From 8ac6c7a54ed1b98d142dce24b11c6de6a1e239a5 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 22 Oct 2024 10:36:11 +0000
Subject: [PATCH] 修改4g拨号为QMI,需要在系统里后台执行quectel-CM
---
kernel/net/core/page_pool.c | 374 ++++++++++++++++++++++++++++++++++++++++++----------
1 files changed, 300 insertions(+), 74 deletions(-)
diff --git a/kernel/net/core/page_pool.c b/kernel/net/core/page_pool.c
index 43a932c..08fbf40 100644
--- a/kernel/net/core/page_pool.c
+++ b/kernel/net/core/page_pool.c
@@ -4,15 +4,22 @@
* Author: Jesper Dangaard Brouer <netoptimizer@brouer.com>
* Copyright (C) 2016 Red Hat, Inc.
*/
+
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.h>
+#include <linux/device.h>
#include <net/page_pool.h>
#include <linux/dma-direction.h>
#include <linux/dma-mapping.h>
#include <linux/page-flags.h>
#include <linux/mm.h> /* for __put_page() */
+
+#include <trace/events/page_pool.h>
+
+#define DEFER_TIME (msecs_to_jiffies(1000))
+#define DEFER_WARN_INTERVAL (60 * HZ)
static int page_pool_init(struct page_pool *pool,
const struct page_pool_params *params)
@@ -36,12 +43,37 @@
* DMA_BIDIRECTIONAL is for allowing page used for DMA sending,
* which is the XDP_TX use-case.
*/
- if ((pool->p.dma_dir != DMA_FROM_DEVICE) &&
- (pool->p.dma_dir != DMA_BIDIRECTIONAL))
- return -EINVAL;
+ if (pool->p.flags & PP_FLAG_DMA_MAP) {
+ if ((pool->p.dma_dir != DMA_FROM_DEVICE) &&
+ (pool->p.dma_dir != DMA_BIDIRECTIONAL))
+ return -EINVAL;
+ }
+
+ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) {
+ /* In order to request DMA-sync-for-device the page
+ * needs to be mapped
+ */
+ if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+ return -EINVAL;
+
+ if (!pool->p.max_len)
+ return -EINVAL;
+
+ /* pool->p.offset has to be set according to the address
+ * offset used by the DMA engine to start copying rx data
+ */
+ }
if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
return -ENOMEM;
+
+ atomic_set(&pool->pages_state_release_cnt, 0);
+
+ /* Driver calling page_pool_create() also call page_pool_destroy() */
+ refcount_set(&pool->user_cnt, 1);
+
+ if (pool->p.flags & PP_FLAG_DMA_MAP)
+ get_device(pool->p.dev);
return 0;
}
@@ -49,7 +81,7 @@
struct page_pool *page_pool_create(const struct page_pool_params *params)
{
struct page_pool *pool;
- int err = 0;
+ int err;
pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, params->nid);
if (!pool)
@@ -61,49 +93,91 @@
kfree(pool);
return ERR_PTR(err);
}
+
return pool;
}
EXPORT_SYMBOL(page_pool_create);
-/* fast path */
-static struct page *__page_pool_get_cached(struct page_pool *pool)
+static void page_pool_return_page(struct page_pool *pool, struct page *page);
+
+noinline
+static struct page *page_pool_refill_alloc_cache(struct page_pool *pool)
{
struct ptr_ring *r = &pool->ring;
struct page *page;
+ int pref_nid; /* preferred NUMA node */
/* Quicker fallback, avoid locks when ring is empty */
if (__ptr_ring_empty(r))
return NULL;
- /* Test for safe-context, caller should provide this guarantee */
- if (likely(in_serving_softirq())) {
- if (likely(pool->alloc.count)) {
- /* Fast-path */
- page = pool->alloc.cache[--pool->alloc.count];
- return page;
- }
- /* Slower-path: Alloc array empty, time to refill
- *
- * Open-coded bulk ptr_ring consumer.
- *
- * Discussion: the ring consumer lock is not really
- * needed due to the softirq/NAPI protection, but
- * later need the ability to reclaim pages on the
- * ring. Thus, keeping the locks.
- */
- spin_lock(&r->consumer_lock);
- while ((page = __ptr_ring_consume(r))) {
- if (pool->alloc.count == PP_ALLOC_CACHE_REFILL)
- break;
+ /* Softirq guarantee CPU and thus NUMA node is stable. This,
+ * assumes CPU refilling driver RX-ring will also run RX-NAPI.
+ */
+#ifdef CONFIG_NUMA
+ pref_nid = (pool->p.nid == NUMA_NO_NODE) ? numa_mem_id() : pool->p.nid;
+#else
+ /* Ignore pool->p.nid setting if !CONFIG_NUMA, helps compiler */
+ pref_nid = numa_mem_id(); /* will be zero like page_to_nid() */
+#endif
+
+ /* Slower-path: Get pages from locked ring queue */
+ spin_lock(&r->consumer_lock);
+
+ /* Refill alloc array, but only if NUMA match */
+ do {
+ page = __ptr_ring_consume(r);
+ if (unlikely(!page))
+ break;
+
+ if (likely(page_to_nid(page) == pref_nid)) {
pool->alloc.cache[pool->alloc.count++] = page;
+ } else {
+ /* NUMA mismatch;
+ * (1) release 1 page to page-allocator and
+ * (2) break out to fallthrough to alloc_pages_node.
