_mapcount-assumption-of-thp-size
+++ a/mm/huge_memory.c
@@ -2558,14 +2558,14 @@ int page_trans_huge_mapcount(struct page
page = compound_head(page);
_total_mapcount = ret = 0;
- for (i = 0; i < HPAGE_PMD_NR; i++) {
+ for (i = 0; i < thp_nr_pages(page); i++) {
mapcount = atomic_read(&page[i]._mapcount) + 1;
ret = max(ret, mapcount);
_total_mapcount += mapcount;
}
if (PageDoubleMap(page)) {
ret -= 1;
- _total_mapcount -= HPAGE_PMD_NR;
+ _total_mapcount -= thp_nr_pages(page);
}
mapcount = compound_mapcount(page);
ret += mapcount;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 025/156] mm/huge_memory: fix can_split_huge_page assumption of THP size
2020-10-16 2:40 incoming Andrew Morton
` (24 preceding siblings ...)
2020-10-16 3:05 ` [patch 024/156] mm/huge_memory: fix page_trans_huge_mapcount assumption of THP size Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 026/156] mm/rmap: fix assumptions " Andrew Morton
` (140 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill.shutemov, mm-commits, sjpark, torvalds, willy, ying.huang
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/huge_memory: fix can_split_huge_page assumption of THP size
Ask the page how many subpages it has instead of assuming it's PMD size.
Link: https://lkml.kernel.org/r/20200908195539.25896-8-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Acked-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/huge_memory.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/mm/huge_memory.c~mm-huge_memory-fix-can_split_huge_page-assumption-of-thp-size
+++ a/mm/huge_memory.c
@@ -2582,9 +2582,9 @@ bool can_split_huge_page(struct page *pa
/* Additional pins from page cache */
if (PageAnon(page))
- extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0;
+ extra_pins = PageSwapCache(page) ? thp_nr_pages(page) : 0;
else
- extra_pins = HPAGE_PMD_NR;
+ extra_pins = thp_nr_pages(page);
if (pextra_pins)
*pextra_pins = extra_pins;
return total_mapcount(page) == page_count(page) - extra_pins - 1;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 026/156] mm/rmap: fix assumptions of THP size
2020-10-16 2:40 incoming Andrew Morton
` (25 preceding siblings ...)
2020-10-16 3:05 ` [patch 025/156] mm/huge_memory: fix can_split_huge_page " Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 027/156] mm/truncate: fix truncation for pages of arbitrary size Andrew Morton
` (139 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill.shutemov, mm-commits, sjpark, torvalds, willy, ying.huang
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/rmap: fix assumptions of THP size
Ask the page what size it is instead of assuming it's PMD size. Do this
for anon pages as well as file pages for when someone decides to support
that. Leave the assumption alone for pages which are PMD mapped; we don't
currently grow THPs beyond PMD size, so we don't need to change this code
yet.
Link: https://lkml.kernel.org/r/20200908195539.25896-9-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/rmap.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
--- a/mm/rmap.c~mm-rmap-fix-assumptions-of-thp-size
+++ a/mm/rmap.c
@@ -1205,7 +1205,7 @@ void page_add_file_rmap(struct page *pag
VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page);
lock_page_memcg(page);
if (compound && PageTransHuge(page)) {
- for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) {
+ for (i = 0, nr = 0; i < thp_nr_pages(page); i++) {
if (atomic_inc_and_test(&page[i]._mapcount))
nr++;
}
@@ -1246,7 +1246,7 @@ static void page_remove_file_rmap(struct
/* page still mapped by someone else? */
if (compound && PageTransHuge(page)) {
- for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) {
+ for (i = 0, nr = 0; i < thp_nr_pages(page); i++) {
if (atomic_add_negative(-1, &page[i]._mapcount))
nr++;
}
@@ -1293,7 +1293,7 @@ static void page_remove_anon_compound_rm
* Subpages can be mapped with PTEs too. Check how many of
* them are still mapped.
*/
- for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) {
+ for (i = 0, nr = 0; i < thp_nr_pages(page); i++) {
if (atomic_add_negative(-1, &page[i]._mapcount))
nr++;
}
@@ -1303,10 +1303,10 @@ static void page_remove_anon_compound_rm
* page of the compound page is unmapped, but at least one
* small page is still mapped.
*/
- if (nr && nr < HPAGE_PMD_NR)
+ if (nr && nr < thp_nr_pages(page))
deferred_split_huge_page(page);
} else {
- nr = HPAGE_PMD_NR;
+ nr = thp_nr_pages(page);
}
if (unlikely(PageMlocked(page)))
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 027/156] mm/truncate: fix truncation for pages of arbitrary size
2020-10-16 2:40 incoming Andrew Morton
` (26 preceding siblings ...)
2020-10-16 3:05 ` [patch 026/156] mm/rmap: fix assumptions " Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 028/156] mm/page-writeback: support tail pages in wait_for_stable_page Andrew Morton
` (138 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill.shutemov, mm-commits, sjpark, torvalds, willy, ying.huang
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/truncate: fix truncation for pages of arbitrary size
Remove the assumption that a compound page is HPAGE_PMD_SIZE, and the
assumption that any page is PAGE_SIZE.
Link: https://lkml.kernel.org/r/20200908195539.25896-10-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/truncate.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
--- a/mm/truncate.c~mm-truncate-fix-truncation-for-pages-of-arbitrary-size
+++ a/mm/truncate.c
@@ -168,7 +168,7 @@ void do_invalidatepage(struct page *page
* becomes orphaned. It will be left on the LRU and may even be mapped into
* user pagetables if we're racing with filemap_fault().
*
- * We need to bale out if page->mapping is no longer equal to the original
+ * We need to bail out if page->mapping is no longer equal to the original
* mapping. This happens a) when the VM reclaimed the page while we waited on
* its lock, b) when a concurrent invalidate_mapping_pages got there first and
* c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
@@ -177,12 +177,12 @@ static void
truncate_cleanup_page(struct address_space *mapping, struct page *page)
{
if (page_mapped(page)) {
- pgoff_t nr = PageTransHuge(page) ? HPAGE_PMD_NR : 1;
+ unsigned int nr = thp_nr_pages(page);
unmap_mapping_pages(mapping, page->index, nr, false);
}
if (page_has_private(page))
- do_invalidatepage(page, 0, PAGE_SIZE);
+ do_invalidatepage(page, 0, thp_size(page));
/*
* Some filesystems seem to re-dirty the page even after
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 028/156] mm/page-writeback: support tail pages in wait_for_stable_page
2020-10-16 2:40 incoming Andrew Morton
` (27 preceding siblings ...)
2020-10-16 3:05 ` [patch 027/156] mm/truncate: fix truncation for pages of arbitrary size Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:05 ` [patch 029/156] mm/vmscan: allow arbitrary sized pages to be paged out Andrew Morton
` (137 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill.shutemov, mm-commits, sjpark, torvalds, willy, ying.huang
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/page-writeback: support tail pages in wait_for_stable_page
page->mapping is undefined for tail pages, so operate exclusively on the
head page.
Link: https://lkml.kernel.org/r/20200908195539.25896-11-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/page-writeback.c | 1 +
1 file changed, 1 insertion(+)
--- a/mm/page-writeback.c~mm-page-writeback-support-tail-pages-in-wait_for_stable_page
+++ a/mm/page-writeback.c
@@ -2849,6 +2849,7 @@ EXPORT_SYMBOL_GPL(wait_on_page_writeback
*/
void wait_for_stable_page(struct page *page)
{
+ page = thp_head(page);
if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES)
wait_on_page_writeback(page);
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 029/156] mm/vmscan: allow arbitrary sized pages to be paged out
2020-10-16 2:40 incoming Andrew Morton
` (28 preceding siblings ...)
2020-10-16 3:05 ` [patch 028/156] mm/page-writeback: support tail pages in wait_for_stable_page Andrew Morton
@ 2020-10-16 3:05 ` Andrew Morton
2020-10-16 3:06 ` [patch 030/156] fs: add a filesystem flag for THPs Andrew Morton
` (136 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:05 UTC (permalink / raw)
To: akpm, kirill.shutemov, mm-commits, sjpark, torvalds, willy, ying.huang
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/vmscan: allow arbitrary sized pages to be paged out
Remove the assumption that a compound page has HPAGE_PMD_NR pins from the
page cache.
Link: https://lkml.kernel.org/r/20200908195539.25896-12-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/vmscan.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
--- a/mm/vmscan.c~mm-vmscan-allow-arbitrary-sized-pages-to-be-paged-out
+++ a/mm/vmscan.c
@@ -725,8 +725,7 @@ static inline int is_page_cache_freeable
* that isolated the page, the page cache and optional buffer
* heads at page->private.
*/
- int page_cache_pins = PageTransHuge(page) && PageSwapCache(page) ?
- HPAGE_PMD_NR : 1;
+ int page_cache_pins = thp_nr_pages(page);
return page_count(page) - page_has_private(page) == 1 + page_cache_pins;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 030/156] fs: add a filesystem flag for THPs
2020-10-16 2:40 incoming Andrew Morton
` (29 preceding siblings ...)
2020-10-16 3:05 ` [patch 029/156] mm/vmscan: allow arbitrary sized pages to be paged out Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 031/156] fs: do not update nr_thps for mappings which support THPs Andrew Morton
` (135 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dchinner, hannes, hch, hughd, kirill.shutemov, mm-commits,
riel, songliubraving, torvalds, viro, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: fs: add a filesystem flag for THPs
The page cache needs to know whether the filesystem supports THPs so that
it doesn't send THPs to filesystems which can't handle them. Dave Chinner
points out that getting from the page mapping to the filesystem type is
too many steps (mapping->host->i_sb->s_type->fs_flags) so cache that
information in the address space flags.
Link: https://lkml.kernel.org/r/20200916032717.22917-1-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/inode.c | 2 ++
include/linux/fs.h | 1 +
include/linux/pagemap.h | 6 ++++++
mm/shmem.c | 2 +-
4 files changed, 10 insertions(+), 1 deletion(-)
--- a/fs/inode.c~fs-add-a-filesystem-flag-for-thps
+++ a/fs/inode.c
@@ -181,6 +181,8 @@ int inode_init_always(struct super_block
mapping->a_ops = &empty_aops;
mapping->host = inode;
mapping->flags = 0;
+ if (sb->s_type->fs_flags & FS_THP_SUPPORT)
+ __set_bit(AS_THP_SUPPORT, &mapping->flags);
mapping->wb_err = 0;
atomic_set(&mapping->i_mmap_writable, 0);
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
--- a/include/linux/fs.h~fs-add-a-filesystem-flag-for-thps
+++ a/include/linux/fs.h
@@ -2209,6 +2209,7 @@ struct file_system_type {
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
#define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */
+#define FS_THP_SUPPORT 8192 /* Remove once all fs converted */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
int (*init_fs_context)(struct fs_context *);
const struct fs_parameter_spec *parameters;
--- a/include/linux/pagemap.h~fs-add-a-filesystem-flag-for-thps
+++ a/include/linux/pagemap.h
@@ -29,6 +29,7 @@ enum mapping_flags {
AS_EXITING = 4, /* final truncate in progress */
/* writeback related tags are not used */
AS_NO_WRITEBACK_TAGS = 5,
+ AS_THP_SUPPORT = 6, /* THPs supported */
};
/**
@@ -120,6 +121,11 @@ static inline void mapping_set_gfp_mask(
m->gfp_mask = mask;
}
+static inline bool mapping_thp_support(struct address_space *mapping)
+{
+ return test_bit(AS_THP_SUPPORT, &mapping->flags);
+}
+
void release_pages(struct page **pages, int nr);
/*
--- a/mm/shmem.c~fs-add-a-filesystem-flag-for-thps
+++ a/mm/shmem.c
@@ -3984,7 +3984,7 @@ static struct file_system_type shmem_fs_
.parameters = shmem_fs_parameters,
#endif
.kill_sb = kill_litter_super,
- .fs_flags = FS_USERNS_MOUNT,
+ .fs_flags = FS_USERNS_MOUNT | FS_THP_SUPPORT,
};
int __init shmem_init(void)
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 031/156] fs: do not update nr_thps for mappings which support THPs
2020-10-16 2:40 incoming Andrew Morton
` (30 preceding siblings ...)
2020-10-16 3:06 ` [patch 030/156] fs: add a filesystem flag for THPs Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 032/156] mm: fix a race during THP splitting Andrew Morton
` (134 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dchinner, hannes, hch, hughd, kirill.shutemov, mm-commits,
riel, songliubraving, torvalds, viro, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: fs: do not update nr_thps for mappings which support THPs
The nr_thps counter is to support THPs in the page cache when the
filesystem doesn't understand THPs. Eventually it will be removed, but we
should still support filesystems which do not understand THPs yet. Move
the nr_thp manipulation functions to filemap.h since they're page-cache
specific.
Link: https://lkml.kernel.org/r/20200916032717.22917-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/fs.h | 27 ---------------------------
include/linux/pagemap.h | 29 +++++++++++++++++++++++++++++
2 files changed, 29 insertions(+), 27 deletions(-)
--- a/include/linux/fs.h~fs-do-not-update-nr_thps-for-mappings-which-support-thps
+++ a/include/linux/fs.h
@@ -2697,33 +2697,6 @@ static inline errseq_t file_sample_sb_er
return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err);
}
-static inline int filemap_nr_thps(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
- return atomic_read(&mapping->nr_thps);
-#else
- return 0;
-#endif
-}
-
-static inline void filemap_nr_thps_inc(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
- atomic_inc(&mapping->nr_thps);
-#else
- WARN_ON_ONCE(1);
-#endif
-}
-
-static inline void filemap_nr_thps_dec(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
- atomic_dec(&mapping->nr_thps);
-#else
- WARN_ON_ONCE(1);
-#endif
-}
-
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
int datasync);
extern int vfs_fsync(struct file *file, int datasync);
--- a/include/linux/pagemap.h~fs-do-not-update-nr_thps-for-mappings-which-support-thps
+++ a/include/linux/pagemap.h
@@ -126,6 +126,35 @@ static inline bool mapping_thp_support(s
return test_bit(AS_THP_SUPPORT, &mapping->flags);
}
+static inline int filemap_nr_thps(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+ return atomic_read(&mapping->nr_thps);
+#else
+ return 0;
+#endif
+}
+
+static inline void filemap_nr_thps_inc(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+ if (!mapping_thp_support(mapping))
+ atomic_inc(&mapping->nr_thps);
+#else
+ WARN_ON_ONCE(1);
+#endif
+}
+
+static inline void filemap_nr_thps_dec(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+ if (!mapping_thp_support(mapping))
+ atomic_dec(&mapping->nr_thps);
+#else
+ WARN_ON_ONCE(1);
+#endif
+}
+
void release_pages(struct page **pages, int nr);
/*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 032/156] mm: fix a race during THP splitting
2020-10-16 2:40 incoming Andrew Morton
` (31 preceding siblings ...)
2020-10-16 3:06 ` [patch 031/156] fs: do not update nr_thps for mappings which support THPs Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 033/156] mm/readahead: add DEFINE_READAHEAD Andrew Morton
` (133 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: aarcange, akpm, aquini, hughd, kirill.shutemov, mm-commits,
torvalds, willy, ying.huang
From: Huang Ying <ying.huang@intel.com>
Subject: mm: fix a race during THP splitting
It is reported that the following bug is triggered if the HDD is used as
swap device,
[ 5758.157556] BUG: kernel NULL pointer dereference, address: 0000000000000007
[ 5758.165331] #PF: supervisor write access in kernel mode
[ 5758.171161] #PF: error_code(0x0002) - not-present page
[ 5758.176894] PGD 0 P4D 0
[ 5758.179721] Oops: 0002 [#1] SMP PTI
[ 5758.183614] CPU: 10 PID: 316 Comm: kswapd1 Kdump: loaded Tainted: G S --------- --- 5.9.0-0.rc3.1.tst.el8.x86_64 #1
[ 5758.196717] Hardware name: Intel Corporation S2600CP/S2600CP, BIOS SE5C600.86B.02.01.0002.082220131453 08/22/2013
[ 5758.208176] RIP: 0010:split_swap_cluster+0x47/0x60
[ 5758.213522] Code: c1 e3 06 48 c1 eb 0f 48 8d 1c d8 48 89 df e8 d0 20 6a 00 80 63 07 fb 48 85 db 74 16 48 89 df c6 07 00 66 66 66 90 31 c0 5b c3 <80> 24 25 07 00 00 00 fb 31 c0 5b c3 b8 f0 ff ff ff 5b c3 66 0f 1f
[ 5758.234478] RSP: 0018:ffffb147442d7af0 EFLAGS: 00010246
[ 5758.240309] RAX: 0000000000000000 RBX: 000000000014b217 RCX: ffffb14779fd9000
[ 5758.248281] RDX: 000000000014b217 RSI: ffff9c52f2ab1400 RDI: 000000000014b217
[ 5758.256246] RBP: ffffe00c51168080 R08: ffffe00c5116fe08 R09: ffff9c52fffd3000
[ 5758.264208] R10: ffffe00c511537c8 R11: ffff9c52fffd3c90 R12: 0000000000000000
[ 5758.272172] R13: ffffe00c51170000 R14: ffffe00c51170000 R15: ffffe00c51168040
[ 5758.280134] FS: 0000000000000000(0000) GS:ffff9c52f2a80000(0000) knlGS:0000000000000000
[ 5758.289163] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 5758.295575] CR2: 0000000000000007 CR3: 0000000022a0e003 CR4: 00000000000606e0
[ 5758.303538] Call Trace:
[ 5758.306273] split_huge_page_to_list+0x88b/0x950
[ 5758.311433] deferred_split_scan+0x1ca/0x310
[ 5758.316202] do_shrink_slab+0x12c/0x2a0
[ 5758.320491] shrink_slab+0x20f/0x2c0
[ 5758.324482] shrink_node+0x240/0x6c0
[ 5758.328469] balance_pgdat+0x2d1/0x550
[ 5758.332652] kswapd+0x201/0x3c0
[ 5758.336157] ? finish_wait+0x80/0x80
[ 5758.340147] ? balance_pgdat+0x550/0x550
[ 5758.344525] kthread+0x114/0x130
[ 5758.348126] ? kthread_park+0x80/0x80
[ 5758.352214] ret_from_fork+0x22/0x30
[ 5758.356203] Modules linked in: fuse zram rfkill sunrpc intel_rapl_msr intel_rapl_common sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp mgag200 iTCO_wdt crct10dif_pclmul iTCO_vendor_support drm_kms_helper crc32_pclmul ghash_clmulni_intel syscopyarea sysfillrect sysimgblt fb_sys_fops cec rapl joydev intel_cstate ipmi_si ipmi_devintf drm intel_uncore i2c_i801 ipmi_msghandler pcspkr lpc_ich mei_me i2c_smbus mei ioatdma ip_tables xfs libcrc32c sr_mod sd_mod cdrom t10_pi sg igb ahci libahci i2c_algo_bit crc32c_intel libata dca wmi dm_mirror dm_region_hash dm_log dm_mod
[ 5758.412673] CR2: 0000000000000007
[ 0.000000] Linux version 5.9.0-0.rc3.1.tst.el8.x86_64 (mockbuild@x86-vm-15.build.eng.bos.redhat.com) (gcc (GCC) 8.3.1 20191121 (Red Hat 8.3.1-5), GNU ld version 2.30-79.el8) #1 SMP Wed Sep 9 16:03:34 EDT 2020
After further digging it's found that the following race condition exists in the
original implementation,
CPU1 CPU2
---- ----
deferred_split_scan()
split_huge_page(page) /* page isn't compound head */
split_huge_page_to_list(page, NULL)
__split_huge_page(page, )
ClearPageCompound(head)
/* unlock all subpages except page (not head) */
add_to_swap(head) /* not THP */
get_swap_page(head)
add_to_swap_cache(head, )
SetPageSwapCache(head)
if PageSwapCache(head)
split_swap_cluster(/* swap entry of head */)
/* Deref sis->cluster_info: NULL accessing! */
So, in split_huge_page_to_list(), PageSwapCache() is called for the already
split and unlocked "head", which may be added to swap cache in another CPU. So
split_swap_cluster() may be called wrongly.
To fix the race, the call to split_swap_cluster() is moved to
__split_huge_page() before all subpages are unlocked. So that the
PageSwapCache() is stable.
Link: https://lkml.kernel.org/r/20201009073647.1531083-1-ying.huang@intel.com
Fixes: 59807685a7e77 ("mm, THP, swap: support splitting THP for THP swap out")
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reported-by: Rafael Aquini <aquini@redhat.com>
Tested-by: Rafael Aquini <aquini@redhat.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/huge_memory.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
--- a/mm/huge_memory.c~mm-fix-a-race-during-split-thp
+++ a/mm/huge_memory.c
@@ -2476,6 +2476,12 @@ static void __split_huge_page(struct pag
remap_page(head, nr);
+ if (PageSwapCache(head)) {
+ swp_entry_t entry = { .val = page_private(head) };
+
+ split_swap_cluster(entry);
+ }
+
for (i = 0; i < nr; i++) {
struct page *subpage = head + i;
if (subpage == page)
@@ -2711,12 +2717,7 @@ int split_huge_page_to_list(struct page
}
__split_huge_page(page, list, end, flags);
- if (PageSwapCache(head)) {
- swp_entry_t entry = { .val = page_private(head) };
-
- ret = split_swap_cluster(entry);
- } else
- ret = 0;
+ ret = 0;
} else {
if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
pr_alert("total_mapcount: %u, page_count(): %u\n",
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 033/156] mm/readahead: add DEFINE_READAHEAD
2020-10-16 2:40 incoming Andrew Morton
` (32 preceding siblings ...)
2020-10-16 3:06 ` [patch 032/156] mm: fix a race during THP splitting Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 034/156] mm/readahead: make page_cache_ra_unbounded take a readahead_control Andrew Morton
` (132 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dhowells, ebiggers, mm-commits, torvalds, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/readahead: add DEFINE_READAHEAD
Patch series "Readahead patches for 5.9/5.10".
These are infrastructure for both the THP patchset and for the fscache
rewrite,
For both pieces of infrastructure being build on top of this patchset, we
want the ractl to be available higher in the call-stack.
For David's work, he wants to add the 'critical page' to the ractl so that
he knows which page NEEDS to be brought in from storage, and which ones
are nice-to-have. We might want something similar in block storage too.
It used to be simple -- the first page was the critical one, but then mmap
added fault-around and so for that usecase, the middle page is the
critical one. Anyway, I don't have any code to show that yet, we just
know that the lowest point in the callchain where we have that information
is do_sync_mmap_readahead() and so the ractl needs to start its life
there.
For THP, we havew the code that needs it. It's actually the apex patch to
the series; the one which finally starts to allocate THPs and present them
to consenting filesystems:
http://git.infradead.org/users/willy/pagecache.git/commitdiff/798bcf30ab2eff278caad03a9edca74d2f8ae760
This patch (of 8):
Allow for a more concise definition of a struct readahead_control.
Link: https://lkml.kernel.org/r/20200903140844.14194-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200903140844.14194-3-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Eric Biggers <ebiggers@google.com>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/pagemap.h | 7 +++++++
mm/readahead.c | 6 +-----
2 files changed, 8 insertions(+), 5 deletions(-)
--- a/include/linux/pagemap.h~mm-readahead-add-define_readahead
+++ a/include/linux/pagemap.h
@@ -812,6 +812,13 @@ struct readahead_control {
unsigned int _batch_count;
};
+#define DEFINE_READAHEAD(rac, f, m, i) \
+ struct readahead_control rac = { \
+ .file = f, \
+ .mapping = m, \
+ ._index = i, \
+ }
+
/**
* readahead_page - Get the next page to read.
* @rac: The current readahead request.
--- a/mm/readahead.c~mm-readahead-add-define_readahead
+++ a/mm/readahead.c
@@ -179,11 +179,7 @@ void page_cache_readahead_unbounded(stru
{
LIST_HEAD(page_pool);
gfp_t gfp_mask = readahead_gfp_mask(mapping);
- struct readahead_control rac = {
- .mapping = mapping,
- .file = file,
- ._index = index,
- };
+ DEFINE_READAHEAD(rac, file, mapping, index);
unsigned long i;
/*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 034/156] mm/readahead: make page_cache_ra_unbounded take a readahead_control
2020-10-16 2:40 incoming Andrew Morton
` (33 preceding siblings ...)
2020-10-16 3:06 ` [patch 033/156] mm/readahead: add DEFINE_READAHEAD Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 035/156] mm/readahead: make do_page_cache_ra " Andrew Morton
` (131 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dhowells, ebiggers, mm-commits, torvalds, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/readahead: make page_cache_ra_unbounded take a readahead_control
Define it in the callers instead of in page_cache_ra_unbounded().
Link: https://lkml.kernel.org/r/20200903140844.14194-4-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/ext4/verity.c | 4 ++--
fs/f2fs/verity.c | 4 ++--
include/linux/pagemap.h | 5 ++---
mm/readahead.c | 30 ++++++++++++++----------------
4 files changed, 20 insertions(+), 23 deletions(-)
--- a/fs/ext4/verity.c~mm-readahead-make-page_cache_ra_unbounded-take-a-readahead_control
+++ a/fs/ext4/verity.c
@@ -349,6 +349,7 @@ static struct page *ext4_read_merkle_tre
pgoff_t index,
unsigned long num_ra_pages)
{
+ DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
struct page *page;
index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;
@@ -358,8 +359,7 @@ static struct page *ext4_read_merkle_tre
if (page)
put_page(page);
else if (num_ra_pages > 1)
- page_cache_readahead_unbounded(inode->i_mapping, NULL,
- index, num_ra_pages, 0);
+ page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
page = read_mapping_page(inode->i_mapping, index, NULL);
}
return page;
--- a/fs/f2fs/verity.c~mm-readahead-make-page_cache_ra_unbounded-take-a-readahead_control
+++ a/fs/f2fs/verity.c
@@ -228,6 +228,7 @@ static struct page *f2fs_read_merkle_tre
pgoff_t index,
unsigned long num_ra_pages)
{
+ DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
struct page *page;
index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;
@@ -237,8 +238,7 @@ static struct page *f2fs_read_merkle_tre
if (page)
put_page(page);
else if (num_ra_pages > 1)
- page_cache_readahead_unbounded(inode->i_mapping, NULL,
- index, num_ra_pages, 0);
+ page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
page = read_mapping_page(inode->i_mapping, index, NULL);
}
return page;
--- a/include/linux/pagemap.h~mm-readahead-make-page_cache_ra_unbounded-take-a-readahead_control
+++ a/include/linux/pagemap.h
@@ -768,9 +768,8 @@ void page_cache_sync_readahead(struct ad
void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
struct file *, struct page *, pgoff_t index,
unsigned long req_count);
-void page_cache_readahead_unbounded(struct address_space *, struct file *,
- pgoff_t index, unsigned long nr_to_read,
- unsigned long lookahead_count);
+void page_cache_ra_unbounded(struct readahead_control *,
+ unsigned long nr_to_read, unsigned long lookahead_count);
/*
* Like add_to_page_cache_locked, but used to add newly allocated pages:
--- a/mm/readahead.c~mm-readahead-make-page_cache_ra_unbounded-take-a-readahead_control
+++ a/mm/readahead.c
@@ -158,10 +158,8 @@ out:
}
/**
- * page_cache_readahead_unbounded - Start unchecked readahead.
- * @mapping: File address space.
- * @file: This instance of the open file; used for authentication.
- * @index: First page index to read.
+ * page_cache_ra_unbounded - Start unchecked readahead.
+ * @ractl: Readahead control.
* @nr_to_read: The number of pages to read.
* @lookahead_size: Where to start the next readahead.
*
@@ -173,13 +171,13 @@ out:
* Context: File is referenced by caller. Mutexes may be held by caller.
* May sleep, but will not reenter filesystem to reclaim memory.
*/
-void page_cache_readahead_unbounded(struct address_space *mapping,
- struct file *file, pgoff_t index, unsigned long nr_to_read,
- unsigned long lookahead_size)
+void page_cache_ra_unbounded(struct readahead_control *ractl,
+ unsigned long nr_to_read, unsigned long lookahead_size)
{
+ struct address_space *mapping = ractl->mapping;
+ unsigned long index = readahead_index(ractl);
LIST_HEAD(page_pool);
gfp_t gfp_mask = readahead_gfp_mask(mapping);
- DEFINE_READAHEAD(rac, file, mapping, index);
unsigned long i;
/*
@@ -200,7 +198,7 @@ void page_cache_readahead_unbounded(stru
for (i = 0; i < nr_to_read; i++) {
struct page *page = xa_load(&mapping->i_pages, index + i);
- BUG_ON(index + i != rac._index + rac._nr_pages);
+ BUG_ON(index + i != ractl->_index + ractl->_nr_pages);
if (page && !xa_is_value(page)) {
/*
@@ -211,7 +209,7 @@ void page_cache_readahead_unbounded(stru
* have a stable reference to this page, and it's
* not worth getting one just for that.
*/
- read_pages(&rac, &page_pool, true);
+ read_pages(ractl, &page_pool, true);
continue;
}
@@ -224,12 +222,12 @@ void page_cache_readahead_unbounded(stru
} else if (add_to_page_cache_lru(page, mapping, index + i,
gfp_mask) < 0) {
put_page(page);
- read_pages(&rac, &page_pool, true);
+ read_pages(ractl, &page_pool, true);
continue;
}
if (i == nr_to_read - lookahead_size)
SetPageReadahead(page);
- rac._nr_pages++;
+ ractl->_nr_pages++;
}
/*
@@ -237,10 +235,10 @@ void page_cache_readahead_unbounded(stru
* uptodate then the caller will launch readpage again, and
* will then handle the error.
*/
- read_pages(&rac, &page_pool, false);
+ read_pages(ractl, &page_pool, false);
memalloc_nofs_restore(nofs);
}
-EXPORT_SYMBOL_GPL(page_cache_readahead_unbounded);
+EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);
/*
* __do_page_cache_readahead() actually reads a chunk of disk. It allocates
@@ -252,6 +250,7 @@ void __do_page_cache_readahead(struct ad
struct file *file, pgoff_t index, unsigned long nr_to_read,
unsigned long lookahead_size)
{
+ DEFINE_READAHEAD(ractl, file, mapping, index);
struct inode *inode = mapping->host;
loff_t isize = i_size_read(inode);
pgoff_t end_index; /* The last page we want to read */
@@ -266,8 +265,7 @@ void __do_page_cache_readahead(struct ad
if (nr_to_read > end_index - index)
nr_to_read = end_index - index + 1;
- page_cache_readahead_unbounded(mapping, file, index, nr_to_read,
- lookahead_size);
+ page_cache_ra_unbounded(&ractl, nr_to_read, lookahead_size);
}
/*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 035/156] mm/readahead: make do_page_cache_ra take a readahead_control
2020-10-16 2:40 incoming Andrew Morton
` (34 preceding siblings ...)
2020-10-16 3:06 ` [patch 034/156] mm/readahead: make page_cache_ra_unbounded take a readahead_control Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 036/156] mm/readahead: make ondemand_readahead " Andrew Morton
` (130 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dhowells, ebiggers, mm-commits, torvalds, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/readahead: make do_page_cache_ra take a readahead_control
Rename __do_page_cache_readahead() to do_page_cache_ra() and call it
directly from ondemand_readahead() instead of indirecting via ra_submit().
Link: https://lkml.kernel.org/r/20200903140844.14194-5-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/internal.h | 11 +++++------
mm/readahead.c | 28 +++++++++++++++-------------
2 files changed, 20 insertions(+), 19 deletions(-)
--- a/mm/internal.h~mm-readahead-make-do_page_cache_ra-take-a-readahead_control
+++ a/mm/internal.h
@@ -51,18 +51,17 @@ void unmap_page_range(struct mmu_gather
void force_page_cache_readahead(struct address_space *, struct file *,
pgoff_t index, unsigned long nr_to_read);
-void __do_page_cache_readahead(struct address_space *, struct file *,
- pgoff_t index, unsigned long nr_to_read,
- unsigned long lookahead_size);
+void do_page_cache_ra(struct readahead_control *,
+ unsigned long nr_to_read, unsigned long lookahead_size);
/*
* Submit IO for the read-ahead request in file_ra_state.
*/
static inline void ra_submit(struct file_ra_state *ra,
- struct address_space *mapping, struct file *filp)
+ struct address_space *mapping, struct file *file)
{
- __do_page_cache_readahead(mapping, filp,
- ra->start, ra->size, ra->async_size);
+ DEFINE_READAHEAD(ractl, file, mapping, ra->start);
+ do_page_cache_ra(&ractl, ra->size, ra->async_size);
}
struct page *find_get_entry(struct address_space *mapping, pgoff_t index);
--- a/mm/readahead.c~mm-readahead-make-do_page_cache_ra-take-a-readahead_control
+++ a/mm/readahead.c
@@ -241,17 +241,16 @@ void page_cache_ra_unbounded(struct read
EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);
/*
- * __do_page_cache_readahead() actually reads a chunk of disk. It allocates
+ * do_page_cache_ra() actually reads a chunk of disk. It allocates
* the pages first, then submits them for I/O. This avoids the very bad
* behaviour which would occur if page allocations are causing VM writeback.
* We really don't want to intermingle reads and writes like that.
*/
-void __do_page_cache_readahead(struct address_space *mapping,
- struct file *file, pgoff_t index, unsigned long nr_to_read,
- unsigned long lookahead_size)
+void do_page_cache_ra(struct readahead_control *ractl,
+ unsigned long nr_to_read, unsigned long lookahead_size)
{
- DEFINE_READAHEAD(ractl, file, mapping, index);
- struct inode *inode = mapping->host;
+ struct inode *inode = ractl->mapping->host;
+ unsigned long index = readahead_index(ractl);
loff_t isize = i_size_read(inode);
pgoff_t end_index; /* The last page we want to read */
@@ -265,7 +264,7 @@ void __do_page_cache_readahead(struct ad
if (nr_to_read > end_index - index)
nr_to_read = end_index - index + 1;
- page_cache_ra_unbounded(&ractl, nr_to_read, lookahead_size);
+ page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size);
}
/*
@@ -273,10 +272,11 @@ void __do_page_cache_readahead(struct ad
* memory at once.
*/
void force_page_cache_readahead(struct address_space *mapping,
- struct file *filp, pgoff_t index, unsigned long nr_to_read)
+ struct file *file, pgoff_t index, unsigned long nr_to_read)
{
+ DEFINE_READAHEAD(ractl, file, mapping, index);
struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
- struct file_ra_state *ra = &filp->f_ra;
+ struct file_ra_state *ra = &file->f_ra;
unsigned long max_pages;
if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages &&
@@ -294,7 +294,7 @@ void force_page_cache_readahead(struct a
if (this_chunk > nr_to_read)
this_chunk = nr_to_read;
- __do_page_cache_readahead(mapping, filp, index, this_chunk, 0);
+ do_page_cache_ra(&ractl, this_chunk, 0);
index += this_chunk;
nr_to_read -= this_chunk;
@@ -432,10 +432,11 @@ static int try_context_readahead(struct
* A minimal readahead algorithm for trivial sequential/random reads.
*/
static void ondemand_readahead(struct address_space *mapping,
- struct file_ra_state *ra, struct file *filp,
+ struct file_ra_state *ra, struct file *file,
bool hit_readahead_marker, pgoff_t index,
unsigned long req_size)
{
+ DEFINE_READAHEAD(ractl, file, mapping, index);
struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
unsigned long max_pages = ra->ra_pages;
unsigned long add_pages;
@@ -516,7 +517,7 @@ static void ondemand_readahead(struct ad
* standalone, small random read
* Read as is, and do not pollute the readahead state.
*/
- __do_page_cache_readahead(mapping, filp, index, req_size, 0);
+ do_page_cache_ra(&ractl, req_size, 0);
return;
initial_readahead:
@@ -542,7 +543,8 @@ readit:
}
}
- ra_submit(ra, mapping, filp);
+ ractl._index = ra->start;
+ do_page_cache_ra(&ractl, ra->size, ra->async_size);
}
/**
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 036/156] mm/readahead: make ondemand_readahead take a readahead_control
2020-10-16 2:40 incoming Andrew Morton
` (35 preceding siblings ...)
2020-10-16 3:06 ` [patch 035/156] mm/readahead: make do_page_cache_ra " Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 037/156] mm/readahead: pass readahead_control to force_page_cache_ra Andrew Morton
` (129 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dhowells, ebiggers, mm-commits, torvalds, willy
From: David Howells <dhowells@redhat.com>
Subject: mm/readahead: make ondemand_readahead take a readahead_control
Make ondemand_readahead() take a readahead_control struct in preparation
for making do_sync_mmap_readahead() pass down an RAC struct.
Link: https://lkml.kernel.org/r/20200903140844.14194-6-willy@infradead.org
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/readahead.c | 29 +++++++++++++++++------------
1 file changed, 17 insertions(+), 12 deletions(-)
--- a/mm/readahead.c~mm-readahead-make-ondemand_readahead-take-a-readahead_control
+++ a/mm/readahead.c
@@ -431,15 +431,14 @@ static int try_context_readahead(struct
/*
* A minimal readahead algorithm for trivial sequential/random reads.
*/
-static void ondemand_readahead(struct address_space *mapping,
- struct file_ra_state *ra, struct file *file,
- bool hit_readahead_marker, pgoff_t index,
+static void ondemand_readahead(struct readahead_control *ractl,
+ struct file_ra_state *ra, bool hit_readahead_marker,
unsigned long req_size)
{
- DEFINE_READAHEAD(ractl, file, mapping, index);
- struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
+ struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host);
unsigned long max_pages = ra->ra_pages;
unsigned long add_pages;
+ unsigned long index = readahead_index(ractl);
pgoff_t prev_index;
/*
@@ -477,7 +476,8 @@ static void ondemand_readahead(struct ad
pgoff_t start;
rcu_read_lock();
- start = page_cache_next_miss(mapping, index + 1, max_pages);
+ start = page_cache_next_miss(ractl->mapping, index + 1,
+ max_pages);
rcu_read_unlock();
if (!start || start - index > max_pages)
@@ -510,14 +510,15 @@ static void ondemand_readahead(struct ad
* Query the page cache and look for the traces(cached history pages)
* that a sequential stream would leave behind.
*/
- if (try_context_readahead(mapping, ra, index, req_size, max_pages))
+ if (try_context_readahead(ractl->mapping, ra, index, req_size,
+ max_pages))
goto readit;
/*
* standalone, small random read
* Read as is, and do not pollute the readahead state.
*/
- do_page_cache_ra(&ractl, req_size, 0);
+ do_page_cache_ra(ractl, req_size, 0);
return;
initial_readahead:
@@ -543,8 +544,8 @@ readit:
}
}
- ractl._index = ra->start;
- do_page_cache_ra(&ractl, ra->size, ra->async_size);
+ ractl->_index = ra->start;
+ do_page_cache_ra(ractl, ra->size, ra->async_size);
}
/**
@@ -564,6 +565,8 @@ void page_cache_sync_readahead(struct ad
struct file_ra_state *ra, struct file *filp,
pgoff_t index, unsigned long req_count)
{
+ DEFINE_READAHEAD(ractl, filp, mapping, index);
+
/* no read-ahead */
if (!ra->ra_pages)
return;
@@ -578,7 +581,7 @@ void page_cache_sync_readahead(struct ad
}
/* do read-ahead */
- ondemand_readahead(mapping, ra, filp, false, index, req_count);
+ ondemand_readahead(&ractl, ra, false, req_count);
}
EXPORT_SYMBOL_GPL(page_cache_sync_readahead);
@@ -602,6 +605,8 @@ page_cache_async_readahead(struct addres
struct page *page, pgoff_t index,
unsigned long req_count)
{
+ DEFINE_READAHEAD(ractl, filp, mapping, index);
+
/* no read-ahead */
if (!ra->ra_pages)
return;
@@ -624,7 +629,7 @@ page_cache_async_readahead(struct addres
return;
/* do read-ahead */
- ondemand_readahead(mapping, ra, filp, true, index, req_count);
+ ondemand_readahead(&ractl, ra, true, req_count);
}
EXPORT_SYMBOL_GPL(page_cache_async_readahead);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 037/156] mm/readahead: pass readahead_control to force_page_cache_ra
2020-10-16 2:40 incoming Andrew Morton
` (36 preceding siblings ...)
2020-10-16 3:06 ` [patch 036/156] mm/readahead: make ondemand_readahead " Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 038/156] mm/readahead: add page_cache_sync_ra and page_cache_async_ra Andrew Morton
` (128 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dhowells, ebiggers, mm-commits, torvalds, willy
From: David Howells <dhowells@redhat.com>
Subject: mm/readahead: pass readahead_control to force_page_cache_ra
Reimplement force_page_cache_readahead() as a wrapper around
force_page_cache_ra(). Pass the existing readahead_control from
page_cache_sync_readahead().
Link: https://lkml.kernel.org/r/20200903140844.14194-7-willy@infradead.org
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/internal.h | 13 +++++++++----
mm/readahead.c | 18 ++++++++++--------
2 files changed, 19 insertions(+), 12 deletions(-)
--- a/mm/internal.h~mm-readahead-pass-readahead_control-to-force_page_cache_ra
+++ a/mm/internal.h
@@ -49,10 +49,15 @@ void unmap_page_range(struct mmu_gather
unsigned long addr, unsigned long end,
struct zap_details *details);
-void force_page_cache_readahead(struct address_space *, struct file *,
- pgoff_t index, unsigned long nr_to_read);
-void do_page_cache_ra(struct readahead_control *,
- unsigned long nr_to_read, unsigned long lookahead_size);
+void do_page_cache_ra(struct readahead_control *, unsigned long nr_to_read,
+ unsigned long lookahead_size);
+void force_page_cache_ra(struct readahead_control *, unsigned long nr);
+static inline void force_page_cache_readahead(struct address_space *mapping,
+ struct file *file, pgoff_t index, unsigned long nr_to_read)
+{
+ DEFINE_READAHEAD(ractl, file, mapping, index);
+ force_page_cache_ra(&ractl, nr_to_read);
+}
/*
* Submit IO for the read-ahead request in file_ra_state.
--- a/mm/readahead.c~mm-readahead-pass-readahead_control-to-force_page_cache_ra
+++ a/mm/readahead.c
@@ -271,13 +271,13 @@ void do_page_cache_ra(struct readahead_c
* Chunk the readahead into 2 megabyte units, so that we don't pin too much
* memory at once.
*/
-void force_page_cache_readahead(struct address_space *mapping,
- struct file *file, pgoff_t index, unsigned long nr_to_read)
+void force_page_cache_ra(struct readahead_control *ractl,
+ unsigned long nr_to_read)
{
- DEFINE_READAHEAD(ractl, file, mapping, index);
+ struct address_space *mapping = ractl->mapping;
struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
- struct file_ra_state *ra = &file->f_ra;
- unsigned long max_pages;
+ struct file_ra_state *ra = &ractl->file->f_ra;
+ unsigned long max_pages, index;
if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages &&
!mapping->a_ops->readahead))
@@ -287,14 +287,16 @@ void force_page_cache_readahead(struct a
* If the request exceeds the readahead window, allow the read to
* be up to the optimal hardware IO size
*/
+ index = readahead_index(ractl);
max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages);
- nr_to_read = min(nr_to_read, max_pages);
+ nr_to_read = min_t(unsigned long, nr_to_read, max_pages);
while (nr_to_read) {
unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE;
if (this_chunk > nr_to_read)
this_chunk = nr_to_read;
- do_page_cache_ra(&ractl, this_chunk, 0);
+ ractl->_index = index;
+ do_page_cache_ra(ractl, this_chunk, 0);
index += this_chunk;
nr_to_read -= this_chunk;
@@ -576,7 +578,7 @@ void page_cache_sync_readahead(struct ad
/* be dumb */
if (filp && (filp->f_mode & FMODE_RANDOM)) {
- force_page_cache_readahead(mapping, filp, index, req_count);
+ force_page_cache_ra(&ractl, req_count);
return;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 038/156] mm/readahead: add page_cache_sync_ra and page_cache_async_ra
2020-10-16 2:40 incoming Andrew Morton
` (37 preceding siblings ...)
2020-10-16 3:06 ` [patch 037/156] mm/readahead: pass readahead_control to force_page_cache_ra Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 039/156] mm/filemap: fold ra_submit into do_sync_mmap_readahead Andrew Morton
` (127 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dhowells, ebiggers, mm-commits, torvalds, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm/readahead: add page_cache_sync_ra and page_cache_async_ra
Reimplement page_cache_sync_readahead() and page_cache_async_readahead()
as wrappers around versions of the function which take a readahead_control
in preparation for making do_sync_mmap_readahead() pass down an RAC
struct.
Link: https://lkml.kernel.org/r/20200903140844.14194-8-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/pagemap.h | 64 ++++++++++++++++++++++++++++++++------
mm/readahead.c | 58 +++++++---------------------------
2 files changed, 66 insertions(+), 56 deletions(-)
--- a/include/linux/pagemap.h~mm-readahead-add-page_cache_sync_ra-and-page_cache_async_ra
+++ a/include/linux/pagemap.h
@@ -761,16 +761,6 @@ int replace_page_cache_page(struct page
void delete_from_page_cache_batch(struct address_space *mapping,
struct pagevec *pvec);
-#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE)
-
-void page_cache_sync_readahead(struct address_space *, struct file_ra_state *,
- struct file *, pgoff_t index, unsigned long req_count);
-void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
- struct file *, struct page *, pgoff_t index,
- unsigned long req_count);
-void page_cache_ra_unbounded(struct readahead_control *,
- unsigned long nr_to_read, unsigned long lookahead_count);
-
/*
* Like add_to_page_cache_locked, but used to add newly allocated pages:
* the page is new, so we can just run __SetPageLocked() against it.
@@ -818,6 +808,60 @@ struct readahead_control {
._index = i, \
}
+#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE)
+
+void page_cache_ra_unbounded(struct readahead_control *,
+ unsigned long nr_to_read, unsigned long lookahead_count);
+void page_cache_sync_ra(struct readahead_control *, struct file_ra_state *,
+ unsigned long req_count);
+void page_cache_async_ra(struct readahead_control *, struct file_ra_state *,
+ struct page *, unsigned long req_count);
+
+/**
+ * page_cache_sync_readahead - generic file readahead
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @file: Used by the filesystem for authentication.
+ * @index: Index of first page to be read.
+ * @req_count: Total number of pages being read by the caller.
+ *
+ * page_cache_sync_readahead() should be called when a cache miss happened:
+ * it will submit the read. The readahead logic may decide to piggyback more
+ * pages onto the read request if access patterns suggest it will improve
+ * performance.
+ */
+static inline
+void page_cache_sync_readahead(struct address_space *mapping,
+ struct file_ra_state *ra, struct file *file, pgoff_t index,
+ unsigned long req_count)
+{
+ DEFINE_READAHEAD(ractl, file, mapping, index);
+ page_cache_sync_ra(&ractl, ra, req_count);
+}
+
+/**
+ * page_cache_async_readahead - file readahead for marked pages
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @file: Used by the filesystem for authentication.
+ * @page: The page at @index which triggered the readahead call.
+ * @index: Index of first page to be read.
+ * @req_count: Total number of pages being read by the caller.
+ *
+ * page_cache_async_readahead() should be called when a page is used which
+ * is marked as PageReadahead; this is a marker to suggest that the application
+ * has used up enough of the readahead window that we should start pulling in
+ * more pages.
+ */
+static inline
+void page_cache_async_readahead(struct address_space *mapping,
+ struct file_ra_state *ra, struct file *file,
+ struct page *page, pgoff_t index, unsigned long req_count)
+{
+ DEFINE_READAHEAD(ractl, file, mapping, index);
+ page_cache_async_ra(&ractl, ra, page, req_count);
+}
+
/**
* readahead_page - Get the next page to read.
* @rac: The current readahead request.
--- a/mm/readahead.c~mm-readahead-add-page_cache_sync_ra-and-page_cache_async_ra
+++ a/mm/readahead.c
@@ -550,25 +550,9 @@ readit:
do_page_cache_ra(ractl, ra->size, ra->async_size);
}
-/**
- * page_cache_sync_readahead - generic file readahead
- * @mapping: address_space which holds the pagecache and I/O vectors
- * @ra: file_ra_state which holds the readahead state
- * @filp: passed on to ->readpage() and ->readpages()
- * @index: Index of first page to be read.
- * @req_count: Total number of pages being read by the caller.
- *
- * page_cache_sync_readahead() should be called when a cache miss happened:
- * it will submit the read. The readahead logic may decide to piggyback more
- * pages onto the read request if access patterns suggest it will improve
- * performance.
- */
-void page_cache_sync_readahead(struct address_space *mapping,
- struct file_ra_state *ra, struct file *filp,
- pgoff_t index, unsigned long req_count)
+void page_cache_sync_ra(struct readahead_control *ractl,
+ struct file_ra_state *ra, unsigned long req_count)
{
- DEFINE_READAHEAD(ractl, filp, mapping, index);
-
/* no read-ahead */
if (!ra->ra_pages)
return;
@@ -577,38 +561,20 @@ void page_cache_sync_readahead(struct ad
return;
/* be dumb */
- if (filp && (filp->f_mode & FMODE_RANDOM)) {
- force_page_cache_ra(&ractl, req_count);
+ if (ractl->file && (ractl->file->f_mode & FMODE_RANDOM)) {
+ force_page_cache_ra(ractl, req_count);
return;
}
/* do read-ahead */
- ondemand_readahead(&ractl, ra, false, req_count);
+ ondemand_readahead(ractl, ra, false, req_count);
}
-EXPORT_SYMBOL_GPL(page_cache_sync_readahead);
+EXPORT_SYMBOL_GPL(page_cache_sync_ra);
-/**
- * page_cache_async_readahead - file readahead for marked pages
- * @mapping: address_space which holds the pagecache and I/O vectors
- * @ra: file_ra_state which holds the readahead state
- * @filp: passed on to ->readpage() and ->readpages()
- * @page: The page at @index which triggered the readahead call.
- * @index: Index of first page to be read.
- * @req_count: Total number of pages being read by the caller.
- *
- * page_cache_async_readahead() should be called when a page is used which
- * is marked as PageReadahead; this is a marker to suggest that the application
- * has used up enough of the readahead window that we should start pulling in
- * more pages.
- */
-void
-page_cache_async_readahead(struct address_space *mapping,
- struct file_ra_state *ra, struct file *filp,
- struct page *page, pgoff_t index,
- unsigned long req_count)
+void page_cache_async_ra(struct readahead_control *ractl,
+ struct file_ra_state *ra, struct page *page,
+ unsigned long req_count)
{
- DEFINE_READAHEAD(ractl, filp, mapping, index);
-
/* no read-ahead */
if (!ra->ra_pages)
return;
@@ -624,16 +590,16 @@ page_cache_async_readahead(struct addres
/*
* Defer asynchronous read-ahead on IO congestion.
*/
- if (inode_read_congested(mapping->host))
+ if (inode_read_congested(ractl->mapping->host))
return;
if (blk_cgroup_congested())
return;
/* do read-ahead */
- ondemand_readahead(&ractl, ra, true, req_count);
+ ondemand_readahead(ractl, ra, true, req_count);
}
-EXPORT_SYMBOL_GPL(page_cache_async_readahead);
+EXPORT_SYMBOL_GPL(page_cache_async_ra);
ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
{
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 039/156] mm/filemap: fold ra_submit into do_sync_mmap_readahead
2020-10-16 2:40 incoming Andrew Morton
` (38 preceding siblings ...)
2020-10-16 3:06 ` [patch 038/156] mm/readahead: add page_cache_sync_ra and page_cache_async_ra Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 040/156] mm/readahead: pass a file_ra_state into force_page_cache_ra Andrew Morton
` (126 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dhowells, ebiggers, mm-commits, torvalds, willy
From: David Howells <dhowells@redhat.com>
Subject: mm/filemap: fold ra_submit into do_sync_mmap_readahead
Fold ra_submit() into its last remaining user and pass the
readahead_control struct to both do_page_cache_ra() and
page_cache_sync_ra().
Link: https://lkml.kernel.org/r/20200903140844.14194-9-willy@infradead.org
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/filemap.c | 10 +++++-----
mm/internal.h | 10 ----------
2 files changed, 5 insertions(+), 15 deletions(-)
--- a/mm/filemap.c~mm-filemap-fold-ra_submit-into-do_sync_mmap_readahead
+++ a/mm/filemap.c
@@ -2588,8 +2588,8 @@ static struct file *do_sync_mmap_readahe
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
+ DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff);
struct file *fpin = NULL;
- pgoff_t offset = vmf->pgoff;
unsigned int mmap_miss;
/* If we don't want any read-ahead, don't bother */
@@ -2600,8 +2600,7 @@ static struct file *do_sync_mmap_readahe
if (vmf->vma->vm_flags & VM_SEQ_READ) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- page_cache_sync_readahead(mapping, ra, file, offset,
- ra->ra_pages);
+ page_cache_sync_ra(&ractl, ra, ra->ra_pages);
return fpin;
}
@@ -2621,10 +2620,11 @@ static struct file *do_sync_mmap_readahe
* mmap read-around
*/
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- ra->start = max_t(long, 0, offset - ra->ra_pages / 2);
+ ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
ra->size = ra->ra_pages;
ra->async_size = ra->ra_pages / 4;
- ra_submit(ra, mapping, file);
+ ractl._index = ra->start;
+ do_page_cache_ra(&ractl, ra->size, ra->async_size);
return fpin;
}
--- a/mm/internal.h~mm-filemap-fold-ra_submit-into-do_sync_mmap_readahead
+++ a/mm/internal.h
@@ -59,16 +59,6 @@ static inline void force_page_cache_read
force_page_cache_ra(&ractl, nr_to_read);
}
-/*
- * Submit IO for the read-ahead request in file_ra_state.
- */
-static inline void ra_submit(struct file_ra_state *ra,
- struct address_space *mapping, struct file *file)
-{
- DEFINE_READAHEAD(ractl, file, mapping, ra->start);
- do_page_cache_ra(&ractl, ra->size, ra->async_size);
-}
-
struct page *find_get_entry(struct address_space *mapping, pgoff_t index);
struct page *find_lock_entry(struct address_space *mapping, pgoff_t index);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 040/156] mm/readahead: pass a file_ra_state into force_page_cache_ra
2020-10-16 2:40 incoming Andrew Morton
` (39 preceding siblings ...)
2020-10-16 3:06 ` [patch 039/156] mm/filemap: fold ra_submit into do_sync_mmap_readahead Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 041/156] mm,hwpoison: cleanup unused PageHuge() check Andrew Morton
` (125 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, dhowells, ebiggers, mm-commits, torvalds, willy
From: David Howells <dhowells@redhat.com>
Subject: mm/readahead: pass a file_ra_state into force_page_cache_ra
The file_ra_state being passed into page_cache_sync_readahead() was being
ignored in favour of using the one embedded in the struct file. The only
caller for which this makes a difference is the fsverity code if the file
has been marked as POSIX_FADV_RANDOM, but it's confusing and worth fixing.
Link: https://lkml.kernel.org/r/20200903140844.14194-10-willy@infradead.org
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/internal.h | 5 +++--
mm/readahead.c | 5 ++---
2 files changed, 5 insertions(+), 5 deletions(-)
--- a/mm/internal.h~mm-readahead-pass-a-file_ra_state-into-force_page_cache_ra
+++ a/mm/internal.h
@@ -51,12 +51,13 @@ void unmap_page_range(struct mmu_gather
void do_page_cache_ra(struct readahead_control *, unsigned long nr_to_read,
unsigned long lookahead_size);
-void force_page_cache_ra(struct readahead_control *, unsigned long nr);
+void force_page_cache_ra(struct readahead_control *, struct file_ra_state *,
+ unsigned long nr);
static inline void force_page_cache_readahead(struct address_space *mapping,
struct file *file, pgoff_t index, unsigned long nr_to_read)
{
DEFINE_READAHEAD(ractl, file, mapping, index);
- force_page_cache_ra(&ractl, nr_to_read);
+ force_page_cache_ra(&ractl, &file->f_ra, nr_to_read);
}
struct page *find_get_entry(struct address_space *mapping, pgoff_t index);
--- a/mm/readahead.c~mm-readahead-pass-a-file_ra_state-into-force_page_cache_ra
+++ a/mm/readahead.c
@@ -272,11 +272,10 @@ void do_page_cache_ra(struct readahead_c
* memory at once.
*/
void force_page_cache_ra(struct readahead_control *ractl,
- unsigned long nr_to_read)
+ struct file_ra_state *ra, unsigned long nr_to_read)
{
struct address_space *mapping = ractl->mapping;
struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
- struct file_ra_state *ra = &ractl->file->f_ra;
unsigned long max_pages, index;
if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages &&
@@ -562,7 +561,7 @@ void page_cache_sync_ra(struct readahead
/* be dumb */
if (ractl->file && (ractl->file->f_mode & FMODE_RANDOM)) {
- force_page_cache_ra(ractl, req_count);
+ force_page_cache_ra(ractl, ra, req_count);
return;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 041/156] mm,hwpoison: cleanup unused PageHuge() check
2020-10-16 2:40 incoming Andrew Morton
` (40 preceding siblings ...)
2020-10-16 3:06 ` [patch 040/156] mm/readahead: pass a file_ra_state into force_page_cache_ra Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 042/156] mm, hwpoison: remove recalculating hpage Andrew Morton
` (124 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm,hwpoison: cleanup unused PageHuge() check
Patch series "HWPOISON: soft offline rework", v7.
This patchset fixes a couple of issues that the patchset Naoya sent [1]
contained due to rebasing problems and a misunterdansting.
Main focus of this series is to stabilize soft offline. Historically soft
offlined pages have suffered from racy conditions because PageHWPoison is
used to a little too aggressively, which (directly or indirectly) invades
other mm code which cares little about hwpoison. This results in
unexpected behavior or kernel panic, which is very far from soft offline's
"do not disturb userspace or other kernel component" policy. An example
of this can be found here [2].
Along with several cleanups, this code refactors and changes the way soft
offline work. Main point of this change set is to contain target page
"via buddy allocator" or in migrating path. For ther former we first free
the target page as we do for normal pages, and once it has reached buddy
and it has been taken off the freelists, we flag it as HWpoison. For the
latter we never get to release the page in unmap_and_move, so the page is
under our control and we can handle it in hwpoison code.
[1] https://patchwork.kernel.org/cover/11704083/
[2] https://lore.kernel.org/linux-mm/20190826104144.GA7849@linux/T/#u
This patch (of 14):
Drop the PageHuge check, which is dead code since memory_failure() forks
into memory_failure_hugetlb() for hugetlb pages.
memory_failure() and memory_failure_hugetlb() shares some functions like
hwpoison_user_mappings() and identify_page_state(), so they should
properly handle 4kB page, thp, and hugetlb.
