* [PATCH v2 0/2] mm: mmap: add mmap trace point [not found] <CGME20200313011430epcas1p423b939dea080fda77a2e0fe3f6531489@epcas1p4.samsung.com> @ 2020-03-13 1:14 ` Jaewon Kim [not found] ` <CGME20200313011430epcas1p129e4033f12b9c02f71443e0b359a26e5@epcas1p1.samsung.com> [not found] ` <CGME20200313011430epcas1p436a6c02a262debcd755f3e1378331764@epcas1p4.samsung.com> 0 siblings, 2 replies; 7+ messages in thread From: Jaewon Kim @ 2020-03-13 1:14 UTC (permalink / raw) To: willy, walken, bp, akpm; +Cc: linux-mm, linux-kernel, jaewon31.kim, Jaewon Kim Create mmap trace file and add trace point of vm_unmapped_area. To include mmap trace, remove inline of vm_unmapped_area and move code to mmap.c. There is no logical change. Jaewon Kim (2): mmap: remove inline of vm_unmapped_area mm: mmap: add trace point of vm_unmapped_area include/linux/mm.h | 21 +----------------- include/trace/events/mmap.h | 52 +++++++++++++++++++++++++++++++++++++++++++++ mm/mmap.c | 24 +++++++++++++++++++++ 3 files changed, 77 insertions(+), 20 deletions(-) create mode 100644 include/trace/events/mmap.h -- 2.13.7 ^ permalink raw reply [flat|nested] 7+ messages in thread
[parent not found: <CGME20200313011430epcas1p129e4033f12b9c02f71443e0b359a26e5@epcas1p1.samsung.com>]
* [PATCH v2 1/2] mmap: remove inline of vm_unmapped_area [not found] ` <CGME20200313011430epcas1p129e4033f12b9c02f71443e0b359a26e5@epcas1p1.samsung.com> @ 2020-03-13 1:14 ` Jaewon Kim 2020-03-13 3:02 ` Andrew Morton 2020-03-13 10:36 ` Vlastimil Babka 0 siblings, 2 replies; 7+ messages in thread From: Jaewon Kim @ 2020-03-13 1:14 UTC (permalink / raw) To: willy, walken, bp, akpm; +Cc: linux-mm, linux-kernel, jaewon31.kim, Jaewon Kim In prepration for next patch remove inline of vm_unmapped_area and move code to mmap.c. There is no logical change. Also remove unmapped_area[_topdown] out of mm.h, there is no code calling to them. Signed-off-by: Jaewon Kim <jaewon31.kim@samsung.com> --- include/linux/mm.h | 21 +-------------------- mm/mmap.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+), 20 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 52269e56c514..1cb01f4a83c9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2364,26 +2364,7 @@ struct vm_unmapped_area_info { unsigned long align_offset; }; -extern unsigned long unmapped_area(struct vm_unmapped_area_info *info); -extern unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info); - -/* - * Search for an unmapped address range. - * - * We are looking for a range that: - * - does not intersect with any VMA; - * - is contained within the [low_limit, high_limit) interval; - * - is at least the desired size. - * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) - */ -static inline unsigned long -vm_unmapped_area(struct vm_unmapped_area_info *info) -{ - if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) - return unmapped_area_topdown(info); - else - return unmapped_area(info); -} +extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ extern void truncate_inode_pages(struct address_space *, loff_t); diff --git a/mm/mmap.c b/mm/mmap.c index d681a20eb4ea..eeaddb76286c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2050,6 +2050,22 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) return gap_end; } +/* + * Search for an unmapped address range. + * + * We are looking for a range that: + * - does not intersect with any VMA; + * - is contained within the [low_limit, high_limit) interval; + * - is