[PATCH 5.9 002/105] mm/zsmalloc.c: drop ZSMALLOC_PGTABLE_MAPPING

From: Greg Kroah-Hartman
Date: Mon Dec 14 2020 - 14:08:11 EST


From: Minchan Kim <minchan@xxxxxxxxxx>

commit e91d8d78237de8d7120c320b3645b7100848f24d upstream.

While I was doing zram testing, I found sometimes decompression failed
since the compression buffer was corrupted. With investigation, I found
below commit calls cond_resched unconditionally so it could make a
problem in atomic context if the task is reschedule.

BUG: sleeping function called from invalid context at mm/vmalloc.c:108
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 946, name: memhog
3 locks held by memhog/946:
#0: ffff9d01d4b193e8 (&mm->mmap_lock#2){++++}-{4:4}, at: __mm_populate+0x103/0x160
#1: ffffffffa3d53de0 (fs_reclaim){+.+.}-{0:0}, at: __alloc_pages_slowpath.constprop.0+0xa98/0x1160
#2: ffff9d01d56b8110 (&zspage->lock){.+.+}-{3:3}, at: zs_map_object+0x8e/0x1f0
CPU: 0 PID: 946 Comm: memhog Not tainted 5.9.3-00011-gc5bfc0287345-dirty #316
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
Call Trace:
unmap_kernel_range_noflush+0x2eb/0x350
unmap_kernel_range+0x14/0x30
zs_unmap_object+0xd5/0xe0
zram_bvec_rw.isra.0+0x38c/0x8e0
zram_rw_page+0x90/0x101
bdev_write_page+0x92/0xe0
__swap_writepage+0x94/0x4a0
pageout+0xe3/0x3a0
shrink_page_list+0xb94/0xd60
shrink_inactive_list+0x158/0x460

We can fix this by removing the ZSMALLOC_PGTABLE_MAPPING feature (which
contains the offending calling code) from zsmalloc.

Even though this option showed some amount improvement(e.g., 30%) in
some arm32 platforms, it has been headache to maintain since it have
abused APIs[1](e.g., unmap_kernel_range in atomic context).

Since we are approaching to deprecate 32bit machines and already made
the config option available for only builtin build since v5.8, lastly it
has been not default option in zsmalloc, it's time to drop the option
for better maintenance.

[1] http://lore.kernel.org/linux-mm/20201105170249.387069-1-minchan@xxxxxxxxxx

Fixes: e47110e90584 ("mm/vunmap: add cond_resched() in vunmap_pmd_range")
Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx>
Cc: Tony Lindgren <tony@xxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Harish Sriram <harish@xxxxxxxxxxxxx>
Cc: Uladzislau Rezki <urezki@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20201117202916.GA3856507@xxxxxxxxxx
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
arch/arm/configs/omap2plus_defconfig | 1
include/linux/zsmalloc.h | 1
mm/Kconfig | 13 ---------
mm/zsmalloc.c | 48 -----------------------------------
4 files changed, 63 deletions(-)

--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -81,7 +81,6 @@ CONFIG_PARTITION_ADVANCED=y
CONFIG_BINFMT_MISC=y
CONFIG_CMA=y
CONFIG_ZSMALLOC=m
-CONFIG_ZSMALLOC_PGTABLE_MAPPING=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -20,7 +20,6 @@
* zsmalloc mapping modes
*
* NOTE: These only make a difference when a mapped object spans pages.
- * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected.
*/
enum zs_mapmode {
ZS_MM_RW, /* normal read-write mapping */
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -706,19 +706,6 @@ config ZSMALLOC
returned by an alloc(). This handle must be mapped in order to
access the allocated space.

-config ZSMALLOC_PGTABLE_MAPPING
- bool "Use page table mapping to access object in zsmalloc"
- depends on ZSMALLOC=y
- help
- By default, zsmalloc uses a copy-based object mapping method to
- access allocations that span two pages. However, if a particular
- architecture (ex, ARM) performs VM mapping faster than copying,
- then you should select this. This causes zsmalloc to use page table
- mapping rather than copying for object mapping.
-
- You can check speed with zsmalloc benchmark:
- https://github.com/spartacus06/zsmapbench
-
config ZSMALLOC_STAT
bool "Export zsmalloc statistics"
depends on ZSMALLOC
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -293,11 +293,7 @@ struct zspage {
};

struct mapping_area {
-#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING
- struct vm_struct *vm; /* vm area for mapping object that span pages */
-#else
char *vm_buf; /* copy buffer for objects that span pages */
-#endif
char *vm_addr; /* address of kmap_atomic()'ed pages */
enum zs_mapmode vm_mm; /* mapping mode */
};
@@ -1113,48 +1109,6 @@ static struct zspage *find_get_zspage(st
return zspage;
}

-#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING
-static inline int __zs_cpu_up(struct mapping_area *area)
-{
- /*
- * Make sure we don't leak memory if a cpu UP notification
- * and zs_init() race and both call zs_cpu_up() on the same cpu
- */
- if (area->vm)
- return 0;
- area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL);
- if (!area->vm)
- return -ENOMEM;
- return 0;
-}
-
-static inline void __zs_cpu_down(struct mapping_area *area)
-{
- if (area->vm)
- free_vm_area(area->vm);
- area->vm = NULL;
-}
-
-static inline void *__zs_map_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- unsigned long addr = (unsigned long)area->vm->addr;
-
- BUG_ON(map_kernel_range(addr, PAGE_SIZE * 2, PAGE_KERNEL, pages) < 0);
- area->vm_addr = area->vm->addr;
- return area->vm_addr + off;
-}
-
-static inline void __zs_unmap_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- unsigned long addr = (unsigned long)area->vm_addr;
-
- unmap_kernel_range(addr, PAGE_SIZE * 2);
-}
-
-#else /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */
-
static inline int __zs_cpu_up(struct mapping_area *area)
{
/*
@@ -1235,8 +1189,6 @@ out:
pagefault_enable();
}

-#endif /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */
-
static int zs_cpu_prepare(unsigned int cpu)
{
struct mapping_area *area;