Link: https://lkml.kernel.org/r/20200922135650.1634-1-osalvador@suse.de
Link: https://lkml.kernel.org/r/20200922135650.1634-2-osalvador@suse.de
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Qian Cai <cai@lca.pw>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Oscar Salvador <osalvador@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory-failure.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
--- a/mm/memory-failure.c~mmhwpoison-cleanup-unused-pagehuge-check
+++ a/mm/memory-failure.c
@@ -1381,10 +1381,7 @@ int memory_failure(unsigned long pfn, in
* page_remove_rmap() in try_to_unmap_one(). So to determine page status
* correctly, we save a copy of the page flags at this time.
*/
- if (PageHuge(p))
- page_flags = hpage->flags;
- else
- page_flags = p->flags;
+ page_flags = p->flags;
/*
* unpoison always clear PG_hwpoison inside page lock
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 042/156] mm, hwpoison: remove recalculating hpage
2020-10-16 2:40 incoming Andrew Morton
` (41 preceding siblings ...)
2020-10-16 3:06 ` [patch 041/156] mm,hwpoison: cleanup unused PageHuge() check Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 043/156] mm,hwpoison-inject: don't pin for hwpoison_filter Andrew Morton
` (123 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm, hwpoison: remove recalculating hpage
hpage is never used after try_to_split_thp_page() in memory_failure(), so
we don't have to update hpage. So let's not recalculate/use hpage.
Link: https://lkml.kernel.org/r/20200922135650.1634-3-osalvador@suse.de
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Suggested-by: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory-failure.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
--- a/mm/memory-failure.c~mm-hwpoison-remove-recalculating-hpage
+++ a/mm/memory-failure.c
@@ -1341,7 +1341,6 @@ int memory_failure(unsigned long pfn, in
}
unlock_page(p);
VM_BUG_ON_PAGE(!page_count(p), p);
- hpage = compound_head(p);
}
/*
@@ -1413,11 +1412,8 @@ int memory_failure(unsigned long pfn, in
/*
* Now take care of user space mappings.
* Abort on fail: __delete_from_page_cache() assumes unmapped page.
- *
- * When the raw error page is thp tail page, hpage points to the raw
- * page after thp split.
*/
- if (!hwpoison_user_mappings(p, pfn, flags, &hpage)) {
+ if (!hwpoison_user_mappings(p, pfn, flags, &p)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
goto out;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 043/156] mm,hwpoison-inject: don't pin for hwpoison_filter
2020-10-16 2:40 incoming Andrew Morton
` (42 preceding siblings ...)
2020-10-16 3:06 ` [patch 042/156] mm, hwpoison: remove recalculating hpage Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 044/156] mm,hwpoison: unexport get_hwpoison_page and make it static Andrew Morton
` (122 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm,hwpoison-inject: don't pin for hwpoison_filter
Another memory error injection interface debugfs:hwpoison/corrupt-pfn also
takes bogus refcount for hwpoison_filter(). It's justified because this
does a coarse filter, expecting that memory_failure() redoes the check for
sure.
Link: https://lkml.kernel.org/r/20200922135650.1634-4-osalvador@suse.de
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/hwpoison-inject.c | 18 +++++-------------
1 file changed, 5 insertions(+), 13 deletions(-)
--- a/mm/hwpoison-inject.c~mmhwpoison-inject-dont-pin-for-hwpoison_filter
+++ a/mm/hwpoison-inject.c
@@ -26,11 +26,6 @@ static int hwpoison_inject(void *data, u
p = pfn_to_page(pfn);
hpage = compound_head(p);
- /*
- * This implies unable to support free buddy pages.
- */
- if (!get_hwpoison_page(p))
- return 0;
if (!hwpoison_filter_enable)
goto inject;
@@ -40,23 +35,20 @@ static int hwpoison_inject(void *data, u
* This implies unable to support non-LRU pages.
*/
if (!PageLRU(hpage) && !PageHuge(p))
- goto put_out;
+ return 0;
/*
- * do a racy check with elevated page count, to make sure PG_hwpoison
- * will only be set for the targeted owner (or on a free page).
+ * do a racy check to make sure PG_hwpoison will only be set for
+ * the targeted owner (or on a free page).
* memory_failure() will redo the check reliably inside page lock.
*/
err = hwpoison_filter(hpage);
if (err)
- goto put_out;
+ return 0;
inject:
pr_info("Injecting memory failure at pfn %#lx\n", pfn);
- return memory_failure(pfn, MF_COUNT_INCREASED);
-put_out:
- put_hwpoison_page(p);
- return 0;
+ return memory_failure(pfn, 0);
}
static int hwpoison_unpoison(void *data, u64 val)
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 044/156] mm,hwpoison: unexport get_hwpoison_page and make it static
2020-10-16 2:40 incoming Andrew Morton
` (43 preceding siblings ...)
2020-10-16 3:06 ` [patch 043/156] mm,hwpoison-inject: don't pin for hwpoison_filter Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 045/156] mm,hwpoison: refactor madvise_inject_error Andrew Morton
` (121 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Oscar Salvador <osalvador@suse.de>
Subject: mm,hwpoison: unexport get_hwpoison_page and make it static
Since get_hwpoison_page is only used in memory-failure code now, let us
un-export it and make it private to that code.
Link: https://lkml.kernel.org/r/20200922135650.1634-5-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/mm.h | 1 -
mm/memory-failure.c | 3 +--
2 files changed, 1 insertion(+), 3 deletions(-)
--- a/include/linux/mm.h~mmhwpoison-unexport-get_hwpoison_page-and-make-it-static
+++ a/include/linux/mm.h
@@ -3025,7 +3025,6 @@ extern int memory_failure(unsigned long
extern void memory_failure_queue(unsigned long pfn, int flags);
extern void memory_failure_queue_kick(int cpu);
extern int unpoison_memory(unsigned long pfn);
-extern int get_hwpoison_page(struct page *page);
#define put_hwpoison_page(page) put_page(page)
extern int sysctl_memory_failure_early_kill;
extern int sysctl_memory_failure_recovery;
--- a/mm/memory-failure.c~mmhwpoison-unexport-get_hwpoison_page-and-make-it-static
+++ a/mm/memory-failure.c
@@ -924,7 +924,7 @@ static int page_action(struct page_state
* Return: return 0 if failed to grab the refcount, otherwise true (some
* non-zero value.)
*/
-int get_hwpoison_page(struct page *page)
+static int get_hwpoison_page(struct page *page)
{
struct page *head = compound_head(page);
@@ -953,7 +953,6 @@ int get_hwpoison_page(struct page *page)
return 0;
}
-EXPORT_SYMBOL_GPL(get_hwpoison_page);
/*
* Do all that is necessary to remove user space mappings. Unmap
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 045/156] mm,hwpoison: refactor madvise_inject_error
2020-10-16 2:40 incoming Andrew Morton
` (44 preceding siblings ...)
2020-10-16 3:06 ` [patch 044/156] mm,hwpoison: unexport get_hwpoison_page and make it static Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:06 ` [patch 046/156] mm,hwpoison: kill put_hwpoison_page Andrew Morton
` (120 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Oscar Salvador <osalvador@suse.de>
Subject: mm,hwpoison: refactor madvise_inject_error
Make a proper if-else condition for {hard,soft}-offline.
Link: https://lkml.kernel.org/r/20200908075626.11976-3-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.com>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/madvise.c | 30 +++++++++++++-----------------
1 file changed, 13 insertions(+), 17 deletions(-)
--- a/mm/madvise.c~mmhwpoison-refactor-madvise_inject_error
+++ a/mm/madvise.c
@@ -872,7 +872,6 @@ static long madvise_remove(struct vm_are
static int madvise_inject_error(int behavior,
unsigned long start, unsigned long end)
{
- struct page *page;
struct zone *zone;
unsigned long size;
@@ -882,6 +881,7 @@ static int madvise_inject_error(int beha
for (; start < end; start += size) {
unsigned long pfn;
+ struct page *page;
int ret;
ret = get_user_pages_fast(start, 1, 0, &page);
@@ -903,25 +903,21 @@ static int madvise_inject_error(int beha
if (behavior == MADV_SOFT_OFFLINE) {
pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n",
- pfn, start);
-
+ pfn, start);
ret = soft_offline_page(pfn, MF_COUNT_INCREASED);
- if (ret)
- return ret;
- continue;
+ } else {
+ pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
+ pfn, start);
+ /*
+ * Drop the page reference taken by get_user_pages_fast(). In
+ * the absence of MF_COUNT_INCREASED the memory_failure()
+ * routine is responsible for pinning the page to prevent it
+ * from being released back to the page allocator.
+ */
+ put_page(page);
+ ret = memory_failure(pfn, 0);
}
- pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
- pfn, start);
-
- /*
- * Drop the page reference taken by get_user_pages_fast(). In
- * the absence of MF_COUNT_INCREASED the memory_failure()
- * routine is responsible for pinning the page to prevent it
- * from being released back to the page allocator.
- */
- put_page(page);
- ret = memory_failure(pfn, 0);
if (ret)
return ret;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 046/156] mm,hwpoison: kill put_hwpoison_page
2020-10-16 2:40 incoming Andrew Morton
` (45 preceding siblings ...)
2020-10-16 3:06 ` [patch 045/156] mm,hwpoison: refactor madvise_inject_error Andrew Morton
@ 2020-10-16 3:06 ` Andrew Morton
2020-10-16 3:07 ` [patch 047/156] mm,hwpoison: unify THP handling for hard and soft offline Andrew Morton
` (119 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:06 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Oscar Salvador <osalvador@suse.de>
Subject: mm,hwpoison: kill put_hwpoison_page
After commit 4e41a30c6d50 ("mm: hwpoison: adjust for new thp
refcounting"), put_hwpoison_page got reduced to a put_page. Let us just
use put_page instead.
Link: https://lkml.kernel.org/r/20200922135650.1634-7-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/mm.h | 1 -
mm/memory-failure.c | 30 +++++++++++++++---------------
2 files changed, 15 insertions(+), 16 deletions(-)
--- a/include/linux/mm.h~mmhwpoison-kill-put_hwpoison_page
+++ a/include/linux/mm.h
@@ -3025,7 +3025,6 @@ extern int memory_failure(unsigned long
extern void memory_failure_queue(unsigned long pfn, int flags);
extern void memory_failure_queue_kick(int cpu);
extern int unpoison_memory(unsigned long pfn);
-#define put_hwpoison_page(page) put_page(page)
extern int sysctl_memory_failure_early_kill;
extern int sysctl_memory_failure_recovery;
extern void shake_page(struct page *p, int access);
--- a/mm/memory-failure.c~mmhwpoison-kill-put_hwpoison_page
+++ a/mm/memory-failure.c
@@ -1143,7 +1143,7 @@ static int memory_failure_hugetlb(unsign
pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
num_poisoned_pages_dec();
unlock_page(head);
- put_hwpoison_page(head);
+ put_page(head);
return 0;
}
@@ -1335,7 +1335,7 @@ int memory_failure(unsigned long pfn, in
pfn);
if (TestClearPageHWPoison(p))
num_poisoned_pages_dec();
- put_hwpoison_page(p);
+ put_page(p);
return -EBUSY;
}
unlock_page(p);
@@ -1388,14 +1388,14 @@ int memory_failure(unsigned long pfn, in
pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
num_poisoned_pages_dec();
unlock_page(p);
- put_hwpoison_page(p);
+ put_page(p);
return 0;
}
if (hwpoison_filter(p)) {
if (TestClearPageHWPoison(p))
num_poisoned_pages_dec();
unlock_page(p);
- put_hwpoison_page(p);
+ put_page(p);
return 0;
}
@@ -1629,9 +1629,9 @@ int unpoison_memory(unsigned long pfn)
}
unlock_page(page);
- put_hwpoison_page(page);
+ put_page(page);
if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
- put_hwpoison_page(page);
+ put_page(page);
return 0;
}
@@ -1692,7 +1692,7 @@ static int get_any_page(struct page *pag
/*
* Try to free it.
*/
- put_hwpoison_page(page);
+ put_page(page);
shake_page(page, 1);
/*
@@ -1701,7 +1701,7 @@ static int get_any_page(struct page *pag
ret = __get_any_page(page, pfn, 0);
if (ret == 1 && !PageLRU(page)) {
/* Drop page reference which is from __get_any_page() */
- put_hwpoison_page(page);
+ put_page(page);
pr_info("soft_offline: %#lx: unknown non LRU page type %lx (%pGp)\n",
pfn, page->flags, &page->flags);
return -EIO;
@@ -1724,7 +1724,7 @@ static int soft_offline_huge_page(struct
lock_page(hpage);
if (PageHWPoison(hpage)) {
unlock_page(hpage);
- put_hwpoison_page(hpage);
+ put_page(hpage);
pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
return -EBUSY;
}
@@ -1735,7 +1735,7 @@ static int soft_offline_huge_page(struct
* get_any_page() and isolate_huge_page() takes a refcount each,
* so need to drop one here.
*/
- put_hwpoison_page(hpage);
+ put_page(hpage);
if (!ret) {
pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
return -EBUSY;
@@ -1784,7 +1784,7 @@ static int __soft_offline_page(struct pa
wait_on_page_writeback(page);
if (PageHWPoison(page)) {
unlock_page(page);
- put_hwpoison_page(page);
+ put_page(page);
pr_info("soft offline: %#lx page already poisoned\n", pfn);
return -EBUSY;
}
@@ -1799,7 +1799,7 @@ static int __soft_offline_page(struct pa
* would need to fix isolation locking first.
*/
if (ret == 1) {
- put_hwpoison_page(page);
+ put_page(page);
pr_info("soft_offline: %#lx: invalidated\n", pfn);
SetPageHWPoison(page);
num_poisoned_pages_inc();
@@ -1819,7 +1819,7 @@ static int __soft_offline_page(struct pa
* Drop page reference which is came from get_any_page()
* successful isolate_lru_page() already took another one.
*/
- put_hwpoison_page(page);
+ put_page(page);
if (!ret) {
LIST_HEAD(pagelist);
/*
@@ -1863,7 +1863,7 @@ static int soft_offline_in_use_page(stru
pr_info("soft offline: %#lx: non anonymous thp\n", page_to_pfn(page));
else
pr_info("soft offline: %#lx: thp split failed\n", page_to_pfn(page));
- put_hwpoison_page(page);
+ put_page(page);
return -EBUSY;
}
unlock_page(page);
@@ -1936,7 +1936,7 @@ int soft_offline_page(unsigned long pfn,
if (PageHWPoison(page)) {
pr_info("soft offline: %#lx page already poisoned\n", pfn);
if (flags & MF_COUNT_INCREASED)
- put_hwpoison_page(page);
+ put_page(page);
return -EBUSY;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 047/156] mm,hwpoison: unify THP handling for hard and soft offline
2020-10-16 2:40 incoming Andrew Morton
` (46 preceding siblings ...)
2020-10-16 3:06 ` [patch 046/156] mm,hwpoison: kill put_hwpoison_page Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 048/156] mm,hwpoison: rework soft offline for free pages Andrew Morton
` (118 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Oscar Salvador <osalvador@suse.de>
Subject: mm,hwpoison: unify THP handling for hard and soft offline
Place the THP's page handling in a helper and use it from both hard and
soft-offline machinery, so we get rid of some duplicated code.
Link: https://lkml.kernel.org/r/20200922135650.1634-8-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory-failure.c | 48 +++++++++++++++++++-----------------------
1 file changed, 22 insertions(+), 26 deletions(-)
--- a/mm/memory-failure.c~mmhwpoison-unify-thp-handling-for-hard-and-soft-offline
+++ a/mm/memory-failure.c
@@ -1102,6 +1102,25 @@ static int identify_page_state(unsigned
return page_action(ps, p, pfn);
}
+static int try_to_split_thp_page(struct page *page, const char *msg)
+{
+ lock_page(page);
+ if (!PageAnon(page) || unlikely(split_huge_page(page))) {
+ unsigned long pfn = page_to_pfn(page);
+
+ unlock_page(page);
+ if (!PageAnon(page))
+ pr_info("%s: %#lx: non anonymous thp\n", msg, pfn);
+ else
+ pr_info("%s: %#lx: thp split failed\n", msg, pfn);
+ put_page(page);
+ return -EBUSY;
+ }
+ unlock_page(page);
+
+ return 0;
+}
+
static int memory_failure_hugetlb(unsigned long pfn, int flags)
{
struct page *p = pfn_to_page(pfn);
@@ -1324,21 +1343,8 @@ int memory_failure(unsigned long pfn, in
}
if (PageTransHuge(hpage)) {
- lock_page(p);
- if (!PageAnon(p) || unlikely(split_huge_page(p))) {
- unlock_page(p);
- if (!PageAnon(p))
- pr_err("Memory failure: %#lx: non anonymous thp\n",
- pfn);
- else
- pr_err("Memory failure: %#lx: thp split failed\n",
- pfn);
- if (TestClearPageHWPoison(p))
- num_poisoned_pages_dec();
- put_page(p);
+ if (try_to_split_thp_page(p, "Memory Failure") < 0)
return -EBUSY;
- }
- unlock_page(p);
VM_BUG_ON_PAGE(!page_count(p), p);
}
@@ -1855,19 +1861,9 @@ static int soft_offline_in_use_page(stru
int mt;
struct page *hpage = compound_head(page);
- if (!PageHuge(page) && PageTransHuge(hpage)) {
- lock_page(page);
- if (!PageAnon(page) || unlikely(split_huge_page(page))) {
- unlock_page(page);
- if (!PageAnon(page))
- pr_info("soft offline: %#lx: non anonymous thp\n", page_to_pfn(page));
- else
- pr_info("soft offline: %#lx: thp split failed\n", page_to_pfn(page));
- put_page(page);
+ if (!PageHuge(page) && PageTransHuge(hpage))
+ if (try_to_split_thp_page(page, "soft offline") < 0)
return -EBUSY;
- }
- unlock_page(page);
- }
/*
* Setting MIGRATE_ISOLATE here ensures that the page will be linked
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 048/156] mm,hwpoison: rework soft offline for free pages
2020-10-16 2:40 incoming Andrew Morton
` (47 preceding siblings ...)
2020-10-16 3:07 ` [patch 047/156] mm,hwpoison: unify THP handling for hard and soft offline Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 049/156] mm,hwpoison: rework soft offline for in-use pages Andrew Morton
` (117 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Oscar Salvador <osalvador@suse.de>
Subject: mm,hwpoison: rework soft offline for free pages
When trying to soft-offline a free page, we need to first take it off the
buddy allocator. Once we know is out of reach, we can safely flag it as
poisoned.
take_page_off_buddy will be used to take a page meant to be poisoned off
the buddy allocator. take_page_off_buddy calls break_down_buddy_pages,
which splits a higher-order page in case our page belongs to one.
Once the page is under our control, we call page_handle_poison to set it
as poisoned and grab a refcount on it.
Link: https://lkml.kernel.org/r/20200922135650.1634-9-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/page-flags.h | 1
mm/memory-failure.c | 18 ++++++---
mm/page_alloc.c | 68 +++++++++++++++++++++++++++++++++++
3 files changed, 81 insertions(+), 6 deletions(-)
--- a/include/linux/page-flags.h~mmhwpoison-rework-soft-offline-for-free-pages
+++ a/include/linux/page-flags.h
@@ -432,6 +432,7 @@ PAGEFLAG(HWPoison, hwpoison, PF_ANY)
TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
#define __PG_HWPOISON (1UL << PG_hwpoison)
extern bool set_hwpoison_free_buddy_page(struct page *page);
+extern bool take_page_off_buddy(struct page *page);
#else
PAGEFLAG_FALSE(HWPoison)
static inline bool set_hwpoison_free_buddy_page(struct page *page)
--- a/mm/memory-failure.c~mmhwpoison-rework-soft-offline-for-free-pages
+++ a/mm/memory-failure.c
@@ -65,6 +65,13 @@ int sysctl_memory_failure_recovery __rea
atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
+static void page_handle_poison(struct page *page)
+{
+ SetPageHWPoison(page);
+ page_ref_inc(page);
+ num_poisoned_pages_inc();
+}
+
#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
u32 hwpoison_filter_enable = 0;
@@ -1884,14 +1891,13 @@ static int soft_offline_in_use_page(stru
static int soft_offline_free_page(struct page *page)
{
- int rc = dissolve_free_huge_page(page);
+ int rc = -EBUSY;
- if (!rc) {
- if (set_hwpoison_free_buddy_page(page))
- num_poisoned_pages_inc();
- else
- rc = -EBUSY;
+ if (!dissolve_free_huge_page(page) && take_page_off_buddy(page)) {
+ page_handle_poison(page);
+ rc = 0;
}
+
return rc;
}
--- a/mm/page_alloc.c~mmhwpoison-rework-soft-offline-for-free-pages
+++ a/mm/page_alloc.c
@@ -8778,6 +8778,74 @@ bool is_free_buddy_page(struct page *pag
#ifdef CONFIG_MEMORY_FAILURE
/*
+ * Break down a higher-order page in sub-pages, and keep our target out of
+ * buddy allocator.
+ */
+static void break_down_buddy_pages(struct zone *zone, struct page *page,
+ struct page *target, int low, int high,
+ int migratetype)
+{
+ unsigned long size = 1 << high;
+ struct page *current_buddy, *next_page;
+
+ while (high > low) {
+ high--;
+ size >>= 1;
+
+ if (target >= &page[size]) {
+ next_page = page + size;
+ current_buddy = page;
+ } else {
+ next_page = page;
+ current_buddy = page + size;
+ }
+
+ if (set_page_guard(zone, current_buddy, high, migratetype))
+ continue;
+
+ if (current_buddy != target) {
+ add_to_free_list(current_buddy, zone, high, migratetype);
+ set_page_order(current_buddy, high);
+ page = next_page;
+ }
+ }
+}
+
+/*
+ * Take a page that will be marked as poisoned off the buddy allocator.
+ */
+bool take_page_off_buddy(struct page *page)
+{
+ struct zone *zone = page_zone(page);
+ unsigned long pfn = page_to_pfn(page);
+ unsigned long flags;
+ unsigned int order;
+ bool ret = false;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ for (order = 0; order < MAX_ORDER; order++) {
+ struct page *page_head = page - (pfn & ((1 << order) - 1));
+ int buddy_order = page_order(page_head);
+
+ if (PageBuddy(page_head) && buddy_order >= order) {
+ unsigned long pfn_head = page_to_pfn(page_head);
+ int migratetype = get_pfnblock_migratetype(page_head,
+ pfn_head);
+
+ del_page_from_free_list(page_head, zone, buddy_order);
+ break_down_buddy_pages(zone, page_head, page, 0,
+ buddy_order, migratetype);
+ ret = true;
+ break;
+ }
+ if (page_count(page_head) > 0)
+ break;
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+ return ret;
+}
+
+/*
* Set PG_hwpoison flag if a given page is confirmed to be a free page. This
* test is performed under the zone lock to prevent a race against page
* allocation.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 049/156] mm,hwpoison: rework soft offline for in-use pages
2020-10-16 2:40 incoming Andrew Morton
` (48 preceding siblings ...)
2020-10-16 3:07 ` [patch 048/156] mm,hwpoison: rework soft offline for free pages Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 050/156] mm,hwpoison: refactor soft_offline_huge_page and __soft_offline_page Andrew Morton
` (116 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Oscar Salvador <osalvador@suse.de>
Subject: mm,hwpoison: rework soft offline for in-use pages
This patch changes the way we set and handle in-use poisoned pages. Until
now, poisoned pages were released to the buddy allocator, trusting that
the checks that take place at allocation time would act as a safe net and
would skip that page.
This has proved to be wrong, as we got some pfn walkers out there, like
compaction, that all they care is the page to be in a buddy freelist.
Although this might not be the only user, having poisoned pages in the
buddy allocator seems a bad idea as we should only have free pages that
are ready and meant to be used as such.
Before explaining the taken approach, let us break down the kind of pages
we can soft offline.
- Anonymous THP (after the split, they end up being 4K pages)
- Hugetlb
- Order-0 pages (that can be either migrated or invalited)
* Normal pages (order-0 and anon-THP)
- If they are clean and unmapped page cache pages, we invalidate
then by means of invalidate_inode_page().
- If they are mapped/dirty, we do the isolate-and-migrate dance.
Either way, do not call put_page directly from those paths. Instead, we
keep the page and send it to page_handle_poison to perform the right
handling.
page_handle_poison sets the HWPoison flag and does the last put_page.
Down the chain, we placed a check for HWPoison page in
free_pages_prepare, that just skips any poisoned page, so those pages
do not end up in any pcplist/freelist.
After that, we set the refcount on the page to 1 and we increment
the poisoned pages counter.
If we see that the check in free_pages_prepare creates trouble, we can
always do what we do for free pages:
- wait until the page hits buddy's freelists
- take it off, and flag it
The downside of the above approach is that we could race with an
allocation, so by the time we want to take the page off the buddy, the
page has been already allocated so we cannot soft offline it.
But the user could always retry it.
* Hugetlb pages
- We isolate-and-migrate them
After the migration has been successful, we call dissolve_free_huge_page,
and we set HWPoison on the page if we succeed.
Hugetlb has a slightly different handling though.
While for non-hugetlb pages we cared about closing the race with an
allocation, doing so for hugetlb pages requires quite some additional
and intrusive code (we would need to hook in free_huge_page and some other
places).
So I decided to not make the code overly complicated and just fail
normally if the page we allocated in the meantime.
We can always build on top of this.
As a bonus, because of the way we handle now in-use pages, we no longer
need the put-as-isolation-migratetype dance, that was guarding for poisoned
pages to end up in pcplists.
Link: https://lkml.kernel.org/r/20200922135650.1634-10-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/page-flags.h | 5 ----
mm/memory-failure.c | 43 +++++++++++------------------------
mm/migrate.c | 11 ++------
mm/page_alloc.c | 39 ++++++++-----------------------
4 files changed, 28 insertions(+), 70 deletions(-)
--- a/include/linux/page-flags.h~mmhwpoison-rework-soft-offline-for-in-use-pages
+++ a/include/linux/page-flags.h
@@ -431,14 +431,9 @@ PAGEFLAG_FALSE(Uncached)
PAGEFLAG(HWPoison, hwpoison, PF_ANY)
TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
#define __PG_HWPOISON (1UL << PG_hwpoison)
-extern bool set_hwpoison_free_buddy_page(struct page *page);
extern bool take_page_off_buddy(struct page *page);
#else
PAGEFLAG_FALSE(HWPoison)
-static inline bool set_hwpoison_free_buddy_page(struct page *page)
-{
- return 0;
-}
#define __PG_HWPOISON 0
#endif
--- a/mm/memory-failure.c~mmhwpoison-rework-soft-offline-for-in-use-pages
+++ a/mm/memory-failure.c
@@ -65,9 +65,11 @@ int sysctl_memory_failure_recovery __rea
atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
-static void page_handle_poison(struct page *page)
+static void page_handle_poison(struct page *page, bool release)
{
SetPageHWPoison(page);
+ if (release)
+ put_page(page);
page_ref_inc(page);
num_poisoned_pages_inc();
}
@@ -1765,19 +1767,13 @@ static int soft_offline_huge_page(struct
ret = -EIO;
} else {
/*
- * We set PG_hwpoison only when the migration source hugepage
- * was successfully dissolved, because otherwise hwpoisoned
- * hugepage remains on free hugepage list, then userspace will
- * find it as SIGBUS by allocation failure. That's not expected
- * in soft-offlining.
+ * We set PG_hwpoison only when we were able to take the page
+ * off the buddy.
*/
- ret = dissolve_free_huge_page(page);
- if (!ret) {
- if (set_hwpoison_free_buddy_page(page))
- num_poisoned_pages_inc();
- else
- ret = -EBUSY;
- }
+ if (!dissolve_free_huge_page(page) && take_page_off_buddy(page))
+ page_handle_poison(page, false);
+ else
+ ret = -EBUSY;
}
return ret;
}
@@ -1812,10 +1808,8 @@ static int __soft_offline_page(struct pa
* would need to fix isolation locking first.
*/
if (ret == 1) {
- put_page(page);
pr_info("soft_offline: %#lx: invalidated\n", pfn);
- SetPageHWPoison(page);
- num_poisoned_pages_inc();
+ page_handle_poison(page, true);
return 0;
}
@@ -1846,7 +1840,9 @@ static int __soft_offline_page(struct pa
list_add(&page->lru, &pagelist);
ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
MIGRATE_SYNC, MR_MEMORY_FAILURE);
- if (ret) {
+ if (!ret) {
+ page_handle_poison(page, true);
+ } else {
if (!list_empty(&pagelist))
putback_movable_pages(&pagelist);
@@ -1865,27 +1861,16 @@ static int __soft_offline_page(struct pa
static int soft_offline_in_use_page(struct page *page, int flags)
{
int ret;
- int mt;
struct page *hpage = compound_head(page);
if (!PageHuge(page) && PageTransHuge(hpage))
if (try_to_split_thp_page(page, "soft offline") < 0)
return -EBUSY;
- /*
- * Setting MIGRATE_ISOLATE here ensures that the page will be linked
- * to free list immediately (not via pcplist) when released after
- * successful page migration. Otherwise we can't guarantee that the
- * page is really free after put_page() returns, so
- * set_hwpoison_free_buddy_page() highly likely fails.
- */
- mt = get_pageblock_migratetype(page);
- set_pageblock_migratetype(page, MIGRATE_ISOLATE);
if (PageHuge(page))
ret = soft_offline_huge_page(page, flags);
else
ret = __soft_offline_page(page, flags);
- set_pageblock_migratetype(page, mt);
return ret;
}
@@ -1894,7 +1879,7 @@ static int soft_offline_free_page(struct
int rc = -EBUSY;
if (!dissolve_free_huge_page(page) && take_page_off_buddy(page)) {
- page_handle_poison(page);
+ page_handle_poison(page, false);
rc = 0;
}
--- a/mm/migrate.c~mmhwpoison-rework-soft-offline-for-in-use-pages
+++ a/mm/migrate.c
@@ -1223,16 +1223,11 @@ out:
* we want to retry.
*/
if (rc == MIGRATEPAGE_SUCCESS) {
- put_page(page);
- if (reason == MR_MEMORY_FAILURE) {
+ if (reason != MR_MEMORY_FAILURE)
/*
- * Set PG_HWPoison on just freed page
- * intentionally. Although it's rather weird,
- * it's how HWPoison flag works at the moment.
+ * We release the page in page_handle_poison.
*/
- if (set_hwpoison_free_buddy_page(page))
- num_poisoned_pages_inc();
- }
+ put_page(page);
} else {
if (rc != -EAGAIN) {
if (likely(!__PageMovable(page))) {
--- a/mm/page_alloc.c~mmhwpoison-rework-soft-offline-for-in-use-pages
+++ a/mm/page_alloc.c
@@ -1174,6 +1174,17 @@ static __always_inline bool free_pages_p
trace_mm_page_free(page, order);
+ if (unlikely(PageHWPoison(page)) && !order) {
+ /*
+ * Do not let hwpoison pages hit pcplists/buddy
+ * Untie memcg state and reset page's owner
+ */
+ if (memcg_kmem_enabled() && PageKmemcg(page))
+ __memcg_kmem_uncharge_page(page, order);
+ reset_page_owner(page, order);
+ return false;
+ }
+
/*
* Check tail pages before head page information is cleared to
* avoid checking PageCompound for order-0 pages.
@@ -8844,32 +8855,4 @@ bool take_page_off_buddy(struct page *pa
spin_unlock_irqrestore(&zone->lock, flags);
return ret;
}
-
-/*
- * Set PG_hwpoison flag if a given page is confirmed to be a free page. This
- * test is performed under the zone lock to prevent a race against page
- * allocation.
- */
-bool set_hwpoison_free_buddy_page(struct page *page)
-{
- struct zone *zone = page_zone(page);
- unsigned long pfn = page_to_pfn(page);
- unsigned long flags;
- unsigned int order;
- bool hwpoisoned = false;
-
- spin_lock_irqsave(&zone->lock, flags);
- for (order = 0; order < MAX_ORDER; order++) {
- struct page *page_head = page - (pfn & ((1 << order) - 1));
-
- if (PageBuddy(page_head) && page_order(page_head) >= order) {
- if (!TestSetPageHWPoison(page))
- hwpoisoned = true;
- break;
- }
- }
- spin_unlock_irqrestore(&zone->lock, flags);
-
- return hwpoisoned;
-}
#endif
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 050/156] mm,hwpoison: refactor soft_offline_huge_page and __soft_offline_page
2020-10-16 2:40 incoming Andrew Morton
` (49 preceding siblings ...)
2020-10-16 3:07 ` [patch 049/156] mm,hwpoison: rework soft offline for in-use pages Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 051/156] mm,hwpoison: return 0 if the page is already poisoned in soft-offline Andrew Morton
` (115 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Oscar Salvador <osalvador@suse.de>
Subject: mm,hwpoison: refactor soft_offline_huge_page and __soft_offline_page
Merging soft_offline_huge_page and __soft_offline_page let us get rid of
quite some duplicated code, and makes the code much easier to follow.
Now, __soft_offline_page will handle both normal and hugetlb pages.
Link: https://lkml.kernel.org/r/20200922135650.1634-11-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory-failure.c | 182 ++++++++++++++++++------------------------
1 file changed, 82 insertions(+), 100 deletions(-)
--- a/mm/memory-failure.c~mmhwpoison-refactor-soft_offline_huge_page-and-__soft_offline_page
+++ a/mm/memory-failure.c
@@ -65,13 +65,31 @@ int sysctl_memory_failure_recovery __rea
atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
-static void page_handle_poison(struct page *page, bool release)
+static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release)
{
+ if (hugepage_or_freepage) {
+ /*
+ * Doing this check for free pages is also fine since dissolve_free_huge_page
+ * returns 0 for non-hugetlb pages as well.
+ */
+ if (dissolve_free_huge_page(page) || !take_page_off_buddy(page))
+ /*
+ * We could fail to take off the target page from buddy
+ * for example due to racy page allocaiton, but that's
+ * acceptable because soft-offlined page is not broken
+ * and if someone really want to use it, they should
+ * take it.
+ */
+ return false;
+ }
+
SetPageHWPoison(page);
if (release)
put_page(page);
page_ref_inc(page);
num_poisoned_pages_inc();
+
+ return true;
}
#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
@@ -1725,63 +1743,51 @@ static int get_any_page(struct page *pag
return ret;
}
-static int soft_offline_huge_page(struct page *page, int flags)
+static bool isolate_page(struct page *page, struct list_head *pagelist)
{
- int ret;
- unsigned long pfn = page_to_pfn(page);
- struct page *hpage = compound_head(page);
- LIST_HEAD(pagelist);
+ bool isolated = false;
+ bool lru = PageLRU(page);
- /*
- * This double-check of PageHWPoison is to avoid the race with
- * memory_failure(). See also comment in __soft_offline_page().
- */
- lock_page(hpage);
- if (PageHWPoison(hpage)) {
- unlock_page(hpage);
- put_page(hpage);
- pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
- return -EBUSY;
+ if (PageHuge(page)) {
+ isolated = isolate_huge_page(page, pagelist);
+ } else {
+ if (lru)
+ isolated = !isolate_lru_page(page);
+ else
+ isolated = !isolate_movable_page(page, ISOLATE_UNEVICTABLE);
+
+ if (isolated)
+ list_add(&page->lru, pagelist);
}
- unlock_page(hpage);
- ret = isolate_huge_page(hpage, &pagelist);
+ if (isolated && lru)
+ inc_node_page_state(page, NR_ISOLATED_ANON +
+ page_is_file_lru(page));
+
/*
- * get_any_page() and isolate_huge_page() takes a refcount each,
- * so need to drop one here.
+ * If we succeed to isolate the page, we grabbed another refcount on
+ * the page, so we can safely drop the one we got from get_any_pages().
+ * If we failed to isolate the page, it means that we cannot go further
+ * and we will return an error, so drop the reference we got from
+ * get_any_pages() as well.
*/
- put_page(hpage);
- if (!ret) {
- pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
- return -EBUSY;
- }
-
- ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
- MIGRATE_SYNC, MR_MEMORY_FAILURE);
- if (ret) {
- pr_info("soft offline: %#lx: hugepage migration failed %d, type %lx (%pGp)\n",
- pfn, ret, page->flags, &page->flags);
- if (!list_empty(&pagelist))
- putback_movable_pages(&pagelist);
- if (ret > 0)
- ret = -EIO;
- } else {
- /*
- * We set PG_hwpoison only when we were able to take the page
- * off the buddy.
- */
- if (!dissolve_free_huge_page(page) && take_page_off_buddy(page))
- page_handle_poison(page, false);
- else
- ret = -EBUSY;
- }
- return ret;
+ put_page(page);
+ return isolated;
}
-static int __soft_offline_page(struct page *page, int flags)
+/*
+ * __soft_offline_page handles hugetlb-pages and non-hugetlb pages.
+ * If the page is a non-dirty unmapped page-cache page, it simply invalidates.
+ * If the page is mapped, it migrates the contents over.
+ */
+static int __soft_offline_page(struct page *page)
{
- int ret;
+ int ret = 0;
unsigned long pfn = page_to_pfn(page);
+ struct page *hpage = compound_head(page);
+ char const *msg_page[] = {"page", "hugepage"};
+ bool huge = PageHuge(page);
+ LIST_HEAD(pagelist);
/*
* Check PageHWPoison again inside page lock because PageHWPoison
@@ -1790,98 +1796,74 @@ static int __soft_offline_page(struct pa
* so there's no race between soft_offline_page() and memory_failure().
*/
lock_page(page);
- wait_on_page_writeback(page);
+ if (!PageHuge(page))
+ wait_on_page_writeback(page);
if (PageHWPoison(page)) {
unlock_page(page);
put_page(page);
pr_info("soft offline: %#lx page already poisoned\n", pfn);
return -EBUSY;
}
- /*
- * Try to invalidate first. This should work for
- * non dirty unmapped page cache pages.
- */
- ret = invalidate_inode_page(page);
+
+ if (!PageHuge(page))
+ /*
+ * Try to invalidate first. This should work for
+ * non dirty unmapped page cache pages.
+ */
+ ret = invalidate_inode_page(page);
unlock_page(page);
+
/*
* RED-PEN would be better to keep it isolated here, but we
* would need to fix isolation locking first.
*/
- if (ret == 1) {
+ if (ret) {
pr_info("soft_offline: %#lx: invalidated\n", pfn);
- page_handle_poison(page, true);
+ page_handle_poison(page, false, true);
return 0;
}
- /*
- * Simple invalidation didn't work.
- * Try to migrate to a new page instead. migrate.c
- * handles a large number of cases for us.
- */
- if (PageLRU(page))
- ret = isolate_lru_page(page);
- else
- ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE);
- /*
- * Drop page reference which is came from get_any_page()
- * successful isolate_lru_page() already took another one.
- */
- put_page(page);
- if (!ret) {
- LIST_HEAD(pagelist);
- /*
- * After isolated lru page, the PageLRU will be cleared,
- * so use !__PageMovable instead for LRU page's mapping
- * cannot have PAGE_MAPPING_MOVABLE.
- */
- if (!__PageMovable(page))
- inc_node_page_state(page, NR_ISOLATED_ANON +
- page_is_file_lru(page));
- list_add(&page->lru, &pagelist);
+ if (isolate_page(hpage, &pagelist)) {
ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
MIGRATE_SYNC, MR_MEMORY_FAILURE);
if (!ret) {
- page_handle_poison(page, true);
+ bool release = !huge;
+
+ if (!page_handle_poison(page, huge, release))
+ ret = -EBUSY;
} else {
if (!list_empty(&pagelist))
putback_movable_pages(&pagelist);
- pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n",
- pfn, ret, page->flags, &page->flags);
+ pr_info("soft offline: %#lx: %s migration failed %d, type %lx (%pGp)\n",
+ pfn, msg_page[huge], ret, page->flags, &page->flags);
if (ret > 0)
ret = -EIO;
}
} else {
- pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx (%pGp)\n",
- pfn, ret, page_count(page), page->flags, &page->flags);
+ pr_info("soft offline: %#lx: %s isolation failed: %d, page count %d, type %lx (%pGp)\n",
+ pfn, msg_page[huge], ret, page_count(page), page->flags, &page->flags);
+ ret = -EBUSY;
}
return ret;
}
-static int soft_offline_in_use_page(struct page *page, int flags)
+static int soft_offline_in_use_page(struct page *page)
{
- int ret;
struct page *hpage = compound_head(page);
if (!PageHuge(page) && PageTransHuge(hpage))
if (try_to_split_thp_page(page, "soft offline") < 0)
return -EBUSY;
-
- if (PageHuge(page))
- ret = soft_offline_huge_page(page, flags);
- else
- ret = __soft_offline_page(page, flags);
- return ret;
+ return __soft_offline_page(page);
}
static int soft_offline_free_page(struct page *page)
{
- int rc = -EBUSY;
+ int rc = 0;
- if (!dissolve_free_huge_page(page) && take_page_off_buddy(page)) {
- page_handle_poison(page, false);
- rc = 0;
- }
+ if (!page_handle_poison(page, true, false))
+ rc = -EBUSY;
return rc;
}
@@ -1932,7 +1914,7 @@ int soft_offline_page(unsigned long pfn,
put_online_mems();
if (ret > 0)
- ret = soft_offline_in_use_page(page, flags);
+ ret = soft_offline_in_use_page(page);
else if (ret == 0)
ret = soft_offline_free_page(page);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 051/156] mm,hwpoison: return 0 if the page is already poisoned in soft-offline
2020-10-16 2:40 incoming Andrew Morton
` (50 preceding siblings ...)
2020-10-16 3:07 ` [patch 050/156] mm,hwpoison: refactor soft_offline_huge_page and __soft_offline_page Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 052/156] mm,hwpoison: introduce MF_MSG_UNSPLIT_THP Andrew Morton
` (114 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Oscar Salvador <osalvador@suse.de>
Subject: mm,hwpoison: return 0 if the page is already poisoned in soft-offline
Currently, there is an inconsistency when calling soft-offline from
different paths on a page that is already poisoned.
1) madvise:
madvise_inject_error skips any poisoned page and continues
the loop.
If that was the only page to madvise, it returns 0.
2) /sys/devices/system/memory/:
When calling soft_offline_page_store()->soft_offline_page(),
we return -EBUSY in case the page is already poisoned.
This is inconsistent with a) the above example and b)
memory_failure, where we return 0 if the page was poisoned.
Fix this by dropping the PageHWPoison() check in madvise_inject_error, and
let soft_offline_page return 0 if it finds the page already poisoned.
Please, note that this represents a user-api change, since now the return
error when calling soft_offline_page_store()->soft_offline_page() will be
different.
Link: https://lkml.kernel.org/r/20200922135650.1634-12-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/madvise.c | 5 -----
mm/memory-failure.c | 4 ++--
2 files changed, 2 insertions(+), 7 deletions(-)
--- a/mm/madvise.c~mmhwpoison-return-0-if-the-page-is-already-poisoned-in-soft-offline
+++ a/mm/madvise.c
@@ -896,11 +896,6 @@ static int madvise_inject_error(int beha
*/
size = page_size(compound_head(page));
- if (PageHWPoison(page)) {
- put_page(page);
- continue;
- }
-
if (behavior == MADV_SOFT_OFFLINE) {
pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n",
pfn, start);
--- a/mm/memory-failure.c~mmhwpoison-return-0-if-the-page-is-already-poisoned-in-soft-offline
+++ a/mm/memory-failure.c
@@ -1802,7 +1802,7 @@ static int __soft_offline_page(struct pa
unlock_page(page);
put_page(page);
pr_info("soft offline: %#lx page already poisoned\n", pfn);
- return -EBUSY;
+ return 0;
}
if (!PageHuge(page))
@@ -1906,7 +1906,7 @@ int soft_offline_page(unsigned long pfn,
pr_info("soft offline: %#lx page already poisoned\n", pfn);
if (flags & MF_COUNT_INCREASED)
put_page(page);
- return -EBUSY;
+ return 0;
}
get_online_mems();
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 052/156] mm,hwpoison: introduce MF_MSG_UNSPLIT_THP
2020-10-16 2:40 incoming Andrew Morton
` (51 preceding siblings ...)
2020-10-16 3:07 ` [patch 051/156] mm,hwpoison: return 0 if the page is already poisoned in soft-offline Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 053/156] mm,hwpoison: double-check page count in __get_any_page() Andrew Morton
` (113 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm,hwpoison: introduce MF_MSG_UNSPLIT_THP
memory_failure() is supposed to call action_result() when it handles a
memory error event, but there's one missing case. So let's add it.
I find that include/ras/ras_event.h has some other MF_MSG_* undefined, so
this patch also adds them.
Link: https://lkml.kernel.org/r/20200922135650.1634-13-osalvador@suse.de
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/mm.h | 1 +
include/ras/ras_event.h | 3 +++
mm/memory-failure.c | 5 ++++-
3 files changed, 8 insertions(+), 1 deletion(-)
--- a/include/linux/mm.h~mmhwpoison-introduce-mf_msg_unsplit_thp
+++ a/include/linux/mm.h
@@ -3064,6 +3064,7 @@ enum mf_action_page_type {
MF_MSG_BUDDY,
MF_MSG_BUDDY_2ND,
MF_MSG_DAX,
+ MF_MSG_UNSPLIT_THP,
MF_MSG_UNKNOWN,
};
--- a/include/ras/ras_event.h~mmhwpoison-introduce-mf_msg_unsplit_thp
+++ a/include/ras/ras_event.h
@@ -361,6 +361,7 @@ TRACE_EVENT(aer_event,
EM ( MF_MSG_POISONED_HUGE, "huge page already hardware poisoned" ) \
EM ( MF_MSG_HUGE, "huge page" ) \
EM ( MF_MSG_FREE_HUGE, "free huge page" ) \
+ EM ( MF_MSG_NON_PMD_HUGE, "non-pmd-sized huge page" ) \
EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" ) \
EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" ) \
EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" ) \
@@ -373,6 +374,8 @@ TRACE_EVENT(aer_event,
EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" ) \
EM ( MF_MSG_BUDDY, "free buddy page" ) \
EM ( MF_MSG_BUDDY_2ND, "free buddy page (2nd try)" ) \
+ EM ( MF_MSG_DAX, "dax page" ) \
+ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \
EMe ( MF_MSG_UNKNOWN, "unknown page" )
/*
--- a/mm/memory-failure.c~mmhwpoison-introduce-mf_msg_unsplit_thp
+++ a/mm/memory-failure.c
@@ -582,6 +582,7 @@ static const char * const action_page_ty
[MF_MSG_BUDDY] = "free buddy page",
[MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)",
[MF_MSG_DAX] = "dax page",
+ [MF_MSG_UNSPLIT_THP] = "unsplit thp",
[MF_MSG_UNKNOWN] = "unknown page",
};
@@ -1370,8 +1371,10 @@ int memory_failure(unsigned long pfn, in
}
if (PageTransHuge(hpage)) {
- if (try_to_split_thp_page(p, "Memory Failure") < 0)
+ if (try_to_split_thp_page(p, "Memory Failure") < 0) {
+ action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
return -EBUSY;
+ }
VM_BUG_ON_PAGE(!page_count(p), p);
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 053/156] mm,hwpoison: double-check page count in __get_any_page()
2020-10-16 2:40 incoming Andrew Morton
` (52 preceding siblings ...)
2020-10-16 3:07 ` [patch 052/156] mm,hwpoison: introduce MF_MSG_UNSPLIT_THP Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 054/156] mm,hwpoison: try to narrow window race for free pages Andrew Morton
` (112 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
tony.luck, torvalds, zeil
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm,hwpoison: double-check page count in __get_any_page()
Soft offlining could fail with EIO due to the race condition with hugepage
migration. This issuse became visible due to the change by previous patch
that makes soft offline handler take page refcount by its own. We have no
way to directly pin zero refcount page, and the page considered as a zero
refcount page could be allocated just after the first check.
This patch adds the second check to find the race and gives us chance to
handle it more reliably.
Link: https://lkml.kernel.org/r/20200922135650.1634-14-osalvador@suse.de
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reported-by: Qian Cai <cai@lca.pw>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory-failure.c | 6 ++++++
1 file changed, 6 insertions(+)
--- a/mm/memory-failure.c~mmhwpoison-double-check-page-count-in-__get_any_page
+++ a/mm/memory-failure.c
@@ -1707,6 +1707,9 @@ static int __get_any_page(struct page *p
} else if (is_free_buddy_page(p)) {
pr_info("%s: %#lx free buddy page\n", __func__, pfn);
ret = 0;
+ } else if (page_count(p)) {
+ /* raced with allocation */
+ ret = -EBUSY;
} else {
pr_info("%s: %#lx: unknown zero refcount page type %lx\n",
__func__, pfn, p->flags);
@@ -1723,6 +1726,9 @@ static int get_any_page(struct page *pag
{
int ret = __get_any_page(page, pfn, flags);
+ if (ret == -EBUSY)
+ ret = __get_any_page(page, pfn, flags);
+
if (ret == 1 && !PageHuge(page) &&
!PageLRU(page) && !__PageMovable(page)) {
/*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 054/156] mm,hwpoison: try to narrow window race for free pages
2020-10-16 2:40 incoming Andrew Morton
` (53 preceding siblings ...)
2020-10-16 3:07 ` [patch 053/156] mm,hwpoison: double-check page count in __get_any_page() Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 055/156] mm/page_poison.c: replace bool variable with static key Andrew Morton
` (111 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, aneesh.kumar, aneesh.kumar, aris, cai, dave.hansen, david,
mhocko, mike.kravetz, mm-commits, naoya.horiguchi, osalvador,
osalvador, tony.luck, torvalds, zeil
From: Oscar Salvador <osalvador@suse.de>
Subject: mm,hwpoison: try to narrow window race for free pages
Aristeu Rozanski reported that a customer test case started to report
-EBUSY after the hwpoison rework patchset.
There is a race window between spotting a free page and taking it off its
buddy freelist, so it might be that by the time we try to take it off, the
page has been already allocated.
This patch tries to handle such race window by trying to handle the new
type of page again if the page was allocated under us.
Link: https://lkml.kernel.org/r/20200922135650.1634-15-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reported-by: Aristeu Rozanski <aris@ruivo.org>
Tested-by: Aristeu Rozanski <aris@ruivo.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory-failure.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
--- a/mm/memory-failure.c~mmhwpoison-try-to-narrow-window-race-for-free-pages
+++ a/mm/memory-failure.c
@@ -1903,6 +1903,7 @@ int soft_offline_page(unsigned long pfn,
{
int ret;
struct page *page;
+ bool try_again = true;
if (!pfn_valid(pfn))
return -ENXIO;
@@ -1918,6 +1919,7 @@ int soft_offline_page(unsigned long pfn,
return 0;
}
+retry:
get_online_mems();
ret = get_any_page(page, pfn, flags);
put_online_mems();
@@ -1925,7 +1927,10 @@ int soft_offline_page(unsigned long pfn,
if (ret > 0)
ret = soft_offline_in_use_page(page);
else if (ret == 0)
- ret = soft_offline_free_page(page);
+ if (soft_offline_free_page(page) && try_again) {
+ try_again = false;
+ goto retry;
+ }
return ret;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 055/156] mm/page_poison.c: replace bool variable with static key
2020-10-16 2:40 incoming Andrew Morton
` (54 preceding siblings ...)
2020-10-16 3:07 ` [patch 054/156] mm,hwpoison: try to narrow window race for free pages Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 056/156] mm/vmstat.c: use helper macro abs() Andrew Morton
` (110 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, mateusznosek0, mm-commits, n-horiguchi, OSalvador, torvalds
From: Mateusz Nosek <mateusznosek0@gmail.com>
Subject: mm/page_poison.c: replace bool variable with static key
Variable 'want_page_poisoning' is a switch deciding if page poisoning
should be enabled. This patch changes it to be static key.
Link: https://lkml.kernel.org/r/20200921152931.938-1-mateusznosek0@gmail.com
Signed-off-by: Mateusz Nosek <mateusznosek0@gmail.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Oscar Salvador <OSalvador@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/page_poison.c | 20 +++++++++++++++-----
1 file changed, 15 insertions(+), 5 deletions(-)
--- a/mm/page_poison.c~mm-page_poisonc-replace-bool-variable-with-static-key
+++ a/mm/page_poison.c
@@ -8,13 +8,23 @@
#include <linux/ratelimit.h>
#include <linux/kasan.h>
-static bool want_page_poisoning __read_mostly;
+static DEFINE_STATIC_KEY_FALSE_RO(want_page_poisoning);
static int __init early_page_poison_param(char *buf)
{
- if (!buf)
- return -EINVAL;
- return strtobool(buf, &want_page_poisoning);
+ int ret;
+ bool tmp;
+
+ ret = strtobool(buf, &tmp);
+ if (ret)
+ return ret;
+
+ if (tmp)
+ static_branch_enable(&want_page_poisoning);
+ else
+ static_branch_disable(&want_page_poisoning);
+
+ return 0;
}
early_param("page_poison", early_page_poison_param);
@@ -31,7 +41,7 @@ bool page_poisoning_enabled(void)
* Page poisoning is debug page alloc for some arches. If
* either of those options are enabled, enable poisoning.
*/
- return (want_page_poisoning ||
+ return (static_branch_unlikely(&want_page_poisoning) ||
(!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) &&
debug_pagealloc_enabled()));
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 056/156] mm/vmstat.c: use helper macro abs()
2020-10-16 2:40 incoming Andrew Morton
` (55 preceding siblings ...)
2020-10-16 3:07 ` [patch 055/156] mm/page_poison.c: replace bool variable with static key Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 057/156] mm/util.c: update the kerneldoc for kstrdup_const() Andrew Morton
` (109 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, linmiaohe, mm-commits, torvalds
From: Miaohe Lin <linmiaohe@huawei.com>
Subject: mm/vmstat.c: use helper macro abs()
Use helper macro abs() to simplify the "x > t || x < -t" cmp.
Link: https://lkml.kernel.org/r/20200905084008.15748-1-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/vmstat.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
--- a/mm/vmstat.c~mm-vmstat-use-helper-macro-abs
+++ a/mm/vmstat.c
@@ -325,7 +325,7 @@ void __mod_zone_page_state(struct zone *
t = __this_cpu_read(pcp->stat_threshold);
- if (unlikely(x > t || x < -t)) {
+ if (unlikely(abs(x) > t)) {
zone_page_state_add(x, zone, item);
x = 0;
}
@@ -350,7 +350,7 @@ void __mod_node_page_state(struct pglist
t = __this_cpu_read(pcp->stat_threshold);
- if (unlikely(x > t || x < -t)) {
+ if (unlikely(abs(x) > t)) {
node_page_state_add(x, pgdat, item);
x = 0;
}
@@ -511,7 +511,7 @@ static inline void mod_zone_state(struct
o = this_cpu_read(*p);
n = delta + o;
- if (n > t || n < -t) {
+ if (abs(n) > t) {
int os = overstep_mode * (t >> 1) ;
/* Overflow must be added to zone counters */
@@ -573,7 +573,7 @@ static inline void mod_node_state(struct
o = this_cpu_read(*p);
n = delta + o;
- if (n > t || n < -t) {
+ if (abs(n) > t) {
int os = overstep_mode * (t >> 1) ;
/* Overflow must be added to node counters */
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 057/156] mm/util.c: update the kerneldoc for kstrdup_const()
2020-10-16 2:40 incoming Andrew Morton
` (56 preceding siblings ...)
2020-10-16 3:07 ` [patch 056/156] mm/vmstat.c: use helper macro abs() Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 058/156] mm/mmu_notifier: fix mmget() assert in __mmu_interval_notifier_insert Andrew Morton
` (108 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, bgolaszewski, mm-commits, torvalds
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Subject: mm/util.c: update the kerneldoc for kstrdup_const()
Memory allocated with kstrdup_const() must not be passed to regular
krealloc() as it is not aware of the possibility of the chunk residing in
.rodata. Since there are no potential users of krealloc_const() at the
moment, let's just update the doc to make it explicit.
Link: http://lkml.kernel.org/r/20200817173927.23389-1-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/util.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
--- a/mm/util.c~mm-util-update-the-kerneldoc-for-kstrdup_const
+++ a/mm/util.c
@@ -69,7 +69,8 @@ EXPORT_SYMBOL(kstrdup);
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
- * Note: Strings allocated by kstrdup_const should be freed by kfree_const.
+ * Note: Strings allocated by kstrdup_const should be freed by kfree_const and
+ * must not be passed to krealloc().
*
* Return: source string if it is in .rodata section otherwise
* fallback to kstrdup.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 058/156] mm/mmu_notifier: fix mmget() assert in __mmu_interval_notifier_insert
2020-10-16 2:40 incoming Andrew Morton
` (57 preceding siblings ...)
2020-10-16 3:07 ` [patch 057/156] mm/util.c: update the kerneldoc for kstrdup_const() Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 059/156] mm/memory_hotplug: inline __offline_pages() into offline_pages() Andrew Morton
` (107 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, christian.koenig, hch, jannh, jgg, jhubbard, mm-commits, torvalds
From: Jann Horn <jannh@google.com>
Subject: mm/mmu_notifier: fix mmget() assert in __mmu_interval_notifier_insert
The comment talks about having to hold mmget() (which means mm_users), but
the actual check is on mm_count (which would be mmgrab()).
Given that MMU notifiers are torn down in mmput() -> __mmput() ->
exit_mmap() -> mmu_notifier_release(), I believe that the comment is
correct and the check should be on mm->mm_users. Fix it up accordingly.
Link: https://lkml.kernel.org/r/20200901000143.207585-1-jannh@google.com
Fixes: 99cb252f5e68 ("mm/mmu_notifier: add an interval tree notifier")
Signed-off-by: Jann Horn <jannh@google.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Christian König <christian.koenig@amd.com
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/mmu_notifier.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/mmu_notifier.c~mm-mmu_notifier-fix-mmget-assert-in-__mmu_interval_notifier_insert
+++ a/mm/mmu_notifier.c
@@ -913,7 +913,7 @@ static int __mmu_interval_notifier_inser
return -EOVERFLOW;
/* Must call with a mmget() held */
- if (WARN_ON(atomic_read(&mm->mm_count) <= 0))
+ if (WARN_ON(atomic_read(&mm->mm_users) <= 0))
return -EINVAL;
/* pairs with mmdrop in mmu_interval_notifier_remove() */
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 059/156] mm/memory_hotplug: inline __offline_pages() into offline_pages()
2020-10-16 2:40 incoming Andrew Morton
` (58 preceding siblings ...)
