--- /dev/null
+From 079be8fc630943d9fc70a97807feb73d169ee3fc Mon Sep 17 00:00:00 2001
+From: Cyril Hrubis <chrubis@suse.cz>
+Date: Mon, 2 Oct 2023 13:55:51 +0200
+Subject: sched/rt: Disallow writing invalid values to sched_rt_period_us
+
+From: Cyril Hrubis <chrubis@suse.cz>
+
+commit 079be8fc630943d9fc70a97807feb73d169ee3fc upstream.
+
+The validation of the value written to sched_rt_period_us was broken
+because:
+
+ - the sysclt_sched_rt_period is declared as unsigned int
+ - parsed by proc_do_intvec()
+ - the range is asserted after the value parsed by proc_do_intvec()
+
+Because of this negative values written to the file were written into a
+unsigned integer that were later on interpreted as large positive
+integers which did passed the check:
+
+ if (sysclt_sched_rt_period <= 0)
+ return EINVAL;
+
+This commit fixes the parsing by setting explicit range for both
+perid_us and runtime_us into the sched_rt_sysctls table and processes
+the values with proc_dointvec_minmax() instead.
+
+Alternatively if we wanted to use full range of unsigned int for the
+period value we would have to split the proc_handler and use
+proc_douintvec() for it however even the
+Documentation/scheduller/sched-rt-group.rst describes the range as 1 to
+INT_MAX.
+
+As far as I can tell the only problem this causes is that the sysctl
+file allows writing negative values which when read back may confuse
+userspace.
+
+There is also a LTP test being submitted for these sysctl files at:
+
+ http://patchwork.ozlabs.org/project/ltp/patch/20230901144433.2526-1-chrubis@suse.cz/
+
+Signed-off-by: Cyril Hrubis <chrubis@suse.cz>
+Signed-off-by: Ingo Molnar <mingo@kernel.org>
+Link: https://lore.kernel.org/r/20231002115553.3007-2-chrubis@suse.cz
+[ pvorel: rebased for 5.4 ]
+Reviewed-by: Petr Vorel <pvorel@suse.cz>
+Signed-off-by: Petr Vorel <pvorel@suse.cz>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/sched/rt.c | 5 +----
+ kernel/sysctl.c | 4 ++++
+ 2 files changed, 5 insertions(+), 4 deletions(-)
+
+--- a/kernel/sched/rt.c
++++ b/kernel/sched/rt.c
+@@ -2659,9 +2659,6 @@ static int sched_rt_global_constraints(v
+
+ static int sched_rt_global_validate(void)
+ {
+- if (sysctl_sched_rt_period <= 0)
+- return -EINVAL;
+-
+ if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+ ((sysctl_sched_rt_runtime > sysctl_sched_rt_period) ||
+ ((u64)sysctl_sched_rt_runtime *
+@@ -2693,7 +2690,7 @@ int sched_rt_handler(struct ctl_table *t
+ old_period = sysctl_sched_rt_period;
+ old_runtime = sysctl_sched_rt_runtime;
+
+- ret = proc_dointvec(table, write, buffer, lenp, ppos);
++ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+ if (!ret && write) {
+ ret = sched_rt_global_validate();
+--- a/kernel/sysctl.c
++++ b/kernel/sysctl.c
+@@ -465,6 +465,8 @@ static struct ctl_table kern_table[] = {
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = sched_rt_handler,
++ .extra1 = SYSCTL_ONE,
++ .extra2 = SYSCTL_INT_MAX,
+ },
+ {
+ .procname = "sched_rt_runtime_us",
+@@ -472,6 +474,8 @@ static struct ctl_table kern_table[] = {
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = sched_rt_handler,
++ .extra1 = &neg_one,
++ .extra2 = SYSCTL_INT_MAX,
+ },
+ {
+ .procname = "sched_rr_timeslice_ms",
--- /dev/null
+From c7fcb99877f9f542c918509b2801065adcaf46fa Mon Sep 17 00:00:00 2001
+From: Cyril Hrubis <chrubis@suse.cz>
+Date: Wed, 2 Aug 2023 17:19:05 +0200
+Subject: sched/rt: Fix sysctl_sched_rr_timeslice intial value
+
+From: Cyril Hrubis <chrubis@suse.cz>
+
+commit c7fcb99877f9f542c918509b2801065adcaf46fa upstream.
+
+There is a 10% rounding error in the intial value of the
+sysctl_sched_rr_timeslice with CONFIG_HZ_300=y.
+
+This was found with LTP test sched_rr_get_interval01:
+
+sched_rr_get_interval01.c:57: TPASS: sched_rr_get_interval() passed
+sched_rr_get_interval01.c:64: TPASS: Time quantum 0s 99999990ns
+sched_rr_get_interval01.c:72: TFAIL: /proc/sys/kernel/sched_rr_timeslice_ms != 100 got 90
+sched_rr_get_interval01.c:57: TPASS: sched_rr_get_interval() passed
+sched_rr_get_interval01.c:64: TPASS: Time quantum 0s 99999990ns
+sched_rr_get_interval01.c:72: TFAIL: /proc/sys/kernel/sched_rr_timeslice_ms != 100 got 90
+
+What this test does is to compare the return value from the
+sched_rr_get_interval() and the sched_rr_timeslice_ms sysctl file and
+fails if they do not match.
+
+The problem it found is the intial sysctl file value which was computed as:
+
+static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+
+which works fine as long as MSEC_PER_SEC is multiple of HZ, however it
+introduces 10% rounding error for CONFIG_HZ_300:
+
+(MSEC_PER_SEC / HZ) * (100 * HZ / 1000)
+
+(1000 / 300) * (100 * 300 / 1000)
+
+3 * 30 = 90
+
+This can be easily fixed by reversing the order of the multiplication
+and division. After this fix we get:
+
+(MSEC_PER_SEC * (100 * HZ / 1000)) / HZ
+
+(1000 * (100 * 300 / 1000)) / 300
+
+(1000 * 30) / 300 = 100
+
+Fixes: 975e155ed873 ("sched/rt: Show the 'sched_rr_timeslice' SCHED_RR timeslice tuning knob in milliseconds")
+Signed-off-by: Cyril Hrubis <chrubis@suse.cz>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Reviewed-by: Petr Vorel <pvorel@suse.cz>
+Acked-by: Mel Gorman <mgorman@suse.de>
+Tested-by: Petr Vorel <pvorel@suse.cz>
+Link: https://lore.kernel.org/r/20230802151906.25258-2-chrubis@suse.cz
+[ pvorel: rebased for 5.4 ]
+Signed-off-by: Petr Vorel <pvorel@suse.cz>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/sched/rt.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/kernel/sched/rt.c
++++ b/kernel/sched/rt.c
+@@ -8,7 +8,7 @@
+ #include "pelt.h"
+
+ int sched_rr_timeslice = RR_TIMESLICE;
+-int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
++int sysctl_sched_rr_timeslice = (MSEC_PER_SEC * RR_TIMESLICE) / HZ;
+ /* More than 4 hours if BW_SHIFT equals 20. */
+ static const u64 max_rt_runtime = MAX_BW;
+
projects / thirdparty / kernel / stable-queue.git / commitdiff
