diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6c6032c03d1d..1b5d0bb008e7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -57,6 +57,7 @@
 #include <linux/lockdep.h>
 #include <linux/file.h>
 #include <linux/tracehook.h>
+#include <linux/psi.h>
 #include <linux/seq_buf.h>
 #include "internal.h"
 #include <net/sock.h>
@@ -2358,12 +2359,68 @@ static void high_work_func(struct work_struct *work)
 	reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
 }
 
+/*
+ * Clamp the maximum sleep time per allocation batch to 2 seconds. This is
+ * enough to still cause a significant slowdown in most cases, while still
+ * allowing diagnostics and tracing to proceed without becoming stuck.
+ */
+#define MEMCG_MAX_HIGH_DELAY_JIFFIES (2UL*HZ)
+
+/*
+ * When calculating the delay, we use these either side of the exponentiation to
+ * maintain precision and scale to a reasonable number of jiffies (see the table
+ * below.
+ *
+ * - MEMCG_DELAY_PRECISION_SHIFT: Extra precision bits while translating the
+ *   overage ratio to a delay.
+ * - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down down the
+ *   proposed penalty in order to reduce to a reasonable number of jiffies, and
+ *   to produce a reasonable delay curve.
+ *
+ * MEMCG_DELAY_SCALING_SHIFT just happens to be a number that produces a
+ * reasonable delay curve compared to precision-adjusted overage, not
+ * penalising heavily at first, but still making sure that growth beyond the
+ * limit penalises misbehaviour cgroups by slowing them down exponentially. For
+ * example, with a high of 100 megabytes:
+ *
+ *  +-------+------------------------+
+ *  | usage | time to allocate in ms |
+ *  +-------+------------------------+
+ *  | 100M  |                      0 |
+ *  | 101M  |                      6 |
+ *  | 102M  |                     25 |
+ *  | 103M  |                     57 |
+ *  | 104M  |                    102 |
+ *  | 105M  |                    159 |
+ *  | 106M  |                    230 |
+ *  | 107M  |                    313 |
+ *  | 108M  |                    409 |
+ *  | 109M  |                    518 |
+ *  | 110M  |                    639 |
+ *  | 111M  |                    774 |
+ *  | 112M  |                    921 |
+ *  | 113M  |                   1081 |
+ *  | 114M  |                   1254 |
+ *  | 115M  |                   1439 |
+ *  | 116M  |                   1638 |
+ *  | 117M  |                   1849 |
+ *  | 118M  |                   2000 |
+ *  | 119M  |                   2000 |
+ *  | 120M  |                   2000 |
+ *  +-------+------------------------+
+ */
+ #define MEMCG_DELAY_PRECISION_SHIFT 20
+ #define MEMCG_DELAY_SCALING_SHIFT 14
+
 /*
  * Scheduled by try_charge() to be executed from the userland return path
  * and reclaims memory over the high limit.
  */
 void mem_cgroup_handle_over_high(void)
 {
+	unsigned long usage, high, clamped_high;
+	unsigned long pflags;
+	unsigned long penalty_jiffies, overage;
 	unsigned int nr_pages = current->memcg_nr_pages_over_high;
 	struct mem_cgroup *memcg;
 
@@ -2372,8 +2429,75 @@ void mem_cgroup_handle_over_high(void)
 
 	memcg = get_mem_cgroup_from_mm(current->mm);
 	reclaim_high(memcg, nr_pages, GFP_KERNEL);
-	css_put(&memcg->css);
 	current->memcg_nr_pages_over_high = 0;
+
+	/*
+	 * memory.high is breached and reclaim is unable to keep up. Throttle
+	 * allocators proactively to slow down excessive growth.
+	 *
+	 * We use overage compared to memory.high to calculate the number of
+	 * jiffies to sleep (penalty_jiffies). Ideally this value should be
+	 * fairly lenient on small overages, and increasingly harsh when the
+	 * memcg in question makes it clear that it has no intention of stopping
+	 * its crazy behaviour, so we exponentially increase the delay based on
+	 * overage amount.
+	 */
+
+	usage = page_counter_read(&memcg->memory);
+	high = READ_ONCE(memcg->high);
+
+	if (usage <= high)
+		goto out;
+
+	/*
+	 * Prevent division by 0 in overage calculation by acting as if it was a
+	 * threshold of 1 page
+	 */
+	clamped_high = max(high, 1UL);
+
+	overage = div_u64((u64)(usage - high) << MEMCG_DELAY_PRECISION_SHIFT,
+			  clamped_high);
+
+	penalty_jiffies = ((u64)overage * overage * HZ)
+		>> (MEMCG_DELAY_PRECISION_SHIFT + MEMCG_DELAY_SCALING_SHIFT);
+
+	/*
+	 * Factor in the task's own contribution to the overage, such that four
+	 * N-sized allocations are throttled approximately the same as one
+	 * 4N-sized allocation.
+	 *
+	 * MEMCG_CHARGE_BATCH pages is nominal, so work out how much smaller or
+	 * larger the current charge patch is than that.
+	 */
+	penalty_jiffies = penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH;
+
+	/*
+	 * Clamp the max delay per usermode return so as to still keep the
+	 * application moving forwards and also permit diagnostics, albeit
+	 * extremely slowly.
+	 */
+	penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
+
+	/*
+	 * Don't sleep if the amount of jiffies this memcg owes us is so low
+	 * that it's not even worth doing, in an attempt to be nice to those who
+	 * go only a small amount over their memory.high value and maybe haven't
+	 * been aggressively reclaimed enough yet.
+	 */
+	if (penalty_jiffies <= HZ / 100)
+		goto out;
+
+	/*
+	 * If we exit early, we're guaranteed to die (since
+	 * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
+	 * need to account for any ill-begotten jiffies to pay them off later.
+	 */
+	psi_memstall_enter(&pflags);
+	schedule_timeout_killable(penalty_jiffies);
+	psi_memstall_leave(&pflags);
+
+out:
+	css_put(&memcg->css);
 }
 
 static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,