2020-10-16 3:07 ` [patch 058/156] mm/mmu_notifier: fix mmget() assert in __mmu_interval_notifier_insert Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 060/156] mm/memory_hotplug: enforce section granularity when onlining/offlining Andrew Morton
` (106 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mgorman, mhocko, mm-commits, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, tony.luck, torvalds,
walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: inline __offline_pages() into offline_pages()
Patch series "mm/memory_hotplug: online_pages()/offline_pages() cleanups", v2.
These are a bunch of cleanups for online_pages()/offline_pages() and
related code, mostly getting rid of memory hole handling that is no longer
necessary. There is only a single walk_system_ram_range() call left in
offline_pages(), to make sure we don't have any memory holes. I had some
of these patches lying around for a longer time but didn't have time to
polish them.
In addition, the last patch marks all pageblocks of memory to get onlined
MIGRATE_ISOLATE, so pages that have just been exposed to the buddy cannot
get allocated before onlining is complete. Once heavy lifting is done,
the pageblocks are set to MIGRATE_MOVABLE, such that allocations are
possible.
I played with DIMMs and virtio-mem on x86-64 and didn't spot any
surprises. I verified that the numer of isolated pageblocks is correctly
handled when onlining/offlining.
This patch (of 10):
There is only a single user, offline_pages(). Let's inline, to make
it look more similar to online_pages().
Link: https://lkml.kernel.org/r/20200819175957.28465-1-david@redhat.com
Link: https://lkml.kernel.org/r/20200819175957.28465-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory_hotplug.c | 16 +++++-----------
1 file changed, 5 insertions(+), 11 deletions(-)
--- a/mm/memory_hotplug.c~mm-memory_hotplug-inline-__offline_pages-into-offline_pages
+++ a/mm/memory_hotplug.c
@@ -1484,11 +1484,10 @@ static int count_system_ram_pages_cb(uns
return 0;
}
-static int __ref __offline_pages(unsigned long start_pfn,
- unsigned long end_pfn)
+int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
{
- unsigned long pfn, nr_pages = 0;
- unsigned long offlined_pages = 0;
+ const unsigned long end_pfn = start_pfn + nr_pages;
+ unsigned long pfn, system_ram_pages = 0, offlined_pages = 0;
int ret, node, nr_isolate_pageblock;
unsigned long flags;
struct zone *zone;
@@ -1505,9 +1504,9 @@ static int __ref __offline_pages(unsigne
* memory holes PG_reserved, don't need pfn_valid() checks, and can
* avoid using walk_system_ram_range() later.
*/
- walk_system_ram_range(start_pfn, end_pfn - start_pfn, &nr_pages,
+ walk_system_ram_range(start_pfn, nr_pages, &system_ram_pages,
count_system_ram_pages_cb);
- if (nr_pages != end_pfn - start_pfn) {
+ if (system_ram_pages != nr_pages) {
ret = -EINVAL;
reason = "memory holes";
goto failed_removal;
@@ -1656,11 +1655,6 @@ failed_removal:
return ret;
}
-int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
-{
- return __offline_pages(start_pfn, start_pfn + nr_pages);
-}
-
static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
{
int ret = !is_memblock_offlined(mem);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 060/156] mm/memory_hotplug: enforce section granularity when onlining/offlining
2020-10-16 2:40 incoming Andrew Morton
` (59 preceding siblings ...)
2020-10-16 3:07 ` [patch 059/156] mm/memory_hotplug: inline __offline_pages() into offline_pages() Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 061/156] mm/memory_hotplug: simplify page offlining Andrew Morton
` (105 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mgorman, mhocko, mm-commits, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, tony.luck, torvalds,
walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: enforce section granularity when onlining/offlining
Already two people (including me) tried to offline subsections, because
the function looks like it can deal with it. But we really can only
online/offline full sections that are properly aligned (e.g., we can only
mark full sections online/offline via SECTION_IS_ONLINE).
Add a simple safety net to document the restriction now. Current users
(core and powernv/memtrace) respect these restrictions.
Link: https://lkml.kernel.org/r/20200819175957.28465-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory_hotplug.c | 10 ++++++++++
1 file changed, 10 insertions(+)
--- a/mm/memory_hotplug.c~mm-memory_hotplug-enforce-section-granularity-when-onlining-offlining
+++ a/mm/memory_hotplug.c
@@ -809,6 +809,11 @@ int __ref online_pages(unsigned long pfn
int ret;
struct memory_notify arg;
+ /* We can only online full sections (e.g., SECTION_IS_ONLINE) */
+ if (WARN_ON_ONCE(!nr_pages ||
+ !IS_ALIGNED(pfn | nr_pages, PAGES_PER_SECTION)))
+ return -EINVAL;
+
mem_hotplug_begin();
/* associate pfn range with the zone */
@@ -1494,6 +1499,11 @@ int __ref offline_pages(unsigned long st
struct memory_notify arg;
char *reason;
+ /* We can only offline full sections (e.g., SECTION_IS_ONLINE) */
+ if (WARN_ON_ONCE(!nr_pages ||
+ !IS_ALIGNED(start_pfn | nr_pages, PAGES_PER_SECTION)))
+ return -EINVAL;
+
mem_hotplug_begin();
/*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 061/156] mm/memory_hotplug: simplify page offlining
2020-10-16 2:40 incoming Andrew Morton
` (60 preceding siblings ...)
2020-10-16 3:07 ` [patch 060/156] mm/memory_hotplug: enforce section granularity when onlining/offlining Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:07 ` [patch 062/156] mm/page_alloc: simplify __offline_isolated_pages() Andrew Morton
` (104 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mgorman, mhocko, mm-commits, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, tony.luck, torvalds,
walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: simplify page offlining
We make sure that we cannot have any memory holes right at the beginning
of offline_pages(). We no longer need walk_system_ram_range() and can
call test_pages_isolated() and __offline_isolated_pages() directly.
offlined_pages always corresponds to nr_pages, so we can simplify that.
[akpm@linux-foundation.org: patch conflict resolution]
Link: https://lkml.kernel.org/r/20200819175957.28465-4-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory_hotplug.c | 44 +++++++++---------------------------------
1 file changed, 10 insertions(+), 34 deletions(-)
--- a/mm/memory_hotplug.c~mm-memory_hotplug-simplify-page-offlining
+++ a/mm/memory_hotplug.c
@@ -1384,28 +1384,6 @@ do_migrate_range(unsigned long start_pfn
return ret;
}
-/* Mark all sections offline and remove all free pages from the buddy. */
-static int
-offline_isolated_pages_cb(unsigned long start, unsigned long nr_pages,
- void *data)
-{
- unsigned long *offlined_pages = (unsigned long *)data;
-
- *offlined_pages += __offline_isolated_pages(start, start + nr_pages);
- return 0;
-}
-
-/*
- * Check all pages in range, recorded as memory resource, are isolated.
- */
-static int
-check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages,
- void *data)
-{
- return test_pages_isolated(start_pfn, start_pfn + nr_pages,
- MEMORY_OFFLINE);
-}
-
static int __init cmdline_parse_movable_node(char *p)
{
movable_node_enabled = true;
@@ -1492,7 +1470,7 @@ static int count_system_ram_pages_cb(uns
int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
{
const unsigned long end_pfn = start_pfn + nr_pages;
- unsigned long pfn, system_ram_pages = 0, offlined_pages = 0;
+ unsigned long pfn, system_ram_pages = 0;
int ret, node, nr_isolate_pageblock;
unsigned long flags;
struct zone *zone;
@@ -1590,9 +1568,7 @@ int __ref offline_pages(unsigned long st
reason = "failure to dissolve huge pages";
goto failed_removal_isolated;
}
- /* check again */
- ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
- NULL, check_pages_isolated_cb);
+
/*
* per-cpu pages are drained in start_isolate_page_range, but if
* there are still pages that are not free, make sure that we
@@ -1605,15 +1581,15 @@ int __ref offline_pages(unsigned long st
* because has_unmovable_pages explicitly checks for
* PageBuddy on freed pages on other zones.
*/
+ ret = test_pages_isolated(start_pfn, end_pfn, MEMORY_OFFLINE);
if (ret)
drain_all_pages(zone);
} while (ret);
- /* Ok, all of our target is isolated.
- We cannot do rollback at this point. */
- walk_system_ram_range(start_pfn, end_pfn - start_pfn,
- &offlined_pages, offline_isolated_pages_cb);
- pr_info("Offlined Pages %ld\n", offlined_pages);
+ /* Mark all sections offline and remove free pages from the buddy. */
+ __offline_isolated_pages(start_pfn, end_pfn);
+ pr_info("Offlined Pages %ld\n", nr_pages);
+
/*
* Onlining will reset pagetype flags and makes migrate type
* MOVABLE, so just need to decrease the number of isolated
@@ -1624,11 +1600,11 @@ int __ref offline_pages(unsigned long st
spin_unlock_irqrestore(&zone->lock, flags);
/* removal success */
- adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages);
- zone->present_pages -= offlined_pages;
+ adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages);
+ zone->present_pages -= nr_pages;
pgdat_resize_lock(zone->zone_pgdat, &flags);
- zone->zone_pgdat->node_present_pages -= offlined_pages;
+ zone->zone_pgdat->node_present_pages -= nr_pages;
pgdat_resize_unlock(zone->zone_pgdat, &flags);
init_per_zone_wmark_min();
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 062/156] mm/page_alloc: simplify __offline_isolated_pages()
2020-10-16 2:40 incoming Andrew Morton
` (61 preceding siblings ...)
2020-10-16 3:07 ` [patch 061/156] mm/memory_hotplug: simplify page offlining Andrew Morton
@ 2020-10-16 3:07 ` Andrew Morton
2020-10-16 3:08 ` [patch 063/156] mm/memory_hotplug: drop nr_isolate_pageblock in offline_pages() Andrew Morton
` (103 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:07 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mgorman, mhocko, mm-commits, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, tony.luck, torvalds,
walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/page_alloc: simplify __offline_isolated_pages()
offline_pages() is the only user. __offline_isolated_pages() never gets
called with ranges that contain memory holes and we no longer care about
the return value. Drop the return value handling and all pfn_valid()
checks.
Update the documentation.
Link: https://lkml.kernel.org/r/20200819175957.28465-5-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memory_hotplug.h | 4 ++--
mm/page_alloc.c | 27 ++++-----------------------
2 files changed, 6 insertions(+), 25 deletions(-)
--- a/include/linux/memory_hotplug.h~mm-page_alloc-simplify-__offline_isolated_pages
+++ a/include/linux/memory_hotplug.h
@@ -103,8 +103,8 @@ extern int online_pages(unsigned long pf
int online_type, int nid);
extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
unsigned long end_pfn);
-extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
- unsigned long end_pfn);
+extern void __offline_isolated_pages(unsigned long start_pfn,
+ unsigned long end_pfn);
typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
--- a/mm/page_alloc.c~mm-page_alloc-simplify-__offline_isolated_pages
+++ a/mm/page_alloc.c
@@ -8704,35 +8704,21 @@ void zone_pcp_reset(struct zone *zone)
#ifdef CONFIG_MEMORY_HOTREMOVE
/*
- * All pages in the range must be in a single zone and isolated
- * before calling this.
+ * All pages in the range must be in a single zone, must not contain holes,
+ * must span full sections, and must be isolated before calling this function.
*/
-unsigned long
-__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
+void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
+ unsigned long pfn = start_pfn;
struct page *page;
struct zone *zone;
unsigned int order;
- unsigned long pfn;
unsigned long flags;
- unsigned long offlined_pages = 0;
-
- /* find the first valid pfn */
- for (pfn = start_pfn; pfn < end_pfn; pfn++)
- if (pfn_valid(pfn))
- break;
- if (pfn == end_pfn)
- return offlined_pages;
offline_mem_sections(pfn, end_pfn);
zone = page_zone(pfn_to_page(pfn));
spin_lock_irqsave(&zone->lock, flags);
- pfn = start_pfn;
while (pfn < end_pfn) {
- if (!pfn_valid(pfn)) {
- pfn++;
- continue;
- }
page = pfn_to_page(pfn);
/*
* The HWPoisoned page may be not in buddy system, and
@@ -8740,7 +8726,6 @@ __offline_isolated_pages(unsigned long s
*/
if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
pfn++;
- offlined_pages++;
continue;
}
/*
@@ -8751,20 +8736,16 @@ __offline_isolated_pages(unsigned long s
BUG_ON(page_count(page));
BUG_ON(PageBuddy(page));
pfn++;
- offlined_pages++;
continue;
}
BUG_ON(page_count(page));
BUG_ON(!PageBuddy(page));
order = page_order(page);
- offlined_pages += 1 << order;
del_page_from_free_list(page, zone, order);
pfn += (1 << order);
}
spin_unlock_irqrestore(&zone->lock, flags);
-
- return offlined_pages;
}
#endif
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 063/156] mm/memory_hotplug: drop nr_isolate_pageblock in offline_pages()
2020-10-16 2:40 incoming Andrew Morton
` (62 preceding siblings ...)
2020-10-16 3:07 ` [patch 062/156] mm/page_alloc: simplify __offline_isolated_pages() Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 064/156] mm/page_isolation: simplify return value of start_isolate_page_range() Andrew Morton
` (102 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mgorman, mhocko, mm-commits, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, tony.luck, torvalds,
walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: drop nr_isolate_pageblock in offline_pages()
We make sure that we cannot have any memory holes right at the beginning
of offline_pages() and we only support to online/offline full sections.
Both, sections and pageblocks are a power of two in size, and sections
always span full pageblocks.
We can directly calculate the number of isolated pageblocks from nr_pages.
Link: https://lkml.kernel.org/r/20200819175957.28465-6-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory_hotplug.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
--- a/mm/memory_hotplug.c~mm-memory_hotplug-drop-nr_isolate_pageblock-in-offline_pages
+++ a/mm/memory_hotplug.c
@@ -1471,10 +1471,10 @@ int __ref offline_pages(unsigned long st
{
const unsigned long end_pfn = start_pfn + nr_pages;
unsigned long pfn, system_ram_pages = 0;
- int ret, node, nr_isolate_pageblock;
unsigned long flags;
struct zone *zone;
struct memory_notify arg;
+ int ret, node;
char *reason;
/* We can only offline full sections (e.g., SECTION_IS_ONLINE) */
@@ -1518,7 +1518,6 @@ int __ref offline_pages(unsigned long st
reason = "failure to isolate range";
goto failed_removal;
}
- nr_isolate_pageblock = ret;
arg.start_pfn = start_pfn;
arg.nr_pages = nr_pages;
@@ -1596,7 +1595,7 @@ int __ref offline_pages(unsigned long st
* pageblocks zone counter here.
*/
spin_lock_irqsave(&zone->lock, flags);
- zone->nr_isolate_pageblock -= nr_isolate_pageblock;
+ zone->nr_isolate_pageblock -= nr_pages / pageblock_nr_pages;
spin_unlock_irqrestore(&zone->lock, flags);
/* removal success */
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 064/156] mm/page_isolation: simplify return value of start_isolate_page_range()
2020-10-16 2:40 incoming Andrew Morton
` (63 preceding siblings ...)
2020-10-16 3:08 ` [patch 063/156] mm/memory_hotplug: drop nr_isolate_pageblock in offline_pages() Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 065/156] mm/memory_hotplug: simplify page onlining Andrew Morton
` (101 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mgorman, mhocko, mm-commits, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, tony.luck, torvalds,
walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/page_isolation: simplify return value of start_isolate_page_range()
Callers no longer need the number of isolated pageblocks. Let's simplify.
Link: https://lkml.kernel.org/r/20200819175957.28465-7-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory_hotplug.c | 2 +-
mm/page_alloc.c | 2 +-
mm/page_isolation.c | 7 ++-----
3 files changed, 4 insertions(+), 7 deletions(-)
--- a/mm/memory_hotplug.c~mm-page_isolation-simplify-return-value-of-start_isolate_page_range
+++ a/mm/memory_hotplug.c
@@ -1514,7 +1514,7 @@ int __ref offline_pages(unsigned long st
ret = start_isolate_page_range(start_pfn, end_pfn,
MIGRATE_MOVABLE,
MEMORY_OFFLINE | REPORT_FAILURE);
- if (ret < 0) {
+ if (ret) {
reason = "failure to isolate range";
goto failed_removal;
}
--- a/mm/page_alloc.c~mm-page_isolation-simplify-return-value-of-start_isolate_page_range
+++ a/mm/page_alloc.c
@@ -8468,7 +8468,7 @@ int alloc_contig_range(unsigned long sta
ret = start_isolate_page_range(pfn_max_align_down(start),
pfn_max_align_up(end), migratetype, 0);
- if (ret < 0)
+ if (ret)
return ret;
/*
--- a/mm/page_isolation.c~mm-page_isolation-simplify-return-value-of-start_isolate_page_range
+++ a/mm/page_isolation.c
@@ -173,8 +173,7 @@ __first_valid_page(unsigned long pfn, un
* (e.g. __offline_pages will need to call it after check for isolated range for
* a next retry).
*
- * Return: the number of isolated pageblocks on success and -EBUSY if any part
- * of range cannot be isolated.
+ * Return: 0 on success and -EBUSY if any part of range cannot be isolated.
*/
int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
unsigned migratetype, int flags)
@@ -182,7 +181,6 @@ int start_isolate_page_range(unsigned lo
unsigned long pfn;
unsigned long undo_pfn;
struct page *page;
- int nr_isolate_pageblock = 0;
BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
@@ -196,10 +194,9 @@ int start_isolate_page_range(unsigned lo
undo_pfn = pfn;
goto undo;
}
- nr_isolate_pageblock++;
}
}
- return nr_isolate_pageblock;
+ return 0;
undo:
for (pfn = start_pfn;
pfn < undo_pfn;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 065/156] mm/memory_hotplug: simplify page onlining
2020-10-16 2:40 incoming Andrew Morton
` (64 preceding siblings ...)
2020-10-16 3:08 ` [patch 064/156] mm/page_isolation: simplify return value of start_isolate_page_range() Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 066/156] mm/page_alloc: drop stale pageblock comment in memmap_init_zone*() Andrew Morton
` (100 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mgorman, mhocko, mm-commits, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, tony.luck, torvalds,
walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: simplify page onlining
We don't allow to offline memory with holes, all boot memory is online,
and all hotplugged memory cannot have holes.
We can now simplify onlining of pages. As we only allow to online/offline
full sections and sections always span full MAX_ORDER_NR_PAGES, we can
just process MAX_ORDER - 1 pages without further special handling.
The number of onlined pages simply corresponds to the number of pages we
were requested to online.
While at it, refine the comment regarding the callback not exposing all
pages to the buddy.
Link: https://lkml.kernel.org/r/20200819175957.28465-8-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory_hotplug.c | 38 ++++++++++----------------------------
1 file changed, 10 insertions(+), 28 deletions(-)
--- a/mm/memory_hotplug.c~mm-memory_hotplug-simplify-page-onlining
+++ a/mm/memory_hotplug.c
@@ -625,31 +625,22 @@ void generic_online_page(struct page *pa
}
EXPORT_SYMBOL_GPL(generic_online_page);
-static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
- void *arg)
+static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages)
{
const unsigned long end_pfn = start_pfn + nr_pages;
unsigned long pfn;
- int order;
/*
- * Online the pages. The callback might decide to keep some pages
- * PG_reserved (to add them to the buddy later), but we still account
- * them as being online/belonging to this zone ("present").
+ * Online the pages in MAX_ORDER - 1 aligned chunks. The callback might
+ * decide to not expose all pages to the buddy (e.g., expose them
+ * later). We account all pages as being online and belonging to this
+ * zone ("present").
*/
- for (pfn = start_pfn; pfn < end_pfn; pfn += 1ul << order) {
- order = min(MAX_ORDER - 1, get_order(PFN_PHYS(end_pfn - pfn)));
- /* __free_pages_core() wants pfns to be aligned to the order */
- if (WARN_ON_ONCE(!IS_ALIGNED(pfn, 1ul << order)))
- order = 0;
- (*online_page_callback)(pfn_to_page(pfn), order);
- }
+ for (pfn = start_pfn; pfn < end_pfn; pfn += MAX_ORDER_NR_PAGES)
+ (*online_page_callback)(pfn_to_page(pfn), MAX_ORDER - 1);
/* mark all involved sections as online */
online_mem_sections(start_pfn, end_pfn);
-
- *(unsigned long *)arg += nr_pages;
- return 0;
}
/* check which state of node_states will be changed when online memory */
@@ -803,7 +794,6 @@ int __ref online_pages(unsigned long pfn
int online_type, int nid)
{
unsigned long flags;
- unsigned long onlined_pages = 0;
struct zone *zone;
int need_zonelists_rebuild = 0;
int ret;
@@ -839,19 +829,11 @@ int __ref online_pages(unsigned long pfn
setup_zone_pageset(zone);
}
- ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
- online_pages_range);
- if (ret) {
- /* not a single memory resource was applicable */
- if (need_zonelists_rebuild)
- zone_pcp_reset(zone);
- goto failed_addition;
- }
-
- zone->present_pages += onlined_pages;
+ online_pages_range(pfn, nr_pages);
+ zone->present_pages += nr_pages;
pgdat_resize_lock(zone->zone_pgdat, &flags);
- zone->zone_pgdat->node_present_pages += onlined_pages;
+ zone->zone_pgdat->node_present_pages += nr_pages;
pgdat_resize_unlock(zone->zone_pgdat, &flags);
/*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 066/156] mm/page_alloc: drop stale pageblock comment in memmap_init_zone*()
2020-10-16 2:40 incoming Andrew Morton
` (65 preceding siblings ...)
2020-10-16 3:08 ` [patch 065/156] mm/memory_hotplug: simplify page onlining Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 067/156] mm: pass migratetype into memmap_init_zone() and move_pfn_range_to_zone() Andrew Morton
` (99 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mgorman, mhocko, mm-commits, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, tony.luck, torvalds,
walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/page_alloc: drop stale pageblock comment in memmap_init_zone*()
Commit ac5d2539b238 ("mm: meminit: reduce number of times pageblocks are
set during struct page init") moved the actual zone range check, leaving
only the alignment check for pageblocks.
Let's drop the stale comment and make the pageblock check easier to read.
Link: https://lkml.kernel.org/r/20200819175957.28465-9-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/page_alloc.c | 14 ++------------
1 file changed, 2 insertions(+), 12 deletions(-)
--- a/mm/page_alloc.c~mm-page_alloc-drop-stale-pageblock-comment-in-memmap_init_zone
+++ a/mm/page_alloc.c
@@ -6042,13 +6042,8 @@ void __meminit memmap_init_zone(unsigned
* to reserve their blocks rather than leaking throughout
* the address space during boot when many long-lived
* kernel allocations are made.
- *
- * bitmap is created for zone's valid pfn range. but memmap
- * can be created for invalid pages (for alignment)
- * check here not to call set_pageblock_migratetype() against
- * pfn out of zone.
*/
- if (!(pfn & (pageblock_nr_pages - 1))) {
+ if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
cond_resched();
}
@@ -6111,15 +6106,10 @@ void __ref memmap_init_zone_device(struc
* the address space during boot when many long-lived
* kernel allocations are made.
*
- * bitmap is created for zone's valid pfn range. but memmap
- * can be created for invalid pages (for alignment)
- * check here not to call set_pageblock_migratetype() against
- * pfn out of zone.
- *
* Please note that MEMINIT_HOTPLUG path doesn't clear memmap
* because this is done early in section_activate()
*/
- if (!(pfn & (pageblock_nr_pages - 1))) {
+ if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
cond_resched();
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 067/156] mm: pass migratetype into memmap_init_zone() and move_pfn_range_to_zone()
2020-10-16 2:40 incoming Andrew Morton
` (66 preceding siblings ...)
2020-10-16 3:08 ` [patch 066/156] mm/page_alloc: drop stale pageblock comment in memmap_init_zone*() Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 068/156] mm/memory_hotplug: mark pageblocks MIGRATE_ISOLATE while onlining memory Andrew Morton
` (98 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mhocko, mm-commits, osalvador, pankaj.gupta.linux,
richard.weiyang, rppt, tony.luck, torvalds, walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm: pass migratetype into memmap_init_zone() and move_pfn_range_to_zone()
On the memory onlining path, we want to start with MIGRATE_ISOLATE, to
un-isolate the pages after memory onlining is complete. Let's allow
passing in the migratetype.
Link: https://lkml.kernel.org/r/20200819175957.28465-10-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/ia64/mm/init.c | 4 ++--
include/linux/memory_hotplug.h | 3 ++-
include/linux/mm.h | 2 +-
mm/memory_hotplug.c | 11 ++++++++---
mm/memremap.c | 3 ++-
mm/page_alloc.c | 21 ++++++++++++---------
6 files changed, 27 insertions(+), 17 deletions(-)
--- a/arch/ia64/mm/init.c~mm-pass-migratetype-into-memmap_init_zone-and-move_pfn_range_to_zone
+++ a/arch/ia64/mm/init.c
@@ -537,7 +537,7 @@ virtual_memmap_init(u64 start, u64 end,
if (map_start < map_end)
memmap_init_zone((unsigned long)(map_end - map_start),
args->nid, args->zone, page_to_pfn(map_start),
- MEMINIT_EARLY, NULL);
+ MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
return 0;
}
@@ -547,7 +547,7 @@ memmap_init (unsigned long size, int nid
{
if (!vmem_map) {
memmap_init_zone(size, nid, zone, start_pfn,
- MEMINIT_EARLY, NULL);
+ MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
} else {
struct page *start;
struct memmap_init_callback_data args;
--- a/include/linux/memory_hotplug.h~mm-pass-migratetype-into-memmap_init_zone-and-move_pfn_range_to_zone
+++ a/include/linux/memory_hotplug.h
@@ -351,7 +351,8 @@ extern int add_memory_resource(int nid,
extern int add_memory_driver_managed(int nid, u64 start, u64 size,
const char *resource_name);
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap);
+ unsigned long nr_pages,
+ struct vmem_altmap *altmap, int migratetype);
extern void remove_pfn_range_from_zone(struct zone *zone,
unsigned long start_pfn,
unsigned long nr_pages);
--- a/include/linux/mm.h~mm-pass-migratetype-into-memmap_init_zone-and-move_pfn_range_to_zone
+++ a/include/linux/mm.h
@@ -2440,7 +2440,7 @@ extern int __meminit __early_pfn_to_nid(
extern void set_dma_reserve(unsigned long new_dma_reserve);
extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
- enum meminit_context, struct vmem_altmap *);
+ enum meminit_context, struct vmem_altmap *, int migratetype);
extern void setup_per_zone_wmarks(void);
extern int __meminit init_per_zone_wmark_min(void);
extern void mem_init(void);
--- a/mm/memory_hotplug.c~mm-pass-migratetype-into-memmap_init_zone-and-move_pfn_range_to_zone
+++ a/mm/memory_hotplug.c
@@ -701,9 +701,14 @@ static void __meminit resize_pgdat_range
* Associate the pfn range with the given zone, initializing the memmaps
* and resizing the pgdat/zone data to span the added pages. After this
* call, all affected pages are PG_reserved.
+ *
+ * All aligned pageblocks are initialized to the specified migratetype
+ * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
+ * zone stats (e.g., nr_isolate_pageblock) are touched.
*/
void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap)
+ unsigned long nr_pages,
+ struct vmem_altmap *altmap, int migratetype)
{
struct pglist_data *pgdat = zone->zone_pgdat;
int nid = pgdat->node_id;
@@ -728,7 +733,7 @@ void __ref move_pfn_range_to_zone(struct
* are reserved so nobody should be touching them so we should be safe
*/
memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
- MEMINIT_HOTPLUG, altmap);
+ MEMINIT_HOTPLUG, altmap, migratetype);
set_zone_contiguous(zone);
}
@@ -808,7 +813,7 @@ int __ref online_pages(unsigned long pfn
/* associate pfn range with the zone */
zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
- move_pfn_range_to_zone(zone, pfn, nr_pages, NULL);
+ move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_MOVABLE);
arg.start_pfn = pfn;
arg.nr_pages = nr_pages;
--- a/mm/memremap.c~mm-pass-migratetype-into-memmap_init_zone-and-move_pfn_range_to_zone
+++ a/mm/memremap.c
@@ -266,7 +266,8 @@ static int pagemap_range(struct dev_page
zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
- PHYS_PFN(range_len(range)), params->altmap);
+ PHYS_PFN(range_len(range)), params->altmap,
+ MIGRATE_MOVABLE);
}
mem_hotplug_done();
--- a/mm/page_alloc.c~mm-pass-migratetype-into-memmap_init_zone-and-move_pfn_range_to_zone
+++ a/mm/page_alloc.c
@@ -5990,10 +5990,15 @@ overlap_memmap_init(unsigned long zone,
* Initially all pages are reserved - free ones are freed
* up by memblock_free_all() once the early boot process is
* done. Non-atomic initialization, single-pass.
+ *
+ * All aligned pageblocks are initialized to the specified migratetype
+ * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
+ * zone stats (e.g., nr_isolate_pageblock) are touched.
*/
void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
- unsigned long start_pfn, enum meminit_context context,
- struct vmem_altmap *altmap)
+ unsigned long start_pfn,
+ enum meminit_context context,
+ struct vmem_altmap *altmap, int migratetype)
{
unsigned long pfn, end_pfn = start_pfn + size;
struct page *page;
@@ -6037,14 +6042,12 @@ void __meminit memmap_init_zone(unsigned
__SetPageReserved(page);
/*
- * Mark the block movable so that blocks are reserved for
- * movable at startup. This will force kernel allocations
- * to reserve their blocks rather than leaking throughout
- * the address space during boot when many long-lived
- * kernel allocations are made.
+ * Usually, we want to mark the pageblock MIGRATE_MOVABLE,
+ * such that unmovable allocations won't be scattered all
+ * over the place during system boot.
*/
if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+ set_pageblock_migratetype(page, migratetype);
cond_resched();
}
pfn++;
@@ -6144,7 +6147,7 @@ void __meminit __weak memmap_init(unsign
if (end_pfn > start_pfn) {
size = end_pfn - start_pfn;
memmap_init_zone(size, nid, zone, start_pfn,
- MEMINIT_EARLY, NULL);
+ MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
}
}
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 068/156] mm/memory_hotplug: mark pageblocks MIGRATE_ISOLATE while onlining memory
2020-10-16 2:40 incoming Andrew Morton
` (67 preceding siblings ...)
2020-10-16 3:08 ` [patch 067/156] mm: pass migratetype into memmap_init_zone() and move_pfn_range_to_zone() Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 069/156] kernel/resource: make release_mem_region_adjustable() never fail Andrew Morton
` (97 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, bhe, charante, dan.j.williams, david, fenghua.yu, logang,
mgorman, mgorman, mhocko, mm-commits, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, tony.luck, torvalds,
walken, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: mark pageblocks MIGRATE_ISOLATE while onlining memory
Currently, it can happen that pages are allocated (and freed) via the
buddy before we finished basic memory onlining.
For example, pages are exposed to the buddy and can be allocated before we
actually mark the sections online. Allocated pages could suddenly fail
pfn_to_online_page() checks. We had similar issues with pcp handling,
when pages are allocated+freed before we reach zone_pcp_update() in
online_pages() [1].
Instead, mark all pageblocks MIGRATE_ISOLATE, such that allocations are
impossible. Once done with the heavy lifting, use
undo_isolate_page_range() to move the pages to the MIGRATE_MOVABLE
freelist, marking them ready for allocation. Similar to offline_pages(),
we have to manually adjust zone->nr_isolate_pageblock.
[1] https://lkml.kernel.org/r/1597150703-19003-1-git-send-email-charante@codeaurora.org
Link: https://lkml.kernel.org/r/20200819175957.28465-11-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/Kconfig | 2 +-
mm/memory_hotplug.c | 32 ++++++++++++++++++++++----------
2 files changed, 23 insertions(+), 11 deletions(-)
--- a/mm/Kconfig~mm-memory_hotplug-mark-pageblocks-migrate_isolate-while-onlining-memory
+++ a/mm/Kconfig
@@ -152,6 +152,7 @@ config HAVE_BOOTMEM_INFO_NODE
# eventually, we can have this option just 'select SPARSEMEM'
config MEMORY_HOTPLUG
bool "Allow for memory hot-add"
+ select MEMORY_ISOLATION
depends on SPARSEMEM || X86_64_ACPI_NUMA
depends on ARCH_ENABLE_MEMORY_HOTPLUG
depends on 64BIT || BROKEN
@@ -178,7 +179,6 @@ config MEMORY_HOTPLUG_DEFAULT_ONLINE
config MEMORY_HOTREMOVE
bool "Allow for memory hot remove"
- select MEMORY_ISOLATION
select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
depends on MIGRATION
--- a/mm/memory_hotplug.c~mm-memory_hotplug-mark-pageblocks-migrate_isolate-while-onlining-memory
+++ a/mm/memory_hotplug.c
@@ -813,7 +813,7 @@ int __ref online_pages(unsigned long pfn
/* associate pfn range with the zone */
zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
- move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_MOVABLE);
+ move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE);
arg.start_pfn = pfn;
arg.nr_pages = nr_pages;
@@ -825,6 +825,14 @@ int __ref online_pages(unsigned long pfn
goto failed_addition;
/*
+ * Fixup the number of isolated pageblocks before marking the sections
+ * onlining, such that undo_isolate_page_range() works correctly.
+ */
+ spin_lock_irqsave(&zone->lock, flags);
+ zone->nr_isolate_pageblock += nr_pages / pageblock_nr_pages;
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ /*
* If this zone is not populated, then it is not in zonelist.
* This means the page allocator ignores this zone.
* So, zonelist must be updated after online.
@@ -841,21 +849,25 @@ int __ref online_pages(unsigned long pfn
zone->zone_pgdat->node_present_pages += nr_pages;
pgdat_resize_unlock(zone->zone_pgdat, &flags);
+ node_states_set_node(nid, &arg);
+ if (need_zonelists_rebuild)
+ build_all_zonelists(NULL);
+ zone_pcp_update(zone);
+
+ /* Basic onlining is complete, allow allocation of onlined pages. */
+ undo_isolate_page_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE);
+
/*
* When exposing larger, physically contiguous memory areas to the
* buddy, shuffling in the buddy (when freeing onlined pages, putting
* them either to the head or the tail of the freelist) is only helpful
* for maintaining the shuffle, but not for creating the initial
* shuffle. Shuffle the whole zone to make sure the just onlined pages
- * are properly distributed across the whole freelist.
+ * are properly distributed across the whole freelist. Make sure to
+ * shuffle once pageblocks are no longer isolated.
*/
shuffle_zone(zone);
- node_states_set_node(nid, &arg);
- if (need_zonelists_rebuild)
- build_all_zonelists(NULL);
- zone_pcp_update(zone);
-
init_per_zone_wmark_min();
kswapd_run(nid);
@@ -1577,9 +1589,9 @@ int __ref offline_pages(unsigned long st
pr_info("Offlined Pages %ld\n", nr_pages);
/*
- * Onlining will reset pagetype flags and makes migrate type
- * MOVABLE, so just need to decrease the number of isolated
- * pageblocks zone counter here.
+ * The memory sections are marked offline, and the pageblock flags
+ * effectively stale; nobody should be touching them. Fixup the number
+ * of isolated pageblocks, memory onlining will properly revert this.
*/
spin_lock_irqsave(&zone->lock, flags);
zone->nr_isolate_pageblock -= nr_pages / pageblock_nr_pages;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 069/156] kernel/resource: make release_mem_region_adjustable() never fail
2020-10-16 2:40 incoming Andrew Morton
` (68 preceding siblings ...)
2020-10-16 3:08 ` [patch 068/156] mm/memory_hotplug: mark pageblocks MIGRATE_ISOLATE while onlining memory Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 070/156] kernel/resource: move and rename IORESOURCE_MEM_DRIVER_MANAGED Andrew Morton
` (96 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, anton, ardb, benh, bhe, boris.ostrovsky, borntraeger,
dan.j.williams, dave.jiang, david, ebiederm, gor, gregkh,
haiyangz, hca, jasowang, jgg, jgross, julien, keescook,
kernelfans, kys, lenb, leobras.c, lpechacek, mhocko, mm-commits,
mpe, mst, natechancellor, nathanl, oohall, pankaj.gupta.linux,
paulus, richardw.yang, rjw, roger.pau, sstabellini, sthemmin,
tglx, torvalds, vishal.l.verma, wei.liu
From: David Hildenbrand <david@redhat.com>
Subject: kernel/resource: make release_mem_region_adjustable() never fail
Patch series "selective merging of system ram resources", v4.
Some add_memory*() users add memory in small, contiguous memory blocks.
Examples include virtio-mem, hyper-v balloon, and the XEN balloon.
This can quickly result in a lot of memory resources, whereby the actual
resource boundaries are not of interest (e.g., it might be relevant for
DIMMs, exposed via /proc/iomem to user space). We really want to merge
added resources in this scenario where possible.
Resources are effectively stored in a list-based tree. Having a lot of
resources not only wastes memory, it also makes traversing that tree more
expensive, and makes /proc/iomem explode in size (e.g., requiring
kexec-tools to manually merge resources when creating a kdump header. The
current kexec-tools resource count limit does not allow for more than
~100GB of memory with a memory block size of 128MB on x86-64).
Let's allow to selectively merge system ram resources by specifying a new
flag for add_memory*(). Patch #5 contains a /proc/iomem example. Only
tested with virtio-mem.
This patch (of 8):
Let's make sure splitting a resource on memory hotunplug will never fail.
This will become more relevant once we merge selected System RAM resources
- then, we'll trigger that case more often on memory hotunplug.
In general, this function is already unlikely to fail. When we remove
memory, we free up quite a lot of metadata (memmap, page tables, memory
block device, etc.). The only reason it could really fail would be when
injecting allocation errors.
All other error cases inside release_mem_region_adjustable() seem to be
sanity checks if the function would be abused in different context - let's
add WARN_ON_ONCE() in these cases so we can catch them.
[natechancellor@gmail.com: fix use of ternary condition in release_mem_region_adjustable]
Link: https://lkml.kernel.org/r/20200922060748.2452056-1-natechancellor@gmail.com
Link: https://github.com/ClangBuiltLinux/linux/issues/1159
Link: https://lkml.kernel.org/r/20200911103459.10306-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monn <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/ioport.h | 4 +--
kernel/resource.c | 49 ++++++++++++++++++++++-----------------
mm/memory_hotplug.c | 22 -----------------
3 files changed, 31 insertions(+), 44 deletions(-)
--- a/include/linux/ioport.h~kernel-resource-make-release_mem_region_adjustable-never-fail
+++ a/include/linux/ioport.h
@@ -248,8 +248,8 @@ extern struct resource * __request_regio
extern void __release_region(struct resource *, resource_size_t,
resource_size_t);
#ifdef CONFIG_MEMORY_HOTREMOVE
-extern int release_mem_region_adjustable(struct resource *, resource_size_t,
- resource_size_t);
+extern void release_mem_region_adjustable(struct resource *, resource_size_t,
+ resource_size_t);
#endif
/* Wrappers for managed devices */
--- a/kernel/resource.c~kernel-resource-make-release_mem_region_adjustable-never-fail
+++ a/kernel/resource.c
@@ -1258,21 +1258,28 @@ EXPORT_SYMBOL(__release_region);
* assumes that all children remain in the lower address entry for
* simplicity. Enhance this logic when necessary.
*/
-int release_mem_region_adjustable(struct resource *parent,
- resource_size_t start, resource_size_t size)
+void release_mem_region_adjustable(struct resource *parent,
+ resource_size_t start, resource_size_t size)
{
+ struct resource *new_res = NULL;
+ bool alloc_nofail = false;
struct resource **p;
struct resource *res;
- struct resource *new_res;
resource_size_t end;
- int ret = -EINVAL;
end = start + size - 1;
- if ((start < parent->start) || (end > parent->end))
- return ret;
+ if (WARN_ON_ONCE((start < parent->start) || (end > parent->end)))
+ return;
- /* The alloc_resource() result gets checked later */
- new_res = alloc_resource(GFP_KERNEL);
+ /*
+ * We free up quite a lot of memory on memory hotunplug (esp., memap),
+ * just before releasing the region. This is highly unlikely to
+ * fail - let's play save and make it never fail as the caller cannot
+ * perform any error handling (e.g., trying to re-add memory will fail
+ * similarly).
+ */
+retry:
+ new_res = alloc_resource(GFP_KERNEL | (alloc_nofail ? __GFP_NOFAIL : 0));
p = &parent->child;
write_lock(&resource_lock);
@@ -1298,7 +1305,6 @@ int release_mem_region_adjustable(struct
* so if we are dealing with them, let us just back off here.
*/
if (!(res->flags & IORESOURCE_SYSRAM)) {
- ret = 0;
break;
}
@@ -1315,20 +1321,23 @@ int release_mem_region_adjustable(struct
/* free the whole entry */
*p = res->sibling;
free_resource(res);
- ret = 0;
} else if (res->start == start && res->end != end) {
/* adjust the start */
- ret = __adjust_resource(res, end + 1,
- res->end - end);
+ WARN_ON_ONCE(__adjust_resource(res, end + 1,
+ res->end - end));
} else if (res->start != start && res->end == end) {
/* adjust the end */
- ret = __adjust_resource(res, res->start,
- start - res->start);
+ WARN_ON_ONCE(__adjust_resource(res, res->start,
+ start - res->start));
} else {
- /* split into two entries */
+ /* split into two entries - we need a new resource */
if (!new_res) {
- ret = -ENOMEM;
- break;
+ new_res = alloc_resource(GFP_ATOMIC);
+ if (!new_res) {
+ alloc_nofail = true;
+ write_unlock(&resource_lock);
+ goto retry;
+ }
}
new_res->name = res->name;
new_res->start = end + 1;
@@ -1339,9 +1348,8 @@ int release_mem_region_adjustable(struct
new_res->sibling = res->sibling;
new_res->child = NULL;
- ret = __adjust_resource(res, res->start,
- start - res->start);
- if (ret)
+ if (WARN_ON_ONCE(__adjust_resource(res, res->start,
+ start - res->start)))
break;
res->sibling = new_res;
new_res = NULL;
@@ -1352,7 +1360,6 @@ int release_mem_region_adjustable(struct
write_unlock(&resource_lock);
free_resource(new_res);
- return ret;
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
--- a/mm/memory_hotplug.c~kernel-resource-make-release_mem_region_adjustable-never-fail
+++ a/mm/memory_hotplug.c
@@ -1727,26 +1727,6 @@ void try_offline_node(int nid)
}
EXPORT_SYMBOL(try_offline_node);
-static void __release_memory_resource(resource_size_t start,
- resource_size_t size)
-{
- int ret;
-
- /*
- * When removing memory in the same granularity as it was added,
- * this function never fails. It might only fail if resources
- * have to be adjusted or split. We'll ignore the error, as
- * removing of memory cannot fail.
- */
- ret = release_mem_region_adjustable(&iomem_resource, start, size);
- if (ret) {
- resource_size_t endres = start + size - 1;
-
- pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
- &start, &endres, ret);
- }
-}
-
static int __ref try_remove_memory(int nid, u64 start, u64 size)
{
int rc = 0;
@@ -1780,7 +1760,7 @@ static int __ref try_remove_memory(int n
memblock_remove(start, size);
}
- __release_memory_resource(start, size);
+ release_mem_region_adjustable(&iomem_resource, start, size);
try_offline_node(nid);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 070/156] kernel/resource: move and rename IORESOURCE_MEM_DRIVER_MANAGED
2020-10-16 2:40 incoming Andrew Morton
` (69 preceding siblings ...)
2020-10-16 3:08 ` [patch 069/156] kernel/resource: make release_mem_region_adjustable() never fail Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 071/156] mm/memory_hotplug: guard more declarations by CONFIG_MEMORY_HOTPLUG Andrew Morton
` (95 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, anton, ardb, benh, bhe, boris.ostrovsky, borntraeger,
dan.j.williams, dave.jiang, david, ebiederm, gor, gregkh,
haiyangz, hca, jasowang, jgg, jgross, julien, keescook,
kernelfans, kys, lenb, leobras.c, lpechacek, mhocko, mm-commits,
mpe, mst, nathanl, oohall, pankaj.gupta.linux, paulus,
richardw.yang, rjw, roger.pau, sstabellini, sthemmin, tglx,
torvalds, vishal.l.verma, wei.liu
From: David Hildenbrand <david@redhat.com>
Subject: kernel/resource: move and rename IORESOURCE_MEM_DRIVER_MANAGED
IORESOURCE_MEM_DRIVER_MANAGED currently uses an unused PnP bit, which is
always set to 0 by hardware. This is far from beautiful (and confusing),
and the bit only applies to SYSRAM. So let's move it out of the
bus-specific (PnP) defined bits.
We'll add another SYSRAM specific bit soon. If we ever need more bits for
other purposes, we can steal some from "desc", or reshuffle/regroup what
we have.
Link: https://lkml.kernel.org/r/20200911103459.10306-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/ioport.h | 4 +++-
kernel/kexec_file.c | 2 +-
mm/memory_hotplug.c | 4 ++--
3 files changed, 6 insertions(+), 4 deletions(-)
--- a/include/linux/ioport.h~kernel-resource-move-and-rename-ioresource_mem_driver_managed
+++ a/include/linux/ioport.h
@@ -58,6 +58,9 @@ struct resource {
#define IORESOURCE_EXT_TYPE_BITS 0x01000000 /* Resource extended types */
#define IORESOURCE_SYSRAM 0x01000000 /* System RAM (modifier) */
+/* IORESOURCE_SYSRAM specific bits. */
+#define IORESOURCE_SYSRAM_DRIVER_MANAGED 0x02000000 /* Always detected via a driver. */
+
#define IORESOURCE_EXCLUSIVE 0x08000000 /* Userland may not map this resource */
#define IORESOURCE_DISABLED 0x10000000
@@ -103,7 +106,6 @@ struct resource {
#define IORESOURCE_MEM_32BIT (3<<3)
#define IORESOURCE_MEM_SHADOWABLE (1<<5) /* dup: IORESOURCE_SHADOWABLE */
#define IORESOURCE_MEM_EXPANSIONROM (1<<6)
-#define IORESOURCE_MEM_DRIVER_MANAGED (1<<7)
/* PnP I/O specific bits (IORESOURCE_BITS) */
#define IORESOURCE_IO_16BIT_ADDR (1<<0)
--- a/kernel/kexec_file.c~kernel-resource-move-and-rename-ioresource_mem_driver_managed
+++ a/kernel/kexec_file.c
@@ -521,7 +521,7 @@ static int locate_mem_hole_callback(stru
/* Returning 0 will take to next memory range */
/* Don't use memory that will be detected and handled by a driver. */
- if (res->flags & IORESOURCE_MEM_DRIVER_MANAGED)
+ if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED)
return 0;
if (sz < kbuf->memsz)
--- a/mm/memory_hotplug.c~kernel-resource-move-and-rename-ioresource_mem_driver_managed
+++ a/mm/memory_hotplug.c
@@ -105,7 +105,7 @@ static struct resource *register_memory_
unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
if (strcmp(resource_name, "System RAM"))
- flags |= IORESOURCE_MEM_DRIVER_MANAGED;
+ flags |= IORESOURCE_SYSRAM_DRIVER_MANAGED;
/*
* Make sure value parsed from 'mem=' only restricts memory adding
@@ -1161,7 +1161,7 @@ EXPORT_SYMBOL_GPL(add_memory);
*
* For this memory, no entries in /sys/firmware/memmap ("raw firmware-provided
* memory map") are created. Also, the created memory resource is flagged
- * with IORESOURCE_MEM_DRIVER_MANAGED, so in-kernel users can special-case
+ * with IORESOURCE_SYSRAM_DRIVER_MANAGED, so in-kernel users can special-case
* this memory as well (esp., not place kexec images onto it).
*
* The resource_name (visible via /proc/iomem) has to have the format
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 071/156] mm/memory_hotplug: guard more declarations by CONFIG_MEMORY_HOTPLUG
2020-10-16 2:40 incoming Andrew Morton
` (70 preceding siblings ...)
2020-10-16 3:08 ` [patch 070/156] kernel/resource: move and rename IORESOURCE_MEM_DRIVER_MANAGED Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 072/156] mm/memory_hotplug: prepare passing flags to add_memory() and friends Andrew Morton
` (94 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, anton, ardb, benh, bhe, boris.ostrovsky, borntraeger,
dan.j.williams, dave.jiang, david, ebiederm, gor, gregkh,
haiyangz, hca, jasowang, jgg, jgross, julien, keescook,
kernelfans, kys, lenb, leobras.c, lpechacek, mhocko, mm-commits,
mpe, mst, nathanl, oohall, pankaj.gupta.linux, paulus,
richardw.yang, rjw, roger.pau, sstabellini, sthemmin, tglx,
torvalds, vishal.l.verma, wei.liu
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: guard more declarations by CONFIG_MEMORY_HOTPLUG
We soon want to pass flags via a new type to add_memory() and friends.
That revealed that we currently don't guard some declarations by
CONFIG_MEMORY_HOTPLUG.
While some definitions could be moved to different places, let's keep it
minimal for now and use CONFIG_MEMORY_HOTPLUG for all functions only
compiled with CONFIG_MEMORY_HOTPLUG.
Wrap sparse_decode_mem_map() into CONFIG_MEMORY_HOTPLUG, it's only called
from CONFIG_MEMORY_HOTPLUG code.
While at it, remove allow_online_pfn_range(), which is no longer around,
and mhp_notimplemented(), which is unused.
Link: https://lkml.kernel.org/r/20200911103459.10306-4-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memory_hotplug.h | 12 +++---------
mm/sparse.c | 2 ++
2 files changed, 5 insertions(+), 9 deletions(-)
--- a/include/linux/memory_hotplug.h~mm-memory_hotplug-guard-more-declarations-by-config_memory_hotplug
+++ a/include/linux/memory_hotplug.h
@@ -247,13 +247,6 @@ static inline void zone_span_writelock(s
static inline void zone_span_writeunlock(struct zone *zone) {}
static inline void zone_seqlock_init(struct zone *zone) {}
-static inline int mhp_notimplemented(const char *func)
-{
- printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
- dump_stack();
- return -ENOSYS;
-}
-
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
}
@@ -344,6 +337,7 @@ static inline void __remove_memory(int n
extern void set_zone_contiguous(struct zone *zone);
extern void clear_zone_contiguous(struct zone *zone);
+#ifdef CONFIG_MEMORY_HOTPLUG
extern void __ref free_area_init_core_hotplug(int nid);
extern int __add_memory(int nid, u64 start, u64 size);
extern int add_memory(int nid, u64 start, u64 size);
@@ -364,8 +358,8 @@ extern void sparse_remove_section(struct
unsigned long map_offset, struct vmem_altmap *altmap);
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
unsigned long pnum);
-extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
- int online_type);
extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
unsigned long nr_pages);
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
#endif /* __LINUX_MEMORY_HOTPLUG_H */
--- a/mm/sparse.c~mm-memory_hotplug-guard-more-declarations-by-config_memory_hotplug
+++ a/mm/sparse.c
@@ -312,6 +312,7 @@ static unsigned long sparse_encode_mem_m
return coded_mem_map;
}
+#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Decode mem_map from the coded memmap
*/
@@ -321,6 +322,7 @@ struct page *sparse_decode_mem_map(unsig
coded_mem_map &= SECTION_MAP_MASK;
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}
+#endif /* CONFIG_MEMORY_HOTPLUG */
static void __meminit sparse_init_one_section(struct mem_section *ms,
unsigned long pnum, struct page *mem_map,
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 072/156] mm/memory_hotplug: prepare passing flags to add_memory() and friends
2020-10-16 2:40 incoming Andrew Morton
` (71 preceding siblings ...)
2020-10-16 3:08 ` [patch 071/156] mm/memory_hotplug: guard more declarations by CONFIG_MEMORY_HOTPLUG Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 073/156] mm/memory_hotplug: MEMHP_MERGE_RESOURCE to specify merging of System RAM resources Andrew Morton
` (93 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, anton, ardb, benh, bhe, boris.ostrovsky, borntraeger,
dan.j.williams, dave.jiang, david, ebiederm, gor, gregkh,
haiyangz, hca, jasowang, jgg, jgross, julien, keescook,
kernelfans, kys, lenb, leobras.c, lpechacek, mhocko, mm-commits,
mpe, mst, nathanl, oohall, pankaj.gupta.linux, paulus,
richardw.yang, rjw, roger.pau, sstabellini, sthemmin, tglx,
torvalds, vishal.l.verma, wei.liu
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: prepare passing flags to add_memory() and friends
We soon want to pass flags, e.g., to mark added System RAM resources.
mergeable. Prepare for that.
This patch is based on a similar patch by Oscar Salvador:
https://lkml.kernel.org/r/20190625075227.15193-3-osalvador@suse.de
Link: https://lkml.kernel.org/r/20200911103459.10306-5-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Wei Liu <wei.liu@kernel.org>
Reviewed-by: Juergen Gross <jgross@suse.com> # Xen related part
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Baoquan He <bhe@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/powerpc/platforms/powernv/memtrace.c | 2 -
arch/powerpc/platforms/pseries/hotplug-memory.c | 2 -
drivers/acpi/acpi_memhotplug.c | 3 +-
drivers/base/memory.c | 3 +-
drivers/dax/kmem.c | 2 -
drivers/hv/hv_balloon.c | 2 -
drivers/s390/char/sclp_cmd.c | 2 -
drivers/virtio/virtio_mem.c | 2 -
drivers/xen/balloon.c | 2 -
include/linux/memory_hotplug.h | 16 ++++++++++----
mm/memory_hotplug.c | 14 ++++++------
11 files changed, 30 insertions(+), 20 deletions(-)
--- a/arch/powerpc/platforms/powernv/memtrace.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/arch/powerpc/platforms/powernv/memtrace.c
@@ -224,7 +224,7 @@ static int memtrace_online(void)
ent->mem = 0;
}
- if (add_memory(ent->nid, ent->start, ent->size)) {
+ if (add_memory(ent->nid, ent->start, ent->size, MHP_NONE)) {
pr_err("Failed to add trace memory to node %d\n",
ent->nid);
ret += 1;
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -606,7 +606,7 @@ static int dlpar_add_lmb(struct drmem_lm
block_sz = memory_block_size_bytes();
/* Add the memory */
- rc = __add_memory(lmb->nid, lmb->base_addr, block_sz);
+ rc = __add_memory(lmb->nid, lmb->base_addr, block_sz, MHP_NONE);
if (rc) {
invalidate_lmb_associativity_index(lmb);
return rc;
--- a/drivers/acpi/acpi_memhotplug.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/drivers/acpi/acpi_memhotplug.c
@@ -194,7 +194,8 @@ static int acpi_memory_enable_device(str
if (node < 0)
node = memory_add_physaddr_to_nid(info->start_addr);
- result = __add_memory(node, info->start_addr, info->length);
+ result = __add_memory(node, info->start_addr, info->length,
+ MHP_NONE);
/*
* If the memory block has been used by the kernel, add_memory()
--- a/drivers/base/memory.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/drivers/base/memory.c
@@ -432,7 +432,8 @@ static ssize_t probe_store(struct device
nid = memory_add_physaddr_to_nid(phys_addr);
ret = __add_memory(nid, phys_addr,
- MIN_MEMORY_BLOCK_SIZE * sections_per_block);
+ MIN_MEMORY_BLOCK_SIZE * sections_per_block,
+ MHP_NONE);
if (ret)
goto out;
--- a/drivers/dax/kmem.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/drivers/dax/kmem.c
@@ -109,7 +109,7 @@ static int dev_dax_kmem_probe(struct dev
* this as RAM automatically.
*/
rc = add_memory_driver_managed(numa_node, range.start,
- range_len(&range), kmem_name);
+ range_len(&range), kmem_name, MHP_NONE);
if (rc) {
dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
--- a/drivers/hv/hv_balloon.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/drivers/hv/hv_balloon.c
@@ -726,7 +726,7 @@ static void hv_mem_hot_add(unsigned long
nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn));
ret = add_memory(nid, PFN_PHYS((start_pfn)),
- (HA_CHUNK << PAGE_SHIFT));
+ (HA_CHUNK << PAGE_SHIFT), MHP_NONE);
if (ret) {
pr_err("hot_add memory failed error is %d\n", ret);
--- a/drivers/s390/char/sclp_cmd.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/drivers/s390/char/sclp_cmd.c
@@ -406,7 +406,7 @@ static void __init add_memory_merged(u16
if (!size)
goto skip_add;
for (addr = start; addr < start + size; addr += block_size)
- add_memory(0, addr, block_size);
+ add_memory(0, addr, block_size, MHP_NONE);
skip_add:
first_rn = rn;
num = 1;
--- a/drivers/virtio/virtio_mem.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/drivers/virtio/virtio_mem.c
@@ -424,7 +424,7 @@ static int virtio_mem_mb_add(struct virt
dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
return add_memory_driver_managed(nid, addr, memory_block_size_bytes(),
- vm->resource_name);
+ vm->resource_name, MHP_NONE);
}
/*
--- a/drivers/xen/balloon.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/drivers/xen/balloon.c
@@ -331,7 +331,7 @@ static enum bp_state reserve_additional_
mutex_unlock(&balloon_mutex);
/* add_memory_resource() requires the device_hotplug lock */
lock_device_hotplug();
- rc = add_memory_resource(nid, resource);
+ rc = add_memory_resource(nid, resource, MHP_NONE);
unlock_device_hotplug();
mutex_lock(&balloon_mutex);
--- a/include/linux/memory_hotplug.h~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/include/linux/memory_hotplug.h
@@ -57,6 +57,12 @@ enum {
MMOP_ONLINE_MOVABLE,
};
+/* Flags for add_memory() and friends to specify memory hotplug details. */
+typedef int __bitwise mhp_t;
+
+/* No special request */
+#define MHP_NONE ((__force mhp_t)0)
+
/*
* Extended parameters for memory hotplug:
* altmap: alternative allocator for memmap array (optional)
@@ -339,11 +345,13 @@ extern void clear_zone_contiguous(struct
#ifdef CONFIG_MEMORY_HOTPLUG
extern void __ref free_area_init_core_hotplug(int nid);
-extern int __add_memory(int nid, u64 start, u64 size);
-extern int add_memory(int nid, u64 start, u64 size);
-extern int add_memory_resource(int nid, struct resource *resource);
+extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
+extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
+extern int add_memory_resource(int nid, struct resource *resource,
+ mhp_t mhp_flags);
extern int add_memory_driver_managed(int nid, u64 start, u64 size,
- const char *resource_name);
+ const char *resource_name,
+ mhp_t mhp_flags);
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
unsigned long nr_pages,
struct vmem_altmap *altmap, int migratetype);
--- a/mm/memory_hotplug.c~mm-memory_hotplug-prepare-passing-flags-to-add_memory-and-friends
+++ a/mm/memory_hotplug.c
@@ -1039,7 +1039,7 @@ static int online_memory_block(struct me
*
* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG
*/
-int __ref add_memory_resource(int nid, struct resource *res)
+int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
{
struct mhp_params params = { .pgprot = PAGE_KERNEL };
u64 start, size;
@@ -1119,7 +1119,7 @@ error:
}
/* requires device_hotplug_lock, see add_memory_resource() */
-int __ref __add_memory(int nid, u64 start, u64 size)
+int __ref __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
{
struct resource *res;
int ret;
@@ -1128,18 +1128,18 @@ int __ref __add_memory(int nid, u64 star
if (IS_ERR(res))
return PTR_ERR(res);
- ret = add_memory_resource(nid, res);
+ ret = add_memory_resource(nid, res, mhp_flags);
if (ret < 0)
release_memory_resource(res);
return ret;
}
-int add_memory(int nid, u64 start, u64 size)
+int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
{
int rc;
lock_device_hotplug();
- rc = __add_memory(nid, start, size);
+ rc = __add_memory(nid, start, size, mhp_flags);
unlock_device_hotplug();
return rc;
@@ -1168,7 +1168,7 @@ EXPORT_SYMBOL_GPL(add_memory);
* "System RAM ($DRIVER)".