at least the desired size. + * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) + */ +unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) +{ + if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) + return unmapped_area_topdown(info); + else + return unmapped_area(info); +} #ifndef arch_get_mmap_end #define arch_get_mmap_end(addr) (TASK_SIZE) -- 2.13.7 ^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH v2 1/2] mmap: remove inline of vm_unmapped_area 2020-03-13 1:14 ` [PATCH v2 1/2] mmap: remove inline of vm_unmapped_area Jaewon Kim @ 2020-03-13 3:02 ` Andrew Morton 2020-03-13 3:27 ` Jaewon Kim 2020-03-13 10:36 ` Vlastimil Babka 1 sibling, 1 reply; 7+ messages in thread From: Andrew Morton @ 2020-03-13 3:02 UTC (permalink / raw) To: Jaewon Kim; +Cc: willy, walken, bp, linux-mm, linux-kernel, jaewon31.kim On Fri, 13 Mar 2020 10:14:19 +0900 Jaewon Kim <jaewon31.kim@samsung.com> wrote: > In prepration for next patch remove inline of vm_unmapped_area and move > code to mmap.c. There is no logical change. > > Also remove unmapped_area[_topdown] out of mm.h, there is no code > calling to them. > Patches seem reasonable. > -extern unsigned long unmapped_area(struct vm_unmapped_area_info *info); > -extern unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info); I believe these can now be made static to mmap.c ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v2 1/2] mmap: remove inline of vm_unmapped_area 2020-03-13 3:02 ` Andrew Morton @ 2020-03-13 3:27 ` Jaewon Kim 0 siblings, 0 replies; 7+ messages in thread From: Jaewon Kim @ 2020-03-13 3:27 UTC (permalink / raw) To: Andrew Morton; +Cc: willy, walken, bp, linux-mm, linux-kernel, jaewon31.kim On 2020년 03월 13일 12:02, Andrew Morton wrote: > On Fri, 13 Mar 2020 10:14:19 +0900 Jaewon Kim <jaewon31.kim@samsung.com> wrote: > >> In prepration for next patch remove inline of vm_unmapped_area and move >> code to mmap.c. There is no logical change. >> >> Also remove unmapped_area[_topdown] out of mm.h, there is no code >> calling to them. >> > Patches seem reasonable. > >> -extern unsigned long unmapped_area(struct vm_unmapped_area_info *info); >> -extern unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info); > I believe these can now be made static to mmap.c Correct. Let me wait for the 2/2 patch to be reviewed, and resubmit this 1/2 patch with having static if need. Thank you for your comment. > > > > ^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v2 1/2] mmap: remove inline of vm_unmapped_area 2020-03-13 1:14 ` [PATCH v2 1/2] mmap: remove inline of vm_unmapped_area Jaewon Kim 2020-03-13 3:02 ` Andrew Morton @ 2020-03-13 10:36 ` Vlastimil Babka 1 sibling, 0 replies; 7+ messages in thread From: Vlastimil Babka @ 2020-03-13 10:36 UTC (permalink / raw) To: Jaewon Kim, willy, walken, bp, akpm; +Cc: linux-mm, linux-kernel, jaewon31.kim On 3/13/20 2:14 AM, Jaewon Kim wrote: > In prepration for next patch remove inline of vm_unmapped_area and move > code to mmap.c. There is no logical change. > > Also remove unmapped_area[_topdown] out of mm.h, there is no code > calling to them. > > Signed-off-by: Jaewon Kim <jaewon31.kim@samsung.com> Assuming the 'static' is added as Andrew pointed out, Reviewed-by: Vlastimil Babka <vbabka@suse.cz> > --- > include/linux/mm.h | 21 +-------------------- > mm/mmap.c | 16 ++++++++++++++++ > 2 files changed, 17 insertions(+), 20 deletions(-) > > diff --git a/include/linux/mm.h b/include/linux/mm.h > index 52269e56c514..1cb01f4a83c9 100644 > --- a/include/linux/mm.h > +++ b/include/linux/mm.h > @@ -2364,26 +2364,7 @@ struct vm_unmapped_area_info { > unsigned long align_offset; > }; > > -extern unsigned long unmapped_area(struct vm_unmapped_area_info *info); > -extern unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info); > - > -/* > - * Search for an unmapped address range. > - * > - * We are looking for a range that: > - * - does not intersect with any VMA; > - * - is contained within the [low_limit, high_limit) interval; > - * - is at least the desired size. > - * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) > - */ > -static inline unsigned long > -vm_unmapped_area(struct vm_unmapped_area_info *info) > -{ > - if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) > - return unmapped_area_topdown(info); > - else > - return unmapped_area(info); > -} > +extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); > > /* truncate.c */ > extern void truncate_inode_pages(struct address_space *, loff_t); > diff --git a/mm/mmap.c b/mm/mmap.c > index d681a20eb4ea..eeaddb76286c 100644 > --- a/mm/mmap.c > +++ b/mm/mmap.c > @@ -2050,6 +2050,22 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) > return gap_end; > } > > +/* > + * Search for an unmapped address range. > + * > + * We are looking for a range that: > + * - does not intersect with any VMA; > + * - is contained within the [low_limit, high_limit) interval; > + * - is at least the desired size. > + * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) > + */ > +unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) > +{ > + if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) > + return unmapped_area_topdown(info); > + else > + return unmapped_area(info); > +} > > #ifndef arch_get_mmap_end > #define arch_get_mmap_end(addr) (TASK_SIZE) > ^ permalink raw reply [flat|nested] 7+ messages in thread
[parent not found: <CGME20200313011430epcas1p436a6c02a262debcd755f3e1378331764@epcas1p4.samsung.com>]
* [PATCH v2 2/2] mm: mmap: add trace point of vm_unmapped_area [not found] ` <CGME20200313011430epcas1p436a6c02a262debcd755f3e1378331764@epcas1p4.samsung.com> @ 2020-03-13 1:14 ` Jaewon Kim 2020-03-13 11:25 ` Vlastimil Babka 0 siblings, 1 reply; 7+ messages in thread From: Jaewon Kim @ 2020-03-13 1:14 UTC (permalink / raw) To: willy, walken, bp, akpm; +Cc: linux-mm, linux-kernel, jaewon31.kim, Jaewon Kim Even on 64 bit kernel, the mmap failure can happen for a 32 bit task. Virtual memory space shortage of a task on mmap is reported to userspace as -ENOMEM. It can be confused as physical memory shortage of overall system. The vm_unmapped_area can be called to by some drivers or other kernel core system like filesystem. In my platform, GPU driver calls to vm_unmapped_area and the driver returns -ENOMEM even in GPU side shortage. It can be hard to distinguish which code layer returns the -ENOMEM. Create mmap trace file and add trace point of vm_unmapped_area. i.e.) 265.214275: vm_unmapped_area: addr=fffffffffffffff4 err=-12 tvm=0xffb08 flags=0x1 len=0x100000 lo=0x8000 hi=0xf7182000 mask=0x0 ofs=0x22 265.214276: vm_unmapped_area: addr=fffffffffffffff4 err=-12 tvm=0xffb08 flags=0x0 len=0x100000 lo=0x40000000 hi=0xfffff000 mask=0x0 ofs=0x22 510.827472: vm_unmapped_area: addr=7377060000 err=0 tvm=0x262f flags=0x1 len=0x7f000 lo=0x8000 hi=0x73795f7000 mask=0x0 ofs=0x22 510.827668: vm_unmapped_area: addr=73794d1000 err=0 tvm=0x25cc flags=0x1 len=0x1000 lo=0x8000 hi=0x73795f7000 mask=0x0 ofs=0x22 Signed-off-by: Jaewon Kim <jaewon31.kim@samsung.com> --- include/trace/events/mmap.h | 52 +++++++++++++++++++++++++++++++++++++++++++++ mm/mmap.c | 12 +++++++++-- 2 files changed, 62 insertions(+), 2 deletions(-) create mode 100644 include/trace/events/mmap.h diff --git a/include/trace/events/mmap.h b/include/trace/events/mmap.h new file mode 100644 index 000000000000..a51dd8af6f8c --- /dev/null +++ b/include/trace/events/mmap.