mm: avoid overflows in dirty throttling logic

The dirty throttling logic is interspersed with assumptions that dirty
limits in PAGE_SIZE units fit into 32-bit (so that various multiplications
fit into 64-bits).  If limits end up being larger, we will hit overflows,
possible divisions by 0 etc.  Fix these problems by never allowing so
large dirty limits as they have dubious practical value anyway.  For
dirty_bytes / dirty_background_bytes interfaces we can just refuse to set
so large limits.  For dirty_ratio / dirty_background_ratio it isn't so
simple as the dirty limit is computed from the amount of available memory
which can change due to memory hotplug etc.  So when converting dirty
limits from ratios to numbers of pages, we just don't allow the result to
exceed UINT_MAX.

This is root-only triggerable problem which occurs when the operator
sets dirty limits to >16 TB.

Link: https://lkml.kernel.org/r/20240621144246.11148-2-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reported-by: Zach O'Keefe <zokeefe@google.com>
Reviewed-By: Zach O'Keefe <zokeefe@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Jan Kara 2024-06-21 16:42:38 +02:00 committed by Andrew Morton
parent 30139c7020
commit 385d838df2

View file

@ -415,13 +415,20 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
else
bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
if (bg_thresh >= thresh)
bg_thresh = thresh / 2;
tsk = current;
if (rt_task(tsk)) {
bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32;
thresh += thresh / 4 + global_wb_domain.dirty_limit / 32;
}
/*
* Dirty throttling logic assumes the limits in page units fit into
* 32-bits. This gives 16TB dirty limits max which is hopefully enough.
*/
if (thresh > UINT_MAX)
thresh = UINT_MAX;
/* This makes sure bg_thresh is within 32-bits as well */
if (bg_thresh >= thresh)
bg_thresh = thresh / 2;
dtc->thresh = thresh;
dtc->bg_thresh = bg_thresh;
@ -471,7 +478,11 @@ static unsigned long node_dirty_limit(struct pglist_data *pgdat)
if (rt_task(tsk))
dirty += dirty / 4;
return dirty;
/*
* Dirty throttling logic assumes the limits in page units fit into
* 32-bits. This gives 16TB dirty limits max which is hopefully enough.
*/
return min_t(unsigned long, dirty, UINT_MAX);
}
/**
@ -508,10 +519,17 @@ static int dirty_background_bytes_handler(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
unsigned long old_bytes = dirty_background_bytes;
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
if (ret == 0 && write) {
if (DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE) >
UINT_MAX) {
dirty_background_bytes = old_bytes;
return -ERANGE;
}
dirty_background_ratio = 0;
}
return ret;
}
@ -537,6 +555,10 @@ static int dirty_bytes_handler(struct ctl_table *table, int write,
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
if (DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) > UINT_MAX) {
vm_dirty_bytes = old_bytes;
return -ERANGE;
}
writeback_set_ratelimit();
vm_dirty_ratio = 0;
}