*/
int add_memory_driver_managed(int nid, u64 start, u64 size,
- const char *resource_name)
+ const char *resource_name, mhp_t mhp_flags)
{
struct resource *res;
int rc;
@@ -1186,7 +1186,7 @@ int add_memory_driver_managed(int nid, u
goto out_unlock;
}
- rc = add_memory_resource(nid, res);
+ rc = add_memory_resource(nid, res, mhp_flags);
if (rc < 0)
release_memory_resource(res);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 073/156] mm/memory_hotplug: MEMHP_MERGE_RESOURCE to specify merging of System RAM resources
2020-10-16 2:40 incoming Andrew Morton
` (72 preceding siblings ...)
2020-10-16 3:08 ` [patch 072/156] mm/memory_hotplug: prepare passing flags to add_memory() and friends Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:08 ` [patch 074/156] virtio-mem: try to merge system ram resources Andrew Morton
` (92 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, anton, ardb, benh, bhe, boris.ostrovsky, borntraeger,
dan.j.williams, dave.jiang, david, ebiederm, gor, gregkh,
haiyangz, hca, jasowang, jgg, jgross, julien, keescook,
kernelfans, kys, lenb, leobras.c, lpechacek, mhocko, mm-commits,
mpe, mst, nathanl, oohall, pankaj.gupta.linux, paulus,
richardw.yang, rjw, roger.pau, sstabellini, sthemmin, tglx,
torvalds, vishal.l.verma, wei.liu
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: MEMHP_MERGE_RESOURCE to specify merging of System RAM resources
Some add_memory*() users add memory in small, contiguous memory blocks.
Examples include virtio-mem, hyper-v balloon, and the XEN balloon.
This can quickly result in a lot of memory resources, whereby the actual
resource boundaries are not of interest (e.g., it might be relevant for
DIMMs, exposed via /proc/iomem to user space). We really want to merge
added resources in this scenario where possible.
Let's provide a flag (MEMHP_MERGE_RESOURCE) to specify that a resource
either created within add_memory*() or passed via add_memory_resource()
shall be marked mergeable and merged with applicable siblings.
To implement that, we need a kernel/resource interface to mark selected
System RAM resources mergeable (IORESOURCE_SYSRAM_MERGEABLE) and trigger
merging.
Note: We really want to merge after the whole operation succeeded, not
directly when adding a resource to the resource tree (it would break
add_memory_resource() and require splitting resources again when the
operation failed - e.g., due to -ENOMEM).
Link: https://lkml.kernel.org/r/20200911103459.10306-6-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Julien Grall <julien@xen.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/ioport.h | 4 ++
include/linux/memory_hotplug.h | 7 +++
kernel/resource.c | 60 +++++++++++++++++++++++++++++++
mm/memory_hotplug.c | 7 +++
4 files changed, 78 insertions(+)
--- a/include/linux/ioport.h~mm-memory_hotplug-memhp_merge_resource-to-specify-merging-of-system-ram-resources
+++ a/include/linux/ioport.h
@@ -60,6 +60,7 @@ struct resource {
/* IORESOURCE_SYSRAM specific bits. */
#define IORESOURCE_SYSRAM_DRIVER_MANAGED 0x02000000 /* Always detected via a driver. */
+#define IORESOURCE_SYSRAM_MERGEABLE 0x04000000 /* Resource can be merged. */
#define IORESOURCE_EXCLUSIVE 0x08000000 /* Userland may not map this resource */
@@ -253,6 +254,9 @@ extern void __release_region(struct reso
extern void release_mem_region_adjustable(struct resource *, resource_size_t,
resource_size_t);
#endif
+#ifdef CONFIG_MEMORY_HOTPLUG
+extern void merge_system_ram_resource(struct resource *res);
+#endif
/* Wrappers for managed devices */
struct device;
--- a/include/linux/memory_hotplug.h~mm-memory_hotplug-memhp_merge_resource-to-specify-merging-of-system-ram-resources
+++ a/include/linux/memory_hotplug.h
@@ -62,6 +62,13 @@ typedef int __bitwise mhp_t;
/* No special request */
#define MHP_NONE ((__force mhp_t)0)
+/*
+ * Allow merging of the added System RAM resource with adjacent,
+ * mergeable resources. After a successful call to add_memory_resource()
+ * with this flag set, the resource pointer must no longer be used as it
+ * might be stale, or the resource might have changed.
+ */
+#define MEMHP_MERGE_RESOURCE ((__force mhp_t)BIT(0))
/*
* Extended parameters for memory hotplug:
--- a/kernel/resource.c~mm-memory_hotplug-memhp_merge_resource-to-specify-merging-of-system-ram-resources
+++ a/kernel/resource.c
@@ -1363,6 +1363,66 @@ retry:
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
+#ifdef CONFIG_MEMORY_HOTPLUG
+static bool system_ram_resources_mergeable(struct resource *r1,
+ struct resource *r2)
+{
+ /* We assume either r1 or r2 is IORESOURCE_SYSRAM_MERGEABLE. */
+ return r1->flags == r2->flags && r1->end + 1 == r2->start &&
+ r1->name == r2->name && r1->desc == r2->desc &&
+ !r1->child && !r2->child;
+}
+
+/*
+ * merge_system_ram_resource - mark the System RAM resource mergeable and try to
+ * merge it with adjacent, mergeable resources
+ * @res: resource descriptor
+ *
+ * This interface is intended for memory hotplug, whereby lots of contiguous
+ * system ram resources are added (e.g., via add_memory*()) by a driver, and
+ * the actual resource boundaries are not of interest (e.g., it might be
+ * relevant for DIMMs). Only resources that are marked mergeable, that have the
+ * same parent, and that don't have any children are considered. All mergeable
+ * resources must be immutable during the request.
+ *
+ * Note:
+ * - The caller has to make sure that no pointers to resources that are
+ * marked mergeable are used anymore after this call - the resource might
+ * be freed and the pointer might be stale!
+ * - release_mem_region_adjustable() will split on demand on memory hotunplug
+ */
+void merge_system_ram_resource(struct resource *res)
+{
+ const unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ struct resource *cur;
+
+ if (WARN_ON_ONCE((res->flags & flags) != flags))
+ return;
+
+ write_lock(&resource_lock);
+ res->flags |= IORESOURCE_SYSRAM_MERGEABLE;
+
+ /* Try to merge with next item in the list. */
+ cur = res->sibling;
+ if (cur && system_ram_resources_mergeable(res, cur)) {
+ res->end = cur->end;
+ res->sibling = cur->sibling;
+ free_resource(cur);
+ }
+
+ /* Try to merge with previous item in the list. */
+ cur = res->parent->child;
+ while (cur && cur->sibling != res)
+ cur = cur->sibling;
+ if (cur && system_ram_resources_mergeable(cur, res)) {
+ cur->end = res->end;
+ cur->sibling = res->sibling;
+ free_resource(res);
+ }
+ write_unlock(&resource_lock);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
/*
* Managed region resource
*/
--- a/mm/memory_hotplug.c~mm-memory_hotplug-memhp_merge_resource-to-specify-merging-of-system-ram-resources
+++ a/mm/memory_hotplug.c
@@ -1103,6 +1103,13 @@ int __ref add_memory_resource(int nid, s
/* device_online() will take the lock when calling online_pages() */
mem_hotplug_done();
+ /*
+ * In case we're allowed to merge the resource, flag it and trigger
+ * merging now that adding succeeded.
+ */
+ if (mhp_flags & MEMHP_MERGE_RESOURCE)
+ merge_system_ram_resource(res);
+
/* online pages if requested */
if (memhp_default_online_type != MMOP_OFFLINE)
walk_memory_blocks(start, size, NULL, online_memory_block);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 074/156] virtio-mem: try to merge system ram resources
2020-10-16 2:40 incoming Andrew Morton
` (73 preceding siblings ...)
2020-10-16 3:08 ` [patch 073/156] mm/memory_hotplug: MEMHP_MERGE_RESOURCE to specify merging of System RAM resources Andrew Morton
@ 2020-10-16 3:08 ` Andrew Morton
2020-10-16 3:09 ` [patch 075/156] xen/balloon: " Andrew Morton
` (91 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:08 UTC (permalink / raw)
To: akpm, anton, ardb, benh, bhe, boris.ostrovsky, borntraeger,
dan.j.williams, dave.jiang, david, ebiederm, gor, gregkh,
haiyangz, hca, jasowang, jgg, jgross, julien, keescook,
kernelfans, kys, lenb, leobras.c, lpechacek, mhocko, mm-commits,
mpe, mst, nathanl, oohall, pankaj.gupta.linux, paulus,
richardw.yang, rjw, roger.pau, sstabellini, sthemmin, tglx,
torvalds, vishal.l.verma, wei.liu
From: David Hildenbrand <david@redhat.com>
Subject: virtio-mem: try to merge system ram resources
virtio-mem adds memory in memory block granularity, to be able to remove
it in the same granularity again later, and to grow slowly on demand.
This, however, results in quite a lot of resources when adding a lot of
memory. Resources are effectively stored in a list-based tree. Having a
lot of resources not only wastes memory, it also makes traversing that
tree more expensive, and makes /proc/iomem explode in size (e.g.,
requiring kexec-tools to manually merge resources later when e.g., trying
to create a kdump header).
Before this patch, we get (/proc/iomem) when hotplugging 2G via virtio-mem
on x86-64:
[...]
100000000-13fffffff : System RAM
140000000-33fffffff : virtio0
140000000-147ffffff : System RAM (virtio_mem)
148000000-14fffffff : System RAM (virtio_mem)
150000000-157ffffff : System RAM (virtio_mem)
158000000-15fffffff : System RAM (virtio_mem)
160000000-167ffffff : System RAM (virtio_mem)
168000000-16fffffff : System RAM (virtio_mem)
170000000-177ffffff : System RAM (virtio_mem)
178000000-17fffffff : System RAM (virtio_mem)
180000000-187ffffff : System RAM (virtio_mem)
188000000-18fffffff : System RAM (virtio_mem)
190000000-197ffffff : System RAM (virtio_mem)
198000000-19fffffff : System RAM (virtio_mem)
1a0000000-1a7ffffff : System RAM (virtio_mem)
1a8000000-1afffffff : System RAM (virtio_mem)
1b0000000-1b7ffffff : System RAM (virtio_mem)
1b8000000-1bfffffff : System RAM (virtio_mem)
3280000000-32ffffffff : PCI Bus 0000:00
With this patch, we get (/proc/iomem):
[...]
fffc0000-ffffffff : Reserved
100000000-13fffffff : System RAM
140000000-33fffffff : virtio0
140000000-1bfffffff : System RAM (virtio_mem)
3280000000-32ffffffff : PCI Bus 0000:00
Of course, with more hotplugged memory, it gets worse. When unplugging
memory blocks again, try_remove_memory() (via offline_and_remove_memory())
will properly split the resource up again.
Link: https://lkml.kernel.org/r/20200911103459.10306-7-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/virtio/virtio_mem.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
--- a/drivers/virtio/virtio_mem.c~virtio-mem-try-to-merge-system-ram-resources
+++ a/drivers/virtio/virtio_mem.c
@@ -424,7 +424,8 @@ static int virtio_mem_mb_add(struct virt
dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
return add_memory_driver_managed(nid, addr, memory_block_size_bytes(),
- vm->resource_name, MHP_NONE);
+ vm->resource_name,
+ MEMHP_MERGE_RESOURCE);
}
/*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 075/156] xen/balloon: try to merge system ram resources
2020-10-16 2:40 incoming Andrew Morton
` (74 preceding siblings ...)
2020-10-16 3:08 ` [patch 074/156] virtio-mem: try to merge system ram resources Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 076/156] hv_balloon: " Andrew Morton
` (90 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, anton, ardb, benh, bhe, boris.ostrovsky, borntraeger,
dan.j.williams, dave.jiang, david, ebiederm, gor, gregkh,
haiyangz, hca, jasowang, jgg, jgross, julien, keescook,
kernelfans, kys, lenb, leobras.c, lpechacek, mhocko, mm-commits,
mpe, mst, nathanl, oohall, pankaj.gupta.linux, paulus,
richardw.yang, rjw, roger.pau, sstabellini, sthemmin, tglx,
torvalds, vishal.l.verma, wei.liu
From: David Hildenbrand <david@redhat.com>
Subject: xen/balloon: try to merge system ram resources
Let's try to merge system ram resources we add, to minimize the number of
resources in /proc/iomem. We don't care about the boundaries of
individual chunks we added.
Link: https://lkml.kernel.org/r/20200911103459.10306-8-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Julien Grall <julien@xen.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/xen/balloon.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/xen/balloon.c~xen-balloon-try-to-merge-system-ram-resources
+++ a/drivers/xen/balloon.c
@@ -331,7 +331,7 @@ static enum bp_state reserve_additional_
mutex_unlock(&balloon_mutex);
/* add_memory_resource() requires the device_hotplug lock */
lock_device_hotplug();
- rc = add_memory_resource(nid, resource, MHP_NONE);
+ rc = add_memory_resource(nid, resource, MEMHP_MERGE_RESOURCE);
unlock_device_hotplug();
mutex_lock(&balloon_mutex);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 076/156] hv_balloon: try to merge system ram resources
2020-10-16 2:40 incoming Andrew Morton
` (75 preceding siblings ...)
2020-10-16 3:09 ` [patch 075/156] xen/balloon: " Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 077/156] kernel/resource: make iomem_resource implicit in release_mem_region_adjustable() Andrew Morton
` (89 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, anton, ardb, benh, bhe, boris.ostrovsky, borntraeger,
dan.j.williams, dave.jiang, david, ebiederm, gor, gregkh,
haiyangz, hca, jasowang, jgg, jgross, julien, keescook,
kernelfans, kys, lenb, leobras.c, lpechacek, mhocko, mm-commits,
mpe, mst, nathanl, oohall, pankaj.gupta.linux, paulus,
richardw.yang, rjw, roger.pau, sstabellini, sthemmin, tglx,
torvalds, vishal.l.verma, wei.liu
From: David Hildenbrand <david@redhat.com>
Subject: hv_balloon: try to merge system ram resources
Let's try to merge system ram resources we add, to minimize the number of
resources in /proc/iomem. We don't care about the boundaries of
individual chunks we added.
Link: https://lkml.kernel.org/r/20200911103459.10306-9-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Wei Liu <wei.liu@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/hv/hv_balloon.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/hv/hv_balloon.c~hv_balloon-try-to-merge-system-ram-resources
+++ a/drivers/hv/hv_balloon.c
@@ -726,7 +726,7 @@ static void hv_mem_hot_add(unsigned long
nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn));
ret = add_memory(nid, PFN_PHYS((start_pfn)),
- (HA_CHUNK << PAGE_SHIFT), MHP_NONE);
+ (HA_CHUNK << PAGE_SHIFT), MEMHP_MERGE_RESOURCE);
if (ret) {
pr_err("hot_add memory failed error is %d\n", ret);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 077/156] kernel/resource: make iomem_resource implicit in release_mem_region_adjustable()
2020-10-16 2:40 incoming Andrew Morton
` (76 preceding siblings ...)
2020-10-16 3:09 ` [patch 076/156] hv_balloon: " Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 078/156] mm: don't panic when links can't be created in sysfs Andrew Morton
` (88 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, ardb, bhe, dan.j.williams, david, jgg, keescook, mhocko,
mm-commits, pankaj.gupta.linux, richard.weiyang, torvalds
From: David Hildenbrand <david@redhat.com>
Subject: kernel/resource: make iomem_resource implicit in release_mem_region_adjustable()
"mem" in the name already indicates the root, similar to
release_mem_region() and devm_request_mem_region(). Make it implicit.
The only single caller always passes iomem_resource, other parents are not
applicable.
Link: https://lkml.kernel.org/r/20200916073041.10355-1-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Suggested-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Reviewed-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/ioport.h | 3 +--
kernel/resource.c | 5 ++---
mm/memory_hotplug.c | 2 +-
3 files changed, 4 insertions(+), 6 deletions(-)
--- a/include/linux/ioport.h~kernel-resource-make-iomem_resource-implicit-in-release_mem_region_adjustable
+++ a/include/linux/ioport.h
@@ -251,8 +251,7 @@ extern struct resource * __request_regio
extern void __release_region(struct resource *, resource_size_t,
resource_size_t);
#ifdef CONFIG_MEMORY_HOTREMOVE
-extern void release_mem_region_adjustable(struct resource *, resource_size_t,
- resource_size_t);
+extern void release_mem_region_adjustable(resource_size_t, resource_size_t);
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
extern void merge_system_ram_resource(struct resource *res);
--- a/kernel/resource.c~kernel-resource-make-iomem_resource-implicit-in-release_mem_region_adjustable
+++ a/kernel/resource.c
@@ -1240,7 +1240,6 @@ EXPORT_SYMBOL(__release_region);
#ifdef CONFIG_MEMORY_HOTREMOVE
/**
* release_mem_region_adjustable - release a previously reserved memory region
- * @parent: parent resource descriptor
* @start: resource start address
* @size: resource region size
*
@@ -1258,9 +1257,9 @@ EXPORT_SYMBOL(__release_region);
* assumes that all children remain in the lower address entry for
* simplicity. Enhance this logic when necessary.
*/
-void release_mem_region_adjustable(struct resource *parent,
- resource_size_t start, resource_size_t size)
+void release_mem_region_adjustable(resource_size_t start, resource_size_t size)
{
+ struct resource *parent = &iomem_resource;
struct resource *new_res = NULL;
bool alloc_nofail = false;
struct resource **p;
--- a/mm/memory_hotplug.c~kernel-resource-make-iomem_resource-implicit-in-release_mem_region_adjustable
+++ a/mm/memory_hotplug.c
@@ -1767,7 +1767,7 @@ static int __ref try_remove_memory(int n
memblock_remove(start, size);
}
- release_mem_region_adjustable(&iomem_resource, start, size);
+ release_mem_region_adjustable(start, size);
try_offline_node(nid);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 078/156] mm: don't panic when links can't be created in sysfs
2020-10-16 2:40 incoming Andrew Morton
` (77 preceding siblings ...)
2020-10-16 3:09 ` [patch 077/156] kernel/resource: make iomem_resource implicit in release_mem_region_adjustable() Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 079/156] mm/page_alloc: convert "report" flag of __free_one_page() to a proper flag Andrew Morton
` (87 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, cheloha, david, fenghua.yu, gregkh, ldufour, mhocko,
mm-commits, nathanl, osalvador, rafael, tony.luck, torvalds
From: Laurent Dufour <ldufour@linux.ibm.com>
Subject: mm: don't panic when links can't be created in sysfs
At boot time, or when doing memory hot-add operations, if the links in
sysfs can't be created, the system is still able to run, so just report
the error in the kernel log rather than BUG_ON and potentially make system
unusable because the callpath can be called with locks held.
Since the number of memory blocks managed could be high, the messages are
rate limited.
As a consequence, link_mem_sections() has no status to report anymore.
Link: https://lkml.kernel.org/r/20200915094143.79181-4-ldufour@linux.ibm.com
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Rafael J . Wysocki" <rafael@kernel.org>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/base/node.c | 33 +++++++++++++++++++++------------
include/linux/node.h | 16 +++++++---------
mm/memory_hotplug.c | 5 ++---
3 files changed, 30 insertions(+), 24 deletions(-)
--- a/drivers/base/node.c~mm-dont-panic-when-links-cant-be-created-in-sysfs
+++ a/drivers/base/node.c
@@ -772,8 +772,8 @@ static int __ref get_nid_for_pfn(unsigne
return pfn_to_nid(pfn);
}
-static int do_register_memory_block_under_node(int nid,
- struct memory_block *mem_blk)
+static void do_register_memory_block_under_node(int nid,
+ struct memory_block *mem_blk)
{
int ret;
@@ -786,12 +786,19 @@ static int do_register_memory_block_unde
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
- if (ret)
- return ret;
+ if (ret && ret != -EEXIST)
+ dev_err_ratelimited(&node_devices[nid]->dev,
+ "can't create link to %s in sysfs (%d)\n",
+ kobject_name(&mem_blk->dev.kobj), ret);
- return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
+ ret = sysfs_create_link_nowarn(&mem_blk->dev.kobj,
&node_devices[nid]->dev.kobj,
kobject_name(&node_devices[nid]->dev.kobj));
+ if (ret && ret != -EEXIST)
+ dev_err_ratelimited(&mem_blk->dev,
+ "can't create link to %s in sysfs (%d)\n",
+ kobject_name(&node_devices[nid]->dev.kobj),
+ ret);
}
/* register memory section under specified node if it spans that node */
@@ -827,7 +834,8 @@ static int register_mem_block_under_node
if (page_nid != nid)
continue;
- return do_register_memory_block_under_node(nid, mem_blk);
+ do_register_memory_block_under_node(nid, mem_blk);
+ return 0;
}
/* mem section does not span the specified node */
return 0;
@@ -842,7 +850,8 @@ static int register_mem_block_under_node
{
int nid = *(int *)arg;
- return do_register_memory_block_under_node(nid, mem_blk);
+ do_register_memory_block_under_node(nid, mem_blk);
+ return 0;
}
/*
@@ -860,8 +869,8 @@ void unregister_memory_block_under_nodes
kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
- enum meminit_context context)
+void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
+ enum meminit_context context)
{
walk_memory_blocks_func_t func;
@@ -870,9 +879,9 @@ int link_mem_sections(int nid, unsigned
else
func = register_mem_block_under_node_early;
- return walk_memory_blocks(PFN_PHYS(start_pfn),
- PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
- func);
+ walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn),
+ (void *)&nid, func);
+ return;
}
#ifdef CONFIG_HUGETLBFS
--- a/include/linux/node.h~mm-dont-panic-when-links-cant-be-created-in-sysfs
+++ a/include/linux/node.h
@@ -99,15 +99,14 @@ extern struct node *node_devices[];
typedef void (*node_registration_func_t)(struct node *);
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn,
- enum meminit_context context);
+void link_mem_sections(int nid, unsigned long start_pfn,
+ unsigned long end_pfn,
+ enum meminit_context context);
#else
-static inline int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn,
- enum meminit_context context)
+static inline void link_mem_sections(int nid, unsigned long start_pfn,
+ unsigned long end_pfn,
+ enum meminit_context context)
{
- return 0;
}
#endif
@@ -130,8 +129,7 @@ static inline int register_one_node(int
if (error)
return error;
/* link memory sections under this node */
- error = link_mem_sections(nid, start_pfn, end_pfn,
- MEMINIT_EARLY);
+ link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY);
}
return error;
--- a/mm/memory_hotplug.c~mm-dont-panic-when-links-cant-be-created-in-sysfs
+++ a/mm/memory_hotplug.c
@@ -1092,9 +1092,8 @@ int __ref add_memory_resource(int nid, s
}
/* link memory sections under this node.*/
- ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
- MEMINIT_HOTPLUG);
- BUG_ON(ret);
+ link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
+ MEMINIT_HOTPLUG);
/* create new memmap entry */
if (!strcmp(res->name, "System RAM"))
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 079/156] mm/page_alloc: convert "report" flag of __free_one_page() to a proper flag
2020-10-16 2:40 incoming Andrew Morton
` (78 preceding siblings ...)
2020-10-16 3:09 ` [patch 078/156] mm: don't panic when links can't be created in sysfs Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 080/156] mm/page_alloc: place pages to tail in __putback_isolated_page() Andrew Morton
` (86 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, alexander.h.duyck, cheloha, dave.hansen, david, haiyangz,
kys, mgorman, mhocko, mhocko, mm-commits, mpe, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, sthemmin, torvalds,
vbabka, wei.liu, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/page_alloc: convert "report" flag of __free_one_page() to a proper flag
Patch series "mm: place pages to the freelist tail when onlining and undoing isolation", v2.
When adding separate memory blocks via add_memory*() and onlining them
immediately, the metadata (especially the memmap) of the next block will
be placed onto one of the just added+onlined block. This creates a chain
of unmovable allocations: If the last memory block cannot get
offlined+removed() so will all dependent ones. We directly have unmovable
allocations all over the place.
This can be observed quite easily using virtio-mem, however, it can also
be observed when using DIMMs. The freshly onlined pages will usually be
placed to the head of the freelists, meaning they will be allocated next,
turning the just-added memory usually immediately un-removable. The fresh
pages are cold, prefering to allocate others (that might be hot) also
feels to be the natural thing to do.
It also applies to the hyper-v balloon xen-balloon, and ppc64 dlpar: when
adding separate, successive memory blocks, each memory block will have
unmovable allocations on them - for example gigantic pages will fail to
allocate.
While the ZONE_NORMAL doesn't provide any guarantees that memory can get
offlined+removed again (any kind of fragmentation with unmovable
allocations is possible), there are many scenarios (hotplugging a lot of
memory, running workload, hotunplug some memory/as much as possible) where
we can offline+remove quite a lot with this patchset.
a) To visualize the problem, a very simple example:
Start a VM with 4GB and 8GB of virtio-mem memory:
[root@localhost ~]# lsmem
RANGE SIZE STATE REMOVABLE BLOCK
0x0000000000000000-0x00000000bfffffff 3G online yes 0-23
0x0000000100000000-0x000000033fffffff 9G online yes 32-103
Memory block size: 128M
Total online memory: 12G
Total offline memory: 0B
Then try to unplug as much as possible using virtio-mem. Observe which
memory blocks are still around. Without this patch set:
[root@localhost ~]# lsmem
RANGE SIZE STATE REMOVABLE BLOCK
0x0000000000000000-0x00000000bfffffff 3G online yes 0-23
0x0000000100000000-0x000000013fffffff 1G online yes 32-39
0x0000000148000000-0x000000014fffffff 128M online yes 41
0x0000000158000000-0x000000015fffffff 128M online yes 43
0x0000000168000000-0x000000016fffffff 128M online yes 45
0x0000000178000000-0x000000017fffffff 128M online yes 47
0x0000000188000000-0x0000000197ffffff 256M online yes 49-50
0x00000001a0000000-0x00000001a7ffffff 128M online yes 52
0x00000001b0000000-0x00000001b7ffffff 128M online yes 54
0x00000001c0000000-0x00000001c7ffffff 128M online yes 56
0x00000001d0000000-0x00000001d7ffffff 128M online yes 58
0x00000001e0000000-0x00000001e7ffffff 128M online yes 60
0x00000001f0000000-0x00000001f7ffffff 128M online yes 62
0x0000000200000000-0x0000000207ffffff 128M online yes 64
0x0000000210000000-0x0000000217ffffff 128M online yes 66
0x0000000220000000-0x0000000227ffffff 128M online yes 68
0x0000000230000000-0x0000000237ffffff 128M online yes 70
0x0000000240000000-0x0000000247ffffff 128M online yes 72
0x0000000250000000-0x0000000257ffffff 128M online yes 74
0x0000000260000000-0x0000000267ffffff 128M online yes 76
0x0000000270000000-0x0000000277ffffff 128M online yes 78
0x0000000280000000-0x0000000287ffffff 128M online yes 80
0x0000000290000000-0x0000000297ffffff 128M online yes 82
0x00000002a0000000-0x00000002a7ffffff 128M online yes 84
0x00000002b0000000-0x00000002b7ffffff 128M online yes 86
0x00000002c0000000-0x00000002c7ffffff 128M online yes 88
0x00000002d0000000-0x00000002d7ffffff 128M online yes 90
0x00000002e0000000-0x00000002e7ffffff 128M online yes 92
0x00000002f0000000-0x00000002f7ffffff 128M online yes 94
0x0000000300000000-0x0000000307ffffff 128M online yes 96
0x0000000310000000-0x0000000317ffffff 128M online yes 98
0x0000000320000000-0x0000000327ffffff 128M online yes 100
0x0000000330000000-0x000000033fffffff 256M online yes 102-103
Memory block size: 128M
Total online memory: 8.1G
Total offline memory: 0B
With this patch set:
[root@localhost ~]# lsmem
RANGE SIZE STATE REMOVABLE BLOCK
0x0000000000000000-0x00000000bfffffff 3G online yes 0-23
0x0000000100000000-0x000000013fffffff 1G online yes 32-39
Memory block size: 128M
Total online memory: 4G
Total offline memory: 0B
All memory can get unplugged, all memory block can get removed. Of
course, no workload ran and the system was basically idle, but it
highlights the issue - the fairly deterministic chain of unmovable
allocations. When a huge page for the 2MB memmap is needed, a
just-onlined 4MB page will be split. The remaining 2MB page will be used
for the memmap of the next memory block. So one memory block will hold
the memmap of the two following memory blocks. Finally the pages of the
last-onlined memory block will get used for the next bigger allocations -
if any allocation is unmovable, all dependent memory blocks cannot get
unplugged and removed until that allocation is gone.
Note that with bigger memory blocks (e.g., 256MB), *all* memory
blocks are dependent and none can get unplugged again!
b) Experiment with memory intensive workload
I performed an experiment with an older version of this patch set (before
we used undo_isolate_page_range() in online_pages(): Hotplug 56GB to a VM
with an initial 4GB, onlining all memory to ZONE_NORMAL right from the
kernel when adding it. I then run various memory intensive workloads that
consume most system memory for a total of 45 minutes. Once finished, I
try to unplug as much memory as possible.
With this change, I am able to remove via virtio-mem (adding individual
128MB memory blocks) 413 out of 448 added memory blocks. Via individual
(256MB) DIMMs 380 out of 448 added memory blocks. (I don't have any
numbers without this patchset, but looking at the above example, it's at
most half of the 448 memory blocks for virtio-mem, and most probably none
for DIMMs).
Again, there are workloads that might behave very differently due to the
nature of ZONE_NORMAL.
This change also affects (besides memory onlining):
- Other users of undo_isolate_page_range(): Pages are always placed to the
tail.
-- When memory offlining fails
-- When memory isolation fails after having isolated some pageblocks
-- When alloc_contig_range() either succeeds or fails
- Other users of __putback_isolated_page(): Pages are always placed to the
tail.
-- Free page reporting
- Other users of __free_pages_core()
-- AFAIKs, any memory that is getting exposed to the buddy during boot.
IIUC we will now usually allocate memory from lower addresses within
a zone first (especially during boot).
- Other users of generic_online_page()
-- Hyper-V balloon
This patch (of 5):
Let's prepare for additional flags and avoid long parameter lists of
bools. Follow-up patches will also make use of the flags in
__free_pages_ok().
Link: https://lkml.kernel.org/r/20201005121534.15649-1-david@redhat.com
Link: https://lkml.kernel.org/r/20201005121534.15649-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/page_alloc.c | 27 ++++++++++++++++++++++-----
1 file changed, 22 insertions(+), 5 deletions(-)
--- a/mm/page_alloc.c~mm-page_alloc-convert-report-flag-of-__free_one_page-to-a-proper-flag
+++ a/mm/page_alloc.c
@@ -78,6 +78,22 @@
#include "shuffle.h"
#include "page_reporting.h"
+/* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */
+typedef int __bitwise fpi_t;
+
+/* No special request */
+#define FPI_NONE ((__force fpi_t)0)
+
+/*
+ * Skip free page reporting notification for the (possibly merged) page.
+ * This does not hinder free page reporting from grabbing the page,
+ * reporting it and marking it "reported" - it only skips notifying
+ * the free page reporting infrastructure about a newly freed page. For
+ * example, used when temporarily pulling a page from a freelist and
+ * putting it back unmodified.
+ */
+#define FPI_SKIP_REPORT_NOTIFY ((__force fpi_t)BIT(0))
+
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
#define MIN_PERCPU_PAGELIST_FRACTION (8)
@@ -952,7 +968,7 @@ buddy_merge_likely(unsigned long pfn, un
static inline void __free_one_page(struct page *page,
unsigned long pfn,
struct zone *zone, unsigned int order,
- int migratetype, bool report)
+ int migratetype, fpi_t fpi_flags)
{
struct capture_control *capc = task_capc(zone);
unsigned long buddy_pfn;
@@ -1039,7 +1055,7 @@ done_merging:
add_to_free_list(page, zone, order, migratetype);
/* Notify page reporting subsystem of freed page */
- if (report)
+ if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY))
page_reporting_notify_free(order);
}
@@ -1380,7 +1396,7 @@ static void free_pcppages_bulk(struct zo
if (unlikely(isolated_pageblocks))
mt = get_pageblock_migratetype(page);
- __free_one_page(page, page_to_pfn(page), zone, 0, mt, true);
+ __free_one_page(page, page_to_pfn(page), zone, 0, mt, FPI_NONE);
trace_mm_page_pcpu_drain(page, 0, mt);
}
spin_unlock(&zone->lock);
@@ -1396,7 +1412,7 @@ static void free_one_page(struct zone *z
is_migrate_isolate(migratetype))) {
migratetype = get_pfnblock_migratetype(page, pfn);
}
- __free_one_page(page, pfn, zone, order, migratetype, true);
+ __free_one_page(page, pfn, zone, order, migratetype, FPI_NONE);
spin_unlock(&zone->lock);
}
@@ -3289,7 +3305,8 @@ void __putback_isolated_page(struct page
lockdep_assert_held(&zone->lock);
/* Return isolated page to tail of freelist. */
- __free_one_page(page, page_to_pfn(page), zone, order, mt, false);
+ __free_one_page(page, page_to_pfn(page), zone, order, mt,
+ FPI_SKIP_REPORT_NOTIFY);
}
/*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 080/156] mm/page_alloc: place pages to tail in __putback_isolated_page()
2020-10-16 2:40 incoming Andrew Morton
` (79 preceding siblings ...)
2020-10-16 3:09 ` [patch 079/156] mm/page_alloc: convert "report" flag of __free_one_page() to a proper flag Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 081/156] mm/page_alloc: move pages to tail in move_to_free_list() Andrew Morton
` (85 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, alexander.h.duyck, cheloha, dave.hansen, david, haiyangz,
kys, mgorman, mhocko, mhocko, mm-commits, mpe, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, sthemmin, torvalds,
vbabka, wei.liu, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/page_alloc: place pages to tail in __putback_isolated_page()
__putback_isolated_page() already documents that pages will be placed to
the tail of the freelist - this is, however, not the case for "order >=
MAX_ORDER - 2" (see buddy_merge_likely()) - which should be the case for
all existing users.
This change affects two users:
- free page reporting
- page isolation, when undoing the isolation (including memory onlining).
This behavior is desirable for pages that haven't really been touched
lately, so exactly the two users that don't actually read/write page
content, but rather move untouched pages.
The new behavior is especially desirable for memory onlining, where we
allow allocation of newly onlined pages via undo_isolate_page_range() in
online_pages(). Right now, we always place them to the head of the
freelist, resulting in undesireable behavior: Assume we add individual
memory chunks via add_memory() and online them right away to the NORMAL
zone. We create a dependency chain of unmovable allocations e.g., via the
memmap. The memmap of the next chunk will be placed onto previous chunks
- if the last block cannot get offlined+removed, all dependent ones cannot
get offlined+removed. While this can already be observed with individual
DIMMs, it's more of an issue for virtio-mem (and I suspect also ppc
DLPAR).
Document that this should only be used for optimizations, and no code
should rely on this behavior for correction (if the order of the freelists
ever changes).
We won't care about page shuffling: memory onlining already properly
shuffles after onlining. free page reporting doesn't care about
physically contiguous ranges, and there are already cases where page
isolation will simply move (physically close) free pages to (currently)
the head of the freelists via move_freepages_block() instead of shuffling.
If this becomes ever relevant, we should shuffle the whole zone when
undoing isolation of larger ranges, and after free_contig_range().
Link: https://lkml.kernel.org/r/20201005121534.15649-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/page_alloc.c | 18 ++++++++++++++++--
1 file changed, 16 insertions(+), 2 deletions(-)
--- a/mm/page_alloc.c~mm-page_alloc-place-pages-to-tail-in-__putback_isolated_page
+++ a/mm/page_alloc.c
@@ -94,6 +94,18 @@ typedef int __bitwise fpi_t;
*/
#define FPI_SKIP_REPORT_NOTIFY ((__force fpi_t)BIT(0))
+/*
+ * Place the (possibly merged) page to the tail of the freelist. Will ignore
+ * page shuffling (relevant code - e.g., memory onlining - is expected to
+ * shuffle the whole zone).
+ *
+ * Note: No code should rely on this flag for correctness - it's purely
+ * to allow for optimizations when handing back either fresh pages
+ * (memory onlining) or untouched pages (page isolation, free page
+ * reporting).
+ */
+#define FPI_TO_TAIL ((__force fpi_t)BIT(1))
+
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
#define MIN_PERCPU_PAGELIST_FRACTION (8)
@@ -1044,7 +1056,9 @@ continue_merging:
done_merging:
set_page_order(page, order);
- if (is_shuffle_order(order))
+ if (fpi_flags & FPI_TO_TAIL)
+ to_tail = true;
+ else if (is_shuffle_order(order))
to_tail = shuffle_pick_tail();
else
to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);
@@ -3306,7 +3320,7 @@ void __putback_isolated_page(struct page
/* Return isolated page to tail of freelist. */
__free_one_page(page, page_to_pfn(page), zone, order, mt,
- FPI_SKIP_REPORT_NOTIFY);
+ FPI_SKIP_REPORT_NOTIFY | FPI_TO_TAIL);
}
/*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 081/156] mm/page_alloc: move pages to tail in move_to_free_list()
2020-10-16 2:40 incoming Andrew Morton
` (80 preceding siblings ...)
2020-10-16 3:09 ` [patch 080/156] mm/page_alloc: place pages to tail in __putback_isolated_page() Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 082/156] mm/page_alloc: place pages to tail in __free_pages_core() Andrew Morton
` (84 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, alexander.h.duyck, cheloha, dave.hansen, david, haiyangz,
kys, mgorman, mhocko, mm-commits, mpe, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, sthemmin, torvalds,
vbabka, wei.liu, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/page_alloc: move pages to tail in move_to_free_list()
Whenever we move pages between freelists via move_to_free_list()/
move_freepages_block(), we don't actually touch the pages:
1. Page isolation doesn't actually touch the pages, it simply isolates
pageblocks and moves all free pages to the MIGRATE_ISOLATE freelist.
When undoing isolation, we move the pages back to the target list.
2. Page stealing (steal_suitable_fallback()) moves free pages directly
between lists without touching them.
3. reserve_highatomic_pageblock()/unreserve_highatomic_pageblock() moves
free pages directly between freelists without touching them.
We already place pages to the tail of the freelists when undoing isolation
via __putback_isolated_page(), let's do it in any case (e.g., if order <=
pageblock_order) and document the behavior. To simplify, let's move the
pages to the tail for all move_to_free_list()/move_freepages_block() users.
In 2., the target list is empty, so there should be no change. In 3., we
might observe a change, however, highatomic is more concerned about
allocations succeeding than cache hotness - if we ever realize this change
degrades a workload, we can special-case this instance and add a proper
comment.
This change results in all pages getting onlined via online_pages() to be
placed to the tail of the freelist.
Link: https://lkml.kernel.org/r/20201005121534.15649-4-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Reviewed-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/page_alloc.c | 10 +++++++---
mm/page_isolation.c | 5 +++++
2 files changed, 12 insertions(+), 3 deletions(-)
--- a/mm/page_alloc.c~mm-page_alloc-move-pages-to-tail-in-move_to_free_list
+++ a/mm/page_alloc.c
@@ -901,13 +901,17 @@ static inline void add_to_free_list_tail
area->nr_free++;
}
-/* Used for pages which are on another list */
+/*
+ * Used for pages which are on another list. Move the pages to the tail
+ * of the list - so the moved pages won't immediately be considered for
+ * allocation again (e.g., optimization for memory onlining).
+ */
static inline void move_to_free_list(struct page *page, struct zone *zone,
unsigned int order, int migratetype)
{
struct free_area *area = &zone->free_area[order];
- list_move(&page->lru, &area->free_list[migratetype]);
+ list_move_tail(&page->lru, &area->free_list[migratetype]);
}
static inline void del_page_from_free_list(struct page *page, struct zone *zone,
@@ -2340,7 +2344,7 @@ static inline struct page *__rmqueue_cma
#endif
/*
- * Move the free pages in a range to the free lists of the requested type.
+ * Move the free pages in a range to the freelist tail of the requested type.
* Note that start_page and end_pages are not aligned on a pageblock
* boundary. If alignment is required, use move_freepages_block()
*/
--- a/mm/page_isolation.c~mm-page_alloc-move-pages-to-tail-in-move_to_free_list
+++ a/mm/page_isolation.c
@@ -106,6 +106,11 @@ static void unset_migratetype_isolate(st
* If we isolate freepage with more than pageblock_order, there
* should be no freepage in the range, so we could avoid costly
* pageblock scanning for freepage moving.
+ *
+ * We didn't actually touch any of the isolated pages, so place them
+ * to the tail of the freelist. This is an optimization for memory
+ * onlining - just onlined memory won't immediately be considered for
+ * allocation.
*/
if (!isolated_page) {
nr_pages = move_freepages_block(zone, page, migratetype, NULL);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 082/156] mm/page_alloc: place pages to tail in __free_pages_core()
2020-10-16 2:40 incoming Andrew Morton
` (81 preceding siblings ...)
2020-10-16 3:09 ` [patch 081/156] mm/page_alloc: move pages to tail in move_to_free_list() Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 083/156] mm/memory_hotplug: update comment regarding zone shuffling Andrew Morton
` (83 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, alexander.h.duyck, cheloha, dave.hansen, david, haiyangz,
kys, mgorman, mhocko, mhocko, mm-commits, mpe, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, sthemmin, torvalds,
vbabka, wei.liu, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/page_alloc: place pages to tail in __free_pages_core()
__free_pages_core() is used when exposing fresh memory to the buddy during
system boot and when onlining memory in generic_online_page().
generic_online_page() is used in two cases:
1. Direct memory onlining in online_pages().
2. Deferred memory onlining in memory-ballooning-like mechanisms (HyperV
balloon and virtio-mem), when parts of a section are kept
fake-offline to be fake-onlined later on.
In 1, we already place pages to the tail of the freelist. Pages will be
freed to MIGRATE_ISOLATE lists first and moved to the tail of the
freelists via undo_isolate_page_range().
In 2, we currently don't implement a proper rule. In case of virtio-mem,
where we currently always online MAX_ORDER - 1 pages, the pages will be
placed to the HEAD of the freelist - undesireable. While the hyper-v
balloon calls generic_online_page() with single pages, usually it will
call it on successive single pages in a larger block.
The pages are fresh, so place them to the tail of the freelist and avoid
the PCP. In __free_pages_core(), remove the now superflouos call to
set_page_refcounted() and add a comment regarding page initialization and
the refcount.
Note: In 2. we currently don't shuffle. If ever relevant (page shuffling
is usually of limited use in virtualized environments), we might want to
shuffle after a sequence of generic_online_page() calls in the relevant
callers.
Link: https://lkml.kernel.org/r/20201005121534.15649-5-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Reviewed-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/page_alloc.c | 33 +++++++++++++++++++++++----------
1 file changed, 23 insertions(+), 10 deletions(-)
--- a/mm/page_alloc.c~mm-page_alloc-place-pages-to-tail-in-__free_pages_core
+++ a/mm/page_alloc.c
@@ -275,7 +275,8 @@ bool pm_suspended_storage(void)
unsigned int pageblock_order __read_mostly;
#endif
-static void __free_pages_ok(struct page *page, unsigned int order);
+static void __free_pages_ok(struct page *page, unsigned int order,
+ fpi_t fpi_flags);
/*
* results with 256, 32 in the lowmem_reserve sysctl:
@@ -687,7 +688,7 @@ out:
void free_compound_page(struct page *page)
{
mem_cgroup_uncharge(page);
- __free_pages_ok(page, compound_order(page));
+ __free_pages_ok(page, compound_order(page), FPI_NONE);
}
void prep_compound_page(struct page *page, unsigned int order)
@@ -1423,14 +1424,14 @@ static void free_pcppages_bulk(struct zo
static void free_one_page(struct zone *zone,
struct page *page, unsigned long pfn,
unsigned int order,
- int migratetype)
+ int migratetype, fpi_t fpi_flags)
{
spin_lock(&zone->lock);
if (unlikely(has_isolate_pageblock(zone) ||
is_migrate_isolate(migratetype))) {
migratetype = get_pfnblock_migratetype(page, pfn);
}
- __free_one_page(page, pfn, zone, order, migratetype, FPI_NONE);
+ __free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
spin_unlock(&zone->lock);
}
@@ -1508,7 +1509,8 @@ void __meminit reserve_bootmem_region(ph
}
}
-static void __free_pages_ok(struct page *page, unsigned int order)
+static void __free_pages_ok(struct page *page, unsigned int order,
+ fpi_t fpi_flags)
{
unsigned long flags;
int migratetype;
@@ -1520,7 +1522,8 @@ static void __free_pages_ok(struct page
migratetype = get_pfnblock_migratetype(page, pfn);
local_irq_save(flags);
__count_vm_events(PGFREE, 1 << order);
- free_one_page(page_zone(page), page, pfn, order, migratetype);
+ free_one_page(page_zone(page), page, pfn, order, migratetype,
+ fpi_flags);
local_irq_restore(flags);
}
@@ -1530,6 +1533,11 @@ void __free_pages_core(struct page *page
struct page *p = page;
unsigned int loop;
+ /*
+ * When initializing the memmap, __init_single_page() sets the refcount
+ * of all pages to 1 ("allocated"/"not free"). We have to set the
+ * refcount of all involved pages to 0.
+ */
prefetchw(p);
for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
prefetchw(p + 1);
@@ -1540,8 +1548,12 @@ void __free_pages_core(struct page *page
set_page_count(p, 0);
atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
- set_page_refcounted(page);
- __free_pages(page, order);
+
+ /*
+ * Bypass PCP and place fresh pages right to the tail, primarily
+ * relevant for memory onlining.
+ */
+ __free_pages_ok(page, order, FPI_TO_TAIL);
}
#ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -3168,7 +3180,8 @@ static void free_unref_page_commit(struc
*/
if (migratetype >= MIGRATE_PCPTYPES) {
if (unlikely(is_migrate_isolate(migratetype))) {
- free_one_page(zone, page, pfn, 0, migratetype);
+ free_one_page(zone, page, pfn, 0, migratetype,
+ FPI_NONE);
return;
}
migratetype = MIGRATE_MOVABLE;
@@ -4991,7 +5004,7 @@ static inline void free_the_page(struct
if (order == 0) /* Via pcp? */
free_unref_page(page);
else
- __free_pages_ok(page, order);
+ __free_pages_ok(page, order, FPI_NONE);
}
void __free_pages(struct page *page, unsigned int order)
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 083/156] mm/memory_hotplug: update comment regarding zone shuffling
2020-10-16 2:40 incoming Andrew Morton
` (82 preceding siblings ...)
2020-10-16 3:09 ` [patch 082/156] mm/page_alloc: place pages to tail in __free_pages_core() Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 084/156] zram: failing to decompress is WARN_ON worthy Andrew Morton
` (82 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, alexander.h.duyck, cheloha, dave.hansen, david, haiyangz,
kys, mgorman, mhocko, mhocko, mm-commits, mpe, osalvador,
pankaj.gupta.linux, richard.weiyang, rppt, sthemmin, torvalds,
vbabka, wei.liu, willy
From: David Hildenbrand <david@redhat.com>
Subject: mm/memory_hotplug: update comment regarding zone shuffling
As we no longer shuffle via generic_online_page() and when undoing
isolation, we can simplify the comment.
We now effectively shuffle only once (properly) when onlining new memory.
Link: https://lkml.kernel.org/r/20201005121534.15649-6-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory_hotplug.c | 11 ++++-------
1 file changed, 4 insertions(+), 7 deletions(-)
--- a/mm/memory_hotplug.c~mm-memory_hotplug-update-comment-regarding-zone-shuffling
+++ a/mm/memory_hotplug.c
@@ -858,13 +858,10 @@ int __ref online_pages(unsigned long pfn
undo_isolate_page_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE);
/*
- * When exposing larger, physically contiguous memory areas to the
- * buddy, shuffling in the buddy (when freeing onlined pages, putting
- * them either to the head or the tail of the freelist) is only helpful
- * for maintaining the shuffle, but not for creating the initial
- * shuffle. Shuffle the whole zone to make sure the just onlined pages
- * are properly distributed across the whole freelist. Make sure to
- * shuffle once pageblocks are no longer isolated.
+ * Freshly onlined pages aren't shuffled (e.g., all pages are placed to
+ * the tail of the freelist when undoing isolation). Shuffle the whole
+ * zone to make sure the just onlined pages are properly distributed
+ * across the whole freelist - to create an initial shuffle.
*/
shuffle_zone(zone);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 084/156] zram: failing to decompress is WARN_ON worthy
2020-10-16 2:40 incoming Andrew Morton
` (83 preceding siblings ...)
2020-10-16 3:09 ` [patch 083/156] mm/memory_hotplug: update comment regarding zone shuffling Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 085/156] mm/slab.h: remove duplicate include Andrew Morton
` (81 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, axboe, dianders, minchan, mm-commits,
sergey.senozhatsky.work, sonnyrao, torvalds
From: Douglas Anderson <dianders@chromium.org>
Subject: zram: failing to decompress is WARN_ON worthy
If we fail to decompress in zram it's a pretty serious problem. We were
entrusted to be able to decompress the old data but we failed. Either
we've got some crazy bug in the compression code or we've got memory
corruption.
At the moment, when this happens the log looks like this:
ERR kernel: [ 1833.099861] zram: Decompression failed! err=-22, page=336112
ERR kernel: [ 1833.099881] zram: Decompression failed! err=-22, page=336112
ALERT kernel: [ 1833.099886] Read-error on swap-device (253:0:2688896)
It is true that we have an "ALERT" level log in there, but (at least to
me) it feels like even this isn't enough to impart the seriousness of this
error. Let's convert to a WARN_ON. Note that WARN_ON is automatically
"unlikely" so we can simply replace the old annotation with the new one.
Link: https://lkml.kernel.org/r/20200917174059.1.If09c882545dbe432268f7a67a4d4cfcb6caace4f@changeid
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: Sonny Rao <sonnyrao@chromium.org>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/block/zram/zram_drv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/block/zram/zram_drv.c~zram-failing-to-decompress-is-warn_on-worthy
+++ a/drivers/block/zram/zram_drv.c
@@ -1270,7 +1270,7 @@ static int __zram_bvec_read(struct zram
zram_slot_unlock(zram, index);
/* Should NEVER happen. Return bio error if it does. */
- if (unlikely(ret))
+ if (WARN_ON(ret))
pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
return ret;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 085/156] mm/slab.h: remove duplicate include
2020-10-16 2:40 incoming Andrew Morton
` (84 preceding siblings ...)
2020-10-16 3:09 ` [patch 084/156] zram: failing to decompress is WARN_ON worthy Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 086/156] mm/page_reporting.c: drop stale list head check in page_reporting_cycle Andrew Morton
` (80 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, mm-commits, penberg, torvalds, yuehaibing
From: YueHaibing <yuehaibing@huawei.com>
Subject: mm/slab.h: remove duplicate include
Remove duplicate header which is included twice.
Link: http://lkml.kernel.org/r/20200818114323.58156-1-yuehaibing@huawei.com
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/slab.h | 1 -
1 file changed, 1 deletion(-)
--- a/mm/slab.h~mm-slab-remove-duplicate-include
+++ a/mm/slab.h
@@ -46,7 +46,6 @@ struct kmem_cache {
#include <linux/kmemleak.h>
#include <linux/random.h>
#include <linux/sched/mm.h>
-#include <linux/kmemleak.h>
/*
* State of the slab allocator.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 086/156] mm/page_reporting.c: drop stale list head check in page_reporting_cycle
2020-10-16 2:40 incoming Andrew Morton
` (85 preceding siblings ...)
2020-10-16 3:09 ` [patch 085/156] mm/slab.h: remove duplicate include Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 087/156] mm/highmem.c: clean up endif comments Andrew Morton
` (79 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, alexander.h.duyck, david, mm-commits, richard.weiyang, torvalds
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Subject: mm/page_reporting.c: drop stale list head check in page_reporting_cycle
list_for_each_entry_safe() guarantees that we will never stumble over the
list head; "&page->lru != list" will always evaluate to true. Let's
simplify.
[david@redhat.com: Changelog refinements]
Link: http://lkml.kernel.org/r/20200818084448.33969-1-richard.weiyang@linux.alibaba.com
Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/page_reporting.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/page_reporting.c~mm-page_reporting-drop-stale-list-head-check-in-page_reporting_cycle
+++ a/mm/page_reporting.c
@@ -178,7 +178,7 @@ page_reporting_cycle(struct page_reporti
* the new head of the free list before we release the
* zone lock.
*/
- if (&page->lru != list && !list_is_first(&page->lru, list))
+ if (!list_is_first(&page->lru, list))
list_rotate_to_front(&page->lru, list);
/* release lock before waiting on report processing */
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 087/156] mm/highmem.c: clean up endif comments
2020-10-16 2:40 incoming Andrew Morton
` (86 preceding siblings ...)
2020-10-16 3:09 ` [patch 086/156] mm/page_reporting.c: drop stale list head check in page_reporting_cycle Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 088/156] mm: use self-explanatory macros rather than "2" Andrew Morton
` (78 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, ira.weiny, mm-commits, rppt, torvalds
From: Ira Weiny <ira.weiny@intel.com>
Subject: mm/highmem.c: clean up endif comments
The #endif at the end of the file matches up with the '#if
defined(HASHED_PAGE_VIRTUAL)' on line 374. Not the CONFIG_HIGHMEM #if
earlier.
Fix comments on both of the #endif's to indicate the correct end of
blocks for each.
Link: https://lkml.kernel.org/r/20200819184635.112579-1-ira.weiny@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/highmem.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/mm/highmem.c~mm-highmem-clean-up-endif-comments
+++ a/mm/highmem.c
@@ -369,7 +369,7 @@ void kunmap_high(struct page *page)
}
EXPORT_SYMBOL(kunmap_high);
-#endif
+#endif /* CONFIG_HIGHMEM */
#if defined(HASHED_PAGE_VIRTUAL)
@@ -481,4 +481,4 @@ void __init page_address_init(void)
}
}
-#endif /* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */
+#endif /* defined(HASHED_PAGE_VIRTUAL) */
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 088/156] mm: use self-explanatory macros rather than "2"
2020-10-16 2:40 incoming Andrew Morton
` (87 preceding siblings ...)
2020-10-16 3:09 ` [patch 087/156] mm/highmem.c: clean up endif comments Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:09 ` [patch 089/156] mm: fix some broken comments Andrew Morton
` (77 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, alex.shi, mm-commits, torvalds, yuzhao
From: Yu Zhao <yuzhao@google.com>
Subject: mm: use self-explanatory macros rather than "2"
Link: http://lkml.kernel.org/r/20200831175042.3527153-2-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Alex Shi <alex.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/mmzone.h | 12 ++++++++----
include/linux/vmstat.h | 2 +-
mm/vmscan.c | 2 +-
3 files changed, 10 insertions(+), 6 deletions(-)
--- a/include/linux/mmzone.h~mm-use-self-explanatory-macros-rather-than-2
+++ a/include/linux/mmzone.h
@@ -266,6 +266,8 @@ static inline bool is_active_lru(enum lr
return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
}
+#define ANON_AND_FILE 2
+
enum lruvec_flags {
LRUVEC_CONGESTED, /* lruvec has many dirty pages
* backed by a congested BDI
@@ -283,8 +285,8 @@ struct lruvec {
unsigned long file_cost;
/* Non-resident age, driven by LRU movement */
atomic_long_t nonresident_age;
- /* Refaults at the time of last reclaim cycle, anon=0, file=1 */
- unsigned long refaults[2];
+ /* Refaults at the time of last reclaim cycle */
+ unsigned long refaults[ANON_AND_FILE];
/* Various lruvec state flags (enum lruvec_flags) */
unsigned long flags;
#ifdef CONFIG_MEMCG
@@ -441,6 +443,8 @@ enum zone_type {
#ifndef __GENERATING_BOUNDS_H
+#define ASYNC_AND_SYNC 2
+
struct zone {
/* Read-mostly fields */
@@ -560,8 +564,8 @@ struct zone {
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* pfn where compaction free scanner should start */
unsigned long compact_cached_free_pfn;
- /* pfn where async and sync compaction migration scanner should start */
- unsigned long compact_cached_migrate_pfn[2];
+ /* pfn where compaction migration scanner should start */
+ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC];
unsigned long compact_init_migrate_pfn;
unsigned long compact_init_free_pfn;
#endif
--- a/include/linux/vmstat.h~mm-use-self-explanatory-macros-rather-than-2
+++ a/include/linux/vmstat.h
@@ -28,7 +28,7 @@ struct reclaim_stat {
unsigned nr_writeback;
unsigned nr_immediate;
unsigned nr_pageout;
- unsigned nr_activate[2];
+ unsigned nr_activate[ANON_AND_FILE];
unsigned nr_ref_keep;
unsigned nr_unmap_fail;
unsigned nr_lazyfree_fail;
--- a/mm/vmscan.c~mm-use-self-explanatory-macros-rather-than-2
+++ a/mm/vmscan.c
@@ -2239,7 +2239,7 @@ static void get_scan_count(struct lruvec
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
unsigned long anon_cost, file_cost, total_cost;
int swappiness = mem_cgroup_swappiness(memcg);
- u64 fraction[2];
+ u64 fraction[ANON_AND_FILE];
u64 denominator = 0; /* gcc */
enum scan_balance scan_balance;
unsigned long ap, fp;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 089/156] mm: fix some broken comments
2020-10-16 2:40 incoming Andrew Morton
` (88 preceding siblings ...)