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mmap + +#if !defined(_TRACE_MMAP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MMAP_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(vm_unmapped_area, + + TP_PROTO(unsigned long addr, struct vm_unmapped_area_info *info), + + TP_ARGS(addr, info), + + TP_STRUCT__entry( + __field(unsigned long, addr) + __field(unsigned long, error) + __field(unsigned long, total_vm) + __field(unsigned long, flags) + __field(unsigned long, length) + __field(unsigned long, low_limit) + __field(unsigned long, high_limit) + __field(unsigned long, align_mask) + __field(unsigned long, align_offset) + ), + + TP_fast_assign( + __entry->addr = addr; + if (IS_ERR_VALUE(addr)) + __entry->error = addr; + else + __entry->error = 0; + __entry->total_vm = current->mm->total_vm; + __entry->flags = info->flags; + __entry->length = info->length; + __entry->low_limit = info->low_limit; + __entry->high_limit = info->high_limit; + __entry->align_mask = info->align_mask; + __entry->align_offset = info->align_offset; + ), + + TP_printk("addr=%lx err=%ld tvm=0x%lx flags=0x%lx len=0x%lx lo=0x%lx hi=0x%lx mask=0x%lx ofs=0x%lx\n", + __entry->addr, __entry->error, __entry->total_vm, + __entry->flags, __entry->length, __entry->low_limit, + __entry->high_limit, __entry->align_mask, + __entry->align_offset) +); +#endif + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/mm/mmap.c b/mm/mmap.c index eeaddb76286c..68ccbd7d5256 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -53,6 +53,9 @@ #include <asm/tlb.h> #include <asm/mmu_context.h> +#define CREATE_TRACE_POINTS +#include <trace/events/mmap.h> + #include "internal.h" #ifndef arch_mmap_check @@ -2061,10 +2064,15 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) */ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) { + unsigned long addr; + if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) - return unmapped_area_topdown(info); + addr = unmapped_area_topdown(info); else - return unmapped_area(info); + addr = unmapped_area(info); + + trace_vm_unmapped_area(addr, info); + return addr; } #ifndef arch_get_mmap_end -- 2.13.7 ^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH v2 2/2] mm: mmap: add trace point of vm_unmapped_area 2020-03-13 1:14 ` [PATCH v2 2/2] mm: mmap: add trace point " Jaewon Kim @ 2020-03-13 11:25 ` Vlastimil Babka 0 siblings, 0 replies; 7+ messages in thread From: Vlastimil Babka @ 2020-03-13 11:25 UTC (permalink / raw) To: Jaewon Kim, willy, walken, bp, akpm Cc: linux-mm, linux-kernel, jaewon31.kim, Steven Rostedt On 3/13/20 2:14 AM, Jaewon Kim wrote: > Even on 64 bit kernel, the mmap failure can happen for a 32 bit task. > Virtual memory space shortage of a task on mmap is reported to userspace > as -ENOMEM. It can be confused as physical memory shortage of overall > system. > > The vm_unmapped_area can be called to by some drivers or other kernel > core system like filesystem. In my platform, GPU driver calls to > vm_unmapped_area and the driver returns -ENOMEM even in GPU side > shortage. It can be hard to distinguish which code layer returns the > -ENOMEM. > > Create mmap trace file and add trace point of vm_unmapped_area. > > i.e.) > 265.214275: vm_unmapped_area: addr=fffffffffffffff4 err=-12 tvm=0xffb08 flags=0x1 len=0x100000 lo=0x8000 hi=0xf7182000 mask=0x0 ofs=0x22 > 265.214276: vm_unmapped_area: addr=fffffffffffffff4 err=-12 tvm=0xffb08 flags=0x0 len=0x100000 lo=0x40000000 hi=0xfffff000 mask=0x0 ofs=0x22 I think it's nicer to print addr as 0 if it was in fact an error. Also "tvm" is cryptic, I would just use total_vm? > 510.827472: vm_unmapped_area: addr=7377060000 err=0 tvm=0x262f flags=0x1 len=0x7f000 lo=0x8000 hi=0x73795f7000 mask=0x0 ofs=0x22 > 510.827668: vm_unmapped_area: addr=73794d1000 err=0 tvm=0x25cc flags=0x1 len=0x1000 lo=0x8000 hi=0x73795f7000 mask=0x0 ofs=0x22 > > Signed-off-by: Jaewon Kim <jaewon31.kim@samsung.com> > --- > include/trace/events/mmap.h | 52 +++++++++++++++++++++++++++++++++++++++++++++ > mm/mmap.c | 12 +++++++++-- > 2 files changed, 62 insertions(+), 2 deletions(-) > create mode 100644 include/trace/events/mmap.h > > diff --git a/include/trace/events/mmap.h b/include/trace/events/mmap.h > new file mode 100644 > index 000000000000..a51dd8af6f8c > --- /dev/null > +++ b/include/trace/events/mmap.h > @@ -0,0 +1,52 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +#undef TRACE_SYSTEM > +#define TRACE_SYSTEM mmap > + > +#if !defined(_TRACE_MMAP_H) || defined(TRACE_HEADER_MULTI_READ) > +#define _TRACE_MMAP_H > + > +#include <linux/tracepoint.h> > + > +TRACE_EVENT(vm_unmapped_area, > + > + TP_PROTO(unsigned long addr, struct vm_unmapped_area_info *info), > + > + TP_ARGS(addr, info), > + > + TP_STRUCT__entry( > + __field(unsigned long, addr) > + __field(unsigned long, error) That seems wasteful to store both, coming from the same value. > + __field(unsigned long, total_vm) > + __field(unsigned long, flags) > + __field(unsigned long, length) > + __field(unsigned long, low_limit) > + __field(unsigned long, high_limit) > + __field(unsigned long, align_mask) > + __field(unsigned long, align_offset) > + ), > + > + TP_fast_assign( > + __entry->addr = addr; > + if (IS_ERR_VALUE(addr)) > + __entry->error = addr; > + else > + __entry->error = 0; fast_assign should be also as fast as possible, i.e. avoid these decision, just store addr... > + __entry->total_vm = current->mm->total_vm; > + __entry->flags = info->flags; > + __entry->length = info->length; > + __entry->low_limit = info->low_limit; > + __entry->high_limit = info->high_limit; > + __entry->align_mask = info->align_mask; > + __entry->align_offset = info->align_offset; > + ), > + > + TP_printk("addr=%lx err=%ld tvm=0x%lx flags=0x%lx len=0x%lx lo=0x%lx hi=0x%lx mask=0x%lx ofs=0x%lx\n", > + __entry->addr, __entry->error, __entry->total_vm, ... and only here do the decisions if you print addr as zero and err as non-zero, or vice versa. Something like the patch at the end of the e-mail. Except then /sys/kernel/debug/tracing/events/mmap/vm_unmapped_area/format contains: print fmt: "addr=%lx err=%ld tvm=0x%lx flags=0x%lx len=0x%lx lo=0x%lx hi=0x%lx mask=0x%lx ofs=0x%lx ", __builtin_expect(!!((unsigned long)(void *)(REC->addr) >= (unsigned long)-4095), 0) ? 0 : REC->addr, __builtin_expect(!!