2020-10-16 3:09 ` [patch 088/156] mm: use self-explanatory macros rather than "2" Andrew Morton
@ 2020-10-16 3:09 ` Andrew Morton
2020-10-16 3:10 ` [patch 090/156] mm: fix some comments formatting Andrew Morton
` (76 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:09 UTC (permalink / raw)
To: akpm, linmiaohe, mm-commits, torvalds
From: Miaohe Lin <linmiaohe@huawei.com>
Subject: mm: fix some broken comments
Fix some broken comments including typo, grammar error and wrong function
name.
Link: https://lkml.kernel.org/r/20200913095456.54873-1-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/filemap.c | 4 ++--
mm/swap_state.c | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
--- a/mm/filemap.c~mm-fix-some-broken-comments
+++ a/mm/filemap.c
@@ -1445,7 +1445,7 @@ static inline bool clear_bit_unlock_is_n
* unlock_page - unlock a locked page
* @page: the page
*
- * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
+ * Unlocks the page and wakes up sleepers in wait_on_page_locked().
* Also wakes sleepers in wait_on_page_writeback() because the wakeup
* mechanism between PageLocked pages and PageWriteback pages is shared.
* But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
@@ -3004,7 +3004,7 @@ filler:
goto out;
/*
- * Page is not up to date and may be locked due one of the following
+ * Page is not up to date and may be locked due to one of the following
* case a: Page is being filled and the page lock is held
* case b: Read/write error clearing the page uptodate status
* case c: Truncation in progress (page locked)
--- a/mm/swap_state.c~mm-fix-some-broken-comments
+++ a/mm/swap_state.c
@@ -246,7 +246,7 @@ int add_to_swap(struct page *page)
goto fail;
/*
* Normally the page will be dirtied in unmap because its pte should be
- * dirty. A special case is MADV_FREE page. The page'e pte could have
+ * dirty. A special case is MADV_FREE page. The page's pte could have
* dirty bit cleared but the page's SwapBacked bit is still set because
* clearing the dirty bit and SwapBacked bit has no lock protected. For
* such page, unmap will not set dirty bit for it, so page reclaim will
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 090/156] mm: fix some comments formatting
2020-10-16 2:40 incoming Andrew Morton
` (89 preceding siblings ...)
2020-10-16 3:09 ` [patch 089/156] mm: fix some broken comments Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 091/156] mm/workingset.c: fix some doc warnings Andrew Morton
` (75 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, chentao3, mm-commits, rppt, torvalds
From: Chen Tao <chentao3@hotmail.com>
Subject: mm: fix some comments formatting
Correct one function name "get_partials" with "get_partial". Update the
old struct name of list3 with kmem_cache_node.
Link: https://lkml.kernel.org/r/Message-ID:
Signed-off-by: Chen Tao <chentao3@hotmail.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/slab.c | 2 +-
mm/slub.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
--- a/mm/slab.c~mm-fix-some-comments-formatting
+++ a/mm/slab.c
@@ -1062,7 +1062,7 @@ int slab_prepare_cpu(unsigned int cpu)
* Even if all the cpus of a node are down, we don't free the
* kmem_cache_node of any cache. This to avoid a race between cpu_down, and
* a kmalloc allocation from another cpu for memory from the node of
- * the cpu going down. The list3 structure is usually allocated from
+ * the cpu going down. The kmem_cache_node structure is usually allocated from
* kmem_cache_create() and gets destroyed at kmem_cache_destroy().
*/
int slab_dead_cpu(unsigned int cpu)
--- a/mm/slub.c~mm-fix-some-comments-formatting
+++ a/mm/slub.c
@@ -1956,7 +1956,7 @@ static void *get_partial_node(struct kme
/*
* Racy check. If we mistakenly see no partial slabs then we
* just allocate an empty slab. If we mistakenly try to get a
- * partial slab and there is none available then get_partials()
+ * partial slab and there is none available then get_partial()
* will return NULL.
*/
if (!n || !n->nr_partial)
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 091/156] mm/workingset.c: fix some doc warnings
2020-10-16 2:40 incoming Andrew Morton
` (90 preceding siblings ...)
2020-10-16 3:10 ` [patch 090/156] mm: fix some comments formatting Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 092/156] mm: use helper function put_write_access() Andrew Morton
` (74 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, mm-commits, tanxiaofei, torvalds
From: Xiaofei Tan <tanxiaofei@huawei.com>
Subject: mm/workingset.c: fix some doc warnings
Fix following warnings caused by mismatch bewteen function parameters and
comments.
mm/workingset.c:228: warning: Function parameter or member 'lruvec' not described in 'workingset_age_nonresident'
mm/workingset.c:228: warning: Excess function parameter 'memcg' description in 'workingset_age_nonresident'
Link: https://lkml.kernel.org/r/1600485913-11192-1-git-send-email-tanxiaofei@huawei.com
Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/workingset.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/workingset.c~mm-fix-some-doc-warnings-in-workingsetc
+++ a/mm/workingset.c
@@ -216,7 +216,7 @@ static void unpack_shadow(void *shadow,
/**
* workingset_age_nonresident - age non-resident entries as LRU ages
- * @memcg: the lruvec that was aged
+ * @lruvec: the lruvec that was aged
* @nr_pages: the number of pages to count
*
* As in-memory pages are aged, non-resident pages need to be aged as
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 092/156] mm: use helper function put_write_access()
2020-10-16 2:40 incoming Andrew Morton
` (91 preceding siblings ...)
2020-10-16 3:10 ` [patch 091/156] mm/workingset.c: fix some doc warnings Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 093/156] include/linux/mmzone.h: remove unused early_pfn_valid() Andrew Morton
` (73 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, linmiaohe, mm-commits, torvalds
From: Miaohe Lin <linmiaohe@huawei.com>
Subject: mm: use helper function put_write_access()
In commit 1da177e4c3f4 ("Linux-2.6.12-rc2"), the helper put_write_access()
came with the atomic_dec operation of the i_writecount field. But it
forgot to use this helper in __vma_link_file() and dup_mmap().
Link: https://lkml.kernel.org/r/20200924115235.5111-1-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/fork.c | 2 +-
mm/mmap.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
--- a/kernel/fork.c~mm-use-helper-function-put_write_access
+++ a/kernel/fork.c
@@ -556,7 +556,7 @@ static __latent_entropy int dup_mmap(str
get_file(file);
if (tmp->vm_flags & VM_DENYWRITE)
- atomic_dec(&inode->i_writecount);
+ put_write_access(inode);
i_mmap_lock_write(mapping);
if (tmp->vm_flags & VM_SHARED)
mapping_allow_writable(mapping);
--- a/mm/mmap.c~mm-use-helper-function-put_write_access
+++ a/mm/mmap.c
@@ -619,7 +619,7 @@ static void __vma_link_file(struct vm_ar
struct address_space *mapping = file->f_mapping;
if (vma->vm_flags & VM_DENYWRITE)
- atomic_dec(&file_inode(file)->i_writecount);
+ put_write_access(file_inode(file));
if (vma->vm_flags & VM_SHARED)
mapping_allow_writable(mapping);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 093/156] include/linux/mmzone.h: remove unused early_pfn_valid()
2020-10-16 2:40 incoming Andrew Morton
` (92 preceding siblings ...)
2020-10-16 3:10 ` [patch 092/156] mm: use helper function put_write_access() Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 094/156] mm: rename page_order() to buddy_order() Andrew Morton
` (72 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, david, mm-commits, rppt, torvalds
From: Mike Rapoport <rppt@linux.ibm.com>
Subject: include/linux/mmzone.h: remove unused early_pfn_valid()
The early_pfn_valid() macro is defined but it is never used. Remove it.
Link: https://lkml.kernel.org/r/20200923162915.26935-1-rppt@kernel.org
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/mmzone.h | 5 -----
1 file changed, 5 deletions(-)
--- a/include/linux/mmzone.h~mm-remove-unused-early_pfn_valid
+++ a/include/linux/mmzone.h
@@ -1420,7 +1420,6 @@ static inline unsigned long next_present
#define pfn_to_nid(pfn) (0)
#endif
-#define early_pfn_valid(pfn) pfn_valid(pfn)
void sparse_init(void);
#else
#define sparse_init() do {} while (0)
@@ -1440,10 +1439,6 @@ struct mminit_pfnnid_cache {
int last_nid;
};
-#ifndef early_pfn_valid
-#define early_pfn_valid(pfn) (1)
-#endif
-
/*
* If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
* need to check pfn validity within that MAX_ORDER_NR_PAGES block.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 094/156] mm: rename page_order() to buddy_order()
2020-10-16 2:40 incoming Andrew Morton
` (93 preceding siblings ...)
2020-10-16 3:10 ` [patch 093/156] include/linux/mmzone.h: remove unused early_pfn_valid() Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 095/156] fs: configfs: delete repeated words in comments Andrew Morton
` (71 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, mm-commits, torvalds, willy
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Subject: mm: rename page_order() to buddy_order()
The current page_order() can only be called on pages in the buddy
allocator. For compound pages, you have to use compound_order(). This is
confusing and led to a bug, so rename page_order() to buddy_order().
Link: https://lkml.kernel.org/r/20201001152259.14932-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/compaction.c | 6 +++---
mm/internal.h | 8 ++++----
mm/page_alloc.c | 30 +++++++++++++++---------------
mm/page_isolation.c | 4 ++--
mm/page_owner.c | 6 +++---
mm/page_reporting.c | 2 +-
mm/shuffle.c | 2 +-
7 files changed, 29 insertions(+), 29 deletions(-)
--- a/mm/compaction.c~mm-rename-page_order-to-buddy_order
+++ a/mm/compaction.c
@@ -625,7 +625,7 @@ static unsigned long isolate_freepages_b
}
/* Found a free page, will break it into order-0 pages */
- order = page_order(page);
+ order = buddy_order(page);
isolated = __isolate_free_page(page, order);
if (!isolated)
break;
@@ -898,7 +898,7 @@ isolate_migratepages_block(struct compac
* potential isolation targets.
*/
if (PageBuddy(page)) {
- unsigned long freepage_order = page_order_unsafe(page);
+ unsigned long freepage_order = buddy_order_unsafe(page);
/*
* Without lock, we cannot be sure that what we got is
@@ -1172,7 +1172,7 @@ static bool suitable_migration_target(st
* the only small danger is that we skip a potentially suitable
* pageblock, so it's not worth to check order for valid range.
*/
- if (page_order_unsafe(page) >= pageblock_order)
+ if (buddy_order_unsafe(page) >= pageblock_order)
return false;
}
--- a/mm/internal.h~mm-rename-page_order-to-buddy_order
+++ a/mm/internal.h
@@ -270,16 +270,16 @@ int find_suitable_fallback(struct free_a
* page from being allocated in parallel and returning garbage as the order.
* If a caller does not hold page_zone(page)->lock, it must guarantee that the
* page cannot be allocated or merged in parallel. Alternatively, it must
- * handle invalid values gracefully, and use page_order_unsafe() below.
+ * handle invalid values gracefully, and use buddy_order_unsafe() below.
*/
-static inline unsigned int page_order(struct page *page)
+static inline unsigned int buddy_order(struct page *page)
{
/* PageBuddy() must be checked by the caller */
return page_private(page);
}
/*
- * Like page_order(), but for callers who cannot afford to hold the zone lock.
+ * Like buddy_order(), but for callers who cannot afford to hold the zone lock.
* PageBuddy() should be checked first by the caller to minimize race window,
* and invalid values must be handled gracefully.
*
@@ -289,7 +289,7 @@ static inline unsigned int page_order(st
* times, potentially observing different values in the tests and the actual
* use of the result.
*/
-#define page_order_unsafe(page) READ_ONCE(page_private(page))
+#define buddy_order_unsafe(page) READ_ONCE(page_private(page))
static inline bool is_cow_mapping(vm_flags_t flags)
{
--- a/mm/page_alloc.c~mm-rename-page_order-to-buddy_order
+++ a/mm/page_alloc.c
@@ -792,7 +792,7 @@ static inline void clear_page_guard(stru
unsigned int order, int migratetype) {}
#endif
-static inline void set_page_order(struct page *page, unsigned int order)
+static inline void set_buddy_order(struct page *page, unsigned int order)
{
set_page_private(page, order);
__SetPageBuddy(page);
@@ -817,7 +817,7 @@ static inline bool page_is_buddy(struct
if (!page_is_guard(buddy) && !PageBuddy(buddy))
return false;
- if (page_order(buddy) != order)
+ if (buddy_order(buddy) != order)
return false;
/*
@@ -1059,7 +1059,7 @@ continue_merging:
}
done_merging:
- set_page_order(page, order);
+ set_buddy_order(page, order);
if (fpi_flags & FPI_TO_TAIL)
to_tail = true;
@@ -2178,7 +2178,7 @@ static inline void expand(struct zone *z
continue;
add_to_free_list(&page[size], zone, high, migratetype);
- set_page_order(&page[size], high);
+ set_buddy_order(&page[size], high);
}
}
@@ -2392,7 +2392,7 @@ static int move_freepages(struct zone *z
VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
VM_BUG_ON_PAGE(page_zone(page) != zone, page);
- order = page_order(page);
+ order = buddy_order(page);
move_to_free_list(page, zone, order, migratetype);
page += 1 << order;
pages_moved += 1 << order;
@@ -2516,7 +2516,7 @@ static inline void boost_watermark(struc
static void steal_suitable_fallback(struct zone *zone, struct page *page,
unsigned int alloc_flags, int start_type, bool whole_block)
{
- unsigned int current_order = page_order(page);
+ unsigned int current_order = buddy_order(page);
int free_pages, movable_pages, alike_pages;
int old_block_type;
@@ -8344,7 +8344,7 @@ struct page *has_unmovable_pages(struct
*/
if (!page_ref_count(page)) {
if (PageBuddy(page))
- iter += (1 << page_order(page)) - 1;
+ iter += (1 << buddy_order(page)) - 1;
continue;
}
@@ -8557,7 +8557,7 @@ int alloc_contig_range(unsigned long sta
}
if (outer_start != start) {
- order = page_order(pfn_to_page(outer_start));
+ order = buddy_order(pfn_to_page(outer_start));
/*
* outer_start page could be small order buddy page and
@@ -8782,7 +8782,7 @@ void __offline_isolated_pages(unsigned l
BUG_ON(page_count(page));
BUG_ON(!PageBuddy(page));
- order = page_order(page);
+ order = buddy_order(page);
del_page_from_free_list(page, zone, order);
pfn += (1 << order);
}
@@ -8801,7 +8801,7 @@ bool is_free_buddy_page(struct page *pag
for (order = 0; order < MAX_ORDER; order++) {
struct page *page_head = page - (pfn & ((1 << order) - 1));
- if (PageBuddy(page_head) && page_order(page_head) >= order)
+ if (PageBuddy(page_head) && buddy_order(page_head) >= order)
break;
}
spin_unlock_irqrestore(&zone->lock, flags);
@@ -8838,7 +8838,7 @@ static void break_down_buddy_pages(struc
if (current_buddy != target) {
add_to_free_list(current_buddy, zone, high, migratetype);
- set_page_order(current_buddy, high);
+ set_buddy_order(current_buddy, high);
page = next_page;
}
}
@@ -8858,16 +8858,16 @@ bool take_page_off_buddy(struct page *pa
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
struct page *page_head = page - (pfn & ((1 << order) - 1));
- int buddy_order = page_order(page_head);
+ int page_order = buddy_order(page_head);
- if (PageBuddy(page_head) && buddy_order >= order) {
+ if (PageBuddy(page_head) && page_order >= order) {
unsigned long pfn_head = page_to_pfn(page_head);
int migratetype = get_pfnblock_migratetype(page_head,
pfn_head);
- del_page_from_free_list(page_head, zone, buddy_order);
+ del_page_from_free_list(page_head, zone, page_order);
break_down_buddy_pages(zone, page_head, page, 0,
- buddy_order, migratetype);
+ page_order, migratetype);
ret = true;
break;
}
--- a/mm/page_isolation.c~mm-rename-page_order-to-buddy_order
+++ a/mm/page_isolation.c
@@ -88,7 +88,7 @@ static void unset_migratetype_isolate(st
* these pages to be merged.
*/
if (PageBuddy(page)) {
- order = page_order(page);
+ order = buddy_order(page);
if (order >= pageblock_order) {
pfn = page_to_pfn(page);
buddy_pfn = __find_buddy_pfn(pfn, order);
@@ -261,7 +261,7 @@ __test_page_isolated_in_pageblock(unsign
* the correct MIGRATE_ISOLATE freelist. There is no
* simple way to verify that as VM_BUG_ON(), though.
*/
- pfn += 1 << page_order(page);
+ pfn += 1 << buddy_order(page);
else if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
/* A HWPoisoned page cannot be also PageBuddy */
pfn++;
--- a/mm/page_owner.c~mm-rename-page_order-to-buddy_order
+++ a/mm/page_owner.c
@@ -295,7 +295,7 @@ void pagetypeinfo_showmixedcount_print(s
if (PageBuddy(page)) {
unsigned long freepage_order;
- freepage_order = page_order_unsafe(page);
+ freepage_order = buddy_order_unsafe(page);
if (freepage_order < MAX_ORDER)
pfn += (1UL << freepage_order) - 1;
continue;
@@ -490,7 +490,7 @@ read_page_owner(struct file *file, char
page = pfn_to_page(pfn);
if (PageBuddy(page)) {
- unsigned long freepage_order = page_order_unsafe(page);
+ unsigned long freepage_order = buddy_order_unsafe(page);
if (freepage_order < MAX_ORDER)
pfn += (1UL << freepage_order) - 1;
@@ -584,7 +584,7 @@ static void init_pages_in_zone(pg_data_t
* heavy lock contention.
*/
if (PageBuddy(page)) {
- unsigned long order = page_order_unsafe(page);
+ unsigned long order = buddy_order_unsafe(page);
if (order > 0 && order < MAX_ORDER)
pfn += (1UL << order) - 1;
--- a/mm/page_reporting.c~mm-rename-page_order-to-buddy_order
+++ a/mm/page_reporting.c
@@ -92,7 +92,7 @@ page_reporting_drain(struct page_reporti
* report on the new larger page when we make our way
* up to that higher order.
*/
- if (PageBuddy(page) && page_order(page) == order)
+ if (PageBuddy(page) && buddy_order(page) == order)
__SetPageReported(page);
} while ((sg = sg_next(sg)));
--- a/mm/shuffle.c~mm-rename-page_order-to-buddy_order
+++ a/mm/shuffle.c
@@ -60,7 +60,7 @@ static struct page * __meminit shuffle_v
* ...is the page on the same list as the page we will
* shuffle it with?
*/
- if (page_order(page) != order)
+ if (buddy_order(page) != order)
return NULL;
return page;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 095/156] fs: configfs: delete repeated words in comments
2020-10-16 2:40 incoming Andrew Morton
` (94 preceding siblings ...)
2020-10-16 3:10 ` [patch 094/156] mm: rename page_order() to buddy_order() Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 096/156] kernel.h: split out min()/max() et al. helpers Andrew Morton
` (70 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, hch, jlbec, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: fs: configfs: delete repeated words in comments
Drop duplicated words {the, that} in comments.
Link: https://lkml.kernel.org/r/20200811021826.25032-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/configfs/dir.c | 2 +-
fs/configfs/file.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
--- a/fs/configfs/dir.c~fs-configfs-delete-repeated-words-in-comments
+++ a/fs/configfs/dir.c
@@ -1168,7 +1168,7 @@ EXPORT_SYMBOL(configfs_depend_item);
/*
* Release the dependent linkage. This is much simpler than
- * configfs_depend_item() because we know that that the client driver is
+ * configfs_depend_item() because we know that the client driver is
* pinned, thus the subsystem is pinned, and therefore configfs is pinned.
*/
void configfs_undepend_item(struct config_item *target)
--- a/fs/configfs/file.c~fs-configfs-delete-repeated-words-in-comments
+++ a/fs/configfs/file.c
@@ -267,7 +267,7 @@ flush_write_buffer(struct file *file, st
* There is no easy way for us to know if userspace is only doing a partial
* write, so we don't support them. We expect the entire buffer to come
* on the first write.
- * Hint: if you're writing a value, first read the file, modify only the
+ * Hint: if you're writing a value, first read the file, modify only
* the value you're changing, then write entire buffer back.
*/
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 096/156] kernel.h: split out min()/max() et al. helpers
2020-10-16 2:40 incoming Andrew Morton
` (95 preceding siblings ...)
2020-10-16 3:10 ` [patch 095/156] fs: configfs: delete repeated words in comments Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 097/156] kernel/sys.c: replace do_brk with do_brk_flags in comment of prctl_set_mm_map() Andrew Morton
` (69 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, andriy.shevchenko, joe, linux, mm-commits, rjw, rostedt, torvalds
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Subject: kernel.h: split out min()/max() et al. helpers
kernel.h is being used as a dump for all kinds of stuff for a long time.
Here is the attempt to start cleaning it up by splitting out min()/max()
et al. helpers.
At the same time convert users in header and lib folder to use new header.
Though for time being include new header back to kernel.h to avoid
twisted indirected includes for other existing users.
Link: https://lkml.kernel.org/r/20200910164152.GA1891694@smile.fi.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Joe Perches <joe@perches.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/blkdev.h | 1
include/linux/bvec.h | 6 +
include/linux/jiffies.h | 3
include/linux/kernel.h | 150 -----------------------------------
include/linux/minmax.h | 153 ++++++++++++++++++++++++++++++++++++
include/linux/nodemask.h | 2
include/linux/uaccess.h | 1
kernel/range.c | 3
lib/find_bit.c | 1
lib/hexdump.c | 1
lib/math/rational.c | 2
lib/math/reciprocal_div.c | 1
12 files changed, 170 insertions(+), 154 deletions(-)
--- a/include/linux/blkdev.h~kernelh-split-out-min-max-et-al-helpers
+++ a/include/linux/blkdev.h
@@ -8,6 +8,7 @@
#include <linux/genhd.h>
#include <linux/list.h>
#include <linux/llist.h>
+#include <linux/minmax.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/pagemap.h>
--- a/include/linux/bvec.h~kernelh-split-out-min-max-et-al-helpers
+++ a/include/linux/bvec.h
@@ -7,10 +7,14 @@
#ifndef __LINUX_BVEC_ITER_H
#define __LINUX_BVEC_ITER_H
-#include <linux/kernel.h>
#include <linux/bug.h>
#include <linux/errno.h>
+#include <linux/limits.h>
+#include <linux/minmax.h>
#include <linux/mm.h>
+#include <linux/types.h>
+
+struct page;
/**
* struct bio_vec - a contiguous range of physical memory addresses
--- a/include/linux/jiffies.h~kernelh-split-out-min-max-et-al-helpers
+++ a/include/linux/jiffies.h
@@ -3,8 +3,9 @@
#define _LINUX_JIFFIES_H
#include <linux/cache.h>
+#include <linux/limits.h>
#include <linux/math64.h>
-#include <linux/kernel.h>
+#include <linux/minmax.h>
#include <linux/types.h>
#include <linux/time.h>
#include <linux/timex.h>
--- a/include/linux/kernel.h~kernelh-split-out-min-max-et-al-helpers
+++ a/include/linux/kernel.h
@@ -11,6 +11,7 @@
#include <linux/compiler.h>
#include <linux/bitops.h>
#include <linux/log2.h>
+#include <linux/minmax.h>
#include <linux/typecheck.h>
#include <linux/printk.h>
#include <linux/build_bug.h>
@@ -833,155 +834,6 @@ ftrace_vprintk(const char *fmt, va_list
static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
#endif /* CONFIG_TRACING */
-/*
- * min()/max()/clamp() macros must accomplish three things:
- *
- * - avoid multiple evaluations of the arguments (so side-effects like
- * "x++" happen only once) when non-constant.
- * - perform strict type-checking (to generate warnings instead of
- * nasty runtime surprises). See the "unnecessary" pointer comparison
- * in __typecheck().
- * - retain result as a constant expressions when called with only
- * constant expressions (to avoid tripping VLA warnings in stack
- * allocation usage).
- */
-#define __typecheck(x, y) \
- (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
-
-/*
- * This returns a constant expression while determining if an argument is
- * a constant expression, most importantly without evaluating the argument.
- * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
- */
-#define __is_constexpr(x) \
- (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
-
-#define __no_side_effects(x, y) \
- (__is_constexpr(x) && __is_constexpr(y))
-
-#define __safe_cmp(x, y) \
- (__typecheck(x, y) && __no_side_effects(x, y))
-
-#define __cmp(x, y, op) ((x) op (y) ? (x) : (y))
-
-#define __cmp_once(x, y, unique_x, unique_y, op) ({ \
- typeof(x) unique_x = (x); \
- typeof(y) unique_y = (y); \
- __cmp(unique_x, unique_y, op); })
-
-#define __careful_cmp(x, y, op) \
- __builtin_choose_expr(__safe_cmp(x, y), \
- __cmp(x, y, op), \
- __cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
-
-/**
- * min - return minimum of two values of the same or compatible types
- * @x: first value
- * @y: second value
- */
-#define min(x, y) __careful_cmp(x, y, <)
-
-/**
- * max - return maximum of two values of the same or compatible types
- * @x: first value
- * @y: second value
- */
-#define max(x, y) __careful_cmp(x, y, >)
-
-/**
- * min3 - return minimum of three values
- * @x: first value
- * @y: second value
- * @z: third value
- */
-#define min3(x, y, z) min((typeof(x))min(x, y), z)
-
-/**
- * max3 - return maximum of three values
- * @x: first value
- * @y: second value
- * @z: third value
- */
-#define max3(x, y, z) max((typeof(x))max(x, y), z)
-
-/**
- * min_not_zero - return the minimum that is _not_ zero, unless both are zero
- * @x: value1
- * @y: value2
- */
-#define min_not_zero(x, y) ({ \
- typeof(x) __x = (x); \
- typeof(y) __y = (y); \
- __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
-
-/**
- * clamp - return a value clamped to a given range with strict typechecking
- * @val: current value
- * @lo: lowest allowable value
- * @hi: highest allowable value
- *
- * This macro does strict typechecking of @lo/@hi to make sure they are of the
- * same type as @val. See the unnecessary pointer comparisons.
- */
-#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
-
-/*
- * ..and if you can't take the strict
- * types, you can specify one yourself.
- *
- * Or not use min/max/clamp at all, of course.
- */
-
-/**
- * min_t - return minimum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define min_t(type, x, y) __careful_cmp((type)(x), (type)(y), <)
-
-/**
- * max_t - return maximum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define max_t(type, x, y) __careful_cmp((type)(x), (type)(y), >)
-
-/**
- * clamp_t - return a value clamped to a given range using a given type
- * @type: the type of variable to use
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of type
- * @type to make all the comparisons.
- */
-#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
-
-/**
- * clamp_val - return a value clamped to a given range using val's type
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of whatever
- * type the input argument @val is. This is useful when @val is an unsigned
- * type and @lo and @hi are literals that will otherwise be assigned a signed
- * integer type.
- */
-#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
-
-
-/**
- * swap - swap values of @a and @b
- * @a: first value
- * @b: second value
- */
-#define swap(a, b) \
- do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
-
/* This counts to 12. Any more, it will return 13th argument. */
#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
--- /dev/null
+++ a/include/linux/minmax.h
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MINMAX_H
+#define _LINUX_MINMAX_H
+
+/*
+ * min()/max()/clamp() macros must accomplish three things:
+ *
+ * - avoid multiple evaluations of the arguments (so side-effects like
+ * "x++" happen only once) when non-constant.
+ * - perform strict type-checking (to generate warnings instead of
+ * nasty runtime surprises). See the "unnecessary" pointer comparison
+ * in __typecheck().
+ * - retain result as a constant expressions when called with only
+ * constant expressions (to avoid tripping VLA warnings in stack
+ * allocation usage).
+ */
+#define __typecheck(x, y) \
+ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
+
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+ (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
+#define __no_side_effects(x, y) \
+ (__is_constexpr(x) && __is_constexpr(y))
+
+#define __safe_cmp(x, y) \
+ (__typecheck(x, y) && __no_side_effects(x, y))
+
+#define __cmp(x, y, op) ((x) op (y) ? (x) : (y))
+
+#define __cmp_once(x, y, unique_x, unique_y, op) ({ \
+ typeof(x) unique_x = (x); \
+ typeof(y) unique_y = (y); \
+ __cmp(unique_x, unique_y, op); })
+
+#define __careful_cmp(x, y, op) \
+ __builtin_choose_expr(__safe_cmp(x, y), \
+ __cmp(x, y, op), \
+ __cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
+
+/**
+ * min - return minimum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
+#define min(x, y) __careful_cmp(x, y, <)
+
+/**
+ * max - return maximum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
+#define max(x, y) __careful_cmp(x, y, >)
+
+/**
+ * min3 - return minimum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
+#define min3(x, y, z) min((typeof(x))min(x, y), z)
+
+/**
+ * max3 - return maximum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
+#define max3(x, y, z) max((typeof(x))max(x, y), z)
+
+/**
+ * min_not_zero - return the minimum that is _not_ zero, unless both are zero
+ * @x: value1
+ * @y: value2
+ */
+#define min_not_zero(x, y) ({ \
+ typeof(x) __x = (x); \
+ typeof(y) __y = (y); \
+ __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
+
+/**
+ * clamp - return a value clamped to a given range with strict typechecking
+ * @val: current value
+ * @lo: lowest allowable value
+ * @hi: highest allowable value
+ *
+ * This macro does strict typechecking of @lo/@hi to make sure they are of the
+ * same type as @val. See the unnecessary pointer comparisons.
+ */
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
+
+/*
+ * ..and if you can't take the strict
+ * types, you can specify one yourself.
+ *
+ * Or not use min/max/clamp at all, of course.
+ */
+
+/**
+ * min_t - return minimum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define min_t(type, x, y) __careful_cmp((type)(x), (type)(y), <)
+
+/**
+ * max_t - return maximum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define max_t(type, x, y) __careful_cmp((type)(x), (type)(y), >)
+
+/**
+ * clamp_t - return a value clamped to a given range using a given type
+ * @type: the type of variable to use
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of type
+ * @type to make all the comparisons.
+ */
+#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
+
+/**
+ * clamp_val - return a value clamped to a given range using val's type
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of whatever
+ * type the input argument @val is. This is useful when @val is an unsigned
+ * type and @lo and @hi are literals that will otherwise be assigned a signed
+ * integer type.
+ */
+#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
+
+/**
+ * swap - swap values of @a and @b
+ * @a: first value
+ * @b: second value
+ */
+#define swap(a, b) \
+ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
+#endif /* _LINUX_MINMAX_H */
--- a/include/linux/nodemask.h~kernelh-split-out-min-max-et-al-helpers
+++ a/include/linux/nodemask.h
@@ -90,9 +90,9 @@
* for such situations. See below and CPUMASK_ALLOC also.
*/
-#include <linux/kernel.h>
#include <linux/threads.h>
#include <linux/bitmap.h>
+#include <linux/minmax.h>
#include <linux/numa.h>
typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
--- a/include/linux/uaccess.h~kernelh-split-out-min-max-et-al-helpers
+++ a/include/linux/uaccess.h
@@ -3,6 +3,7 @@
#define __LINUX_UACCESS_H__
#include <linux/instrumented.h>
+#include <linux/minmax.h>
#include <linux/sched.h>
#include <linux/thread_info.h>
--- a/kernel/range.c~kernelh-split-out-min-max-et-al-helpers
+++ a/kernel/range.c
@@ -2,8 +2,9 @@
/*
* Range add and subtract
*/
-#include <linux/kernel.h>
#include <linux/init.h>
+#include <linux/minmax.h>
+#include <linux/printk.h>
#include <linux/sort.h>
#include <linux/string.h>
#include <linux/range.h>
--- a/lib/find_bit.c~kernelh-split-out-min-max-et-al-helpers
+++ a/lib/find_bit.c
@@ -16,6 +16,7 @@
#include <linux/bitmap.h>
#include <linux/export.h>
#include <linux/kernel.h>
+#include <linux/minmax.h>
#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \
!defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \
--- a/lib/hexdump.c~kernelh-split-out-min-max-et-al-helpers
+++ a/lib/hexdump.c
@@ -7,6 +7,7 @@
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/kernel.h>
+#include <linux/minmax.h>
#include <linux/export.h>
#include <asm/unaligned.h>
--- a/lib/math/rational.c~kernelh-split-out-min-max-et-al-helpers
+++ a/lib/math/rational.c
@@ -11,7 +11,7 @@
#include <linux/rational.h>
#include <linux/compiler.h>
#include <linux/export.h>
-#include <linux/kernel.h>
+#include <linux/minmax.h>
/*
* calculate best rational approximation for a given fraction
--- a/lib/math/reciprocal_div.c~kernelh-split-out-min-max-et-al-helpers
+++ a/lib/math/reciprocal_div.c
@@ -4,6 +4,7 @@
#include <asm/div64.h>
#include <linux/reciprocal_div.h>
#include <linux/export.h>
+#include <linux/minmax.h>
/*
* For a description of the algorithm please have a look at
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 097/156] kernel/sys.c: replace do_brk with do_brk_flags in comment of prctl_set_mm_map()
2020-10-16 2:40 incoming Andrew Morton
` (96 preceding siblings ...)
2020-10-16 3:10 ` [patch 096/156] kernel.h: split out min()/max() et al. helpers Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 098/156] kernel/: fix repeated words in comments Andrew Morton
` (68 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, liao.pingfang, mm-commits, torvalds, wang.yi59
From: Liao Pingfang <liao.pingfang@zte.com.cn>
Subject: kernel/sys.c: replace do_brk with do_brk_flags in comment of prctl_set_mm_map()
Replace do_brk with do_brk_flags in comment of prctl_set_mm_map(), since
do_brk was removed in following commit.
Link: https://lkml.kernel.org/r/1600650751-43127-1-git-send-email-wang.yi59@zte.com.cn
Fixes: bb177a732c4369 ("mm: do not bug_on on incorrect length in __mm_populate()")
Signed-off-by: Liao Pingfang <liao.pingfang@zte.com.cn>
Signed-off-by: Yi Wang <wang.yi59@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/sys.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/kernel/sys.c~kernel-sysc-replace-do_brk-with-do_brk_flags-in-comment-of-prctl_set_mm_map
+++ a/kernel/sys.c
@@ -2034,7 +2034,7 @@ static int prctl_set_mm_map(int opt, con
* VMAs already unmapped and kernel uses these members for statistics
* output in procfs mostly, except
*
- * - @start_brk/@brk which are used in do_brk but kernel lookups
+ * - @start_brk/@brk which are used in do_brk_flags but kernel lookups
* for VMAs when updating these memvers so anything wrong written
* here cause kernel to swear at userspace program but won't lead
* to any problem in kernel itself
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 098/156] kernel/: fix repeated words in comments
2020-10-16 2:40 incoming Andrew Morton
` (97 preceding siblings ...)
2020-10-16 3:10 ` [patch 097/156] kernel/sys.c: replace do_brk with do_brk_flags in comment of prctl_set_mm_map() Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 099/156] kernel: acct.c: fix some kernel-doc nits Andrew Morton
` (67 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: kernel/: fix repeated words in comments
Fix multiple occurrences of duplicated words in kernel/.
Fix one typo/spello on the same line as a duplicate word. Change one
instance of "the the" to "that the". Otherwise just drop one of the
repeated words.
Link: https://lkml.kernel.org/r/98202fa6-8919-ef63-9efe-c0fad5ca7af1@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/acct.c | 2 +-
kernel/cgroup/cpuset.c | 2 +-
kernel/dma/direct.c | 2 +-
kernel/fork.c | 2 +-
kernel/futex.c | 2 +-
kernel/irq/timings.c | 2 +-
kernel/jump_label.c | 2 +-
kernel/kcsan/encoding.h | 2 +-
kernel/kexec_core.c | 2 +-
kernel/kthread.c | 2 +-
kernel/livepatch/state.c | 2 +-
kernel/pid_namespace.c | 2 +-
kernel/power/snapshot.c | 2 +-
kernel/smp.c | 2 +-
kernel/user_namespace.c | 2 +-
15 files changed, 15 insertions(+), 15 deletions(-)
--- a/kernel/acct.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/acct.c
@@ -25,7 +25,7 @@
* Now we silently close acct_file on attempt to reopen. Cleaned sys_acct().
* XTerms and EMACS are manifestations of pure evil. 21/10/98, AV.
*
- * Fixed a nasty interaction with with sys_umount(). If the accointing
+ * Fixed a nasty interaction with sys_umount(). If the accounting
* was suspeneded we failed to stop it on umount(). Messy.
* Another one: remount to readonly didn't stop accounting.
* Question: what should we do if we have CAP_SYS_ADMIN but not
--- a/kernel/cgroup/cpuset.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/cgroup/cpuset.c
@@ -390,7 +390,7 @@ static void guarantee_online_cpus(struct
* The top cpuset doesn't have any online cpu as a
* consequence of a race between cpuset_hotplug_work
* and cpu hotplug notifier. But we know the top
- * cpuset's effective_cpus is on its way to to be
+ * cpuset's effective_cpus is on its way to be
* identical to cpu_online_mask.
*/
cpumask_copy(pmask, cpu_online_mask);
--- a/kernel/dma/direct.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/dma/direct.c
@@ -16,7 +16,7 @@
#include "direct.h"
/*
- * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
+ * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use
* it for entirely different regions. In that case the arch code needs to
* override the variable below for dma-direct to work properly.
*/
--- a/kernel/fork.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/fork.c
@@ -2189,7 +2189,7 @@ static __latent_entropy struct task_stru
/*
* Ensure that the cgroup subsystem policies allow the new process to be
- * forked. It should be noted the the new process's css_set can be changed
+ * forked. It should be noted that the new process's css_set can be changed
* between here and cgroup_post_fork() if an organisation operation is in
* progress.
*/
--- a/kernel/futex.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/futex.c
@@ -916,7 +916,7 @@ static inline void exit_pi_state_list(st
* [10] Found | Found | task | !=taskTID | 0/1 | Invalid
*
* [1] Indicates that the kernel can acquire the futex atomically. We
- * came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
+ * came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
*
* [2] Valid, if TID does not belong to a kernel thread. If no matching
* thread is found then it indicates that the owner TID has died.
--- a/kernel/irq/timings.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/irq/timings.c
@@ -604,7 +604,7 @@ int irq_timings_alloc(int irq)
/*
* Some platforms can have the same private interrupt per cpu,
- * so this function may be be called several times with the
+ * so this function may be called several times with the
* same interrupt number. Just bail out in case the per cpu
* stat structure is already allocated.
*/
--- a/kernel/jump_label.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/jump_label.c
@@ -19,7 +19,7 @@
#include <linux/cpu.h>
#include <asm/sections.h>
-/* mutex to protect coming/going of the the jump_label table */
+/* mutex to protect coming/going of the jump_label table */
static DEFINE_MUTEX(jump_label_mutex);
void jump_label_lock(void)
--- a/kernel/kcsan/encoding.h~kernel-fix-repeated-words-in-comments
+++ a/kernel/kcsan/encoding.h
@@ -32,7 +32,7 @@
* 1. different addresses but with the same encoded address race;
* 2. and both map onto the same watchpoint slots;
*
- * Both these are assumed to be very unlikely. However, in case it still happens
+ * Both these are assumed to be very unlikely. However, in case it still
* happens, the report logic will filter out the false positive (see report.c).
*/
#define WATCHPOINT_ADDR_BITS (BITS_PER_LONG-1 - WATCHPOINT_SIZE_BITS)
--- a/kernel/kexec_core.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/kexec_core.c
@@ -109,7 +109,7 @@ EXPORT_SYMBOL_GPL(kexec_crash_loaded);
* defined more restrictively in <asm/kexec.h>.
*
* The code for the transition from the current kernel to the
- * the new kernel is placed in the control_code_buffer, whose size
+ * new kernel is placed in the control_code_buffer, whose size
* is given by KEXEC_CONTROL_PAGE_SIZE. In the best case only a single
* page of memory is necessary, but some architectures require more.
* Because this memory must be identity mapped in the transition from
--- a/kernel/kthread.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/kthread.c
@@ -775,7 +775,7 @@ EXPORT_SYMBOL(kthread_create_worker);
/**
* kthread_create_worker_on_cpu - create a kthread worker and bind it
- * it to a given CPU and the associated NUMA node.
+ * to a given CPU and the associated NUMA node.
* @cpu: CPU number
* @flags: flags modifying the default behavior of the worker
* @namefmt: printf-style name for the kthread worker (task).
--- a/kernel/livepatch/state.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/livepatch/state.c
@@ -55,7 +55,7 @@ EXPORT_SYMBOL_GPL(klp_get_state);
*
* The function can be called only during transition when a new
* livepatch is being enabled or when such a transition is reverted.
- * It is typically called only from from pre/post (un)patch
+ * It is typically called only from pre/post (un)patch
* callbacks.
*
* Return: pointer to the latest struct klp_state from already
--- a/kernel/pid_namespace.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/pid_namespace.c
@@ -233,7 +233,7 @@ void zap_pid_ns_processes(struct pid_nam
* to pid_ns->child_reaper. Thus pidns->child_reaper needs to
* stay valid until they all go away.
*
- * The code relies on the the pid_ns->child_reaper ignoring
+ * The code relies on the pid_ns->child_reaper ignoring
* SIGCHILD to cause those EXIT_ZOMBIE processes to be
* autoreaped if reparented.
*
--- a/kernel/power/snapshot.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/power/snapshot.c
@@ -735,7 +735,7 @@ zone_found:
*/
/*
- * If the zone we wish to scan is the the current zone and the
+ * If the zone we wish to scan is the current zone and the
* pfn falls into the current node then we do not need to walk
* the tree.
*/
--- a/kernel/smp.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/smp.c
@@ -741,7 +741,7 @@ EXPORT_SYMBOL(on_each_cpu_mask);
* for all the required CPUs to finish. This may include the local
* processor.
* @cond_func: A callback function that is passed a cpu id and
- * the the info parameter. The function is called
+ * the info parameter. The function is called
* with preemption disabled. The function should
* return a blooean value indicating whether to IPI
* the specified CPU.
--- a/kernel/user_namespace.c~kernel-fix-repeated-words-in-comments
+++ a/kernel/user_namespace.c
@@ -515,7 +515,7 @@ EXPORT_SYMBOL(from_kgid_munged);
*
* When there is no mapping defined for the user-namespace projid
* pair INVALID_PROJID is returned. Callers are expected to test
- * for and handle handle INVALID_PROJID being returned. INVALID_PROJID
+ * for and handle INVALID_PROJID being returned. INVALID_PROJID
* may be tested for using projid_valid().
*/
kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid)
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 099/156] kernel: acct.c: fix some kernel-doc nits
2020-10-16 2:40 incoming Andrew Morton
` (98 preceding siblings ...)
2020-10-16 3:10 ` [patch 098/156] kernel/: fix repeated words in comments Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 100/156] get_maintainer: add test for file in VCS Andrew Morton
` (66 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds, viro
From: Randy Dunlap <rdunlap@infradead.org>
Subject: kernel: acct.c: fix some kernel-doc nits
Fix kernel-doc notation to use the documented Returns: syntax and place
the function description for acct_process() on the first line where it
should be.
Link: https://lkml.kernel.org/r/b4c33e5d-98e8-0c47-77b6-ac1859f94d7f@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/acct.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
--- a/kernel/acct.c~kernel-acctc-fix-some-kernel-doc-nits
+++ a/kernel/acct.c
@@ -263,12 +263,12 @@ static DEFINE_MUTEX(acct_on_mutex);
* sys_acct - enable/disable process accounting
* @name: file name for accounting records or NULL to shutdown accounting
*
- * Returns 0 for success or negative errno values for failure.
- *
* sys_acct() is the only system call needed to implement process
* accounting. It takes the name of the file where accounting records
* should be written. If the filename is NULL, accounting will be
* shutdown.
+ *
+ * Returns: 0 for success or negative errno values for failure.
*/
SYSCALL_DEFINE1(acct, const char __user *, name)
{
@@ -586,9 +586,7 @@ static void slow_acct_process(struct pid
}
/**
- * acct_process
- *
- * handles process accounting for an exiting task
+ * acct_process - handles process accounting for an exiting task
*/
void acct_process(void)
{
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 100/156] get_maintainer: add test for file in VCS
2020-10-16 2:40 incoming Andrew Morton
` (99 preceding siblings ...)
2020-10-16 3:10 ` [patch 099/156] kernel: acct.c: fix some kernel-doc nits Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 101/156] get_maintainer: exclude MAINTAINERS file(s) from --git-fallback Andrew Morton
` (65 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, joe, mm-commits, torvalds
From: Joe Perches <joe@perches.com>
Subject: get_maintainer: add test for file in VCS
It's somewhat common for me to ask get_maintainer to tell me who maintains
a patch file rather than the files modified by the patch.
Emit a warning if using get_maintainer.pl -f <patchfile>
Link: https://lkml.kernel.org/r/f63229c051567041819f25e76f49d83c6e4c0f71.camel@perches.com
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/get_maintainer.pl | 3 +++
1 file changed, 3 insertions(+)
--- a/scripts/get_maintainer.pl~get_maintainer-add-test-for-file-in-vcs
+++ a/scripts/get_maintainer.pl
@@ -541,6 +541,9 @@ foreach my $file (@ARGV) {
die "$P: file '${file}' not found\n";
}
}
+ if ($from_filename && (vcs_exists() && !vcs_file_exists($file))) {
+ warn "$P: file '$file' not found in version control $!\n";
+ }
if ($from_filename || ($file ne "&STDIN" && vcs_file_exists($file))) {
$file =~ s/^\Q${cur_path}\E//; #strip any absolute path
$file =~ s/^\Q${lk_path}\E//; #or the path to the lk tree
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 101/156] get_maintainer: exclude MAINTAINERS file(s) from --git-fallback
2020-10-16 2:40 incoming Andrew Morton
` (100 preceding siblings ...)
2020-10-16 3:10 ` [patch 100/156] get_maintainer: add test for file in VCS Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 102/156] MAINTAINERS: jarkko.sakkinen@linux.intel.com -> jarkko@kernel.org Andrew Morton
` (64 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, davem, joe, mchehab+huawei, mm-commits, robh, torvalds
From: Joe Perches <joe@perches.com>
Subject: get_maintainer: exclude MAINTAINERS file(s) from --git-fallback
MAINTAINERS files generally have no specific maintainer but are updated by
individuals for subsystems all over the source tree.
Exclude MAINTAINERS file(s) from --git-fallback searches so the unlucky
individuals that update the files the most are not shown by default.
Link: https://lkml.kernel.org/r/2bacb0a9c06fbb6d56a43bf930e808c74243c908.camel@perches.com
Signed-off-by: Joe Perches <joe@perches.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/get_maintainer.pl | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
--- a/scripts/get_maintainer.pl~get_maintainer-exclude-maintainers-files-from-git-fallback
+++ a/scripts/get_maintainer.pl
@@ -957,8 +957,10 @@ sub get_maintainers {
foreach my $file (@files) {
if ($email &&
- ($email_git || ($email_git_fallback &&
- !$exact_pattern_match_hash{$file}))) {
+ ($email_git ||
+ ($email_git_fallback &&
+ $file !~ /MAINTAINERS$/ &&
+ !$exact_pattern_match_hash{$file}))) {
vcs_file_signoffs($file);
}
if ($email && $email_git_blame) {
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 102/156] MAINTAINERS: jarkko.sakkinen@linux.intel.com -> jarkko@kernel.org
2020-10-16 2:40 incoming Andrew Morton
` (101 preceding siblings ...)
2020-10-16 3:10 ` [patch 101/156] get_maintainer: exclude MAINTAINERS file(s) from --git-fallback Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 103/156] lib: bitmap: delete duplicated words Andrew Morton
` (63 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, corbet, davem, jarkko.sakkinen, joe, keescook,
mchehab+huawei, mm-commits, robh, torvalds
From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Subject: MAINTAINERS: jarkko.sakkinen@linux.intel.com -> jarkko@kernel.org
Use @kernel.org address as the main communications end point. Update the
corresponding M-entries and .mailmap (for git shortlog translation).
Link: https://lkml.kernel.org/r/20201015142710.8371-1-jarkko.sakkinen@linux.intel.com
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: Joe Perches <joe@perches.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Rob Herring <robh@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
.mailmap | 1 +
MAINTAINERS | 6 +++---
2 files changed, 4 insertions(+), 3 deletions(-)
--- a/.mailmap~maintainers-jarkkosakkinen-linuxintelcom-jarkko-kernelorg
+++ a/.mailmap
@@ -133,6 +133,7 @@ James Ketrenos <jketreno@io.(none)>
Jan Glauber <jan.glauber@gmail.com> <jang@de.ibm.com>
Jan Glauber <jan.glauber@gmail.com> <jang@linux.vnet.ibm.com>
Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com>
+Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@linux.intel.com>
Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com>
Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
--- a/MAINTAINERS~maintainers-jarkkosakkinen-linuxintelcom-jarkko-kernelorg
+++ a/MAINTAINERS
@@ -9701,7 +9701,7 @@ F: security/keys/encrypted-keys/
KEYS-TRUSTED
M: James Bottomley <jejb@linux.ibm.com>
-M: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
+M: Jarkko Sakkinen <jarkko@kernel.org>
M: Mimi Zohar <zohar@linux.ibm.com>
L: linux-integrity@vger.kernel.org
L: keyrings@vger.kernel.org
@@ -9713,7 +9713,7 @@ F: security/keys/trusted-keys/
KEYS/KEYRINGS
M: David Howells <dhowells@redhat.com>
-M: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
+M: Jarkko Sakkinen <jarkko@kernel.org>
L: keyrings@vger.kernel.org
S: Maintained
F: Documentation/security/keys/core.rst
@@ -17684,7 +17684,7 @@ F: drivers/platform/x86/toshiba-wmi.c
TPM DEVICE DRIVER
M: Peter Huewe <peterhuewe@gmx.de>
-M: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
+M: Jarkko Sakkinen <jarkko@kernel.org>
R: Jason Gunthorpe <jgg@ziepe.ca>
L: linux-integrity@vger.kernel.org
S: Maintained
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 103/156] lib: bitmap: delete duplicated words
2020-10-16 2:40 incoming Andrew Morton
` (102 preceding siblings ...)
2020-10-16 3:10 ` [patch 102/156] MAINTAINERS: jarkko.sakkinen@linux.intel.com -> jarkko@kernel.org Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 104/156] lib: libcrc32c: " Andrew Morton
` (62 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: lib: bitmap: delete duplicated words
Drop the repeated word "an".
Link: https://lkml.kernel.org/r/20200823040424.25760-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/bitmap.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/bitmap.c~lib-bitmap-delete-duplicated-words
+++ a/lib/bitmap.c
@@ -23,7 +23,7 @@
/**
* DOC: bitmap introduction
*
- * bitmaps provide an array of bits, implemented using an an
+ * bitmaps provide an array of bits, implemented using an
* array of unsigned longs. The number of valid bits in a
* given bitmap does _not_ need to be an exact multiple of
* BITS_PER_LONG.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 104/156] lib: libcrc32c: delete duplicated words
2020-10-16 2:40 incoming Andrew Morton
` (103 preceding siblings ...)
2020-10-16 3:10 ` [patch 103/156] lib: bitmap: delete duplicated words Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 105/156] lib: decompress_bunzip2: " Andrew Morton
` (61 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: lib: libcrc32c: delete duplicated words
Drop the repeated word "the".
Link: https://lkml.kernel.org/r/20200823040430.25807-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/libcrc32c.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/libcrc32c.c~lib-libcrc32c-delete-duplicated-words
+++ a/lib/libcrc32c.c
@@ -12,7 +12,7 @@
* pages = {},
* month = {June},
*}
- * Used by the iSCSI driver, possibly others, and derived from the
+ * Used by the iSCSI driver, possibly others, and derived from
* the iscsi-crc.c module of the linux-iscsi driver at
* http://linux-iscsi.sourceforge.net.
*
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 105/156] lib: decompress_bunzip2: delete duplicated words
2020-10-16 2:40 incoming Andrew Morton
` (104 preceding siblings ...)
2020-10-16 3:10 ` [patch 104/156] lib: libcrc32c: " Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:10 ` [patch 106/156] lib: dynamic_queue_limits: delete duplicated words + fix typo Andrew Morton
` (60 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: lib: decompress_bunzip2: delete duplicated words
Drop the repeated word "how".
Link: https://lkml.kernel.org/r/20200823040436.25852-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/decompress_bunzip2.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/decompress_bunzip2.c~lib-decompress_bunzip2-delete-duplicated-words
+++ a/lib/decompress_bunzip2.c
@@ -390,7 +390,7 @@ static int INIT get_next_block(struct bu
j = (bd->inbufBits >> bd->inbufBitCount)&
((1 << hufGroup->maxLen)-1);
got_huff_bits:
- /* Figure how how many bits are in next symbol and
+ /* Figure how many bits are in next symbol and
* unget extras */
i = hufGroup->minLen;
while (j > limit[i])
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 106/156] lib: dynamic_queue_limits: delete duplicated words + fix typo
2020-10-16 2:40 incoming Andrew Morton
` (105 preceding siblings ...)
2020-10-16 3:10 ` [patch 105/156] lib: decompress_bunzip2: " Andrew Morton
@ 2020-10-16 3:10 ` Andrew Morton
2020-10-16 3:11 ` [patch 107/156] lib: earlycpio: delete duplicated words Andrew Morton
` (59 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:10 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: lib: dynamic_queue_limits: delete duplicated words + fix typo
Drop the repeated word "the".
Fix spelling of "excess".
Link: https://lkml.kernel.org/r/20200823040449.25946-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/dynamic_queue_limits.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/lib/dynamic_queue_limits.c~lib-dynamic_queue_limits-delete-duplicated-words-fix-typo
+++ a/lib/dynamic_queue_limits.c
@@ -60,8 +60,8 @@ void dql_completed(struct dql *dql, unsi
* A decrease is only considered if the queue has been busy in
* the whole interval (the check above).
*
- * If there is slack, the amount of execess data queued above
- * the the amount needed to prevent starvation, the queue limit
+ * If there is slack, the amount of excess data queued above
+ * the amount needed to prevent starvation, the queue limit
* can be decreased. To avoid hysteresis we consider the
* minimum amount of slack found over several iterations of the
* completion routine.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 107/156] lib: earlycpio: delete duplicated words
2020-10-16 2:40 incoming Andrew Morton
` (106 preceding siblings ...)
2020-10-16 3:10 ` [patch 106/156] lib: dynamic_queue_limits: delete duplicated words + fix typo Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 108/156] lib: radix-tree: " Andrew Morton
` (58 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: lib: earlycpio: delete duplicated words
Drop the repeated word "the".
Link: https://lkml.kernel.org/r/20200823040455.25995-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/earlycpio.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/earlycpio.c~lib-earlycpio-delete-duplicated-words
+++ a/lib/earlycpio.c
@@ -42,7 +42,7 @@ enum cpio_fields {
/**
* cpio_data find_cpio_data - Search for files in an uncompressed cpio
* @path: The directory to search for, including a slash at the end
- * @data: Pointer to the the cpio archive or a header inside
+ * @data: Pointer to the cpio archive or a header inside
* @len: Remaining length of the cpio based on data pointer
* @nextoff: When a matching file is found, this is the offset from the
* beginning of the cpio to the beginning of the next file, not the
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 108/156] lib: radix-tree: delete duplicated words
2020-10-16 2:40 incoming Andrew Morton
` (107 preceding siblings ...)
2020-10-16 3:11 ` [patch 107/156] lib: earlycpio: delete duplicated words Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 109/156] lib: syscall: " Andrew Morton
` (57 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: lib: radix-tree: delete duplicated words
Drop the repeated word "be".
Link: https://lkml.kernel.org/r/20200823040508.26086-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/radix-tree.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/radix-tree.c~lib-radix-tree-delete-duplicated-words
+++ a/lib/radix-tree.c
@@ -325,7 +325,7 @@ static __must_check int __radix_tree_pre
int ret = -ENOMEM;
/*
- * Nodes preloaded by one cgroup can be be used by another cgroup, so
+ * Nodes preloaded by one cgroup can be used by another cgroup, so
* they should never be accounted to any particular memory cgroup.
*/
gfp_mask &= ~__GFP_ACCOUNT;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 109/156] lib: syscall: delete duplicated words
2020-10-16 2:40 incoming Andrew Morton
` (108 preceding siblings ...)
2020-10-16 3:11 ` [patch 108/156] lib: radix-tree: " Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 110/156] lib: test_sysctl: " Andrew Morton
` (56 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: lib: syscall: delete duplicated words
Drop the repeated word "the".
Link: https://lkml.kernel.org/r/20200823040514.26136-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/syscall.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/syscall.c~lib-syscall-delete-duplicated-words
+++ a/lib/syscall.c
@@ -44,7 +44,7 @@ static int collect_syscall(struct task_s
* .data.instruction_pointer - filled with user PC
*
* If @target is blocked in a system call, returns zero with @info.data.nr
- * set to the the call's number and @info.data.args filled in with its
+ * set to the call's number and @info.data.args filled in with its
* arguments. Registers not used for system call arguments may not be available
* and it is not kosher to use &struct user_regset calls while the system
* call is still in progress. Note we may get this result if @target
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 110/156] lib: test_sysctl: delete duplicated words
2020-10-16 2:40 incoming Andrew Morton
` (109 preceding siblings ...)
2020-10-16 3:11 ` [patch 109/156] lib: syscall: " Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 111/156] lib/mpi/mpi-bit.c: fix spello of "functions" Andrew Morton
` (55 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: lib: test_sysctl: delete duplicated words
Drop the repeated word "the".
Link: https://lkml.kernel.org/r/20200823040520.1999-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/test_sysctl.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/test_sysctl.c~lib-test_sysctl-delete-duplicated-words
+++ a/lib/test_sysctl.c
@@ -16,7 +16,7 @@
*/
/*
- * This module provides an interface to the the proc sysctl interfaces. This
+ * This module provides an interface to the proc sysctl interfaces. This
* driver requires CONFIG_PROC_SYSCTL. It will not normally be loaded by the
* system unless explicitly requested by name. You can also build this driver
* into your kernel.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 111/156] lib/mpi/mpi-bit.c: fix spello of "functions"
2020-10-16 2:40 incoming Andrew Morton
` (110 preceding siblings ...)
2020-10-16 3:11 ` [patch 110/156] lib: test_sysctl: " Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 112/156] lib/idr.c: document calling context for IDA APIs mustn't use locks Andrew Morton
` (54 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, mm-commits, rdunlap, torvalds
From: Randy Dunlap <rdunlap@infradead.org>
Subject: lib/mpi/mpi-bit.c: fix spello of "functions"
Fix typo/spello of "functions".
Link: https://lkml.kernel.org/r/8df15173-a6df-9426-7cad-a2d279bf1170@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/mpi/mpi-bit.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/mpi/mpi-bit.c~lib-mpi-fix-spello-of-functions
+++ a/lib/mpi/mpi-bit.c
@@ -1,4 +1,4 @@
-/* mpi-bit.c - MPI bit level fucntions
+/* mpi-bit.c - MPI bit level functions
* Copyright (C) 1998, 1999 Free Software Foundation, Inc.
*
* This file is part of GnuPG.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 112/156] lib/idr.c: document calling context for IDA APIs mustn't use locks
2020-10-16 2:40 incoming Andrew Morton
` (111 preceding siblings ...)
2020-10-16 3:11 ` [patch 111/156] lib/mpi/mpi-bit.c: fix spello of "functions" Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 113/156] lib/idr.c: document that ida_simple_{get,remove}() are deprecated Andrew Morton
` (53 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, corbet, gregkh, mm-commits, swboyd, torvalds, trong, willy
From: Stephen Boyd <swboyd@chromium.org>
Subject: lib/idr.c: document calling context for IDA APIs mustn't use locks
The documentation for these functions indicates that callers don't need to
hold a lock while calling them, but that documentation is only in one
place under "IDA Usage". Let's state the same information on each IDA
function so that it's clear what the calling context requires.
Furthermore, let's document ida_simple_get() with the same information so
that callers know how this API works.
Link: https://lkml.kernel.org/r/20200910055246.2297797-1-swboyd@chromium.org
Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Tri Vo <trong@android.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/idr.h | 9 ++++++---
lib/idr.c | 9 ++++++---
2 files changed, 12 insertions(+), 6 deletions(-)
--- a/include/linux/idr.h~idr-document-calling-context-for-ida-apis-mustnt-use-locks
+++ a/include/linux/idr.h
@@ -263,7 +263,8 @@ void ida_destroy(struct ida *ida);
*
* Allocate an ID between 0 and %INT_MAX, inclusive.
*
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
* Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
* or %-ENOSPC if there are no free IDs.
*/
@@ -280,7 +281,8 @@ static inline int ida_alloc(struct ida *
*
* Allocate an ID between @min and %INT_MAX, inclusive.
*
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
* Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
* or %-ENOSPC if there are no free IDs.
*/
@@ -297,7 +299,8 @@ static inline int ida_alloc_min(struct i
*
* Allocate an ID between 0 and @max, inclusive.
*
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
* Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
* or %-ENOSPC if there are no free IDs.
*/
--- a/lib/idr.c~idr-document-calling-context-for-ida-apis-mustnt-use-locks
+++ a/lib/idr.c
@@ -372,7 +372,8 @@ EXPORT_SYMBOL(idr_replace);
* Allocate an ID between @min and @max, inclusive. The allocated ID will
* not exceed %INT_MAX, even if @max is larger.
*
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
* Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
* or %-ENOSPC if there are no free IDs.
*/
@@ -479,7 +480,8 @@ EXPORT_SYMBOL(ida_alloc_range);
* @ida: IDA handle.
* @id: Previously allocated ID.
*
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
*/
void ida_free(struct ida *ida, unsigned int id)
{
@@ -531,7 +533,8 @@ EXPORT_SYMBOL(ida_free);
* or freed. If the IDA is already empty, there is no need to call this
* function.
*
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
*/
void ida_destroy(struct ida *ida)
{
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 113/156] lib/idr.c: document that ida_simple_{get,remove}() are deprecated
2020-10-16 2:40 incoming Andrew Morton
` (112 preceding siblings ...)
2020-10-16 3:11 ` [patch 112/156] lib/idr.c: document calling context for IDA APIs mustn't use locks Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 114/156] lib/scatterlist.c: avoid a double memset Andrew Morton
` (52 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, corbet, gregkh, mm-commits, swboyd, torvalds, trong, willy
From: Stephen Boyd <swboyd@chromium.org>
Subject: lib/idr.c: document that ida_simple_{get,remove}() are deprecated
These two functions are deprecated. Users should call ida_alloc() or
ida_free() respectively instead. Add documentation to this effect until
the macro can be removed.
Link: https://lkml.kernel.org/r/20200910055246.2297797-2-swboyd@chromium.org
Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Tri Vo <trong@android.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/idr.h | 4 ++++
1 file changed, 4 insertions(+)
--- a/include/linux/idr.h~idr-document-that-ida_simple_getremove-are-deprecated
+++ a/include/linux/idr.h
@@ -314,6 +314,10 @@ static inline void ida_init(struct ida *
xa_init_flags(&ida->xa, IDA_INIT_FLAGS);
}
+/*
+ * ida_simple_get() and ida_simple_remove() are deprecated. Use
+ * ida_alloc() and ida_free() instead respectively.
+ */
#define ida_simple_get(ida, start, end, gfp) \
ida_alloc_range(ida, start, (end) - 1, gfp)
#define ida_simple_remove(ida, id) ida_free(ida, id)
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 114/156] lib/scatterlist.c: avoid a double memset
2020-10-16 2:40 incoming Andrew Morton
` (113 preceding siblings ...)
2020-10-16 3:11 ` [patch 113/156] lib/idr.c: document that ida_simple_{get,remove}() are deprecated Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 115/156] lib/percpu_counter.c: use helper macro abs() Andrew Morton
` (51 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, christophe.jaillet, mm-commits, torvalds
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Subject: lib/scatterlist.c: avoid a double memset
'sgl' is zeroed a few lines below in 'sg_init_table()'. There is no need to
clear it twice.
Remove the redundant initialization.
Link: https://lkml.kernel.org/r/20200920071544.368841-1-christophe.jaillet@wanadoo.fr
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/scatterlist.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/scatterlist.c~lib-scatterlist-avoid-a-double-memset
+++ a/lib/scatterlist.c
@@ -504,7 +504,7 @@ struct scatterlist *sgl_alloc_order(unsi
nalloc++;
}
sgl = kmalloc_array(nalloc, sizeof(struct scatterlist),
- (gfp & ~GFP_DMA) | __GFP_ZERO);
+ gfp & ~GFP_DMA);
if (!sgl)
return NULL;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 115/156] lib/percpu_counter.c: use helper macro abs()
2020-10-16 2:40 incoming Andrew Morton
` (114 preceding siblings ...)
2020-10-16 3:11 ` [patch 114/156] lib/scatterlist.c: avoid a double memset Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 116/156] include/linux/list.h: add a macro to test if entry is pointing to the head Andrew Morton
` (50 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, linmiaohe, mm-commits, torvalds
From: Miaohe Lin <linmiaohe@huawei.com>
Subject: lib/percpu_counter.c: use helper macro abs()
Use helper macro abs() to simplify the "x >= t || x <= -t" cmp.
Link: https://lkml.kernel.org/r/20200927122746.5964-1-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/percpu_counter.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/percpu_counter.c~percpu_counter-use-helper-macro-abs
+++ a/lib/percpu_counter.c
@@ -85,7 +85,7 @@ void percpu_counter_add_batch(struct per
preempt_disable();
count = __this_cpu_read(*fbc->counters) + amount;
- if (count >= batch || count <= -batch) {
+ if (abs(count) >= batch) {
unsigned long flags;
raw_spin_lock_irqsave(&fbc->lock, flags);
fbc->count += count;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 116/156] include/linux/list.h: add a macro to test if entry is pointing to the head
2020-10-16 2:40 incoming Andrew Morton
` (115 preceding siblings ...)
2020-10-16 3:11 ` [patch 115/156] lib/percpu_counter.c: use helper macro abs() Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 117/156] lib/test_hmm.c: fix an error code in dmirror_allocate_chunk() Andrew Morton
` (49 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, andriy.shevchenko, cezary.rojewski, mm-commits, torvalds
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Subject: include/linux/list.h: add a macro to test if entry is pointing to the head
Add a macro to test if entry is pointing to the head of the list which is
useful in cases like:
list_for_each_entry(pos, &head, member) {
if (cond)
break;
}
if (list_entry_is_head(pos, &head, member))
return -ERRNO;
that allows to avoid additional variable to be added to track if loop has
not been stopped in the middle.
While here, convert list_for_each_entry*() family of macros to use a new one.
Link: https://lkml.kernel.org/r/20200929134342.51489-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/list.h | 29 +++++++++++++++++++----------
1 file changed, 19 insertions(+), 10 deletions(-)
--- a/include/linux/list.h~list-add-a-macro-to-test-if-entry-is-pointing-to-the-head
+++ a/include/linux/list.h
@@ -610,6 +610,15 @@ static inline void list_splice_tail_init
pos = n, n = pos->prev)
/**
+ * list_entry_is_head - test if the entry points to the head of the list
+ * @pos: the type * to cursor
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_entry_is_head(pos, head, member) \
+ (&pos->member == (head))
+
+/**
* list_for_each_entry - iterate over list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
@@ -617,7 +626,7 @@ static inline void list_splice_tail_init
*/
#define list_for_each_entry(pos, head, member) \
for (pos = list_first_entry(head, typeof(*pos), member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = list_next_entry(pos, member))
/**
@@ -628,7 +637,7 @@ static inline void list_splice_tail_init
*/
#define list_for_each_entry_reverse(pos, head, member) \
for (pos = list_last_entry(head, typeof(*pos), member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = list_prev_entry(pos, member))
/**
@@ -653,7 +662,7 @@ static inline void list_splice_tail_init
*/
#define list_for_each_entry_continue(pos, head, member) \
for (pos = list_next_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = list_next_entry(pos, member))
/**
@@ -667,7 +676,7 @@ static inline void list_splice_tail_init
*/
#define list_for_each_entry_continue_reverse(pos, head, member) \
for (pos = list_prev_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = list_prev_entry(pos, member))
/**
@@ -679,7 +688,7 @@ static inline void list_splice_tail_init
* Iterate over list of given type, continuing from current position.
*/
#define list_for_each_entry_from(pos, head, member) \
- for (; &pos->member != (head); \
+ for (; !list_entry_is_head(pos, head, member); \
pos = list_next_entry(pos, member))
/**
@@ -692,7 +701,7 @@ static inline void list_splice_tail_init
* Iterate backwards over list of given type, continuing from current position.
*/
#define list_for_each_entry_from_reverse(pos, head, member) \
- for (; &pos->member != (head); \
+ for (; !list_entry_is_head(pos, head, member); \
pos = list_prev_entry(pos, member))
/**
@@ -705,7 +714,7 @@ static inline void list_splice_tail_init
#define list_for_each_entry_safe(pos, n, head, member) \
for (pos = list_first_entry(head, typeof(*pos), member), \
n = list_next_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = n, n = list_next_entry(n, member))
/**
@@ -721,7 +730,7 @@ static inline void list_splice_tail_init
#define list_for_each_entry_safe_continue(pos, n, head, member) \
for (pos = list_next_entry(pos, member), \
n = list_next_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = n, n = list_next_entry(n, member))
/**
@@ -736,7 +745,7 @@ static inline void list_splice_tail_init
*/
#define list_for_each_entry_safe_from(pos, n, head, member) \
for (n = list_next_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = n, n = list_next_entry(n, member))
/**
@@ -752,7 +761,7 @@ static inline void list_splice_tail_init
#define list_for_each_entry_safe_reverse(pos, n, head, member) \
for (pos = list_last_entry(head, typeof(*pos), member), \
n = list_prev_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = n, n = list_prev_entry(n, member))
/**
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 117/156] lib/test_hmm.c: fix an error code in dmirror_allocate_chunk()
2020-10-16 2:40 incoming Andrew Morton
` (116 preceding siblings ...)
2020-10-16 3:11 ` [patch 116/156] include/linux/list.h: add a macro to test if entry is pointing to the head Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 118/156] lib/crc32.c: fix trivial typo in preprocessor condition Andrew Morton
` (48 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, dan.carpenter, dan.j.williams, jgg, jglisse, mm-commits,
rcampbell, sfr, torvalds
From: Dan Carpenter <dan.carpenter@oracle.com>
Subject: lib/test_hmm.c: fix an error code in dmirror_allocate_chunk()
This is supposed to return false on failure, not a negative error code.
Link: https://lkml.kernel.org/r/20201010200812.GA1886610@mwanda
Fixes: 170e38548b81 ("mm/hmm/test: use after free in dmirror_allocate_chunk()")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/test_hmm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/test_hmm.c~mm-hmm-test-fix-an-error-code-in-dmirror_allocate_chunk
+++ a/lib/test_hmm.c
@@ -461,7 +461,7 @@ static bool dmirror_allocate_chunk(struc
devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
if (!devmem)
- return -ENOMEM;
+ return false;
res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
"hmm_dmirror");
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 118/156] lib/crc32.c: fix trivial typo in preprocessor condition
2020-10-16 2:40 incoming Andrew Morton
` (117 preceding siblings ...)
2020-10-16 3:11 ` [patch 117/156] lib/test_hmm.c: fix an error code in dmirror_allocate_chunk() Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 119/156] bitops: simplify get_count_order_long() Andrew Morton
` (47 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, corbet, kernel, krzk, mchehab+huawei, mm-commits, torvalds
From: Tobias Jordan <kernel@cdqe.de>
Subject: lib/crc32.c: fix trivial typo in preprocessor condition
Whether crc32_be needs a lookup table is chosen based on CRC_LE_BITS.
Obviously, the _be function should be governed by the _BE_ define.
This probably never pops up as it's hard to come up with a configuration
where CRC_BE_BITS isn't the same as CRC_LE_BITS and as nobody is using
bitwise CRC anyway.
Link: https://lkml.kernel.org/r/20200923182122.GA3338@agrajag.zerfleddert.de
Fixes: 46c5801eaf86 ("crc32: bolt on crc32c")
Signed-off-by: Tobias Jordan <kernel@cdqe.de>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/crc32.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/crc32.c~lib-crc32c-fix-trivial-typo-in-preprocessor-condition
+++ a/lib/crc32.c
@@ -331,7 +331,7 @@ static inline u32 __pure crc32_be_generi
return crc;
}
-#if CRC_LE_BITS == 1
+#if CRC_BE_BITS == 1
u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
{
return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 119/156] bitops: simplify get_count_order_long()
2020-10-16 2:40 incoming Andrew Morton
` (118 preceding siblings ...)
2020-10-16 3:11 ` [patch 118/156] lib/crc32.c: fix trivial typo in preprocessor condition Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 120/156] bitops: use the same mechanism for get_count_order[_long] Andrew Morton
` (46 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, andriy.shevchenko, christian.brauner, mm-commits,
richard.weiyang, torvalds
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Subject: bitops: simplify get_count_order_long()
These two cases could be unified into one.
Link: https://lkml.kernel.org/r/20200807085837.11697-2-richard.weiyang@linux.alibaba.com
Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/bitops.h | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
--- a/include/linux/bitops.h~bitops-simplify-get_count_order_long
+++ a/include/linux/bitops.h
@@ -206,10 +206,7 @@ static inline int get_count_order_long(u
{
if (l == 0UL)
return -1;
- else if (l & (l - 1UL))
- return (int)fls_long(l);
- else
- return (int)fls_long(l) - 1;
+ return (int)fls_long(--l);
}
/**
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 120/156] bitops: use the same mechanism for get_count_order[_long]
2020-10-16 2:40 incoming Andrew Morton
` (119 preceding siblings ...)
2020-10-16 3:11 ` [patch 119/156] bitops: simplify get_count_order_long() Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 121/156] checkpatch: add --kconfig-prefix Andrew Morton
` (45 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, andriy.shevchenko, christian.brauner, mm-commits,
richard.weiyang, torvalds
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Subject: bitops: use the same mechanism for get_count_order[_long]
These two functions share the same logic.
Link: https://lkml.kernel.org/r/20200807085837.11697-3-richard.weiyang@linux.alibaba.com
Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/bitops.h | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
--- a/include/linux/bitops.h~bitops-use-the-same-mechanism-for-get_count_order
+++ a/include/linux/bitops.h
@@ -188,12 +188,10 @@ static inline unsigned fls_long(unsigned
static inline int get_count_order(unsigned int count)
{
- int order;
+ if (count == 0)
+ return -1;
- order = fls(count) - 1;
- if (count & (count - 1))
- order++;
- return order;
+ return fls(--count);
}
/**
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 121/156] checkpatch: add --kconfig-prefix
2020-10-16 2:40 incoming Andrew Morton
` (120 preceding siblings ...)
2020-10-16 3:11 ` [patch 120/156] bitops: use the same mechanism for get_count_order[_long] Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 122/156] checkpatch: move repeated word test Andrew Morton
` (44 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, jerome, joe, mm-commits, torvalds
From: Jerome Forissier <jerome@forissier.org>
Subject: checkpatch: add --kconfig-prefix
Kconfig allows to customize the CONFIG_ prefix via the $CONFIG_
environment variable. Out-of-tree projects may therefore use Kconfig with
a different prefix, or they may use a custom configuration tool which does
not use the CONFIG_ prefix at all. Such projects may still want to adhere
to the Linux kernel coding style and run checkpatch.pl.
One example is OP-TEE [1] which does not use Kconfig but does have
configuration options prefixed with CFG_. It also mostly follows the
kernel coding style and therefore being able to use checkpatch is quite
valuable.
To make this possible, add the --kconfig-prefix command line option.
[1] https://github.com/OP-TEE/optee_os
Link: http://lkml.kernel.org/r/20200818081732.800449-1-jerome@forissier.org
Signed-off-by: Jerome Forissier <jerome@forissier.org>
Acked-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
--- a/scripts/checkpatch.pl~checkpatch-add-kconfig-prefix
+++ a/scripts/checkpatch.pl
@@ -65,6 +65,7 @@ my $allow_c99_comments = 1; # Can be ove
# git output parsing needs US English output, so first set backtick child process LANGUAGE
my $git_command ='export LANGUAGE=en_US.UTF-8; git';
my $tabsize = 8;
+my ${CONFIG_} = "CONFIG_";
sub help {
my ($exitcode) = @_;
@@ -127,6 +128,8 @@ Options:
--typedefsfile Read additional types from this file
--color[=WHEN] Use colors 'always', 'never', or only when output
is a terminal ('auto'). Default is 'auto'.
+ --kconfig-prefix=WORD use WORD as a prefix for Kconfig symbols (default
+ ${CONFIG_})
-h, --help, --version display this help and exit
When FILE is - read standard input.
@@ -235,6 +238,7 @@ GetOptions(
'color=s' => \$color,
'no-color' => \$color, #keep old behaviors of -nocolor
'nocolor' => \$color, #keep old behaviors of -nocolor
+ 'kconfig-prefix=s' => \${CONFIG_},
'h|help' => \$help,
'version' => \$help
) or help(1);
@@ -6524,16 +6528,16 @@ sub process {
}
# check for IS_ENABLED() without CONFIG_<FOO> ($rawline for comments too)
- if ($rawline =~ /\bIS_ENABLED\s*\(\s*(\w+)\s*\)/ && $1 !~ /^CONFIG_/) {
+ if ($rawline =~ /\bIS_ENABLED\s*\(\s*(\w+)\s*\)/ && $1 !~ /^${CONFIG_}/) {
WARN("IS_ENABLED_CONFIG",
- "IS_ENABLED($1) is normally used as IS_ENABLED(CONFIG_$1)\n" . $herecurr);
+ "IS_ENABLED($1) is normally used as IS_ENABLED(${CONFIG_}$1)\n" . $herecurr);
}
# check for #if defined CONFIG_<FOO> || defined CONFIG_<FOO>_MODULE
- if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(CONFIG_[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) {
+ if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(${CONFIG_}[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) {
my $config = $1;
if (WARN("PREFER_IS_ENABLED",
- "Prefer IS_ENABLED(<FOO>) to CONFIG_<FOO> || CONFIG_<FOO>_MODULE\n" . $herecurr) &&
+ "Prefer IS_ENABLED(<FOO>) to ${CONFIG_}<FOO> || ${CONFIG_}<FOO>_MODULE\n" . $herecurr) &&
$fix) {
$fixed[$fixlinenr] = "\+#if IS_ENABLED($config)";
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 122/156] checkpatch: move repeated word test
2020-10-16 2:40 incoming Andrew Morton
` (121 preceding siblings ...)
2020-10-16 3:11 ` [patch 121/156] checkpatch: add --kconfig-prefix Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 123/156] checkpatch: add test for comma use that should be semicolon Andrew Morton
` (43 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, joe, mm-commits, torvalds
From: Joe Perches <joe@perches.com>
Subject: checkpatch: move repeated word test
Currently this test only works on .[ch] files.
Move the test to check more file types and the commit log.
Link: http://lkml.kernel.org/r/180b3b5677771c902b2e2f7a2b7090ede65fe004.camel@perches.com
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 72 ++++++++++++++++++++--------------------
1 file changed, 36 insertions(+), 36 deletions(-)
--- a/scripts/checkpatch.pl~checkpatch-move-repeated-word-test
+++ a/scripts/checkpatch.pl
@@ -2991,6 +2991,42 @@ sub process {
}
}
+# check for repeated words separated by a single space
+ if ($rawline =~ /^\+/ || $in_commit_log) {
+ while ($rawline =~ /\b($word_pattern) (?=($word_pattern))/g) {
+
+ my $first = $1;
+ my $second = $2;
+
+ if ($first =~ /(?:struct|union|enum)/) {
+ pos($rawline) += length($first) + length($second) + 1;
+ next;
+ }
+
+ next if ($first ne $second);
+ next if ($first eq 'long');
+
+ if (WARN("REPEATED_WORD",
+ "Possible repeated word: '$first'\n" . $herecurr) &&
+ $fix) {
+ $fixed[$fixlinenr] =~ s/\b$first $second\b/$first/;
+ }
+ }
+
+ # if it's a repeated word on consecutive lines in a comment block
+ if ($prevline =~ /$;+\s*$/ &&
+ $prevrawline =~ /($word_pattern)\s*$/) {
+ my $last_word = $1;
+ if ($rawline =~ /^\+\s*\*\s*$last_word /) {
+ if (WARN("REPEATED_WORD",
+ "Possible repeated word: '$last_word'\n" . $hereprev) &&
+ $fix) {
+ $fixed[$fixlinenr] =~ s/(\+\s*\*\s*)$last_word /$1/;
+ }
+ }
+ }
+ }
+
# ignore non-hunk lines and lines being removed
next if (!$hunk_line || $line =~ /^-/);
@@ -3314,42 +3350,6 @@ sub process {
}
}
-# check for repeated words separated by a single space
- if ($rawline =~ /^\+/) {
- while ($rawline =~ /\b($word_pattern) (?=($word_pattern))/g) {
-
- my $first = $1;
- my $second = $2;
-
- if ($first =~ /(?:struct|union|enum)/) {
- pos($rawline) += length($first) + length($second) + 1;
- next;
- }
-
- next if ($first ne $second);
- next if ($first eq 'long');
-
- if (WARN("REPEATED_WORD",
- "Possible repeated word: '$first'\n" . $herecurr) &&
- $fix) {
- $fixed[$fixlinenr] =~ s/\b$first $second\b/$first/;
- }
- }
-
- # if it's a repeated word on consecutive lines in a comment block
- if ($prevline =~ /$;+\s*$/ &&
- $prevrawline =~ /($word_pattern)\s*$/) {
- my $last_word = $1;
- if ($rawline =~ /^\+\s*\*\s*$last_word /) {
- if (WARN("REPEATED_WORD",
- "Possible repeated word: '$last_word'\n" . $hereprev) &&
- $fix) {
- $fixed[$fixlinenr] =~ s/(\+\s*\*\s*)$last_word /$1/;
- }
- }
- }
- }
-
# check for space before tabs.
if ($rawline =~ /^\+/ && $rawline =~ / \t/) {
my $herevet = "$here\n" . cat_vet($rawline) . "\n";
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 123/156] checkpatch: add test for comma use that should be semicolon
2020-10-16 2:40 incoming Andrew Morton
` (122 preceding siblings ...)
2020-10-16 3:11 ` [patch 122/156] checkpatch: move repeated word test Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:11 ` [patch 124/156] const_structs.checkpatch: add phy_ops Andrew Morton
` (42 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, joe, mm-commits, torvalds
From: Joe Perches <joe@perches.com>
Subject: checkpatch: add test for comma use that should be semicolon
There are commas used as statement terminations that should typically have
used semicolons instead. Only direct assignments or use of a single
function or value on a single line are detected by this test.
e.g.:
foo = bar(), /* typical use is semicolon not comma */
bar = baz();
Add an imperfect test to detect these comma uses.
No false positives were found in testing, but many types of false
negatives are possible.
e.g.:
foo = bar() + 1, /* comma use, but not direct assignment */
bar = baz();
Link: https://lkml.kernel.org/r/3bf27caf462007dfa75647b040ab3191374a59de.camel@perches.com
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 11 +++++++++++
1 file changed, 11 insertions(+)
--- a/scripts/checkpatch.pl~checkpatch-add-test-for-comma-use-that-should-be-semicolon
+++ a/scripts/checkpatch.pl
@@ -4940,6 +4940,17 @@ sub process {
}
}
+# check if a statement with a comma should be two statements like:
+# foo = bar(), /* comma should be semicolon */
+# bar = baz();
+ if (defined($stat) &&
+ $stat =~ /^\+\s*(?:$Lval\s*$Assignment\s*)?$FuncArg\s*,\s*(?:$Lval\s*$Assignment\s*)?$FuncArg\s*;\s*$/) {
+ my $cnt = statement_rawlines($stat);
+ my $herectx = get_stat_here($linenr, $cnt, $here);
+ WARN("SUSPECT_COMMA_SEMICOLON",
+ "Possible comma where semicolon could be used\n" . $herectx);
+ }
+
# return is not a function
if (defined($stat) && $stat =~ /^.\s*return(\s*)\(/s) {
my $spacing = $1;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 124/156] const_structs.checkpatch: add phy_ops
2020-10-16 2:40 incoming Andrew Morton
` (123 preceding siblings ...)
2020-10-16 3:11 ` [patch 123/156] checkpatch: add test for comma use that should be semicolon Andrew Morton
@ 2020-10-16 3:11 ` Andrew Morton
2020-10-16 3:12 ` [patch 125/156] checkpatch: warn if trace_printk and friends are called Andrew Morton
` (41 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:11 UTC (permalink / raw)
To: akpm, joe, kishon, mm-commits, rikard.falkeborn, torvalds, vkoul
From: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Subject: const_structs.checkpatch: add phy_ops
All usages of phy_ops in include/linux uses const phy_ops * and all
instances of phy_ops in the kernel that are not const already can be made
const (patches have been posted for those separately).
Link: https://lkml.kernel.org/r/20200824214132.9072-1-rikard.falkeborn@gmail.com
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Suggested-by: Joe Perches <joe@perches.com>
Cc: Kishon Vijay Abraham I <kishon@ti.com>
Cc: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/const_structs.checkpatch | 1 +
1 file changed, 1 insertion(+)
--- a/scripts/const_structs.checkpatch~const_structscheckpatch-add-phy_ops
+++ a/scripts/const_structs.checkpatch
@@ -39,6 +39,7 @@ nlmsvc_binding
nvkm_device_chip
of_device_id
pci_raw_ops
+phy_ops
pipe_buf_operations
platform_hibernation_ops
platform_suspend_ops
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 125/156] checkpatch: warn if trace_printk and friends are called
2020-10-16 2:40 incoming Andrew Morton
` (124 preceding siblings ...)
2020-10-16 3:11 ` [patch 124/156] const_structs.checkpatch: add phy_ops Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 126/156] const_structs.checkpatch: add pinctrl_ops and pinmux_ops Andrew Morton
` (40 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, drinkcat, joe, mm-commits, rostedt, torvalds
From: Nicolas Boichat <drinkcat@chromium.org>
Subject: checkpatch: warn if trace_printk and friends are called
trace_printk is meant as a debugging tool, and should not be compiled into
production code without specific debug Kconfig options enabled, or source
code changes, as indicated by the warning that shows up on boot if any
trace_printk is called:
** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **
** **
** trace_printk() being used. Allocating extra memory. **
** **
** This means that this is a DEBUG kernel and it is **
** unsafe for production use. **
Let's warn developers when they try to submit such a change.
Link: https://lkml.kernel.org/r/20200825193600.v2.1.I723c43c155f02f726c97501be77984f1e6bb740a@changeid
Signed-off-by: Nicolas Boichat <drinkcat@chromium.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 6 ++++++
1 file changed, 6 insertions(+)
--- a/scripts/checkpatch.pl~checkpatch-warn-if-trace_printk-and-friends-are-called
+++ a/scripts/checkpatch.pl
@@ -4274,6 +4274,12 @@ sub process {
"Prefer dev_$level(... to dev_printk(KERN_$orig, ...\n" . $herecurr);
}
+# trace_printk should not be used in production code.
+ if ($line =~ /\b(trace_printk|trace_puts|ftrace_vprintk)\s*\(/) {
+ WARN("TRACE_PRINTK",
+ "Do not use $1() in production code (this can be ignored if built only with a debug config option)\n" . $herecurr);
+ }
+
# ENOSYS means "bad syscall nr" and nothing else. This will have a small
# number of false positives, but assembly files are not checked, so at
# least the arch entry code will not trigger this warning.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 126/156] const_structs.checkpatch: add pinctrl_ops and pinmux_ops
2020-10-16 2:40 incoming Andrew Morton
` (125 preceding siblings ...)
2020-10-16 3:12 ` [patch 125/156] checkpatch: warn if trace_printk and friends are called Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 127/156] checkpatch: warn on self-assignments Andrew Morton
` (39 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: afaerber, akpm, joe, linus.walleij, manivannan.sadhasivam,
mm-commits, rikard.falkeborn, torvalds
From: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Subject: const_structs.checkpatch: add pinctrl_ops and pinmux_ops
All usages of include/linux of these are const pointers, and all instances
in the kernel except one, that are not const can be made const (patches
have been posted for those separately).
Link: https://lkml.kernel.org/r/20200830224352.37114-1-rikard.falkeborn@gmail.com
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Cc: Joe Perches <joe@perches.com>
Cc: Andreas Färber <afaerber@suse.de>
Cc: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/const_structs.checkpatch | 2 ++
1 file changed, 2 insertions(+)
--- a/scripts/const_structs.checkpatch~const_structscheckpatch-add-pinctrl_ops-and-pinmux_ops
+++ a/scripts/const_structs.checkpatch
@@ -40,6 +40,8 @@ nvkm_device_chip
of_device_id
pci_raw_ops
phy_ops
+pinctrl_ops
+pinmux_ops
pipe_buf_operations
platform_hibernation_ops
platform_suspend_ops
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 127/156] checkpatch: warn on self-assignments
2020-10-16 2:40 incoming Andrew Morton
` (126 preceding siblings ...)
2020-10-16 3:12 ` [patch 126/156] const_structs.checkpatch: add pinctrl_ops and pinmux_ops Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 128/156] checkpatch: allow not using -f with files that are in git Andrew Morton
` (38 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, efremov, gustavoars, joe, julia.lawall, keescook,
mm-commits, torvalds
From: Joe Perches <joe@perches.com>
Subject: checkpatch: warn on self-assignments
The uninitialized_var() macro was removed recently via commit 63a0895d960a
("compiler: Remove uninitialized_var() macro") as it's not a particularly
useful warning and its use can "paper over real bugs".
Add a checkpatch test to warn on self-assignments as a means to avoid
compiler warnings and as a back-door mechanism to reproduce the old
uninitialized_var macro behavior.
[akpm@linux-foundation.org: coding style fixes]
Link: https://lkml.kernel.org/r/afc2cffdd315d3e4394af149278df9e8af7f49f4.camel@perches.com
Signed-off-by: Joe Perches <joe@perches.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: Denis Efremov <efremov@linux.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 11 +++++++++++
1 file changed, 11 insertions(+)
--- a/scripts/checkpatch.pl~checkpatch-warn-on-self-assignments
+++ a/scripts/checkpatch.pl
@@ -3899,6 +3899,17 @@ sub process {
#ignore lines not being added
next if ($line =~ /^[^\+]/);
+# check for self assignments used to avoid compiler warnings
+# e.g.: int foo = foo, *bar = NULL;
+# struct foo bar = *(&(bar));
+ if ($line =~ /^\+\s*(?:$Declare)?([A-Za-z_][A-Za-z\d_]*)\s*=/) {
+ my $var = $1;
+ if ($line =~ /^\+\s*(?:$Declare)?$var\s*=\s*(?:$var|\*\s*\(?\s*&\s*\(?\s*$var\s*\)?\s*\)?)\s*[;,]/) {
+ WARN("SELF_ASSIGNMENT",
+ "Do not use self-assignments to avoid compiler warnings\n" . $herecurr);
+ }
+ }
+
# check for dereferences that span multiple lines
if ($prevline =~ /^\+.*$Lval\s*(?:\.|->)\s*$/ &&
$line =~ /^\+\s*(?!\#\s*(?!define\s+|if))\s*$Lval/) {
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 128/156] checkpatch: allow not using -f with files that are in git
2020-10-16 2:40 incoming Andrew Morton
` (127 preceding siblings ...)
2020-10-16 3:12 ` [patch 127/156] checkpatch: warn on self-assignments Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 129/156] checkpatch: extend author Signed-off-by check for split From: header Andrew Morton
` (37 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, joe, julia.lawall, linux, mm-commits, torvalds
From: Joe Perches <joe@perches.com>
Subject: checkpatch: allow not using -f with files that are in git
If a file exists in git and checkpatch is used without the -f flag for
scanning a file, then checkpatch will scan the file assuming it's a patch
and emit:
ERROR: Does not appear to be a unified-diff format patch
Change the behavior to assume the -f flag if the file exists in git.
[joe@perches.com: fix git "fatal" warning if file argument outside kernel tree]
Link: https://lkml.kernel.org/r/b6afa04112d450c2fc120a308d706acd60cee294.camel@perches.com
Link: https://lkml.kernel.org/r/45b81a48e1568bd0126a96f5046eb7aaae9b83c9.camel@perches.com
Signed-off-by: Joe Perches <joe@perches.com>
Reviewed-by: Julia Lawall <julia.lawall@inria.fr>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 14 ++++++++++++++
1 file changed, 14 insertions(+)
--- a/scripts/checkpatch.pl~checkpatch-allow-not-using-f-with-files-that-are-in-git
+++ a/scripts/checkpatch.pl
@@ -974,6 +974,16 @@ sub seed_camelcase_includes {
}
}
+sub git_is_single_file {
+ my ($filename) = @_;
+
+ return 0 if ((which("git") eq "") || !(-e "$gitroot"));
+
+ my $output = `${git_command} ls-files -- $filename 2>/dev/null`;
+ my $count = $output =~ tr/\n//;
+ return $count eq 1 && $output =~ m{^${filename}$};
+}
+
sub git_commit_info {
my ($commit, $id, $desc) = @_;
@@ -1047,6 +1057,9 @@ my $vname;
$allow_c99_comments = !defined $ignore_type{"C99_COMMENT_TOLERANCE"};
for my $filename (@ARGV) {
my $FILE;
+ my $is_git_file = git_is_single_file($filename);
+ my $oldfile = $file;
+ $file = 1 if ($is_git_file);
if ($git) {
open($FILE, '-|', "git format-patch -M --stdout -1 $filename") ||
die "$P: $filename: git format-patch failed - $!\n";
@@ -1091,6 +1104,7 @@ for my $filename (@ARGV) {
@modifierListFile = ();
@typeListFile = ();
build_types();
+ $file = $oldfile if ($is_git_file);
}
if (!$quiet) {
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 129/156] checkpatch: extend author Signed-off-by check for split From: header
2020-10-16 2:40 incoming Andrew Morton
` (128 preceding siblings ...)
2020-10-16 3:12 ` [patch 128/156] checkpatch: allow not using -f with files that are in git Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 130/156] checkpatch: emit a warning on embedded filenames Andrew Morton
` (36 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, dwaipayanray1, joe, lukas.bulwahn, mm-commits, torvalds
From: Dwaipayan Ray <dwaipayanray1@gmail.com>
Subject: checkpatch: extend author Signed-off-by check for split From: header
Checkpatch did not handle cases where the author From: header was split
into multiple lines. The author identity could not be resolved and
checkpatch generated a false NO_AUTHOR_SIGN_OFF warning.
A typical example is commit e33bcbab16d1 ("tee: add support for session's
client UUID generation"). When checkpatch was run on this commit, it
displayed:
"WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal
patch author ''"
This was due to split header lines not being handled properly and the
author himself wrote in commit cd2614967d8b ("checkpatch: warn if missing
author Signed-off-by"):
"Split From: headers are not fully handled: only the first part
is compared."
Support split From: headers by correctly parsing the header extension
lines. RFC 5322, Section-2.2.3 stated that each extended line must start
with a WSP character (a space or htab). The solution was therefore to
concatenate the lines which start with a WSP to get the correct long
header.
Link: https://lore.kernel.org/linux-kernel-mentees/f5d8124e54a50480b0a9fa638787bc29b6e09854.camel@perches.com/
Link: https://lkml.kernel.org/r/20200921085436.63003-1-dwaipayanray1@gmail.com
Signed-off-by: Dwaipayan Ray <dwaipayanray1@gmail.com>
Suggested-by: Joe Perches <joe@perches.com>
Reviewed-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Tested-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Acked-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 4 ++++
1 file changed, 4 insertions(+)
--- a/scripts/checkpatch.pl~checkpatch-extend-author-signed-off-by-check-for-split-from-header
+++ a/scripts/checkpatch.pl
@@ -2679,6 +2679,10 @@ sub process {
# Check the patch for a From:
if (decode("MIME-Header", $line) =~ /^From:\s*(.*)/) {
$author = $1;
+ my $curline = $linenr;
+ while(defined($rawlines[$curline]) && ($rawlines[$curline++] =~ /^[ \t]\s*(.*)/)) {
+ $author .= $1;
+ }
$author = encode("utf8", $author) if ($line =~ /=\?utf-8\?/i);
$author =~ s/"//g;
$author = reformat_email($author);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 130/156] checkpatch: emit a warning on embedded filenames
2020-10-16 2:40 incoming Andrew Morton
` (129 preceding siblings ...)
2020-10-16 3:12 ` [patch 129/156] checkpatch: extend author Signed-off-by check for split From: header Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 131/156] checkpatch: fix multi-statement macro checks for while blocks Andrew Morton
` (35 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, joe, mm-commits, torvalds
From: Joe Perches <joe@perches.com>
Subject: checkpatch: emit a warning on embedded filenames
Embedding the complete filename path inside the file isn't particularly
useful as often the path is moved around and becomes incorrect.
Emit a warning when the source contains the filename.
[akpm@linux-foundation.org: remove stray " di"]
Link: https://lkml.kernel.org/r/1fd5f9188a14acdca703ca00301ee323de672a8d.camel@perches.com
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 6 ++++++
1 file changed, 6 insertions(+)
--- a/scripts/checkpatch.pl~checkpatch-emit-a-warning-on-embedded-filenames
+++ a/scripts/checkpatch.pl
@@ -3271,6 +3271,12 @@ sub process {
}
}
+# check for embedded filenames
+ if ($rawline =~ /^\+.*\Q$realfile\E/) {
+ WARN("EMBEDDED_FILENAME",
+ "It's generally not useful to have the filename in the file\n" . $herecurr);
+ }
+
# check we are in a valid source file if not then ignore this hunk
next if ($realfile !~ /\.(h|c|s|S|sh|dtsi|dts)$/);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 131/156] checkpatch: fix multi-statement macro checks for while blocks.
2020-10-16 2:40 incoming Andrew Morton
` (130 preceding siblings ...)
2020-10-16 3:12 ` [patch 130/156] checkpatch: emit a warning on embedded filenames Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 132/156] checkpatch: fix false positive on empty block comment lines Andrew Morton
` (34 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, dwaipayanray1, joe, mm-commits, torvalds
From: Dwaipayan Ray <dwaipayanray1@gmail.com>
Subject: checkpatch: fix multi-statement macro checks for while blocks.
Checkpatch.pl doesn't have a check for excluding while (...) {...} blocks
from MULTISTATEMENT_MACRO_USE_DO_WHILE error.
For example, running checkpatch.pl on the file mm/maccess.c in the kernel
generates the following error:
ERROR: Macros with complex values should be enclosed in parentheses
+#define copy_from_kernel_nofault_loop(dst, src, len, type, err_label) \
+ while (len >= sizeof(type)) { \
+ __get_kernel_nofault(dst, src, type, err_label); \
+ dst += sizeof(type); \
+ src += sizeof(type); \
+ len -= sizeof(type); \
+ }
The error is misleading for this case. Enclosing it in parentheses
doesn't make any sense.
Checkpatch already has an exception list for such common macro types.
Added a new exception for while (...) {...} style blocks to the same.
In addition, the brace flatten logic was modified by changing the
substitution characters from "1" to "1u". This was done to ensure that
macros in the form "#define foo(bar) while(bar){bar--;}" were also
correctly procecssed.
Link: https://lore.kernel.org/linux-kernel-mentees/dc985938aa3986702815a0bd68dfca8a03c85447.camel@perches.com/
Link: https://lkml.kernel.org/r/20201001171903.312021-1-dwaipayanray1@gmail.com
Signed-off-by: Dwaipayan Ray <dwaipayanray1@gmail.com>
Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
--- a/scripts/checkpatch.pl~checkpatch-fix-multi-statement-macro-checks-for-while-blocks
+++ a/scripts/checkpatch.pl
@@ -5351,9 +5351,9 @@ sub process {
$dstat =~ s/\s*$//s;
# Flatten any parentheses and braces
- while ($dstat =~ s/\([^\(\)]*\)/1/ ||
- $dstat =~ s/\{[^\{\}]*\}/1/ ||
- $dstat =~ s/.\[[^\[\]]*\]/1/)
+ while ($dstat =~ s/\([^\(\)]*\)/1u/ ||
+ $dstat =~ s/\{[^\{\}]*\}/1u/ ||
+ $dstat =~ s/.\[[^\[\]]*\]/1u/)
{
}
@@ -5394,6 +5394,7 @@ sub process {
$dstat !~ /^\.$Ident\s*=/ && # .foo =
$dstat !~ /^(?:\#\s*$Ident|\#\s*$Constant)\s*$/ && # stringification #foo
$dstat !~ /^do\s*$Constant\s*while\s*$Constant;?$/ && # do {...} while (...); // do {...} while (...)
+ $dstat !~ /^while\s*$Constant\s*$Constant\s*$/ && # while (...) {...}
$dstat !~ /^for\s*$Constant$/ && # for (...)
$dstat !~ /^for\s*$Constant\s+(?:$Ident|-?$Constant)$/ && # for (...) bar()
$dstat !~ /^do\s*{/ && # do {...
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 132/156] checkpatch: fix false positive on empty block comment lines
2020-10-16 2:40 incoming Andrew Morton
` (131 preceding siblings ...)
2020-10-16 3:12 ` [patch 131/156] checkpatch: fix multi-statement macro checks for while blocks Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 133/156] checkpatch: add new warnings to author signoff checks Andrew Morton
` (33 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, b.zolnierkie, joe, l.stelmach, m.szyprowski, mm-commits, torvalds
From: Łukasz Stelmach <l.stelmach@samsung.com>
Subject: checkpatch: fix false positive on empty block comment lines
To avoid false positives in presence of SPDX-License-Identifier in
networking files it is required to increase the leeway for empty block
comment lines by one line.
For example, checking drivers/net/loopback.c which starts with
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
rsults in an unnecessary warning
WARNING: networking block comments don't use an empty /* line, use /* Comment...
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
Link: https://lkml.kernel.org/r/20201006083509.19934-1-l.stelmach@samsung.com
Signed-off-by: Łukasz Stelmach <l.stelmach@samsung.com>
Acked-by: Joe Perches <joe@perches.com>
Cc: Bartłomiej Żolnierkiewicz <b.zolnierkie@samsung.co>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/scripts/checkpatch.pl~checkpatch-fix-false-positive-on-empty-block-comment-lines
+++ a/scripts/checkpatch.pl
@@ -3464,7 +3464,7 @@ sub process {
if ($realfile =~ m@^(drivers/net/|net/)@ &&
$prevrawline =~ /^\+[ \t]*\/\*[ \t]*$/ &&
$rawline =~ /^\+[ \t]*\*/ &&
- $realline > 2) {
+ $realline > 3) { # Do not warn about the initial copyright comment block after SPDX-License-Identifier
WARN("NETWORKING_BLOCK_COMMENT_STYLE",
"networking block comments don't use an empty /* line, use /* Comment...\n" . $hereprev);
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 133/156] checkpatch: add new warnings to author signoff checks.
2020-10-16 2:40 incoming Andrew Morton
` (132 preceding siblings ...)
2020-10-16 3:12 ` [patch 132/156] checkpatch: fix false positive on empty block comment lines Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 134/156] fs/binfmt_elf: use PT_LOAD p_align values for suitable start address Andrew Morton
` (32 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, dwaipayanray1, joe, mm-commits, torvalds
From: Dwaipayan Ray <dwaipayanray1@gmail.com>
Subject: checkpatch: add new warnings to author signoff checks.
The author signed-off-by checks are currently very vague. Cases like same
name or same address are not handled separately.
For example, running checkpatch on commit be6577af0cef ("parisc: Add
atomic64_set_release() define to avoid CPU soft lockups"), gives:
WARNING: Missing Signed-off-by: line by nominal patch author
'John David Anglin <dave.anglin@bell.net>'
The signoff line was:
"Signed-off-by: Dave Anglin <dave.anglin@bell.net>"
Clearly the author has signed off but with a slightly different version
of his name. A more appropriate warning would have been to point out
at the name mismatch instead.
Previously, the values assumed by $authorsignoff were either 0 or 1
to indicate whether a proper sign off by author is present.
Extended the checks to handle four new cases.
$authorsignoff values now denote the following:
0: Missing sign off by patch author.
1: Sign off present and identical.
2: Addresses and names match, but comments differ.
"James Watson(JW) <james@gmail.com>", "James Watson <james@gmail.com>"
3: Addresses match, but names are different.
"James Watson <james@gmail.com>", "James <james@gmail.com>"
4: Names match, but addresses are different.
"James Watson <james@watson.com>", "James Watson <james@gmail.com>"
5: Names match, addresses excluding subaddress details (RFC 5233) match.
"James Watson <james@gmail.com>", "James Watson <james+a@gmail.com>"
Also introduced a new message type FROM_SIGN_OFF_MISMATCH
for cases 2, 3, 4 and 5.
Link: https://lore.kernel.org/linux-kernel-mentees/c1ca28e77e8e3bfa7aadf3efa8ed70f97a9d369c.camel@perches.com/
Link: https://lkml.kernel.org/r/20201007192029.551744-1-dwaipayanray1@gmail.com
Signed-off-by: Dwaipayan Ray <dwaipayanray1@gmail.com>
Suggested-by: Joe Perches <joe@perches.com>
Acked-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/checkpatch.pl | 93 +++++++++++++++++++++++++++++++++-------
1 file changed, 77 insertions(+), 16 deletions(-)
--- a/scripts/checkpatch.pl~checkpatch-add-new-warnings-to-author-signoff-checks
+++ a/scripts/checkpatch.pl
@@ -1181,10 +1181,10 @@ sub parse_email {
}
}
+ $comment = trim($comment);
$name = trim($name);
$name =~ s/^\"|\"$//g;
- $name =~ s/(\s*\([^\)]+\))\s*//;
- if (defined($1)) {
+ if ($name =~ s/(\s*\([^\)]+\))\s*//) {
$name_comment = trim($1);
}
$address = trim($address);
@@ -1199,10 +1199,12 @@ sub parse_email {
}
sub format_email {
- my ($name, $address) = @_;
+ my ($name, $name_comment, $address, $comment) = @_;
my $formatted_email;
+ $name_comment = trim($name_comment);
+ $comment = trim($comment);
$name = trim($name);
$name =~ s/^\"|\"$//g;
$address = trim($address);
@@ -1215,9 +1217,9 @@ sub format_email {
if ("$name" eq "") {
$formatted_email = "$address";
} else {
- $formatted_email = "$name <$address>";
+ $formatted_email = "$name$name_comment <$address>";
}
-
+ $formatted_email .= "$comment";
return $formatted_email;
}
@@ -1225,17 +1227,23 @@ sub reformat_email {
my ($email) = @_;
my ($email_name, $name_comment, $email_address, $comment) = parse_email($email);
- return format_email($email_name, $email_address);
+ return format_email($email_name, $name_comment, $email_address, $comment);
}
sub same_email_addresses {
- my ($email1, $email2) = @_;
+ my ($email1, $email2, $match_comment) = @_;
my ($email1_name, $name1_comment, $email1_address, $comment1) = parse_email($email1);
my ($email2_name, $name2_comment, $email2_address, $comment2) = parse_email($email2);
+ if ($match_comment != 1) {
+ return $email1_name eq $email2_name &&
+ $email1_address eq $email2_address;
+ }
return $email1_name eq $email2_name &&
- $email1_address eq $email2_address;
+ $email1_address eq $email2_address &&
+ $name1_comment eq $name2_comment &&
+ $comment1 eq $comment2;
}
sub which {
@@ -2365,6 +2373,7 @@ sub process {
my $signoff = 0;
my $author = '';
my $authorsignoff = 0;
+ my $author_sob = '';
my $is_patch = 0;
my $is_binding_patch = -1;
my $in_header_lines = $file ? 0 : 1;
@@ -2692,9 +2701,37 @@ sub process {
if ($line =~ /^\s*signed-off-by:\s*(.*)/i) {
$signoff++;
$in_commit_log = 0;
- if ($author ne '') {
- if (same_email_addresses($1, $author)) {
+ if ($author ne '' && $authorsignoff != 1) {
+ if (same_email_addresses($1, $author, 1)) {
$authorsignoff = 1;
+ } else {
+ my $ctx = $1;
+ my ($email_name, $email_comment, $email_address, $comment1) = parse_email($ctx);
+ my ($author_name, $author_comment, $author_address, $comment2) = parse_email($author);
+
+ if ($email_address eq $author_address && $email_name eq $author_name) {
+ $author_sob = $ctx;
+ $authorsignoff = 2;
+ } elsif ($email_address eq $author_address) {
+ $author_sob = $ctx;
+ $authorsignoff = 3;
+ } elsif ($email_name eq $author_name) {
+ $author_sob = $ctx;
+ $authorsignoff = 4;
+
+ my $address1 = $email_address;
+ my $address2 = $author_address;
+
+ if ($address1 =~ /(\S+)\+\S+(\@.*)/) {
+ $address1 = "$1$2";
+ }
+ if ($address2 =~ /(\S+)\+\S+(\@.*)/) {
+ $address2 = "$1$2";
+ }
+ if ($address1 eq $address2) {
+ $authorsignoff = 5;
+ }
+ }
}
}
}
@@ -2751,7 +2788,7 @@ sub process {
}
my ($email_name, $name_comment, $email_address, $comment) = parse_email($email);
- my $suggested_email = format_email(($email_name, $email_address));
+ my $suggested_email = format_email(($email_name, $name_comment, $email_address, $comment));
if ($suggested_email eq "") {
ERROR("BAD_SIGN_OFF",
"Unrecognized email address: '$email'\n" . $herecurr);
@@ -2761,9 +2798,9 @@ sub process {
$dequoted =~ s/" </ </;
# Don't force email to have quotes
# Allow just an angle bracketed address
- if (!same_email_addresses($email, $suggested_email)) {
+ if (!same_email_addresses($email, $suggested_email, 0)) {
WARN("BAD_SIGN_OFF",
- "email address '$email' might be better as '$suggested_email$comment'\n" . $herecurr);
+ "email address '$email' might be better as '$suggested_email'\n" . $herecurr);
}
}
@@ -6943,9 +6980,33 @@ sub process {
if ($signoff == 0) {
ERROR("MISSING_SIGN_OFF",
"Missing Signed-off-by: line(s)\n");
- } elsif (!$authorsignoff) {
- WARN("NO_AUTHOR_SIGN_OFF",
- "Missing Signed-off-by: line by nominal patch author '$author'\n");
+ } elsif ($authorsignoff != 1) {
+ # authorsignoff values:
+ # 0 -> missing sign off
+ # 1 -> sign off identical
+ # 2 -> names and addresses match, comments mismatch
+ # 3 -> addresses match, names different
+ # 4 -> names match, addresses different
+ # 5 -> names match, addresses excluding subaddress details (refer RFC 5233) match
+
+ my $sob_msg = "'From: $author' != 'Signed-off-by: $author_sob'";
+
+ if ($authorsignoff == 0) {
+ ERROR("NO_AUTHOR_SIGN_OFF",
+ "Missing Signed-off-by: line by nominal patch author '$author'\n");
+ } elsif ($authorsignoff == 2) {
+ CHK("FROM_SIGN_OFF_MISMATCH",
+ "From:/Signed-off-by: email comments mismatch: $sob_msg\n");
+ } elsif ($authorsignoff == 3) {
+ WARN("FROM_SIGN_OFF_MISMATCH",
+ "From:/Signed-off-by: email name mismatch: $sob_msg\n");
+ } elsif ($authorsignoff == 4) {
+ WARN("FROM_SIGN_OFF_MISMATCH",
+ "From:/Signed-off-by: email address mismatch: $sob_msg\n");
+ } elsif ($authorsignoff == 5) {
+ WARN("FROM_SIGN_OFF_MISMATCH",
+ "From:/Signed-off-by: email subaddress mismatch: $sob_msg\n");
+ }
}
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 134/156] fs/binfmt_elf: use PT_LOAD p_align values for suitable start address
2020-10-16 2:40 incoming Andrew Morton
` (133 preceding siblings ...)
2020-10-16 3:12 ` [patch 133/156] checkpatch: add new warnings to author signoff checks Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 135/156] tools/testing/selftests: add self-test for verifying load alignment Andrew Morton
` (31 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: adobriyan, akpm, ckennelly, hughd, irogers, kirill.shutemov,
maskray, mike.kravetz, mm-commits, ndesaulniers, rientjes, shuah,
songliubraving, sspatil, surenb, torvalds, viro
From: Chris Kennelly <ckennelly@google.com>
Subject: fs/binfmt_elf: use PT_LOAD p_align values for suitable start address
Patch series "Selecting Load Addresses According to p_align", v3.
The current ELF loading mechancism provides page-aligned mappings. This
can lead to the program being loaded in a way unsuitable for file-backed,
transparent huge pages when handling PIE executables.
While specifying -z,max-page-size=0x200000 to the linker will generate
suitably aligned segments for huge pages on x86_64, the executable needs
to be loaded at a suitably aligned address as well. This alignment
requires the binary's cooperation, as distinct segments need to be
appropriately paddded to be eligible for THP.
For binaries built with increased alignment, this limits the number of
bits usable for ASLR, but provides some randomization over using fixed
load addresses/non-PIE binaries.
This patch (of 2):
The current ELF loading mechancism provides page-aligned mappings. This
can lead to the program being loaded in a way unsuitable for file-backed,
transparent huge pages when handling PIE executables.
For binaries built with increased alignment, this limits the number of
bits usable for ASLR, but provides some randomization over using fixed
load addresses/non-PIE binaries.
Tested by verifying program with -Wl,-z,max-page-size=0x200000 loading.
[akpm@linux-foundation.org: fix max() warning]
[ckennelly@google.com: augment comment]
Link: https://lkml.kernel.org/r/20200821233848.3904680-2-ckennelly@google.com
Link: https://lkml.kernel.org/r/20200820170541.1132271-1-ckennelly@google.com
Link: https://lkml.kernel.org/r/20200820170541.1132271-2-ckennelly@google.com
Signed-off-by: Chris Kennelly <ckennelly@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Hugh Dickens <hughd@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/binfmt_elf.c | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
--- a/fs/binfmt_elf.c~fs-binfmt_elf-use-pt_load-p_align-values-for-suitable-start-address
+++ a/fs/binfmt_elf.c
@@ -13,6 +13,7 @@
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/fs.h>
+#include <linux/log2.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/errno.h>
@@ -421,6 +422,26 @@ static int elf_read(struct file *file, v
return 0;
}
+static unsigned long maximum_alignment(struct elf_phdr *cmds, int nr)
+{
+ unsigned long alignment = 0;
+ int i;
+
+ for (i = 0; i < nr; i++) {
+ if (cmds[i].p_type == PT_LOAD) {
+ unsigned long p_align = cmds[i].p_align;
+
+ /* skip non-power of two alignments as invalid */
+ if (!is_power_of_2(p_align))
+ continue;
+ alignment = max(alignment, p_align);
+ }
+ }
+
+ /* ensure we align to at least one page */
+ return ELF_PAGEALIGN(alignment);
+}
+
/**
* load_elf_phdrs() - load ELF program headers
* @elf_ex: ELF header of the binary whose program headers should be loaded
@@ -1008,6 +1029,7 @@ out_free_interp:
int elf_prot, elf_flags;
unsigned long k, vaddr;
unsigned long total_size = 0;
+ unsigned long alignment;
if (elf_ppnt->p_type != PT_LOAD)
continue;
@@ -1086,6 +1108,9 @@ out_free_interp:
load_bias = ELF_ET_DYN_BASE;
if (current->flags & PF_RANDOMIZE)
load_bias += arch_mmap_rnd();
+ alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
+ if (alignment)
+ load_bias &= ~(alignment - 1);
elf_flags |= MAP_FIXED;
} else
load_bias = 0;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 135/156] tools/testing/selftests: add self-test for verifying load alignment
2020-10-16 2:40 incoming Andrew Morton
` (134 preceding siblings ...)
2020-10-16 3:12 ` [patch 134/156] fs/binfmt_elf: use PT_LOAD p_align values for suitable start address Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 136/156] binfmt_elf_fdpic: stop using dump_emit() on user pointers on !MMU Andrew Morton
` (30 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: adobriyan, akpm, ckennelly, hughd, irogers, kirill.shutemov,
maskray, mike.kravetz, mm-commits, ndesaulniers, rientjes, shuah,
songliubraving, sspatil, surenb, torvalds, viro
From: Chris Kennelly <ckennelly@google.com>
Subject: tools/testing/selftests: add self-test for verifying load alignment
This produces a PIE binary with a variety of p_align requirements,
suitable for verifying that the load address meets that alignment
requirement.
Link: https://lkml.kernel.org/r/20200820170541.1132271-3-ckennelly@google.com
Link: https://lkml.kernel.org/r/20200821233848.3904680-3-ckennelly@google.com
Signed-off-by: Chris Kennelly <ckennelly@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Hugh Dickens <hughd@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
tools/testing/selftests/exec/.gitignore | 1
tools/testing/selftests/exec/Makefile | 9 +-
tools/testing/selftests/exec/load_address.c | 68 ++++++++++++++++++
3 files changed, 76 insertions(+), 2 deletions(-)
--- a/tools/testing/selftests/exec/.gitignore~add-self-test-for-verifying-load-alignment
+++ a/tools/testing/selftests/exec/.gitignore
@@ -7,6 +7,7 @@ execveat.moved
execveat.path.ephemeral
execveat.ephemeral
execveat.denatured
+/load_address_*
/recursion-depth
xxxxxxxx*
pipe
--- /dev/null
+++ a/tools/testing/selftests/exec/load_address.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <link.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+struct Statistics {
+ unsigned long long load_address;
+ unsigned long long alignment;
+};
+
+int ExtractStatistics(struct dl_phdr_info *info, size_t size, void *data)
+{
+ struct Statistics *stats = (struct Statistics *) data;
+ int i;
+
+ if (info->dlpi_name != NULL && info->dlpi_name[0] != '\0') {
+ // Ignore headers from other than the executable.