((unsigned long)(void *)(REC->addr) >= (unsigned long)-4095), 0) ? REC->addr : 0, REC->total_vm, REC->flags, REC->length, REC->low_limit, REC->high_limit, REC->align_mask, REC->align_offset and trace-cmd doesn't like it: sleep-381 [001] 93.434157: vm_unmapped_area: [FAILED TO PARSE] addr=0x7f7f32c47000 total_vm=0x2a flags=0x1 length=0x2d000 low_limit=0x1000 high_limit=0x7f7f32c74000 align_mask=0x0 align_offset=0x0 CC Steven, any idea? Does it not like the __builtin_epect, i.e. unlikely() that's part of IS_ERR_VALUE? Thanks, Vlastimil > + __entry->flags, __entry->length, __entry->low_limit, > + __entry->high_limit, __entry->align_mask, > + __entry->align_offset) > +); > +#endif > + > +/* This part must be outside protection */ > +#include <trace/define_trace.h> > diff --git a/mm/mmap.c b/mm/mmap.c > index eeaddb76286c..68ccbd7d5256 100644 > --- a/mm/mmap.c > +++ b/mm/mmap.c > @@ -53,6 +53,9 @@ > #include <asm/tlb.h> > #include <asm/mmu_context.h> > > +#define CREATE_TRACE_POINTS > +#include <trace/events/mmap.h> > + > #include "internal.h" > > #ifndef arch_mmap_check > @@ -2061,10 +2064,15 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) > */ > unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) > { > + unsigned long addr; > + > if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) > - return unmapped_area_topdown(info); > + addr = unmapped_area_topdown(info); > else > - return unmapped_area(info); > + addr = unmapped_area(info); > + > + trace_vm_unmapped_area(addr, info); > + return addr; > } > > #ifndef arch_get_mmap_end > ------8<------ diff --git a/include/trace/events/mmap.h b/include/trace/events/mmap.h index a51dd8af6f8c..57cccf731721 100644 --- a/include/trace/events/mmap.h +++ b/include/trace/events/mmap.h @@ -15,7 +15,6 @@ TRACE_EVENT(vm_unmapped_area, TP_STRUCT__entry( __field(unsigned long, addr) - __field(unsigned long, error) __field(unsigned long, total_vm) __field(unsigned long, flags) __field(unsigned long, length) @@ -27,10 +26,6 @@ TRACE_EVENT(vm_unmapped_area, TP_fast_assign( __entry->addr = addr; - if (IS_ERR_VALUE(addr)) - __entry->error = addr; - else - __entry->error = 0; __entry->total_vm = current->mm->total_vm; __entry->flags = info->flags; __entry->length = info->length; @@ -41,8 +36,8 @@ TRACE_EVENT(vm_unmapped_area, ), TP_printk("addr=%lx err=%ld tvm=0x%lx flags=0x%lx len=0x%lx lo=0x%lx hi=0x%lx mask=0x%lx ofs=0x%lx\n", - __entry->addr, __entry->error, __entry->total_vm, - __entry->flags, __entry->length, __entry->low_limit, + IS_ERR_VALUE(__entry->addr) ? 0 : __entry->addr, IS_ERR_VALUE(__entry->addr) ? __entry->addr : 0, + __entry->total_vm, __entry->flags, __entry->length, __entry->low_limit, __entry->high_limit, __entry->align_mask, __entry->align_offset) ); ^ permalink raw reply related [flat|nested] 7+ messages in thread
end of thread, other threads:[~2020-03-13 11:26 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <CGME20200313011430epcas1p423b939dea080fda77a2e0fe3f6531489@epcas1p4.samsung.com>
2020-03-13 1:14 ` [PATCH v2 0/2] mm: mmap: add mmap trace point Jaewon Kim
[not found] ` <CGME20200313011430epcas1p129e4033f12b9c02f71443e0b359a26e5@epcas1p1.samsung.com>
2020-03-13 1:14 ` [PATCH v2 1/2] mmap: remove inline of vm_unmapped_area Jaewon Kim
2020-03-13 3:02 ` Andrew Morton
2020-03-13 3:27 ` Jaewon Kim
2020-03-13 10:36 ` Vlastimil Babka
[not found] ` <CGME20200313011430epcas1p436a6c02a262debcd755f3e1378331764@epcas1p4.samsung.com>
2020-03-13 1:14 ` [PATCH v2 2/2] mm: mmap: add trace point " Jaewon Kim
2020-03-13 11:25 ` Vlastimil Babka
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).