+ return 2;
+ }
+
+ stats->load_address = (unsigned long long) info->dlpi_addr;
+ stats->alignment = 0;
+
+ for (i = 0; i < info->dlpi_phnum; i++) {
+ if (info->dlpi_phdr[i].p_type != PT_LOAD)
+ continue;
+
+ if (info->dlpi_phdr[i].p_align > stats->alignment)
+ stats->alignment = info->dlpi_phdr[i].p_align;
+ }
+
+ return 1; // Terminate dl_iterate_phdr.
+}
+
+int main(int argc, char **argv)
+{
+ struct Statistics extracted;
+ unsigned long long misalign;
+ int ret;
+
+ ret = dl_iterate_phdr(ExtractStatistics, &extracted);
+ if (ret != 1) {
+ fprintf(stderr, "FAILED\n");
+ return 1;
+ }
+
+ if (extracted.alignment == 0) {
+ fprintf(stderr, "No alignment found\n");
+ return 1;
+ } else if (extracted.alignment & (extracted.alignment - 1)) {
+ fprintf(stderr, "Alignment is not a power of 2\n");
+ return 1;
+ }
+
+ misalign = extracted.load_address & (extracted.alignment - 1);
+ if (misalign) {
+ printf("alignment = %llu, load_address = %llu\n",
+ extracted.alignment, extracted.load_address);
+ fprintf(stderr, "FAILED\n");
+ return 1;
+ }
+
+ fprintf(stderr, "PASS\n");
+ return 0;
+}
--- a/tools/testing/selftests/exec/Makefile~add-self-test-for-verifying-load-alignment
+++ a/tools/testing/selftests/exec/Makefile
@@ -4,7 +4,7 @@ CFLAGS += -Wno-nonnull
CFLAGS += -D_GNU_SOURCE
TEST_PROGS := binfmt_script non-regular
-TEST_GEN_PROGS := execveat
+TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216
TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe
# Makefile is a run-time dependency, since it's accessed by the execveat test
TEST_FILES := Makefile
@@ -27,4 +27,9 @@ $(OUTPUT)/execveat.symlink: $(OUTPUT)/ex
$(OUTPUT)/execveat.denatured: $(OUTPUT)/execveat
cp $< $@
chmod -x $@
-
+$(OUTPUT)/load_address_4096: load_address.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie $< -o $@
+$(OUTPUT)/load_address_2097152: load_address.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie $< -o $@
+$(OUTPUT)/load_address_16777216: load_address.c
+ $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie $< -o $@
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 136/156] binfmt_elf_fdpic: stop using dump_emit() on user pointers on !MMU
2020-10-16 2:40 incoming Andrew Morton
` (135 preceding siblings ...)
2020-10-16 3:12 ` [patch 135/156] tools/testing/selftests: add self-test for verifying load alignment Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 137/156] coredump: let dump_emit() bail out on short writes Andrew Morton
` (29 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, ebiederm, hch, hughd, jannh, mm-commits, oleg, torvalds, viro
From: Jann Horn <jannh@google.com>
Subject: binfmt_elf_fdpic: stop using dump_emit() on user pointers on !MMU
Patch series "Fix ELF / FDPIC ELF core dumping, and use mmap_lock properly in there", v5.
At the moment, we have that rather ugly mmget_still_valid() helper to work
around <https://crbug.com/project-zero/1790>: ELF core dumping doesn't
take the mmap_sem while traversing the task's VMAs, and if anything (like
userfaultfd) then remotely messes with the VMA tree, fireworks ensue. So
at the moment we use mmget_still_valid() to bail out in any writers that
might be operating on a remote mm's VMAs.
With this series, I'm trying to get rid of the need for that as cleanly as
possible. ("cleanly" meaning "avoid holding the mmap_lock across
unbounded sleeps".)
Patches 1, 2, 3 and 4 are relatively unrelated cleanups in the core
dumping code.
Patches 5 and 6 implement the main change: Instead of repeatedly accessing
the VMA list with sleeps in between, we snapshot it at the start with
proper locking, and then later we just use our copy of the VMA list. This
ensures that the kernel won't crash, that VMA metadata in the coredump is
consistent even in the presence of concurrent modifications, and that any
virtual addresses that aren't being concurrently modified have their
contents show up in the core dump properly.
The disadvantage of this approach is that we need a bit more memory during
core dumping for storing metadata about all VMAs.
At the end of the series, patch 7 removes the old workaround for this
issue (mmget_still_valid()).
I have tested:
- Creating a simple core dump on X86-64 still works.
- The created coredump on X86-64 opens in GDB and looks plausible.
- X86-64 core dumps contain the first page for executable mappings at
offset 0, and don't contain the first page for non-executable file
mappings or executable mappings at offset !=0.
- NOMMU 32-bit ARM can still generate plausible-looking core dumps
through the FDPIC implementation. (I can't test this with GDB because
GDB is missing some structure definition for nommu ARM, but I've
poked around in the hexdump and it looked decent.)
This patch (of 7):
dump_emit() is for kernel pointers, and VMAs describe userspace memory.
Let's be tidy here and avoid accessing userspace pointers under KERNEL_DS,
even if it probably doesn't matter much on !MMU systems - especially given
that it looks like we can just use the same get_dump_page() as on MMU if
we move it out of the CONFIG_MMU block.
One small change we have to make in get_dump_page() is to use
__get_user_pages_locked() instead of __get_user_pages(), since the latter
doesn't exist on nommu. On mmu builds, __get_user_pages_locked() will
just call __get_user_pages() for us.
Link: http://lkml.kernel.org/r/20200827114932.3572699-1-jannh@google.com
Link: http://lkml.kernel.org/r/20200827114932.3572699-2-jannh@google.com
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/binfmt_elf_fdpic.c | 8 -----
mm/gup.c | 57 +++++++++++++++++++---------------------
2 files changed, 28 insertions(+), 37 deletions(-)
--- a/fs/binfmt_elf_fdpic.c~binfmt_elf_fdpic-stop-using-dump_emit-on-user-pointers-on-mmu
+++ a/fs/binfmt_elf_fdpic.c
@@ -1529,14 +1529,11 @@ static bool elf_fdpic_dump_segments(stru
struct vm_area_struct *vma;
for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
-#ifdef CONFIG_MMU
unsigned long addr;
-#endif
if (!maydump(vma, cprm->mm_flags))
continue;
-#ifdef CONFIG_MMU
for (addr = vma->vm_start; addr < vma->vm_end;
addr += PAGE_SIZE) {
bool res;
@@ -1552,11 +1549,6 @@ static bool elf_fdpic_dump_segments(stru
if (!res)
return false;
}
-#else
- if (!dump_emit(cprm, (void *) vma->vm_start,
- vma->vm_end - vma->vm_start))
- return false;
-#endif
}
return true;
}
--- a/mm/gup.c~binfmt_elf_fdpic-stop-using-dump_emit-on-user-pointers-on-mmu
+++ a/mm/gup.c
@@ -1490,35 +1490,6 @@ int __mm_populate(unsigned long start, u
mmap_read_unlock(mm);
return ret; /* 0 or negative error code */
}
-
-/**
- * get_dump_page() - pin user page in memory while writing it to core dump
- * @addr: user address
- *
- * Returns struct page pointer of user page pinned for dump,
- * to be freed afterwards by put_page().
- *
- * Returns NULL on any kind of failure - a hole must then be inserted into
- * the corefile, to preserve alignment with its headers; and also returns
- * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
- * allowing a hole to be left in the corefile to save diskspace.
- *
- * Called without mmap_lock, but after all other threads have been killed.
- */
-#ifdef CONFIG_ELF_CORE
-struct page *get_dump_page(unsigned long addr)
-{
- struct vm_area_struct *vma;
- struct page *page;
-
- if (__get_user_pages(current->mm, addr, 1,
- FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
- NULL) < 1)
- return NULL;
- flush_cache_page(vma, addr, page_to_pfn(page));
- return page;
-}
-#endif /* CONFIG_ELF_CORE */
#else /* CONFIG_MMU */
static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
unsigned long nr_pages, struct page **pages,
@@ -1564,6 +1535,34 @@ finish_or_fault:
}
#endif /* !CONFIG_MMU */
+/**
+ * get_dump_page() - pin user page in memory while writing it to core dump
+ * @addr: user address
+ *
+ * Returns struct page pointer of user page pinned for dump,
+ * to be freed afterwards by put_page().
+ *
+ * Returns NULL on any kind of failure - a hole must then be inserted into
+ * the corefile, to preserve alignment with its headers; and also returns
+ * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
+ * allowing a hole to be left in the corefile to save diskspace.
+ *
+ * Called without mmap_lock, but after all other threads have been killed.
+ */
+#ifdef CONFIG_ELF_CORE
+struct page *get_dump_page(unsigned long addr)
+{
+ struct vm_area_struct *vma;
+ struct page *page;
+
+ if (__get_user_pages_locked(current->mm, addr, 1, &page, &vma, NULL,
+ FOLL_FORCE | FOLL_DUMP | FOLL_GET) < 1)
+ return NULL;
+ flush_cache_page(vma, addr, page_to_pfn(page));
+ return page;
+}
+#endif /* CONFIG_ELF_CORE */
+
#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
{
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 137/156] coredump: let dump_emit() bail out on short writes
2020-10-16 2:40 incoming Andrew Morton
` (136 preceding siblings ...)
2020-10-16 3:12 ` [patch 136/156] binfmt_elf_fdpic: stop using dump_emit() on user pointers on !MMU Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 138/156] coredump: refactor page range dumping into common helper Andrew Morton
` (28 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, ebiederm, hch, hughd, jannh, mm-commits, oleg, torvalds, viro
From: Jann Horn <jannh@google.com>
Subject: coredump: let dump_emit() bail out on short writes
dump_emit() has a retry loop, but there seems to be no way for that retry
logic to actually be used; and it was also buggy, writing the same data
repeatedly after a short write.
Let's just bail out on a short write.
Link: http://lkml.kernel.org/r/20200827114932.3572699-3-jannh@google.com
Signed-off-by: Jann Horn <jannh@google.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/coredump.c | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
--- a/fs/coredump.c~coredump-let-dump_emit-bail-out-on-short-writes
+++ a/fs/coredump.c
@@ -840,17 +840,17 @@ int dump_emit(struct coredump_params *cp
ssize_t n;
if (cprm->written + nr > cprm->limit)
return 0;
- while (nr) {
- if (dump_interrupted())
- return 0;
- n = __kernel_write(file, addr, nr, &pos);
- if (n <= 0)
- return 0;
- file->f_pos = pos;
- cprm->written += n;
- cprm->pos += n;
- nr -= n;
- }
+
+
+ if (dump_interrupted())
+ return 0;
+ n = __kernel_write(file, addr, nr, &pos);
+ if (n != nr)
+ return 0;
+ file->f_pos = pos;
+ cprm->written += n;
+ cprm->pos += n;
+
return 1;
}
EXPORT_SYMBOL(dump_emit);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 138/156] coredump: refactor page range dumping into common helper
2020-10-16 2:40 incoming Andrew Morton
` (137 preceding siblings ...)
2020-10-16 3:12 ` [patch 137/156] coredump: let dump_emit() bail out on short writes Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 139/156] coredump: rework elf/elf_fdpic vma_dump_size() " Andrew Morton
` (27 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, ebiederm, hch, hughd, jannh, mm-commits, oleg, torvalds, viro
From: Jann Horn <jannh@google.com>
Subject: coredump: refactor page range dumping into common helper
Both fs/binfmt_elf.c and fs/binfmt_elf_fdpic.c need to dump ranges of
pages into the coredump file. Extract that logic into a common helper.
Link: http://lkml.kernel.org/r/20200827114932.3572699-4-jannh@google.com
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/binfmt_elf.c | 22 ++--------------------
fs/binfmt_elf_fdpic.c | 18 +++---------------
fs/coredump.c | 34 ++++++++++++++++++++++++++++++++++
include/linux/coredump.h | 2 ++
4 files changed, 41 insertions(+), 35 deletions(-)
--- a/fs/binfmt_elf.c~coredump-refactor-page-range-dumping-into-common-helper
+++ a/fs/binfmt_elf.c
@@ -2444,26 +2444,8 @@ static int elf_core_dump(struct coredump
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
- unsigned long addr;
- unsigned long end;
-
- end = vma->vm_start + vma_filesz[i++];
-
- for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
- struct page *page;
- int stop;
-
- page = get_dump_page(addr);
- if (page) {
- void *kaddr = kmap(page);
- stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
- kunmap(page);
- put_page(page);
- } else
- stop = !dump_skip(cprm, PAGE_SIZE);
- if (stop)
- goto end_coredump;
- }
+ if (!dump_user_range(cprm, vma->vm_start, vma_filesz[i++]))
+ goto end_coredump;
}
dump_truncate(cprm);
--- a/fs/binfmt_elf_fdpic.c~coredump-refactor-page-range-dumping-into-common-helper
+++ a/fs/binfmt_elf_fdpic.c
@@ -1534,21 +1534,9 @@ static bool elf_fdpic_dump_segments(stru
if (!maydump(vma, cprm->mm_flags))
continue;
- for (addr = vma->vm_start; addr < vma->vm_end;
- addr += PAGE_SIZE) {
- bool res;
- struct page *page = get_dump_page(addr);
- if (page) {
- void *kaddr = kmap(page);
- res = dump_emit(cprm, kaddr, PAGE_SIZE);
- kunmap(page);
- put_page(page);
- } else {
- res = dump_skip(cprm, PAGE_SIZE);
- }
- if (!res)
- return false;
- }
+ if (!dump_user_range(cprm, vma->vm_start,
+ vma->vma_end - vma->vm_start))
+ return false;
}
return true;
}
--- a/fs/coredump.c~coredump-refactor-page-range-dumping-into-common-helper
+++ a/fs/coredump.c
@@ -876,6 +876,40 @@ int dump_skip(struct coredump_params *cp
}
EXPORT_SYMBOL(dump_skip);
+#ifdef CONFIG_ELF_CORE
+int dump_user_range(struct coredump_params *cprm, unsigned long start,
+ unsigned long len)
+{
+ unsigned long addr;
+
+ for (addr = start; addr < start + len; addr += PAGE_SIZE) {
+ struct page *page;
+ int stop;
+
+ /*
+ * To avoid having to allocate page tables for virtual address
+ * ranges that have never been used yet, and also to make it
+ * easy to generate sparse core files, use a helper that returns
+ * NULL when encountering an empty page table entry that would
+ * otherwise have been filled with the zero page.
+ */
+ page = get_dump_page(addr);
+ if (page) {
+ void *kaddr = kmap(page);
+
+ stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
+ kunmap(page);
+ put_page(page);
+ } else {
+ stop = !dump_skip(cprm, PAGE_SIZE);
+ }
+ if (stop)
+ return 0;
+ }
+ return 1;
+}
+#endif
+
int dump_align(struct coredump_params *cprm, int align)
{
unsigned mod = cprm->pos & (align - 1);
--- a/include/linux/coredump.h~coredump-refactor-page-range-dumping-into-common-helper
+++ a/include/linux/coredump.h
@@ -16,6 +16,8 @@ extern int dump_skip(struct coredump_par
extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
extern int dump_align(struct coredump_params *cprm, int align);
extern void dump_truncate(struct coredump_params *cprm);
+int dump_user_range(struct coredump_params *cprm, unsigned long start,
+ unsigned long len);
#ifdef CONFIG_COREDUMP
extern void do_coredump(const kernel_siginfo_t *siginfo);
#else
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 139/156] coredump: rework elf/elf_fdpic vma_dump_size() into common helper
2020-10-16 2:40 incoming Andrew Morton
` (138 preceding siblings ...)
2020-10-16 3:12 ` [patch 138/156] coredump: refactor page range dumping into common helper Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 140/156] binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot Andrew Morton
` (26 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, ebiederm, hch, hughd, jannh, mm-commits, oleg, torvalds, viro
From: Jann Horn <jannh@google.com>
Subject: coredump: rework elf/elf_fdpic vma_dump_size() into common helper
At the moment, the binfmt_elf and binfmt_elf_fdpic code have slightly
different code to figure out which VMAs should be dumped, and if so,
whether the dump should contain the entire VMA or just its first page.
Eliminate duplicate code by reworking the binfmt_elf version into a
generic core dumping helper in coredump.c.
As part of that, change the heuristic for detecting executable/library
header pages to check whether the inode is executable instead of looking
at the file mode.
This is less problematic in terms of locking because it lets us avoid
get_user() under the mmap_sem. (And arguably it looks nicer and makes
more sense in generic code.)
Adjust a little bit based on the binfmt_elf_fdpic version: ->anon_vma is
only meaningful under CONFIG_MMU, otherwise we have to assume that the VMA
has been written to.
Link: http://lkml.kernel.org/r/20200827114932.3572699-5-jannh@google.com
Signed-off-by: Jann Horn <jannh@google.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/binfmt_elf.c | 120 -------------------------------------
fs/binfmt_elf_fdpic.c | 83 +------------------------
fs/coredump.c | 101 +++++++++++++++++++++++++++++++
include/linux/coredump.h | 1
4 files changed, 106 insertions(+), 199 deletions(-)
--- a/fs/binfmt_elf.c~coredump-rework-elf-elf_fdpic-vma_dump_size-into-common-helper
+++ a/fs/binfmt_elf.c
@@ -1414,126 +1414,6 @@ out:
* Jeremy Fitzhardinge <jeremy@sw.oz.au>
*/
-/*
- * The purpose of always_dump_vma() is to make sure that special kernel mappings
- * that are useful for post-mortem analysis are included in every core dump.
- * In that way we ensure that the core dump is fully interpretable later
- * without matching up the same kernel and hardware config to see what PC values
- * meant. These special mappings include - vDSO, vsyscall, and other
- * architecture specific mappings
- */
-static bool always_dump_vma(struct vm_area_struct *vma)
-{
- /* Any vsyscall mappings? */
- if (vma == get_gate_vma(vma->vm_mm))
- return true;
-
- /*
- * Assume that all vmas with a .name op should always be dumped.
- * If this changes, a new vm_ops field can easily be added.
- */
- if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
- return true;
-
- /*
- * arch_vma_name() returns non-NULL for special architecture mappings,
- * such as vDSO sections.
- */
- if (arch_vma_name(vma))
- return true;
-
- return false;
-}
-
-/*
- * Decide what to dump of a segment, part, all or none.
- */
-static unsigned long vma_dump_size(struct vm_area_struct *vma,
- unsigned long mm_flags)
-{
-#define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type))
-
- /* always dump the vdso and vsyscall sections */
- if (always_dump_vma(vma))
- goto whole;
-
- if (vma->vm_flags & VM_DONTDUMP)
- return 0;
-
- /* support for DAX */
- if (vma_is_dax(vma)) {
- if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
- goto whole;
- if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
- goto whole;
- return 0;
- }
-
- /* Hugetlb memory check */
- if (is_vm_hugetlb_page(vma)) {
- if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
- goto whole;
- if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
- goto whole;
- return 0;
- }
-
- /* Do not dump I/O mapped devices or special mappings */
- if (vma->vm_flags & VM_IO)
- return 0;
-
- /* By default, dump shared memory if mapped from an anonymous file. */
- if (vma->vm_flags & VM_SHARED) {
- if (file_inode(vma->vm_file)->i_nlink == 0 ?
- FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
- goto whole;
- return 0;
- }
-
- /* Dump segments that have been written to. */
- if (vma->anon_vma && FILTER(ANON_PRIVATE))
- goto whole;
- if (vma->vm_file == NULL)
- return 0;
-
- if (FILTER(MAPPED_PRIVATE))
- goto whole;
-
- /*
- * If this looks like the beginning of a DSO or executable mapping,
- * check for an ELF header. If we find one, dump the first page to
- * aid in determining what was mapped here.
- */
- if (FILTER(ELF_HEADERS) &&
- vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ)) {
- u32 __user *header = (u32 __user *) vma->vm_start;
- u32 word;
- /*
- * Doing it this way gets the constant folded by GCC.
- */
- union {
- u32 cmp;
- char elfmag[SELFMAG];
- } magic;
- BUILD_BUG_ON(SELFMAG != sizeof word);
- magic.elfmag[EI_MAG0] = ELFMAG0;
- magic.elfmag[EI_MAG1] = ELFMAG1;
- magic.elfmag[EI_MAG2] = ELFMAG2;
- magic.elfmag[EI_MAG3] = ELFMAG3;
- if (unlikely(get_user(word, header)))
- word = 0;
- if (word == magic.cmp)
- return PAGE_SIZE;
- }
-
-#undef FILTER
-
- return 0;
-
-whole:
- return vma->vm_end - vma->vm_start;
-}
-
/* An ELF note in memory */
struct memelfnote
{
--- a/fs/binfmt_elf_fdpic.c~coredump-rework-elf-elf_fdpic-vma_dump_size-into-common-helper
+++ a/fs/binfmt_elf_fdpic.c
@@ -1215,76 +1215,6 @@ struct elf_prstatus_fdpic
int pr_fpvalid; /* True if math co-processor being used. */
};
-/*
- * Decide whether a segment is worth dumping; default is yes to be
- * sure (missing info is worse than too much; etc).
- * Personally I'd include everything, and use the coredump limit...
- *
- * I think we should skip something. But I am not sure how. H.J.
- */
-static int maydump(struct vm_area_struct *vma, unsigned long mm_flags)
-{
- int dump_ok;
-
- /* Do not dump I/O mapped devices or special mappings */
- if (vma->vm_flags & VM_IO) {
- kdcore("%08lx: %08lx: no (IO)", vma->vm_start, vma->vm_flags);
- return 0;
- }
-
- /* If we may not read the contents, don't allow us to dump
- * them either. "dump_write()" can't handle it anyway.
- */
- if (!(vma->vm_flags & VM_READ)) {
- kdcore("%08lx: %08lx: no (!read)", vma->vm_start, vma->vm_flags);
- return 0;
- }
-
- /* support for DAX */
- if (vma_is_dax(vma)) {
- if (vma->vm_flags & VM_SHARED) {
- dump_ok = test_bit(MMF_DUMP_DAX_SHARED, &mm_flags);
- kdcore("%08lx: %08lx: %s (DAX shared)", vma->vm_start,
- vma->vm_flags, dump_ok ? "yes" : "no");
- } else {
- dump_ok = test_bit(MMF_DUMP_DAX_PRIVATE, &mm_flags);
- kdcore("%08lx: %08lx: %s (DAX private)", vma->vm_start,
- vma->vm_flags, dump_ok ? "yes" : "no");
- }
- return dump_ok;
- }
-
- /* By default, dump shared memory if mapped from an anonymous file. */
- if (vma->vm_flags & VM_SHARED) {
- if (file_inode(vma->vm_file)->i_nlink == 0) {
- dump_ok = test_bit(MMF_DUMP_ANON_SHARED, &mm_flags);
- kdcore("%08lx: %08lx: %s (share)", vma->vm_start,
- vma->vm_flags, dump_ok ? "yes" : "no");
- return dump_ok;
- }
-
- dump_ok = test_bit(MMF_DUMP_MAPPED_SHARED, &mm_flags);
- kdcore("%08lx: %08lx: %s (share)", vma->vm_start,
- vma->vm_flags, dump_ok ? "yes" : "no");
- return dump_ok;
- }
-
-#ifdef CONFIG_MMU
- /* By default, if it hasn't been written to, don't write it out */
- if (!vma->anon_vma) {
- dump_ok = test_bit(MMF_DUMP_MAPPED_PRIVATE, &mm_flags);
- kdcore("%08lx: %08lx: %s (!anon)", vma->vm_start,
- vma->vm_flags, dump_ok ? "yes" : "no");
- return dump_ok;
- }
-#endif
-
- dump_ok = test_bit(MMF_DUMP_ANON_PRIVATE, &mm_flags);
- kdcore("%08lx: %08lx: %s", vma->vm_start, vma->vm_flags,
- dump_ok ? "yes" : "no");
- return dump_ok;
-}
-
/* An ELF note in memory */
struct memelfnote
{
@@ -1529,13 +1459,9 @@ static bool elf_fdpic_dump_segments(stru
struct vm_area_struct *vma;
for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
- unsigned long addr;
-
- if (!maydump(vma, cprm->mm_flags))
- continue;
+ unsigned long size = vma_dump_size(vma, cprm->mm_flags);
- if (!dump_user_range(cprm, vma->vm_start,
- vma->vma_end - vma->vm_start))
+ if (!dump_user_range(cprm, vma->vm_start, size))
return false;
}
return true;
@@ -1547,8 +1473,7 @@ static size_t elf_core_vma_data_size(uns
size_t size = 0;
for (vma = current->mm->mmap; vma; vma = vma->vm_next)
- if (maydump(vma, mm_flags))
- size += vma->vm_end - vma->vm_start;
+ size += vma_dump_size(vma, mm_flags);
return size;
}
@@ -1694,7 +1619,7 @@ static int elf_fdpic_core_dump(struct co
phdr.p_offset = offset;
phdr.p_vaddr = vma->vm_start;
phdr.p_paddr = 0;
- phdr.p_filesz = maydump(vma, cprm->mm_flags) ? sz : 0;
+ phdr.p_filesz = vma_dump_size(vma, cprm->mm_flags);
phdr.p_memsz = sz;
offset += phdr.p_filesz;
phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
--- a/fs/coredump.c~coredump-rework-elf-elf_fdpic-vma_dump_size-into-common-helper
+++ a/fs/coredump.c
@@ -936,3 +936,104 @@ void dump_truncate(struct coredump_param
}
}
EXPORT_SYMBOL(dump_truncate);
+
+/*
+ * The purpose of always_dump_vma() is to make sure that special kernel mappings
+ * that are useful for post-mortem analysis are included in every core dump.
+ * In that way we ensure that the core dump is fully interpretable later
+ * without matching up the same kernel and hardware config to see what PC values
+ * meant. These special mappings include - vDSO, vsyscall, and other
+ * architecture specific mappings
+ */
+static bool always_dump_vma(struct vm_area_struct *vma)
+{
+ /* Any vsyscall mappings? */
+ if (vma == get_gate_vma(vma->vm_mm))
+ return true;
+
+ /*
+ * Assume that all vmas with a .name op should always be dumped.
+ * If this changes, a new vm_ops field can easily be added.
+ */
+ if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
+ return true;
+
+ /*
+ * arch_vma_name() returns non-NULL for special architecture mappings,
+ * such as vDSO sections.
+ */
+ if (arch_vma_name(vma))
+ return true;
+
+ return false;
+}
+
+/*
+ * Decide how much of @vma's contents should be included in a core dump.
+ */
+unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags)
+{
+#define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type))
+
+ /* always dump the vdso and vsyscall sections */
+ if (always_dump_vma(vma))
+ goto whole;
+
+ if (vma->vm_flags & VM_DONTDUMP)
+ return 0;
+
+ /* support for DAX */
+ if (vma_is_dax(vma)) {
+ if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
+ goto whole;
+ if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
+ goto whole;
+ return 0;
+ }
+
+ /* Hugetlb memory check */
+ if (is_vm_hugetlb_page(vma)) {
+ if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
+ goto whole;
+ if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
+ goto whole;
+ return 0;
+ }
+
+ /* Do not dump I/O mapped devices or special mappings */
+ if (vma->vm_flags & VM_IO)
+ return 0;
+
+ /* By default, dump shared memory if mapped from an anonymous file. */
+ if (vma->vm_flags & VM_SHARED) {
+ if (file_inode(vma->vm_file)->i_nlink == 0 ?
+ FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
+ goto whole;
+ return 0;
+ }
+
+ /* Dump segments that have been written to. */
+ if ((!IS_ENABLED(CONFIG_MMU) || vma->anon_vma) && FILTER(ANON_PRIVATE))
+ goto whole;
+ if (vma->vm_file == NULL)
+ return 0;
+
+ if (FILTER(MAPPED_PRIVATE))
+ goto whole;
+
+ /*
+ * If this is the beginning of an executable file mapping,
+ * dump the first page to aid in determining what was mapped here.
+ */
+ if (FILTER(ELF_HEADERS) &&
+ vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ) &&
+ (READ_ONCE(file_inode(vma->vm_file)->i_mode) & 0111) != 0)
+ return PAGE_SIZE;
+
+#undef FILTER
+
+ return 0;
+
+whole:
+ return vma->vm_end - vma->vm_start;
+}
--- a/include/linux/coredump.h~coredump-rework-elf-elf_fdpic-vma_dump_size-into-common-helper
+++ a/include/linux/coredump.h
@@ -16,6 +16,7 @@ extern int dump_skip(struct coredump_par
extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
extern int dump_align(struct coredump_params *cprm, int align);
extern void dump_truncate(struct coredump_params *cprm);
+unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags);
int dump_user_range(struct coredump_params *cprm, unsigned long start,
unsigned long len);
#ifdef CONFIG_COREDUMP
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 140/156] binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot
2020-10-16 2:40 incoming Andrew Morton
` (139 preceding siblings ...)
2020-10-16 3:12 ` [patch 139/156] coredump: rework elf/elf_fdpic vma_dump_size() " Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:12 ` [patch 141/156] mm/gup: take mmap_lock in get_dump_page() Andrew Morton
` (25 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, ebiederm, hch, hughd, jannh, mm-commits, oleg, torvalds, viro
From: Jann Horn <jannh@google.com>
Subject: binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot
In both binfmt_elf and binfmt_elf_fdpic, use a new helper
dump_vma_snapshot() to take a snapshot of the VMA list (including the gate
VMA, if we have one) while protected by the mmap_lock, and then use that
snapshot instead of walking the VMA list without locking.
An alternative approach would be to keep the mmap_lock held across the
entire core dumping operation; however, keeping the mmap_lock locked while
we may be blocked for an unbounded amount of time (e.g. because we're
dumping to a FUSE filesystem or so) isn't really optimal; the mmap_lock
blocks things like the ->release handler of userfaultfd, and we don't
really want critical system daemons to grind to a halt just because
someone "gifted" them SCM_RIGHTS to an eternally-locked userfaultfd, or
something like that.
Since both the normal ELF code and the FDPIC ELF code need this
functionality (and if any other binfmt wants to add coredump support in
the future, they'd probably need it, too), implement this with a common
helper in fs/coredump.c.
A downside of this approach is that we now need a bigger amount of kernel
memory per userspace VMA in the normal ELF case, and that we need O(n)
kernel memory in the FDPIC ELF case at all; but 40 bytes per VMA shouldn't
be terribly bad.
There currently is a data race between stack expansion and anything that
reads ->vm_start or ->vm_end under the mmap_lock held in read mode; to
mitigate that for core dumping, take the mmap_lock in write mode when
taking a snapshot of the VMA hierarchy. (If we only took the mmap_lock in
read mode, we could end up with a corrupted core dump if someone does
get_user_pages_remote() concurrently. Not really a major problem, but
taking the mmap_lock either way works here, so we might as well avoid the
issue.) (This doesn't do anything about the existing data races with stack
expansion in other mm code.)
Link: http://lkml.kernel.org/r/20200827114932.3572699-6-jannh@google.com
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/binfmt_elf.c | 100 ++++++++-----------------------------
fs/binfmt_elf_fdpic.c | 67 +++++++++---------------
fs/coredump.c | 81 +++++++++++++++++++++++++++++
include/linux/coredump.h | 10 +++
4 files changed, 138 insertions(+), 120 deletions(-)
--- a/fs/binfmt_elf.c~binfmt_elf-binfmt_elf_fdpic-use-a-vma-list-snapshot
+++ a/fs/binfmt_elf.c
@@ -2125,32 +2125,6 @@ static void free_note_info(struct elf_no
#endif
-static struct vm_area_struct *first_vma(struct task_struct *tsk,
- struct vm_area_struct *gate_vma)
-{
- struct vm_area_struct *ret = tsk->mm->mmap;
-
- if (ret)
- return ret;
- return gate_vma;
-}
-/*
- * Helper function for iterating across a vma list. It ensures that the caller
- * will visit `gate_vma' prior to terminating the search.
- */
-static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
- struct vm_area_struct *gate_vma)
-{
- struct vm_area_struct *ret;
-
- ret = this_vma->vm_next;
- if (ret)
- return ret;
- if (this_vma == gate_vma)
- return NULL;
- return gate_vma;
-}
-
static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
elf_addr_t e_shoff, int segs)
{
@@ -2177,9 +2151,8 @@ static void fill_extnum_info(struct elfh
static int elf_core_dump(struct coredump_params *cprm)
{
int has_dumped = 0;
- int segs, i;
- size_t vma_data_size = 0;
- struct vm_area_struct *vma, *gate_vma;
+ int vma_count, segs, i;
+ size_t vma_data_size;
struct elfhdr elf;
loff_t offset = 0, dataoff;
struct elf_note_info info = { };
@@ -2187,30 +2160,16 @@ static int elf_core_dump(struct coredump
struct elf_shdr *shdr4extnum = NULL;
Elf_Half e_phnum;
elf_addr_t e_shoff;
- elf_addr_t *vma_filesz = NULL;
+ struct core_vma_metadata *vma_meta;
+
+ if (dump_vma_snapshot(cprm, &vma_count, &vma_meta, &vma_data_size))
+ return 0;
- /*
- * We no longer stop all VM operations.
- *
- * This is because those proceses that could possibly change map_count
- * or the mmap / vma pages are now blocked in do_exit on current
- * finishing this core dump.
- *
- * Only ptrace can touch these memory addresses, but it doesn't change
- * the map_count or the pages allocated. So no possibility of crashing
- * exists while dumping the mm->vm_next areas to the core file.
- */
-
/*
* The number of segs are recored into ELF header as 16bit value.
* Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
*/
- segs = current->mm->map_count;
- segs += elf_core_extra_phdrs();
-
- gate_vma = get_gate_vma(current->mm);
- if (gate_vma != NULL)
- segs++;
+ segs = vma_count + elf_core_extra_phdrs();
/* for notes section */
segs++;
@@ -2248,24 +2207,6 @@ static int elf_core_dump(struct coredump
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
- /*
- * Zero vma process will get ZERO_SIZE_PTR here.
- * Let coredump continue for register state at least.
- */
- vma_filesz = kvmalloc(array_size(sizeof(*vma_filesz), (segs - 1)),
- GFP_KERNEL);
- if (!vma_filesz)
- goto end_coredump;
-
- for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
- vma = next_vma(vma, gate_vma)) {
- unsigned long dump_size;
-
- dump_size = vma_dump_size(vma, cprm->mm_flags);
- vma_filesz[i++] = dump_size;
- vma_data_size += dump_size;
- }
-
offset += vma_data_size;
offset += elf_core_extra_data_size();
e_shoff = offset;
@@ -2286,21 +2227,23 @@ static int elf_core_dump(struct coredump
goto end_coredump;
/* Write program headers for segments dump */
- for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
- vma = next_vma(vma, gate_vma)) {
+ for (i = 0; i < vma_count; i++) {
+ struct core_vma_metadata *meta = vma_meta + i;
struct elf_phdr phdr;
phdr.p_type = PT_LOAD;
phdr.p_offset = offset;
- phdr.p_vaddr = vma->vm_start;
+ phdr.p_vaddr = meta->start;
phdr.p_paddr = 0;
- phdr.p_filesz = vma_filesz[i++];
- phdr.p_memsz = vma->vm_end - vma->vm_start;
+ phdr.p_filesz = meta->dump_size;
+ phdr.p_memsz = meta->end - meta->start;
offset += phdr.p_filesz;
- phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
- if (vma->vm_flags & VM_WRITE)
+ phdr.p_flags = 0;
+ if (meta->flags & VM_READ)
+ phdr.p_flags |= PF_R;
+ if (meta->flags & VM_WRITE)
phdr.p_flags |= PF_W;
- if (vma->vm_flags & VM_EXEC)
+ if (meta->flags & VM_EXEC)
phdr.p_flags |= PF_X;
phdr.p_align = ELF_EXEC_PAGESIZE;
@@ -2322,9 +2265,10 @@ static int elf_core_dump(struct coredump
if (!dump_skip(cprm, dataoff - cprm->pos))
goto end_coredump;
- for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
- vma = next_vma(vma, gate_vma)) {
- if (!dump_user_range(cprm, vma->vm_start, vma_filesz[i++]))
+ for (i = 0; i < vma_count; i++) {
+ struct core_vma_metadata *meta = vma_meta + i;
+
+ if (!dump_user_range(cprm, meta->start, meta->dump_size))
goto end_coredump;
}
dump_truncate(cprm);
@@ -2340,7 +2284,7 @@ static int elf_core_dump(struct coredump
end_coredump:
free_note_info(&info);
kfree(shdr4extnum);
- kvfree(vma_filesz);
+ kvfree(vma_meta);
kfree(phdr4note);
return has_dumped;
}
--- a/fs/binfmt_elf_fdpic.c~binfmt_elf-binfmt_elf_fdpic-use-a-vma-list-snapshot
+++ a/fs/binfmt_elf_fdpic.c
@@ -1454,29 +1454,21 @@ static void fill_extnum_info(struct elfh
/*
* dump the segments for an MMU process
*/
-static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
+static bool elf_fdpic_dump_segments(struct coredump_params *cprm,
+ struct core_vma_metadata *vma_meta,
+ int vma_count)
{
- struct vm_area_struct *vma;
+ int i;
- for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
- unsigned long size = vma_dump_size(vma, cprm->mm_flags);
+ for (i = 0; i < vma_count; i++) {
+ struct core_vma_metadata *meta = vma_meta + i;
- if (!dump_user_range(cprm, vma->vm_start, size))
+ if (!dump_user_range(cprm, meta->start, meta->dump_size))
return false;
}
return true;
}
-static size_t elf_core_vma_data_size(unsigned long mm_flags)
-{
- struct vm_area_struct *vma;
- size_t size = 0;
-
- for (vma = current->mm->mmap; vma; vma = vma->vm_next)
- size += vma_dump_size(vma, mm_flags);
- return size;
-}
-
/*
* Actual dumper
*
@@ -1487,9 +1479,8 @@ static size_t elf_core_vma_data_size(uns
static int elf_fdpic_core_dump(struct coredump_params *cprm)
{
int has_dumped = 0;
- int segs;
+ int vma_count, segs;
int i;
- struct vm_area_struct *vma;
struct elfhdr *elf = NULL;
loff_t offset = 0, dataoff;
struct memelfnote psinfo_note, auxv_note;
@@ -1503,18 +1494,8 @@ static int elf_fdpic_core_dump(struct co
elf_addr_t e_shoff;
struct core_thread *ct;
struct elf_thread_status *tmp;
-
- /*
- * We no longer stop all VM operations.
- *
- * This is because those proceses that could possibly change map_count
- * or the mmap / vma pages are now blocked in do_exit on current
- * finishing this core dump.
- *
- * Only ptrace can touch these memory addresses, but it doesn't change
- * the map_count or the pages allocated. So no possibility of crashing
- * exists while dumping the mm->vm_next areas to the core file.
- */
+ struct core_vma_metadata *vma_meta = NULL;
+ size_t vma_data_size;
/* alloc memory for large data structures: too large to be on stack */
elf = kmalloc(sizeof(*elf), GFP_KERNEL);
@@ -1524,6 +1505,9 @@ static int elf_fdpic_core_dump(struct co
if (!psinfo)
goto end_coredump;
+ if (dump_vma_snapshot(cprm, &vma_count, &vma_meta, &vma_data_size))
+ goto end_coredump;
+
for (ct = current->mm->core_state->dumper.next;
ct; ct = ct->next) {
tmp = elf_dump_thread_status(cprm->siginfo->si_signo,
@@ -1543,8 +1527,7 @@ static int elf_fdpic_core_dump(struct co
tmp->next = thread_list;
thread_list = tmp;
- segs = current->mm->map_count;
- segs += elf_core_extra_phdrs();
+ segs = vma_count + elf_core_extra_phdrs();
/* for notes section */
segs++;
@@ -1589,7 +1572,7 @@ static int elf_fdpic_core_dump(struct co
/* Page-align dumped data */
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
- offset += elf_core_vma_data_size(cprm->mm_flags);
+ offset += vma_data_size;
offset += elf_core_extra_data_size();
e_shoff = offset;
@@ -1609,23 +1592,26 @@ static int elf_fdpic_core_dump(struct co
goto end_coredump;
/* write program headers for segments dump */
- for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
+ for (i = 0; i < vma_count; i++) {
+ struct core_vma_metadata *meta = vma_meta + i;
struct elf_phdr phdr;
size_t sz;
- sz = vma->vm_end - vma->vm_start;
+ sz = meta->end - meta->start;
phdr.p_type = PT_LOAD;
phdr.p_offset = offset;
- phdr.p_vaddr = vma->vm_start;
+ phdr.p_vaddr = meta->start;
phdr.p_paddr = 0;
- phdr.p_filesz = vma_dump_size(vma, cprm->mm_flags);
+ phdr.p_filesz = meta->dump_size;
phdr.p_memsz = sz;
offset += phdr.p_filesz;
- phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
- if (vma->vm_flags & VM_WRITE)
+ phdr.p_flags = 0;
+ if (meta->flags & VM_READ)
+ phdr.p_flags |= PF_R;
+ if (meta->flags & VM_WRITE)
phdr.p_flags |= PF_W;
- if (vma->vm_flags & VM_EXEC)
+ if (meta->flags & VM_EXEC)
phdr.p_flags |= PF_X;
phdr.p_align = ELF_EXEC_PAGESIZE;
@@ -1657,7 +1643,7 @@ static int elf_fdpic_core_dump(struct co
if (!dump_skip(cprm, dataoff - cprm->pos))
goto end_coredump;
- if (!elf_fdpic_dump_segments(cprm))
+ if (!elf_fdpic_dump_segments(cprm, vma_meta, vma_count))
goto end_coredump;
if (!elf_core_write_extra_data(cprm))
@@ -1681,6 +1667,7 @@ end_coredump:
thread_list = thread_list->next;
kfree(tmp);
}
+ kvfree(vma_meta);
kfree(phdr4note);
kfree(elf);
kfree(psinfo);
--- a/fs/coredump.c~binfmt_elf-binfmt_elf_fdpic-use-a-vma-list-snapshot
+++ a/fs/coredump.c
@@ -971,7 +971,8 @@ static bool always_dump_vma(struct vm_ar
/*
* Decide how much of @vma's contents should be included in a core dump.
*/
-unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags)
+static unsigned long vma_dump_size(struct vm_area_struct *vma,
+ unsigned long mm_flags)
{
#define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type))
@@ -1037,3 +1038,81 @@ unsigned long vma_dump_size(struct vm_ar
whole:
return vma->vm_end - vma->vm_start;
}
+
+static struct vm_area_struct *first_vma(struct task_struct *tsk,
+ struct vm_area_struct *gate_vma)
+{
+ struct vm_area_struct *ret = tsk->mm->mmap;
+
+ if (ret)
+ return ret;
+ return gate_vma;
+}
+
+/*
+ * Helper function for iterating across a vma list. It ensures that the caller
+ * will visit `gate_vma' prior to terminating the search.
+ */
+static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
+ struct vm_area_struct *gate_vma)
+{
+ struct vm_area_struct *ret;
+
+ ret = this_vma->vm_next;
+ if (ret)
+ return ret;
+ if (this_vma == gate_vma)
+ return NULL;
+ return gate_vma;
+}
+
+/*
+ * Under the mmap_lock, take a snapshot of relevant information about the task's
+ * VMAs.
+ */
+int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
+ struct core_vma_metadata **vma_meta,
+ size_t *vma_data_size_ptr)
+{
+ struct vm_area_struct *vma, *gate_vma;
+ struct mm_struct *mm = current->mm;
+ int i;
+ size_t vma_data_size = 0;
+
+ /*
+ * Once the stack expansion code is fixed to not change VMA bounds
+ * under mmap_lock in read mode, this can be changed to take the
+ * mmap_lock in read mode.
+ */
+ if (mmap_write_lock_killable(mm))
+ return -EINTR;
+
+ gate_vma = get_gate_vma(mm);
+ *vma_count = mm->map_count + (gate_vma ? 1 : 0);
+
+ *vma_meta = kvmalloc_array(*vma_count, sizeof(**vma_meta), GFP_KERNEL);
+ if (!*vma_meta) {
+ mmap_write_unlock(mm);
+ return -ENOMEM;
+ }
+
+ for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
+ vma = next_vma(vma, gate_vma), i++) {
+ struct core_vma_metadata *m = (*vma_meta) + i;
+
+ m->start = vma->vm_start;
+ m->end = vma->vm_end;
+ m->flags = vma->vm_flags;
+ m->dump_size = vma_dump_size(vma, cprm->mm_flags);
+
+ vma_data_size += m->dump_size;
+ }
+
+ mmap_write_unlock(mm);
+
+ if (WARN_ON(i != *vma_count))
+ return -EFAULT;
+
+ *vma_data_size_ptr = vma_data_size;
+ return 0;
+}
--- a/include/linux/coredump.h~binfmt_elf-binfmt_elf_fdpic-use-a-vma-list-snapshot
+++ a/include/linux/coredump.h
@@ -7,6 +7,12 @@
#include <linux/fs.h>
#include <asm/siginfo.h>
+struct core_vma_metadata {
+ unsigned long start, end;
+ unsigned long flags;
+ unsigned long dump_size;
+};
+
/*
* These are the only things you should do on a core-file: use only these
* functions to write out all the necessary info.
@@ -16,9 +22,11 @@ extern int dump_skip(struct coredump_par
extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
extern int dump_align(struct coredump_params *cprm, int align);
extern void dump_truncate(struct coredump_params *cprm);
-unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags);
int dump_user_range(struct coredump_params *cprm, unsigned long start,
unsigned long len);
+int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
+ struct core_vma_metadata **vma_meta,
+ size_t *vma_data_size_ptr);
#ifdef CONFIG_COREDUMP
extern void do_coredump(const kernel_siginfo_t *siginfo);
#else
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 141/156] mm/gup: take mmap_lock in get_dump_page()
2020-10-16 2:40 incoming Andrew Morton
` (140 preceding siblings ...)
2020-10-16 3:12 ` [patch 140/156] binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot Andrew Morton
@ 2020-10-16 3:12 ` Andrew Morton
2020-10-16 3:13 ` [patch 142/156] mm: remove the now-unnecessary mmget_still_valid() hack Andrew Morton
` (24 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:12 UTC (permalink / raw)
To: akpm, ebiederm, hch, hughd, jannh, mm-commits, oleg, torvalds, viro
From: Jann Horn <jannh@google.com>
Subject: mm/gup: take mmap_lock in get_dump_page()
Properly take the mmap_lock before calling into the GUP code from
get_dump_page(); and play nice, allowing the GUP code to drop the
mmap_lock if it has to sleep.
As Linus pointed out, we don't actually need the VMA because
__get_user_pages() will flush the dcache for us if necessary.
Link: http://lkml.kernel.org/r/20200827114932.3572699-7-jannh@google.com
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/gup.c | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
--- a/mm/gup.c~mm-gup-take-mmap_lock-in-get_dump_page
+++ a/mm/gup.c
@@ -1547,19 +1547,23 @@ finish_or_fault:
* NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
* allowing a hole to be left in the corefile to save diskspace.
*
- * Called without mmap_lock, but after all other threads have been killed.
+ * Called without mmap_lock (takes and releases the mmap_lock by itself).
*/
#ifdef CONFIG_ELF_CORE
struct page *get_dump_page(unsigned long addr)
{
- struct vm_area_struct *vma;
+ struct mm_struct *mm = current->mm;
struct page *page;
+ int locked = 1;
+ int ret;
- if (__get_user_pages_locked(current->mm, addr, 1, &page, &vma, NULL,
- FOLL_FORCE | FOLL_DUMP | FOLL_GET) < 1)
+ if (mmap_read_lock_killable(mm))
return NULL;
- flush_cache_page(vma, addr, page_to_pfn(page));
- return page;
+ ret = __get_user_pages_locked(mm, addr, 1, &page, NULL, &locked,
+ FOLL_FORCE | FOLL_DUMP | FOLL_GET);
+ if (locked)
+ mmap_read_unlock(mm);
+ return (ret == 1) ? page : NULL;
}
#endif /* CONFIG_ELF_CORE */
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 142/156] mm: remove the now-unnecessary mmget_still_valid() hack
2020-10-16 2:40 incoming Andrew Morton
` (141 preceding siblings ...)
2020-10-16 3:12 ` [patch 141/156] mm/gup: take mmap_lock in get_dump_page() Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 143/156] ramfs: fix nommu mmap with gaps in the page cache Andrew Morton
` (23 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, ebiederm, hch, hughd, jannh, mm-commits, oleg, torvalds, viro
From: Jann Horn <jannh@google.com>
Subject: mm: remove the now-unnecessary mmget_still_valid() hack
The preceding patches have ensured that core dumping properly takes the
mmap_lock. Thanks to that, we can now remove mmget_still_valid() and all
its users.
Link: http://lkml.kernel.org/r/20200827114932.3572699-8-jannh@google.com
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/infiniband/core/uverbs_main.c | 3 -
drivers/vfio/pci/vfio_pci.c | 38 +++++++++++-------------
fs/proc/task_mmu.c | 18 -----------
fs/userfaultfd.c | 28 +++++------------
include/linux/sched/mm.h | 25 ---------------
mm/khugepaged.c | 2 -
mm/madvise.c | 17 ----------
mm/mmap.c | 5 ---
8 files changed, 29 insertions(+), 107 deletions(-)
--- a/drivers/infiniband/core/uverbs_main.c~mm-remove-the-now-unnecessary-mmget_still_valid-hack
+++ a/drivers/infiniband/core/uverbs_main.c
@@ -845,8 +845,6 @@ void uverbs_user_mmap_disassociate(struc
* will only be one mm, so no big deal.
*/
mmap_read_lock(mm);
- if (!mmget_still_valid(mm))
- goto skip_mm;
mutex_lock(&ufile->umap_lock);
list_for_each_entry_safe (priv, next_priv, &ufile->umaps,
list) {
@@ -865,7 +863,6 @@ void uverbs_user_mmap_disassociate(struc
}
}
mutex_unlock(&ufile->umap_lock);
- skip_mm:
mmap_read_unlock(mm);
mmput(mm);
}
--- a/drivers/vfio/pci/vfio_pci.c~mm-remove-the-now-unnecessary-mmget_still_valid-hack
+++ a/drivers/vfio/pci/vfio_pci.c
@@ -1480,31 +1480,29 @@ static int vfio_pci_zap_and_vma_lock(str
} else {
mmap_read_lock(mm);
}
- if (mmget_still_valid(mm)) {
- if (try) {
- if (!mutex_trylock(&vdev->vma_lock)) {
- mmap_read_unlock(mm);
- mmput(mm);
- return 0;
- }
- } else {
- mutex_lock(&vdev->vma_lock);
+ if (try) {
+ if (!mutex_trylock(&vdev->vma_lock)) {
+ mmap_read_unlock(mm);
+ mmput(mm);
+ return 0;
}
- list_for_each_entry_safe(mmap_vma, tmp,
- &vdev->vma_list, vma_next) {
- struct vm_area_struct *vma = mmap_vma->vma;
+ } else {
+ mutex_lock(&vdev->vma_lock);
+ }
+ list_for_each_entry_safe(mmap_vma, tmp,
+ &vdev->vma_list, vma_next) {
+ struct vm_area_struct *vma = mmap_vma->vma;
- if (vma->vm_mm != mm)
- continue;
+ if (vma->vm_mm != mm)
+ continue;
- list_del(&mmap_vma->vma_next);
- kfree(mmap_vma);
+ list_del(&mmap_vma->vma_next);
+ kfree(mmap_vma);
- zap_vma_ptes(vma, vma->vm_start,
- vma->vm_end - vma->vm_start);
- }
- mutex_unlock(&vdev->vma_lock);
+ zap_vma_ptes(vma, vma->vm_start,
+ vma->vm_end - vma->vm_start);
}
+ mutex_unlock(&vdev->vma_lock);
mmap_read_unlock(mm);
mmput(mm);
}
--- a/fs/proc/task_mmu.c~mm-remove-the-now-unnecessary-mmget_still_valid-hack
+++ a/fs/proc/task_mmu.c
@@ -1244,24 +1244,6 @@ static ssize_t clear_refs_write(struct f
count = -EINTR;
goto out_mm;
}
- /*
- * Avoid to modify vma->vm_flags
- * without locked ops while the
- * coredump reads the vm_flags.
- */
- if (!mmget_still_valid(mm)) {
- /*
- * Silently return "count"
- * like if get_task_mm()
- * failed. FIXME: should this
- * function have returned
- * -ESRCH if get_task_mm()
- * failed like if
- * get_proc_task() fails?
- */
- mmap_write_unlock(mm);
- goto out_mm;
- }
for (vma = mm->mmap; vma; vma = vma->vm_next) {
vma->vm_flags &= ~VM_SOFTDIRTY;
vma_set_page_prot(vma);
--- a/fs/userfaultfd.c~mm-remove-the-now-unnecessary-mmget_still_valid-hack
+++ a/fs/userfaultfd.c
@@ -601,8 +601,6 @@ static void userfaultfd_event_wait_compl
/* the various vma->vm_userfaultfd_ctx still points to it */
mmap_write_lock(mm);
- /* no task can run (and in turn coredump) yet */
- VM_WARN_ON(!mmget_still_valid(mm));
for (vma = mm->mmap; vma; vma = vma->vm_next)
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
@@ -842,7 +840,6 @@ static int userfaultfd_release(struct in
/* len == 0 means wake all */
struct userfaultfd_wake_range range = { .len = 0, };
unsigned long new_flags;
- bool still_valid;
WRITE_ONCE(ctx->released, true);
@@ -858,7 +855,6 @@ static int userfaultfd_release(struct in
* taking the mmap_lock for writing.
*/
mmap_write_lock(mm);
- still_valid = mmget_still_valid(mm);
prev = NULL;
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cond_resched();
@@ -869,17 +865,15 @@ static int userfaultfd_release(struct in
continue;
}
new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
- if (still_valid) {
- prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
- new_flags, vma->anon_vma,
- vma->vm_file, vma->vm_pgoff,
- vma_policy(vma),
- NULL_VM_UFFD_CTX);
- if (prev)
- vma = prev;
- else
- prev = vma;
- }
+ prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
+ new_flags, vma->anon_vma,
+ vma->vm_file, vma->vm_pgoff,
+ vma_policy(vma),
+ NULL_VM_UFFD_CTX);
+ if (prev)
+ vma = prev;
+ else
+ prev = vma;
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
@@ -1309,8 +1303,6 @@ static int userfaultfd_register(struct u
goto out;
mmap_write_lock(mm);
- if (!mmget_still_valid(mm))
- goto out_unlock;
vma = find_vma_prev(mm, start, &prev);
if (!vma)
goto out_unlock;
@@ -1511,8 +1503,6 @@ static int userfaultfd_unregister(struct
goto out;
mmap_write_lock(mm);
- if (!mmget_still_valid(mm))
- goto out_unlock;
vma = find_vma_prev(mm, start, &prev);
if (!vma)
goto out_unlock;
--- a/include/linux/sched/mm.h~mm-remove-the-now-unnecessary-mmget_still_valid-hack
+++ a/include/linux/sched/mm.h
@@ -49,31 +49,6 @@ static inline void mmdrop(struct mm_stru
__mmdrop(mm);
}
-/*
- * This has to be called after a get_task_mm()/mmget_not_zero()
- * followed by taking the mmap_lock for writing before modifying the
- * vmas or anything the coredump pretends not to change from under it.
- *
- * It also has to be called when mmgrab() is used in the context of
- * the process, but then the mm_count refcount is transferred outside
- * the context of the process to run down_write() on that pinned mm.
- *
- * NOTE: find_extend_vma() called from GUP context is the only place
- * that can modify the "mm" (notably the vm_start/end) under mmap_lock
- * for reading and outside the context of the process, so it is also
- * the only case that holds the mmap_lock for reading that must call
- * this function. Generally if the mmap_lock is hold for reading
- * there's no need of this check after get_task_mm()/mmget_not_zero().
- *
- * This function can be obsoleted and the check can be removed, after
- * the coredump code will hold the mmap_lock for writing before
- * invoking the ->core_dump methods.
- */
-static inline bool mmget_still_valid(struct mm_struct *mm)
-{
- return likely(!mm->core_state);
-}
-
/**
* mmget() - Pin the address space associated with a &struct mm_struct.
* @mm: The address space to pin.
--- a/mm/khugepaged.c~mm-remove-the-now-unnecessary-mmget_still_valid-hack
+++ a/mm/khugepaged.c
@@ -434,7 +434,7 @@ static void insert_to_mm_slots_hash(stru
static inline int khugepaged_test_exit(struct mm_struct *mm)
{
- return atomic_read(&mm->mm_users) == 0 || !mmget_still_valid(mm);
+ return atomic_read(&mm->mm_users) == 0;
}
static bool hugepage_vma_check(struct vm_area_struct *vma,
--- a/mm/madvise.c~mm-remove-the-now-unnecessary-mmget_still_valid-hack
+++ a/mm/madvise.c
@@ -1085,23 +1085,6 @@ int do_madvise(unsigned long start, size
if (write) {
if (mmap_write_lock_killable(current->mm))
return -EINTR;
-
- /*
- * We may have stolen the mm from another process
- * that is undergoing core dumping.
- *
- * Right now that's io_ring, in the future it may
- * be remote process management and not "current"
- * at all.
- *
- * We need to fix core dumping to not do this,
- * but for now we have the mmget_still_valid()
- * model.
- */
- if (!mmget_still_valid(current->mm)) {
- mmap_write_unlock(current->mm);
- return -EINTR;
- }
} else {
mmap_read_lock(current->mm);
}
--- a/mm/mmap.c~mm-remove-the-now-unnecessary-mmget_still_valid-hack
+++ a/mm/mmap.c
@@ -2562,7 +2562,7 @@ find_extend_vma(struct mm_struct *mm, un
if (vma && (vma->vm_start <= addr))
return vma;
/* don't alter vm_end if the coredump is running */
- if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr))
+ if (!prev || expand_stack(prev, addr))
return NULL;
if (prev->vm_flags & VM_LOCKED)
populate_vma_page_range(prev, addr, prev->vm_end, NULL);
@@ -2588,9 +2588,6 @@ find_extend_vma(struct mm_struct *mm, un
return vma;
if (!(vma->vm_flags & VM_GROWSDOWN))
return NULL;
- /* don't alter vm_start if the coredump is running */
- if (!mmget_still_valid(mm))
- return NULL;
start = vma->vm_start;
if (expand_stack(vma, addr))
return NULL;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 143/156] ramfs: fix nommu mmap with gaps in the page cache
2020-10-16 2:40 incoming Andrew Morton
` (142 preceding siblings ...)
2020-10-16 3:13 ` [patch 142/156] mm: remove the now-unnecessary mmget_still_valid() hack Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 144/156] autofs: harden ioctl table Andrew Morton
` (22 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, dhowells, mm-commits, torvalds, willy
From: Matthew Wilcox (Oracle) <willy@infradead.org>
Subject: ramfs: fix nommu mmap with gaps in the page cache
ramfs needs to check that pages are both physically contiguous and
contiguous in the file. If the page cache happens to have, eg, page A for
index 0 of the file, no page for index 1, and page A+1 for index 2, then
an mmap of the first two pages of the file will succeed when it should
fail.
Link: https://lkml.kernel.org/r/20200914122239.GO6583@casper.infradead.org
Fixes: 642fb4d1f1dd ("[PATCH] NOMMU: Provide shared-writable mmap support on ramfs")
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/ramfs/file-nommu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/fs/ramfs/file-nommu.c~ramfs-fix-nommu-mmap-with-gaps-in-the-page-cache
+++ a/fs/ramfs/file-nommu.c
@@ -224,7 +224,7 @@ static unsigned long ramfs_nommu_get_unm
if (!pages)
goto out_free;
- nr = find_get_pages(inode->i_mapping, &pgoff, lpages, pages);
+ nr = find_get_pages_contig(inode->i_mapping, pgoff, lpages, pages);
if (nr != lpages)
goto out_free_pages; /* leave if some pages were missing */
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 144/156] autofs: harden ioctl table
2020-10-16 2:40 incoming Andrew Morton
` (143 preceding siblings ...)
2020-10-16 3:13 ` [patch 143/156] ramfs: fix nommu mmap with gaps in the page cache Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 145/156] nilfs2: fix some kernel-doc warnings for nilfs2 Andrew Morton
` (21 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, mm-commits, raven, torvalds, willy
From: Matthew Wilcox <willy@infradead.org>
Subject: autofs: harden ioctl table
The table of ioctl functions should be marked const in order to put them
in read-only memory, and we should use array_index_nospec() to avoid
speculation disclosing the contents of kernel memory to userspace.
Link: https://lkml.kernel.org/r/20200818122203.GO17456@casper.infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Ian Kent <raven@themaw.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/autofs/dev-ioctl.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
--- a/fs/autofs/dev-ioctl.c~harden-autofs-ioctl-table
+++ a/fs/autofs/dev-ioctl.c
@@ -8,6 +8,7 @@
#include <linux/compat.h>
#include <linux/syscalls.h>
#include <linux/magic.h>
+#include <linux/nospec.h>
#include "autofs_i.h"
@@ -563,7 +564,7 @@ out:
static ioctl_fn lookup_dev_ioctl(unsigned int cmd)
{
- static ioctl_fn _ioctls[] = {
+ static const ioctl_fn _ioctls[] = {
autofs_dev_ioctl_version,
autofs_dev_ioctl_protover,
autofs_dev_ioctl_protosubver,
@@ -581,7 +582,10 @@ static ioctl_fn lookup_dev_ioctl(unsigne
};
unsigned int idx = cmd_idx(cmd);
- return (idx >= ARRAY_SIZE(_ioctls)) ? NULL : _ioctls[idx];
+ if (idx >= ARRAY_SIZE(_ioctls))
+ return NULL;
+ idx = array_index_nospec(idx, ARRAY_SIZE(_ioctls));
+ return _ioctls[idx];
}
/* ioctl dispatcher */
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 145/156] nilfs2: fix some kernel-doc warnings for nilfs2
2020-10-16 2:40 incoming Andrew Morton
` (144 preceding siblings ...)
2020-10-16 3:13 ` [patch 144/156] autofs: harden ioctl table Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 146/156] rapidio: fix error handling path Andrew Morton
` (20 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, konishi.ryusuke, mm-commits, torvalds, wanghai38
From: Wang Hai <wanghai38@huawei.com>
Subject: nilfs2: fix some kernel-doc warnings for nilfs2
Fixes the following W=1 kernel build warning(s):
fs/nilfs2/bmap.c:378: warning: Excess function parameter 'bhp' description in 'nilfs_bmap_assign'
fs/nilfs2/cpfile.c:907: warning: Excess function parameter 'status' description in 'nilfs_cpfile_change_cpmode'
fs/nilfs2/cpfile.c:946: warning: Excess function parameter 'stat' description in 'nilfs_cpfile_get_stat'
fs/nilfs2/page.c:76: warning: Excess function parameter 'inode' description in 'nilfs_forget_buffer'
fs/nilfs2/sufile.c:563: warning: Excess function parameter 'stat' description in 'nilfs_sufile_get_stat'
Link: https://lkml.kernel.org/r/1601386269-2423-1-git-send-email-konishi.ryusuke@gmail.com
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/nilfs2/bmap.c | 2 +-
fs/nilfs2/cpfile.c | 6 +++---
fs/nilfs2/page.c | 1 -
fs/nilfs2/sufile.c | 4 ++--
4 files changed, 6 insertions(+), 7 deletions(-)
--- a/fs/nilfs2/bmap.c~nilfs2-fix-some-kernel-doc-warnings-for-nilfs2
+++ a/fs/nilfs2/bmap.c
@@ -355,7 +355,7 @@ void nilfs_bmap_lookup_dirty_buffers(str
/**
* nilfs_bmap_assign - assign a new block number to a block
* @bmap: bmap
- * @bhp: pointer to buffer head
+ * @bh: pointer to buffer head
* @blocknr: block number
* @binfo: block information
*
--- a/fs/nilfs2/cpfile.c~nilfs2-fix-some-kernel-doc-warnings-for-nilfs2
+++ a/fs/nilfs2/cpfile.c
@@ -889,7 +889,7 @@ int nilfs_cpfile_is_snapshot(struct inod
* nilfs_cpfile_change_cpmode - change checkpoint mode
* @cpfile: inode of checkpoint file
* @cno: checkpoint number
- * @status: mode of checkpoint
+ * @mode: mode of checkpoint
*
* Description: nilfs_change_cpmode() changes the mode of the checkpoint
* specified by @cno. The mode @mode is NILFS_CHECKPOINT or NILFS_SNAPSHOT.
@@ -930,12 +930,12 @@ int nilfs_cpfile_change_cpmode(struct in
/**
* nilfs_cpfile_get_stat - get checkpoint statistics
* @cpfile: inode of checkpoint file
- * @stat: pointer to a structure of checkpoint statistics
+ * @cpstat: pointer to a structure of checkpoint statistics
*
* Description: nilfs_cpfile_get_stat() returns information about checkpoints.
*
* Return Value: On success, 0 is returned, and checkpoints information is
- * stored in the place pointed by @stat. On error, one of the following
+ * stored in the place pointed by @cpstat. On error, one of the following
* negative error codes is returned.
*
* %-EIO - I/O error.
--- a/fs/nilfs2/page.c~nilfs2-fix-some-kernel-doc-warnings-for-nilfs2
+++ a/fs/nilfs2/page.c
@@ -69,7 +69,6 @@ struct buffer_head *nilfs_grab_buffer(st
/**
* nilfs_forget_buffer - discard dirty state
- * @inode: owner inode of the buffer
* @bh: buffer head of the buffer to be discarded
*/
void nilfs_forget_buffer(struct buffer_head *bh)
--- a/fs/nilfs2/sufile.c~nilfs2-fix-some-kernel-doc-warnings-for-nilfs2
+++ a/fs/nilfs2/sufile.c
@@ -546,13 +546,13 @@ int nilfs_sufile_set_segment_usage(struc
/**
* nilfs_sufile_get_stat - get segment usage statistics
* @sufile: inode of segment usage file
- * @stat: pointer to a structure of segment usage statistics
+ * @sustat: pointer to a structure of segment usage statistics
*
* Description: nilfs_sufile_get_stat() returns information about segment
* usage.
*
* Return Value: On success, 0 is returned, and segment usage information is
- * stored in the place pointed by @stat. On error, one of the following
+ * stored in the place pointed by @sustat. On error, one of the following
* negative error codes is returned.
*
* %-EIO - I/O error.
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 146/156] rapidio: fix error handling path
2020-10-16 2:40 incoming Andrew Morton
` (145 preceding siblings ...)
2020-10-16 3:13 ` [patch 145/156] nilfs2: fix some kernel-doc warnings for nilfs2 Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 147/156] rapidio: fix the missed put_device() for rio_mport_add_riodev Andrew Morton
` (19 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, alex.bou9, dan.carpenter, gustavoars, ira.weiny, jhubbard,
jrdr.linux, madhuparnabhowmik10, mm-commits, mporter, torvalds,
willy
From: Souptick Joarder <jrdr.linux@gmail.com>
Subject: rapidio: fix error handling path
rio_dma_transfer() attempts to clamp the return value of
pin_user_pages_fast() to be >= 0. However, the attempt fails because
nr_pages is overridden a few lines later, and restored to the undesirable
-ERRNO value.
The return value is ultimately stored in nr_pages, which in turn is passed
to unpin_user_pages(), which expects nr_pages >= 0, else, disaster.
Fix this by fixing the nesting of the assignment to nr_pages: nr_pages
should be clamped to zero if pin_user_pages_fast() returns -ERRNO, or set
to the return value of pin_user_pages_fast(), otherwise.
[jhubbard@nvidia.com: new changelog]
Link: https://lkml.kernel.org/r/1600227737-20785-1-git-send-email-jrdr.linux@gmail.com
Fixes: e8de370188d09 ("rapidio: add mport char device driver")
Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: Madhuparna Bhowmik <madhuparnabhowmik10@gmail.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/rapidio/devices/rio_mport_cdev.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
--- a/drivers/rapidio/devices/rio_mport_cdev.c~rapidio-fix-error-handling-path
+++ a/drivers/rapidio/devices/rio_mport_cdev.c
@@ -871,15 +871,16 @@ rio_dma_transfer(struct file *filp, u32
rmcd_error("pin_user_pages_fast err=%ld",
pinned);
nr_pages = 0;
- } else
+ } else {
rmcd_error("pinned %ld out of %ld pages",
pinned, nr_pages);
+ /*
+ * Set nr_pages up to mean "how many pages to unpin, in
+ * the error handler:
+ */
+ nr_pages = pinned;
+ }
ret = -EFAULT;
- /*
- * Set nr_pages up to mean "how many pages to unpin, in
- * the error handler:
- */
- nr_pages = pinned;
goto err_pg;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 147/156] rapidio: fix the missed put_device() for rio_mport_add_riodev
2020-10-16 2:40 incoming Andrew Morton
` (146 preceding siblings ...)
2020-10-16 3:13 ` [patch 146/156] rapidio: fix error handling path Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 148/156] panic: dump registers on panic_on_warn Andrew Morton
` (18 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, alex.bou9, dan.carpenter, gustavoars, jhubbard,
jingxiangfeng, keescook, madhuparnabhowmik10, mm-commits,
mporter, torvalds
From: Jing Xiangfeng <jingxiangfeng@huawei.com>
Subject: rapidio: fix the missed put_device() for rio_mport_add_riodev
rio_mport_add_riodev() misses to call put_device() when the device already
exists. Add the missed function call to fix it.
Link: https://lkml.kernel.org/r/20200922072525.42330-1-jingxiangfeng@huawei.com
Fixes: e8de370188d0 ("rapidio: add mport char device driver")
Signed-off-by: Jing Xiangfeng <jingxiangfeng@huawei.com>
Reviewed-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Madhuparna Bhowmik <madhuparnabhowmik10@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/rapidio/devices/rio_mport_cdev.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
--- a/drivers/rapidio/devices/rio_mport_cdev.c~rapidio-fix-the-missed-put_device-for-rio_mport_add_riodev
+++ a/drivers/rapidio/devices/rio_mport_cdev.c
@@ -1680,6 +1680,7 @@ static int rio_mport_add_riodev(struct m
struct rio_dev *rdev;
struct rio_switch *rswitch = NULL;
struct rio_mport *mport;
+ struct device *dev;
size_t size;
u32 rval;
u32 swpinfo = 0;
@@ -1694,8 +1695,10 @@ static int rio_mport_add_riodev(struct m
rmcd_debug(RDEV, "name:%s ct:0x%x did:0x%x hc:0x%x", dev_info.name,
dev_info.comptag, dev_info.destid, dev_info.hopcount);
- if (bus_find_device_by_name(&rio_bus_type, NULL, dev_info.name)) {
+ dev = bus_find_device_by_name(&rio_bus_type, NULL, dev_info.name);
+ if (dev) {
rmcd_debug(RDEV, "device %s already exists", dev_info.name);
+ put_device(dev);
return -EEXIST;
}
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 148/156] panic: dump registers on panic_on_warn
2020-10-16 2:40 incoming Andrew Morton
` (147 preceding siblings ...)
2020-10-16 3:13 ` [patch 147/156] rapidio: fix the missed put_device() for rio_mport_add_riodev Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 149/156] kernel/relay.c: drop unneeded initialization Andrew Morton
` (17 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: aik, akpm, aquini, dianders, keescook, mingo, mm-commits,
npiggin, tglx, torvalds, will
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Subject: panic: dump registers on panic_on_warn
Currently we print stack and registers for ordinary warnings but we do not
for panic_on_warn which looks as oversight - panic() will reboot the
machine but won't print registers.
This moves printing of registers and modules earlier.
This does not move the stack dumping as panic() dumps it.
Link: https://lkml.kernel.org/r/20200804095054.68724-1-aik@ozlabs.ru
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Douglas Anderson <dianders@chromium.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/panic.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
--- a/kernel/panic.c~panic-dump-registers-on-panic_on_warn
+++ a/kernel/panic.c
@@ -589,6 +589,11 @@ void __warn(const char *file, int line,
if (args)
vprintk(args->fmt, args->args);
+ print_modules();
+
+ if (regs)
+ show_regs(regs);
+
if (panic_on_warn) {
/*
* This thread may hit another WARN() in the panic path.
@@ -600,12 +605,7 @@ void __warn(const char *file, int line,
panic("panic_on_warn set ...\n");
}
- print_modules();
-
- if (regs)
- show_regs(regs);
- else
- dump_stack();
+ dump_stack();
print_irqtrace_events(current);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 149/156] kernel/relay.c: drop unneeded initialization
2020-10-16 2:40 incoming Andrew Morton
` (148 preceding siblings ...)
2020-10-16 3:13 ` [patch 148/156] panic: dump registers on panic_on_warn Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 150/156] scripts/gdb/proc: add struct mount & struct super_block addr in lx-mounts command Andrew Morton
` (16 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, mm-commits, sudipm.mukherjee, torvalds
From: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Subject: kernel/relay.c: drop unneeded initialization
The variable 'consumed' is initialized with the consumed count but
immediately after that the consumed count is updated and assigned to
'consumed' again thus overwriting the previous value. So, drop the
unneeded initialization.
Link: https://lkml.kernel.org/r/20201005205727.1147-1-sudipm.mukherjee@gmail.com
Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/relay.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/kernel/relay.c~kernel-relayc-drop-unneeded-initialization
+++ a/kernel/relay.c
@@ -1002,7 +1002,7 @@ static int relay_file_read_avail(struct
size_t subbuf_size = buf->chan->subbuf_size;
size_t n_subbufs = buf->chan->n_subbufs;
size_t produced = buf->subbufs_produced;
- size_t consumed = buf->subbufs_consumed;
+ size_t consumed;
relay_file_read_consume(buf, 0, 0);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 150/156] scripts/gdb/proc: add struct mount & struct super_block addr in lx-mounts command
2020-10-16 2:40 incoming Andrew Morton
` (149 preceding siblings ...)
2020-10-16 3:13 ` [patch 149/156] kernel/relay.c: drop unneeded initialization Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 151/156] scripts/gdb/tasks: add headers and improve spacing format Andrew Morton
` (15 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, jan.kiszka, kbingham, mm-commits, riteshh, torvalds
From: Ritesh Harjani <riteshh@linux.ibm.com>
Subject: scripts/gdb/proc: add struct mount & struct super_block addr in lx-mounts command
This is many times found useful while debugging some FS related
issue.
<e.g. output>
mount super_block devname pathname fstype options
0xffff888a0bfa4b40 0xffff888a0bfc1000 none / rootfs rw 0 0
0xffff888a033f75c0 0xffff8889fcf65000 /dev/root / ext4 rw,relatime 0 0
0xffff8889fc8ce040 0xffff888a0bb51000 devtmpfs /dev devtmpfs rw,relatime 0 0
Link: http://lkml.kernel.org/r/a3c4177e1597b3e06d66d55e07d72c0c46a03571.1597742951.git.riteshh@linux.ibm.com
Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/gdb/linux/proc.py | 15 +++++++--------
1 file changed, 7 insertions(+), 8 deletions(-)
--- a/scripts/gdb/linux/proc.py~proc-add-struct-mount-struct-super_block-addr-in-lx-mounts-command
+++ a/scripts/gdb/linux/proc.py
@@ -167,6 +167,9 @@ values of that process namespace"""
if not namespace:
raise gdb.GdbError("No namespace for current process")
+ gdb.write("{:^18} {:^15} {:>9} {} {} options\n".format(
+ "mount", "super_block", "devname", "pathname", "fstype"))
+
for vfs in lists.list_for_each_entry(namespace['list'],
mount_ptr_type, "mnt_list"):
devname = vfs['mnt_devname'].string()
@@ -190,14 +193,10 @@ values of that process namespace"""
m_flags = int(vfs['mnt']['mnt_flags'])
rd = "ro" if (s_flags & constants.LX_SB_RDONLY) else "rw"
- gdb.write(
- "{} {} {} {}{}{} 0 0\n"
- .format(devname,
- pathname,
- fstype,
- rd,
- info_opts(FS_INFO, s_flags),
- info_opts(MNT_INFO, m_flags)))
+ gdb.write("{} {} {} {} {} {}{}{} 0 0\n".format(
+ vfs.format_string(), superblock.format_string(), devname,
+ pathname, fstype, rd, info_opts(FS_INFO, s_flags),
+ info_opts(MNT_INFO, m_flags)))
LxMounts()
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 151/156] scripts/gdb/tasks: add headers and improve spacing format
2020-10-16 2:40 incoming Andrew Morton
` (150 preceding siblings ...)
2020-10-16 3:13 ` [patch 150/156] scripts/gdb/proc: add struct mount & struct super_block addr in lx-mounts command Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 152/156] sched.h: drop in_ubsan field when UBSAN is in trap mode Andrew Morton
` (14 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, jan.kiszka, kbingham, mm-commits, riteshh, torvalds
From: Ritesh Harjani <riteshh@linux.ibm.com>
Subject: scripts/gdb/tasks: add headers and improve spacing format
With the patch.
<e.g. o/p>
TASK PID COMM
0xffffffff82c2b8c0 0 swapper/0
0xffff888a0ba20040 1 systemd
0xffff888a0ba24040 2 kthreadd
0xffff888a0ba28040 3 rcu_gp
w/o
0xffffffff82c2b8c0 <init_task> 0 swapper/0
0xffff888a0ba20040 1 systemd
0xffff888a0ba24040 2 kthreadd
0xffff888a0ba28040 3 rcu_gp
Link: http://lkml.kernel.org/r/54c868c79b5fc364a8be7799891934a6fe6d1464.1597742951.git.riteshh@linux.ibm.com
Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
scripts/gdb/linux/tasks.py | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
--- a/scripts/gdb/linux/tasks.py~tasks-add-headers-and-improve-spacing-format
+++ a/scripts/gdb/linux/tasks.py
@@ -73,11 +73,12 @@ class LxPs(gdb.Command):
super(LxPs, self).__init__("lx-ps", gdb.COMMAND_DATA)
def invoke(self, arg, from_tty):
+ gdb.write("{:>10} {:>12} {:>7}\n".format("TASK", "PID", "COMM"))
for task in task_lists():
- gdb.write("{address} {pid} {comm}\n".format(
- address=task,
- pid=task["pid"],
- comm=task["comm"].string()))
+ gdb.write("{} {:^5} {}\n".format(
+ task.format_string().split()[0],
+ task["pid"].format_string(),
+ task["comm"].string()))
LxPs()
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 152/156] sched.h: drop in_ubsan field when UBSAN is in trap mode
2020-10-16 2:40 incoming Andrew Morton
` (151 preceding siblings ...)
2020-10-16 3:13 ` [patch 151/156] scripts/gdb/tasks: add headers and improve spacing format Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 153/156] ubsan: introduce CONFIG_UBSAN_LOCAL_BOUNDS for Clang Andrew Morton
` (13 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, jannh, keescook, lenaptr, mm-commits, torvalds
From: Elena Petrova <lenaptr@google.com>
Subject: sched.h: drop in_ubsan field when UBSAN is in trap mode
in_ubsan field of task_struct is only used in lib/ubsan.c, which in its
turn is used only `ifneq ($(CONFIG_UBSAN_TRAP),y)`.
Removing unnecessary field from a task_struct will help preserve the ABI
between vanilla and CONFIG_UBSAN_TRAP'ed kernels. In particular, this
will help enabling bounds sanitizer transparently for Android's GKI.
Link: https://lkml.kernel.org/r/20200910134802.3160311-1-lenaptr@google.com
Signed-off-by: Elena Petrova <lenaptr@google.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/sched.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/include/linux/sched.h~schedh-drop-in_ubsan-field-when-ubsan-is-in-trap-mode
+++ a/include/linux/sched.h
@@ -1013,7 +1013,7 @@ struct task_struct {
struct held_lock held_locks[MAX_LOCK_DEPTH];
#endif
-#ifdef CONFIG_UBSAN
+#if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP)
unsigned int in_ubsan;
#endif
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 153/156] ubsan: introduce CONFIG_UBSAN_LOCAL_BOUNDS for Clang
2020-10-16 2:40 incoming Andrew Morton
` (152 preceding siblings ...)
2020-10-16 3:13 ` [patch 152/156] sched.h: drop in_ubsan field when UBSAN is in trap mode Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 154/156] ROMFS: support inode blocks calculation Andrew Morton
` (12 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: a.p.zijlstra, akpm, arnd, dbrazdil, dvyukov, elver, georgepope,
keescook, masahiroy, michal.lkml, mm-commits, natechancellor,
ndesaulniers, torvalds
From: George Popescu <georgepope@android.com>
Subject: ubsan: introduce CONFIG_UBSAN_LOCAL_BOUNDS for Clang
When the kernel is compiled with Clang, -fsanitize=bounds expands to
-fsanitize=array-bounds and -fsanitize=local-bounds.
Enabling -fsanitize=local-bounds with Clang has the unfortunate
side-effect of inserting traps; this goes back to its original intent,
which was as a hardening and not a debugging feature [1]. The same
feature made its way into -fsanitize=bounds, but the traps remained. For
that reason, -fsanitize=bounds was split into 'array-bounds' and
'local-bounds' [2].
Since 'local-bounds' doesn't behave like a normal sanitizer, enable it
with Clang only if trapping behaviour was requested by
CONFIG_UBSAN_TRAP=y.
Add the UBSAN_BOUNDS_LOCAL config to Kconfig.ubsan to enable the
'local-bounds' option by default when UBSAN_TRAP is enabled.
[1] http://lists.llvm.org/pipermail/llvm-dev/2012-May/049972.html
[2] http://lists.llvm.org/pipermail/cfe-commits/Week-of-Mon-20131021/091536.html
Link: https://lkml.kernel.org/r/20200922074330.2549523-1-georgepope@google.com
Suggested-by: Marco Elver <elver@google.com>
Reviewed-by: David Brazdil <dbrazdil@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Signed-off-by: George Popescu <georgepope@android.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/Kconfig.ubsan | 14 ++++++++++++++
scripts/Makefile.ubsan | 10 +++++++++-
2 files changed, 23 insertions(+), 1 deletion(-)
--- a/lib/Kconfig.ubsan~ubsan-introducing-config_ubsan_local_bounds-for-clang
+++ a/lib/Kconfig.ubsan
@@ -47,6 +47,20 @@ config UBSAN_BOUNDS
to the {str,mem}*cpy() family of functions (that is addressed
by CONFIG_FORTIFY_SOURCE).
+config UBSAN_LOCAL_BOUNDS
+ bool "Perform array local bounds checking"
+ depends on UBSAN_TRAP
+ depends on CC_IS_CLANG
+ depends on !UBSAN_KCOV_BROKEN
+ help
+ This option enables -fsanitize=local-bounds which traps when an
+ exception/error is detected. Therefore, it should be enabled only
+ if trapping is expected.
+ Enabling this option detects errors due to accesses through a
+ pointer that is derived from an object of a statically-known size,
+ where an added offset (which may not be known statically) is
+ out-of-bounds.
+
config UBSAN_MISC
bool "Enable all other Undefined Behavior sanity checks"
default UBSAN
--- a/scripts/Makefile.ubsan~ubsan-introducing-config_ubsan_local_bounds-for-clang
+++ a/scripts/Makefile.ubsan
@@ -4,7 +4,15 @@ ifdef CONFIG_UBSAN_ALIGNMENT
endif
ifdef CONFIG_UBSAN_BOUNDS
- CFLAGS_UBSAN += $(call cc-option, -fsanitize=bounds)
+ ifdef CONFIG_CC_IS_CLANG
+ CFLAGS_UBSAN += -fsanitize=array-bounds
+ else
+ CFLAGS_UBSAN += $(call cc-option, -fsanitize=bounds)
+ endif
+endif
+
+ifdef CONFIG_UBSAN_LOCAL_BOUNDS
+ CFLAGS_UBSAN += -fsanitize=local-bounds
endif
ifdef CONFIG_UBSAN_MISC
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 154/156] ROMFS: support inode blocks calculation
2020-10-16 2:40 incoming Andrew Morton
` (153 preceding siblings ...)
2020-10-16 3:13 ` [patch 153/156] ubsan: introduce CONFIG_UBSAN_LOCAL_BOUNDS for Clang Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 155/156] lib, include/linux: add usercopy failure capability Andrew Morton
` (11 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akpm, dhowells, libing.zhou, mm-commits, torvalds, viro
From: Libing Zhou <libing.zhou@nokia-sbell.com>
Subject: ROMFS: support inode blocks calculation
When use 'stat' tool to display file status, the 'Blocks' field always in
'0', this is not good for tool 'du'(e.g.: busybox 'du'), it always output
'0' size for the files under ROMFS since such tool calculates number of
512B Blocks.
This patch calculates approx. number of 512B blocks based on inode size.
Link: http://lkml.kernel.org/r/20200811052606.4243-1-libing.zhou@nokia-sbell.com
Signed-off-by: Libing Zhou <libing.zhou@nokia-sbell.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/romfs/super.c | 1 +
1 file changed, 1 insertion(+)
--- a/fs/romfs/super.c~romfs-support-inode-blocks-calculation
+++ a/fs/romfs/super.c
@@ -356,6 +356,7 @@ static struct inode *romfs_iget(struct s
}
i->i_mode = mode;
+ i->i_blocks = (i->i_size + 511) >> 9;
unlock_new_inode(i);
return i;
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 155/156] lib, include/linux: add usercopy failure capability
2020-10-16 2:40 incoming Andrew Morton
` (154 preceding siblings ...)
2020-10-16 3:13 ` [patch 154/156] ROMFS: support inode blocks calculation Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-16 3:13 ` [patch 156/156] lib, uaccess: add failure injection to usercopy functions Andrew Morton
` (10 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akinobu.mita, akpm, alinde, andreyknvl, arnd, bp, corbet,
dvyukov, elver, glider, hch, hpa, mingo, mm-commits, peterz,
tglx, torvalds, viro
From: Albert van der Linde <alinde@google.com>
Subject: lib, include/linux: add usercopy failure capability
Patch series "add fault injection to user memory access", v3.
The goal of this series is to improve testing of fault-tolerance in usages
of user memory access functions, by adding support for fault injection.
syzkaller/syzbot are using the existing fault injection modes and will use
this particular feature also.
The first patch adds failure injection capability for usercopy functions.
The second changes usercopy functions to use this new failure capability
(copy_from_user, ...). The third patch adds get/put/clear_user failures
to x86.
This patch (of 3):
Add a failure injection capability to improve testing of fault-tolerance
in usages of user memory access functions.
Add CONFIG_FAULT_INJECTION_USERCOPY to enable faults in usercopy
functions. The should_fail_usercopy function is to be called by these
functions (copy_from_user, get_user, ...) in order to fail or not.
Link: http://lkml.kernel.org/r/20200831171733.955393-1-alinde@google.com
Link: http://lkml.kernel.org/r/20200831171733.955393-2-alinde@google.com
Signed-off-by: Albert van der Linde <alinde@google.com>
Reviewed-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
Documentation/admin-guide/kernel-parameters.txt | 1
Documentation/fault-injection/fault-injection.rst | 7 +-
include/linux/fault-inject-usercopy.h | 22 ++++++
lib/Kconfig.debug | 7 ++
lib/Makefile | 1
lib/fault-inject-usercopy.c | 39 ++++++++++++
6 files changed, 76 insertions(+), 1 deletion(-)
--- a/Documentation/admin-guide/kernel-parameters.txt~lib-include-linux-add-usercopy-failure-capability
+++ a/Documentation/admin-guide/kernel-parameters.txt
@@ -1343,6 +1343,7 @@
current integrity status.
failslab=
+ fail_usercopy=
fail_page_alloc=
fail_make_request=[KNL]
General fault injection mechanism.
--- a/Documentation/fault-injection/fault-injection.rst~lib-include-linux-add-usercopy-failure-capability
+++ a/Documentation/fault-injection/fault-injection.rst
@@ -16,6 +16,10 @@ Available fault injection capabilities
injects page allocation failures. (alloc_pages(), get_free_pages(), ...)
+- fail_usercopy
+
+ injects failures in user memory access functions. (copy_from_user(), get_user(), ...)
+
- fail_futex
injects futex deadlock and uaddr fault errors.
@@ -177,6 +181,7 @@ use the boot option::
failslab=
fail_page_alloc=
+ fail_usercopy=
fail_make_request=
fail_futex=
mmc_core.fail_request=<interval>,<probability>,<space>,<times>
@@ -222,7 +227,7 @@ How to add new fault injection capabilit
- debugfs entries
- failslab, fail_page_alloc, and fail_make_request use this way.
+ failslab, fail_page_alloc, fail_usercopy, and fail_make_request use this way.
Helper functions:
fault_create_debugfs_attr(name, parent, attr);
--- /dev/null
+++ a/include/linux/fault-inject-usercopy.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_FAULT_INJECT_USERCOPY_H__
+#define __LINUX_FAULT_INJECT_USERCOPY_H__
+
+/*
+ * This header provides a wrapper for injecting failures to user space memory
+ * access functions.
+ */
+
+#include <linux/types.h>
+
+#ifdef CONFIG_FAULT_INJECTION_USERCOPY
+
+bool should_fail_usercopy(void);
+
+#else
+
+static inline bool should_fail_usercopy(void) { return false; }
+
+#endif /* CONFIG_FAULT_INJECTION_USERCOPY */
+
+#endif /* __LINUX_FAULT_INJECT_USERCOPY_H__ */
--- /dev/null
+++ a/lib/fault-inject-usercopy.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/fault-inject.h>
+#include <linux/fault-inject-usercopy.h>
+
+static struct {
+ struct fault_attr attr;
+} fail_usercopy = {
+ .attr = FAULT_ATTR_INITIALIZER,
+};
+
+static int __init setup_fail_usercopy(char *str)
+{
+ return setup_fault_attr(&fail_usercopy.attr, str);
+}
+__setup("fail_usercopy=", setup_fail_usercopy);
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static int __init fail_usercopy_debugfs(void)
+{
+ struct dentry *dir;
+
+ dir = fault_create_debugfs_attr("fail_usercopy", NULL,
+ &fail_usercopy.attr);
+ if (IS_ERR(dir))
+ return PTR_ERR(dir);
+
+ return 0;
+}
+
+late_initcall(fail_usercopy_debugfs);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
+
+bool should_fail_usercopy(void)
+{
+ return should_fail(&fail_usercopy.attr, 1);
+}
+EXPORT_SYMBOL_GPL(should_fail_usercopy);
--- a/lib/Kconfig.debug~lib-include-linux-add-usercopy-failure-capability
+++ a/lib/Kconfig.debug
@@ -1768,6 +1768,13 @@ config FAIL_PAGE_ALLOC
help
Provide fault-injection capability for alloc_pages().
+config FAULT_INJECTION_USERCOPY
+ bool "Fault injection capability for usercopy functions"
+ depends on FAULT_INJECTION
+ help
+ Provides fault-injection capability to inject failures
+ in usercopy functions (copy_from_user(), get_user(), ...).
+
config FAIL_MAKE_REQUEST
bool "Fault-injection capability for disk IO"
depends on FAULT_INJECTION && BLOCK
--- a/lib/Makefile~lib-include-linux-add-usercopy-failure-capability
+++ a/lib/Makefile
@@ -210,6 +210,7 @@ obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += co
obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
+obj-$(CONFIG_FAULT_INJECTION_USERCOPY) += fault-inject-usercopy.o
obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [patch 156/156] lib, uaccess: add failure injection to usercopy functions
2020-10-16 2:40 incoming Andrew Morton
` (155 preceding siblings ...)
2020-10-16 3:13 ` [patch 155/156] lib, include/linux: add usercopy failure capability Andrew Morton
@ 2020-10-16 3:13 ` Andrew Morton
2020-10-17 23:03 ` [folded-merged] selftests-vm-hmm-tests-remove-the-libhugetlbfs-dependency-fix.patch removed from -mm tree Andrew Morton
` (9 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-16 3:13 UTC (permalink / raw)
To: akinobu.mita, akpm, alinde, andreyknvl, arnd, bp, corbet,
dvyukov, elver, glider, hch, hpa, mingo, mm-commits, peterz,
tglx, torvalds, viro
From: Albert van der Linde <alinde@google.com>
Subject: lib, uaccess: add failure injection to usercopy functions
To test fault-tolerance of user memory access functions, introduce fault
injection to usercopy functions.
If a failure is expected return either -EFAULT or the total amount of
bytes that were not copied.
Link: http://lkml.kernel.org/r/20200831171733.955393-3-alinde@google.com
Signed-off-by: Albert van der Linde <alinde@google.com>
Reviewed-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Marco Elver <elver@google.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/uaccess.h | 11 ++++++++++-
lib/iov_iter.c | 5 +++++
lib/strncpy_from_user.c | 3 +++
lib/usercopy.c | 5 ++++-
4 files changed, 22 insertions(+), 2 deletions(-)
--- a/include/linux/uaccess.h~lib-uaccess-add-failure-injection-to-usercopy-functions
+++ a/include/linux/uaccess.h
@@ -2,6 +2,7 @@
#ifndef __LINUX_UACCESS_H__
#define __LINUX_UACCESS_H__
+#include <linux/fault-inject-usercopy.h>
#include <linux/instrumented.h>
#include <linux/minmax.h>
#include <linux/sched.h>
@@ -84,6 +85,8 @@ static __always_inline __must_check unsi
__copy_from_user(void *to, const void __user *from, unsigned long n)
{
might_fault();
+ if (should_fail_usercopy())
+ return n;
instrument_copy_from_user(to, from, n);
check_object_size(to, n, false);
return raw_copy_from_user(to, from, n);
@@ -105,6 +108,8 @@ __copy_from_user(void *to, const void __
static __always_inline __must_check unsigned long
__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
{
+ if (should_fail_usercopy())
+ return n;
instrument_copy_to_user(to, from, n);
check_object_size(from, n, true);
return raw_copy_to_user(to, from, n);
@@ -114,6 +119,8 @@ static __always_inline __must_check unsi
__copy_to_user(void __user *to, const void *from, unsigned long n)
{
might_fault();
+ if (should_fail_usercopy())
+ return n;
instrument_copy_to_user(to, from, n);
check_object_size(from, n, true);
return raw_copy_to_user(to, from, n);
@@ -125,7 +132,7 @@ _copy_from_user(void *to, const void __u
{
unsigned long res = n;
might_fault();
- if (likely(access_ok(from, n))) {
+ if (!should_fail_usercopy() && likely(access_ok(from, n))) {
instrument_copy_from_user(to, from, n);
res = raw_copy_from_user(to, from, n);
}
@@ -143,6 +150,8 @@ static inline __must_check unsigned long
_copy_to_user(void __user *to, const void *from, unsigned long n)
{
might_fault();
+ if (should_fail_usercopy())
+ return n;
if (access_ok(to, n)) {
instrument_copy_to_user(to, from, n);
n = raw_copy_to_user(to, from, n);
--- a/lib/iov_iter.c~lib-uaccess-add-failure-injection-to-usercopy-functions
+++ a/lib/iov_iter.c
@@ -2,6 +2,7 @@
#include <crypto/hash.h>
#include <linux/export.h>
#include <linux/bvec.h>
+#include <linux/fault-inject-usercopy.h>
#include <linux/uio.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
@@ -140,6 +141,8 @@
static int copyout(void __user *to, const void *from, size_t n)
{
+ if (should_fail_usercopy())
+ return n;
if (access_ok(to, n)) {
instrument_copy_to_user(to, from, n);
n = raw_copy_to_user(to, from, n);
@@ -149,6 +152,8 @@ static int copyout(void __user *to, cons
static int copyin(void *to, const void __user *from, size_t n)
{
+ if (should_fail_usercopy())
+ return n;
if (access_ok(from, n)) {
instrument_copy_from_user(to, from, n);
n = raw_copy_from_user(to, from, n);
--- a/lib/strncpy_from_user.c~lib-uaccess-add-failure-injection-to-usercopy-functions
+++ a/lib/strncpy_from_user.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <linux/export.h>
+#include <linux/fault-inject-usercopy.h>
#include <linux/kasan-checks.h>
#include <linux/thread_info.h>
#include <linux/uaccess.h>
@@ -99,6 +100,8 @@ long strncpy_from_user(char *dst, const
unsigned long max_addr, src_addr;
might_fault();
+ if (should_fail_usercopy())
+ return -EFAULT;
if (unlikely(count <= 0))
return 0;
--- a/lib/usercopy.c~lib-uaccess-add-failure-injection-to-usercopy-functions
+++ a/lib/usercopy.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bitops.h>
+#include <linux/fault-inject-usercopy.h>
#include <linux/instrumented.h>
#include <linux/uaccess.h>
@@ -10,7 +11,7 @@ unsigned long _copy_from_user(void *to,
{
unsigned long res = n;
might_fault();
- if (likely(access_ok(from, n))) {
+ if (!should_fail_usercopy() && likely(access_ok(from, n))) {
instrument_copy_from_user(to, from, n);
res = raw_copy_from_user(to, from, n);
}
@@ -25,6 +26,8 @@ EXPORT_SYMBOL(_copy_from_user);
unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
{
might_fault();
+ if (should_fail_usercopy())
+ return n;
if (likely(access_ok(to, n))) {
instrument_copy_to_user(to, from, n);
n = raw_copy_to_user(to, from, n);
_
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] selftests-vm-hmm-tests-remove-the-libhugetlbfs-dependency-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (156 preceding siblings ...)
2020-10-16 3:13 ` [patch 156/156] lib, uaccess: add failure injection to usercopy functions Andrew Morton
@ 2020-10-17 23:03 ` Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix.patch " Andrew Morton
` (8 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:03 UTC (permalink / raw)
To: jhubbard, mm-commits
The patch titled
Subject: selftests/vm: fix an improper dependency upon executable script permissions
has been removed from the -mm tree. Its filename was
selftests-vm-hmm-tests-remove-the-libhugetlbfs-dependency-fix.patch
This patch was dropped because it was folded into selftests-vm-hmm-tests-remove-the-libhugetlbfs-dependency.patch
------------------------------------------------------
From: John Hubbard <jhubbard@nvidia.com>
Subject: selftests/vm: fix an improper dependency upon executable script permissions
commit 30fb9454ab23 ("selftests/vm: hmm-tests: remove the libhugetlbfs
dependency") created the new check_config.sh file without the execute bit
set. This is a problem because that same commit caused the Makefile to
invoke it "./check_config.sh", so now "make" is failing in that directory.
Scripts are not supposed to depend on the executable bit being set,
because patch(1) doesn't set it, and using patch to install a kernel is
supported. Therefore, this fix involves two parts:
1) Invoke the new script via /bin/sh, to fix the problem, and
2) As an nice touch, make check_config.sh executable as well.
Link: https://lkml.kernel.org/r/20201003002142.32671-2-jhubbard@nvidia.com
Fixes: commit 30fb9454ab23 ("selftests/vm: hmm-tests: remove the libhugetlbfs dependency")
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
tools/testing/selftests/vm/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/tools/testing/selftests/vm/Makefile~selftests-vm-hmm-tests-remove-the-libhugetlbfs-dependency-fix
+++ a/tools/testing/selftests/vm/Makefile
@@ -138,7 +138,7 @@ $(OUTPUT)/hmm-tests: local_config.h
$(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS)
local_config.mk local_config.h: check_config.sh
- ./check_config.sh $(CC)
+ /bin/sh ./check_config.sh $(CC)
EXTRA_CLEAN += local_config.mk local_config.h
_
Patches currently in -mm which might be from jhubbard@nvidia.com are
mm-gup_benchmark-rename-to-mm-gup_test.patch
selftests-vm-use-a-common-gup_testh.patch
selftests-vm-rename-run_vmtests-run_vmtestssh.patch
selftests-vm-minor-cleanup-makefile-and-gup_testc.patch
selftests-vm-only-some-gup_test-items-are-really-benchmarks.patch
selftests-vm-gup_test-introduce-the-dump_pages-sub-test.patch
selftests-vm-run_vmtestsh-update-and-clean-up-gup_test-invocation.patch
selftests-vm-hmm-tests-remove-the-libhugetlbfs-dependency.patch
selftests-vm-10x-speedup-for-hmm-tests.patch
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (157 preceding siblings ...)
2020-10-17 23:03 ` [folded-merged] selftests-vm-hmm-tests-remove-the-libhugetlbfs-dependency-fix.patch removed from -mm tree Andrew Morton
@ 2020-10-17 23:04 ` Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix.patch " Andrew Morton
` (7 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:04 UTC (permalink / raw)
To: fw, minchan, mm-commits
The patch titled
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix
has been removed from the -mm tree. Its filename was
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix.patch
This patch was dropped because it was folded into mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
------------------------------------------------------
From: Minchan Kim <minchan@kernel.org>
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix
make process_madvise() vlen arg have type size_t, per Florian
Cc: Minchan Kim <minchan@kernel.org>
Cc: Florian Weimer <fw@deneb.enyo.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/syscalls.h | 2 +-
mm/madvise.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
--- a/include/linux/syscalls.h~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix
+++ a/include/linux/syscalls.h
@@ -880,7 +880,7 @@ asmlinkage long sys_mincore(unsigned lon
unsigned char __user * vec);
asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior);
asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec,
- unsigned long vlen, int behavior, unsigned int flags);
+ size_t vlen, int behavior, unsigned int flags);
asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
unsigned long prot, unsigned long pgoff,
unsigned long flags);
--- a/mm/madvise.c~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix
+++ a/mm/madvise.c
@@ -1232,7 +1232,7 @@ put_pid:
return ret;
}
-static inline int madv_import_iovec(int type, const struct iovec __user *uvec, unsigned int nr_segs,
+static inline int madv_import_iovec(int type, const struct iovec __user *uvec, size_t nr_segs,
unsigned int fast_segs, struct iovec **iov, struct iov_iter *i)
{
#ifdef CONFIG_COMPAT
@@ -1245,7 +1245,7 @@ static inline int madv_import_iovec(int
}
SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
- unsigned long, vlen, int, behavior, unsigned int, flags)
+ size_t, vlen, int, behavior, unsigned int, flags)
{
ssize_t ret;
struct iovec iovstack[UIO_FASTIOV];
_
Patches currently in -mm which might be from minchan@kernel.org are
mm-madvise-pass-mm-to-do_madvise.patch
pid-move-pidfd_get_pid-to-pidc.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix.patch
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (158 preceding siblings ...)
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix.patch " Andrew Morton
@ 2020-10-17 23:04 ` Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix.patch " Andrew Morton
` (6 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:04 UTC (permalink / raw)
To: akpm, fw, minchan, mm-commits
The patch titled
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix
has been removed from the -mm tree. Its filename was
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix.patch
This patch was dropped because it was folded into mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
------------------------------------------------------
From: Andrew Morton <akpm@linux-foundation.org>
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix
fix i386 build
mm/madvise.c: In function process_madvise_vec:
mm/madvise.c:1168:15: error: storage size of iovec isnt known
struct iovec iovec;
Cc: Florian Weimer <fw@deneb.enyo.de>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/madvise.c | 1 +
1 file changed, 1 insertion(+)
--- a/mm/madvise.c~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix
+++ a/mm/madvise.c
@@ -18,6 +18,7 @@
#include <linux/fadvise.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
+#include <linux/uio.h>
#include <linux/ksm.h>
#include <linux/fs.h>
#include <linux/file.h>
_
Patches currently in -mm which might be from akpm@linux-foundation.org are
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix.patch
mm.patch
mm-vmstat-fix-proc-sys-vm-stat_refresh-generating-false-warnings-fix-2.patch
kernel-forkc-export-kernel_thread-to-modules.patch
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (159 preceding siblings ...)
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix.patch " Andrew Morton
@ 2020-10-17 23:04 ` Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix.patch " Andrew Morton
` (5 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:04 UTC (permalink / raw)
To: minchan, mm-commits, sfr
The patch titled
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix
has been removed from the -mm tree. Its filename was
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix.patch
This patch was dropped because it was folded into mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
------------------------------------------------------
From: Stephen Rothwell <sfr@canb.auug.org.au>
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix
Link: https://lkml.kernel.org/r/20200905142639.49fc3f1a@canb.auug.org.au
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/arm64/include/asm/unistd32.h | 2 +-
include/uapi/asm-generic/unistd.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
--- a/arch/arm64/include/asm/unistd32.h~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix
+++ a/arch/arm64/include/asm/unistd32.h
@@ -887,7 +887,7 @@ __SYSCALL(__NR_openat2, sys_openat2)
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
#define __NR_faccessat2 439
__SYSCALL(__NR_faccessat2, sys_faccessat2)
-#define __NR_watch_mount 440
+#define __NR_process_madvise 440
__SYSCALL(__NR_process_madvise, sys_process_madvise)
/*
--- a/include/uapi/asm-generic/unistd.h~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix
+++ a/include/uapi/asm-generic/unistd.h
@@ -857,7 +857,7 @@ __SYSCALL(__NR_openat2, sys_openat2)
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
#define __NR_faccessat2 439
__SYSCALL(__NR_faccessat2, sys_faccessat2)
-#define __NR_watch_mount 441
+#define __NR_process_madvise 440
__SYSCALL(__NR_process_madvise, sys_process_madvise)
#undef __NR_syscalls
_
Patches currently in -mm which might be from sfr@canb.auug.org.au are
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix-fix.patch
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (160 preceding siblings ...)
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix.patch " Andrew Morton
@ 2020-10-17 23:04 ` Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix.patch " Andrew Morton
` (4 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:04 UTC (permalink / raw)
To: minchan, mm-commits, sfr
The patch titled
Subject: fix for "mm/madvise: introduce process_madvise() syscall: an external memory hinting API"
has been removed from the -mm tree. Its filename was
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix.patch
This patch was dropped because it was folded into mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
------------------------------------------------------
From: Stephen Rothwell <sfr@canb.auug.org.au>
Subject: fix for "mm/madvise: introduce process_madvise() syscall: an external memory hinting API"
Link: https://lkml.kernel.org/r/20200908204547.285646b4@canb.auug.org.au
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/madvise.c | 1 +
1 file changed, 1 insertion(+)
--- a/mm/madvise.c~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix
+++ a/mm/madvise.c
@@ -7,6 +7,7 @@
*/
#include <linux/mman.h>
+#include <linux/compat.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/mempolicy.h>
_
Patches currently in -mm which might be from sfr@canb.auug.org.au are
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix-fix.patch
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (161 preceding siblings ...)
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix.patch " Andrew Morton
@ 2020-10-17 23:04 ` Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix.patch " Andrew Morton
` (3 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:04 UTC (permalink / raw)
To: lkp, minchan, mm-commits
The patch titled
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix
has been removed from the -mm tree. Its filename was
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix.patch
This patch was dropped because it was folded into mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
------------------------------------------------------
From: Minchan Kim <minchan@kernel.org>
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix
fix mips build
warning: #warning syscall process_madvise not implemented [-Wcpp]
warning: #warning syscall process_madvise not implemented [-Wcpp]
Link: https://lkml.kernel.org/r/20200909173655.GC2435453@google.com
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/mips/kernel/syscalls/syscall_n64.tbl | 1 +
1 file changed, 1 insertion(+)
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix
+++ a/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -354,3 +354,4 @@
437 n64 openat2 sys_openat2
438 n64 pidfd_getfd sys_pidfd_getfd
439 n64 faccessat2 sys_faccessat2
+440 n64 process_madvise sys_process_madvise
_
Patches currently in -mm which might be from minchan@kernel.org are
mm-madvise-pass-mm-to-do_madvise.patch
pid-move-pidfd_get_pid-to-pidc.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix.patch
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (162 preceding siblings ...)
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix.patch " Andrew Morton
@ 2020-10-17 23:04 ` Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix.patch " Andrew Morton
` (2 subsequent siblings)
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:04 UTC (permalink / raw)
To: minchan, mm-commits, yuehaibing
The patch titled
Subject: mm/madvise: remove duplicate include
has been removed from the -mm tree. Its filename was
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix.patch
This patch was dropped because it was folded into mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
------------------------------------------------------
From: YueHaibing <yuehaibing@huawei.com>
Subject: mm/madvise: remove duplicate include
Remove duplicate header which is included twice.
Link: https://lkml.kernel.org/r/20200915121550.30584-1-yuehaibing@huawei.com
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/madvise.c | 1 -
1 file changed, 1 deletion(-)
--- a/mm/madvise.c~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix
+++ a/mm/madvise.c
@@ -30,7 +30,6 @@
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/mmu_notifier.h>
-#include <linux/sched/mm.h>
#include <asm/tlb.h>
_
Patches currently in -mm which might be from yuehaibing@huawei.com are
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (163 preceding siblings ...)
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix.patch " Andrew Morton
@ 2020-10-17 23:04 ` Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix.patch " Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix-fix.patch " Andrew Morton
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:04 UTC (permalink / raw)
To: hch, minchan, mm-commits
The patch titled
Subject: mm: do not use helper functions for process_madvise
has been removed from the -mm tree. Its filename was
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix.patch
This patch was dropped because it was folded into mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
------------------------------------------------------
From: Minchan Kim <minchan@kernel.org>
Subject: mm: do not use helper functions for process_madvise
This patch removes helper functions process_madvise_vec,
do_process_madvise and madv_import_iovec and use them inline.
Link: https://lkml.kernel.org/r/20200921175539.GB387368@google.com
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/madvise.c | 97 +++++++++++++++++++++----------------------------
1 file changed, 43 insertions(+), 54 deletions(-)
--- a/mm/madvise.c~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix
+++ a/mm/madvise.c
@@ -1171,37 +1171,40 @@ SYSCALL_DEFINE3(madvise, unsigned long,
return do_madvise(current->mm, start, len_in, behavior);
}
-static int process_madvise_vec(struct mm_struct *mm, struct iov_iter *iter, int behavior)
-{
- struct iovec iovec;
- int ret = 0;
-
- while (iov_iter_count(iter)) {
- iovec = iov_iter_iovec(iter);
- ret = do_madvise(mm, (unsigned long)iovec.iov_base, iovec.iov_len, behavior);
- if (ret < 0)
- break;
- iov_iter_advance(iter, iovec.iov_len);
- }
-
- return ret;
-}
-
-static ssize_t do_process_madvise(int pidfd, struct iov_iter *iter,
- int behavior, unsigned int flags)
+SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
+ size_t, vlen, int, behavior, unsigned int, flags)
{
ssize_t ret;
+ struct iovec iovstack[UIO_FASTIOV], iovec;
+ struct iovec *iov = iovstack;
+ struct iov_iter iter;
struct pid *pid;
struct task_struct *task;
struct mm_struct *mm;
- size_t total_len = iov_iter_count(iter);
+ size_t total_len;
+
+ if (flags != 0) {
+ ret = -EINVAL;
+ goto out;
+ }
- if (flags != 0)
- return -EINVAL;
+#ifdef CONFIG_COMPAT
+ if (in_compat_syscall())
+ ret = compat_import_iovec(READ,
+ (struct compat_iovec __user *)vec, vlen,
+ ARRAY_SIZE(iovstack), &iov, &iter);
+ else
+#endif
+ ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack),
+ &iov, &iter);
+ if (ret < 0)
+ goto out;
pid = pidfd_get_pid(pidfd);
- if (IS_ERR(pid))
- return PTR_ERR(pid);
+ if (IS_ERR(pid)) {
+ ret = PTR_ERR(pid);
+ goto free_iov;
+ }
task = get_pid_task(pid, PIDTYPE_PID);
if (!task) {
@@ -1221,43 +1224,29 @@ static ssize_t do_process_madvise(int pi
goto release_task;
}
- ret = process_madvise_vec(mm, iter, behavior);
- if (ret >= 0)
- ret = total_len - iov_iter_count(iter);
+ total_len = iov_iter_count(&iter);
+
+ while (iov_iter_count(&iter)) {
+ iovec = iov_iter_iovec(&iter);
+ ret = do_madvise(mm, (unsigned long)iovec.iov_base,
+ iovec.iov_len, behavior);
+ if (ret < 0)
+ break;
+ iov_iter_advance(&iter, iovec.iov_len);
+ }
+
+ if (ret == 0)
+ ret = total_len - iov_iter_count(&iter);
mmput(mm);
+ return ret;
+
release_task:
put_task_struct(task);
put_pid:
put_pid(pid);
- return ret;
-}
-
-static inline int madv_import_iovec(int type, const struct iovec __user *uvec, size_t nr_segs,
- unsigned int fast_segs, struct iovec **iov, struct iov_iter *i)
-{
-#ifdef CONFIG_COMPAT
- if (in_compat_syscall())
- return compat_import_iovec(type, (struct compat_iovec __user *)uvec, nr_segs,
- fast_segs, iov, i);
-#endif
-
- return import_iovec(type, uvec, nr_segs, fast_segs, iov, i);
-}
-
-SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
- size_t, vlen, int, behavior, unsigned int, flags)
-{
- ssize_t ret;
- struct iovec iovstack[UIO_FASTIOV];
- struct iovec *iov = iovstack;
- struct iov_iter iter;
-
- ret = madv_import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
- if (ret < 0)
- return ret;
-
- ret = do_process_madvise(pidfd, &iter, behavior, flags);
+free_iov:
kfree(iov);
+out:
return ret;
}
_
Patches currently in -mm which might be from minchan@kernel.org are
mm-madvise-pass-mm-to-do_madvise.patch
pid-move-pidfd_get_pid-to-pidc.patch
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (164 preceding siblings ...)
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix.patch " Andrew Morton
@ 2020-10-17 23:04 ` Andrew Morton
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix-fix.patch " Andrew Morton
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:04 UTC (permalink / raw)
To: akpm, minchan, mm-commits
The patch titled
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix
has been removed from the -mm tree. Its filename was
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix.patch
This patch was dropped because it was folded into mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
------------------------------------------------------
From: Andrew Morton <akpm@linux-foundation.org>
Subject: mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix
pidfd_get_pid() gained an argument
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/madvise.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
--- a/mm/madvise.c~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix
+++ a/mm/madvise.c
@@ -1182,6 +1182,7 @@ SYSCALL_DEFINE5(process_madvise, int, pi
struct task_struct *task;
struct mm_struct *mm;
size_t total_len;
+ unsigned int f_flags;
if (flags != 0) {
ret = -EINVAL;
@@ -1200,7 +1201,7 @@ SYSCALL_DEFINE5(process_madvise, int, pi
if (ret < 0)
goto out;
- pid = pidfd_get_pid(pidfd);
+ pid = pidfd_get_pid(pidfd, &f_flags);
if (IS_ERR(pid)) {
ret = PTR_ERR(pid);
goto free_iov;
_
Patches currently in -mm which might be from akpm@linux-foundation.org are
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
mm.patch
mm-vmstat-fix-proc-sys-vm-stat_refresh-generating-false-warnings-fix-2.patch
kernel-forkc-export-kernel_thread-to-modules.patch
^ permalink raw reply [flat|nested] 169+ messages in thread* [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix-fix.patch removed from -mm tree
2020-10-16 2:40 incoming Andrew Morton
` (165 preceding siblings ...)
2020-10-17 23:04 ` [folded-merged] mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix.patch " Andrew Morton
@ 2020-10-17 23:04 ` Andrew Morton
166 siblings, 0 replies; 169+ messages in thread
From: Andrew Morton @ 2020-10-17 23:04 UTC (permalink / raw)
To: hch, minchan, mm-commits, sfr
The patch titled
Subject: fix up for "iov_iter: transparently handle compat iovecs in import_iovec"
has been removed from the -mm tree. Its filename was
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix-fix.patch
This patch was dropped because it was folded into mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
------------------------------------------------------
From: Stephen Rothwell <sfr@canb.auug.org.au>
Subject: fix up for "iov_iter: transparently handle compat iovecs in import_iovec"
Link: https://lkml.kernel.org/r/20200928212542.468e1fef@canb.auug.org.au
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/madvise.c | 11 +----------
1 file changed, 1 insertion(+), 10 deletions(-)
--- a/mm/madvise.c~mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api-fix-fix-fix-fix-fix-fix-fix-fix-fix
+++ a/mm/madvise.c
@@ -7,7 +7,6 @@
*/
#include <linux/mman.h>
-#include <linux/compat.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/mempolicy.h>
@@ -1189,15 +1188,7 @@ SYSCALL_DEFINE5(process_madvise, int, pi
goto out;
}
-#ifdef CONFIG_COMPAT
- if (in_compat_syscall())
- ret = compat_import_iovec(READ,
- (struct compat_iovec __user *)vec, vlen,
- ARRAY_SIZE(iovstack), &iov, &iter);
- else
-#endif
- ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack),
- &iov, &iter);
+ ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
if (ret < 0)
goto out;
_
Patches currently in -mm which might be from sfr@canb.auug.org.au are
mm-madvise-introduce-process_madvise-syscall-an-external-memory-hinting-api.patch
^ permalink raw reply [flat|nested] 169+ messages in thread