+ * This limit stress on page buddy alloactor.
+ */
+ page_pool_return_page(pool, page);
+ page = NULL;
+ break;
}
- spin_unlock(&r->consumer_lock);
- return page;
+ } while (pool->alloc.count < PP_ALLOC_CACHE_REFILL);
+
+ /* Return last page */
+ if (likely(pool->alloc.count > 0))
+ page = pool->alloc.cache[--pool->alloc.count];
+
+ spin_unlock(&r->consumer_lock);
+ return page;
+}
+
+/* fast path */
+static struct page *__page_pool_get_cached(struct page_pool *pool)
+{
+ struct page *page;
+
+ /* Caller MUST guarantee safe non-concurrent access, e.g. softirq */
+ if (likely(pool->alloc.count)) {
+ /* Fast-path */
+ page = pool->alloc.cache[--pool->alloc.count];
+ } else {
+ page = page_pool_refill_alloc_cache(pool);
}
- /* Slow-path: Get page from locked ring queue */
- page = ptr_ring_consume(&pool->ring);
return page;
+}
+
+static void page_pool_dma_sync_for_device(struct page_pool *pool,
+ struct page *page,
+ unsigned int dma_sync_size)
+{
+ dma_addr_t dma_addr = page_pool_get_dma_addr(page);
+
+ dma_sync_size = min(dma_sync_size, pool->p.max_len);
+ dma_sync_single_range_for_device(pool->p.dev, dma_addr,
+ pool->p.offset, dma_sync_size,
+ pool->p.dma_dir);
}
/* slow path */
@@ -129,26 +203,40 @@
*/
/* Cache was empty, do real allocation */
+#ifdef CONFIG_NUMA
page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
+#else
+ page = alloc_pages(gfp, pool->p.order);
+#endif
if (!page)
return NULL;
if (!(pool->p.flags & PP_FLAG_DMA_MAP))
goto skip_dma_map;
- /* Setup DMA mapping: use page->private for DMA-addr
+ /* Setup DMA mapping: use 'struct page' area for storing DMA-addr
+ * since dma_addr_t can be either 32 or 64 bits and does not always fit
+ * into page private data (i.e 32bit cpu with 64bit DMA caps)
* This mapping is kept for lifetime of page, until leaving pool.
*/
- dma = dma_map_page(pool->p.dev, page, 0,
- (PAGE_SIZE << pool->p.order),
- pool->p.dma_dir);
+ dma = dma_map_page_attrs(pool->p.dev, page, 0,
+ (PAGE_SIZE << pool->p.order),
+ pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC);
if (dma_mapping_error(pool->p.dev, dma)) {
put_page(page);
return NULL;
}
- set_page_private(page, dma); /* page->private = dma; */
+ page_pool_set_dma_addr(page, dma);
+
+ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+ page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
skip_dma_map:
+ /* Track how many pages are held 'in-flight' */
+ pool->pages_state_hold_cnt++;
+
+ trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt);
+
/* When page just alloc'ed is should/must have refcnt 1. */
return page;
}
@@ -171,23 +259,62 @@
}
EXPORT_SYMBOL(page_pool_alloc_pages);
-/* Cleanup page_pool state from page */
-static void __page_pool_clean_page(struct page_pool *pool,
- struct page *page)
-{
- if (!(pool->p.flags & PP_FLAG_DMA_MAP))
- return;
+/* Calculate distance between two u32 values, valid if distance is below 2^(31)
+ * https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution
+ */
+#define _distance(a, b) (s32)((a) - (b))
- /* DMA unmap */
- dma_unmap_page(pool->p.dev, page_private(page),
- PAGE_SIZE << pool->p.order, pool->p.dma_dir);
- set_page_private(page, 0);
+static s32 page_pool_inflight(struct page_pool *pool)
+{
+ u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
+ u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
+ s32 inflight;
+
+ inflight = _distance(hold_cnt, release_cnt);
+
+ trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
+ WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
+
+ return inflight;
}
-/* Return a page to the page allocator, cleaning up our state */
-static void __page_pool_return_page(struct page_pool *pool, struct page *page)
+/* Disconnects a page (from a page_pool). API users can have a need
+ * to disconnect a page (from a page_pool), to allow it to be used as
+ * a regular page (that will eventually be returned to the normal
+ * page-allocator via put_page).
+ */
+void page_pool_release_page(struct page_pool *pool, struct page *page)
{
- __page_pool_clean_page(pool, page);
+ dma_addr_t dma;
+ int count;
+
+ if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+ /* Always account for inflight pages, even if we didn't
+ * map them
+ */
+ goto skip_dma_unmap;
+
+ dma = page_pool_get_dma_addr(page);
+
+ /* When page is unmapped, it cannot be returned to our pool */
+ dma_unmap_page_attrs(pool->p.dev, dma,
+ PAGE_SIZE << pool->p.order, pool->p.dma_dir,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ page_pool_set_dma_addr(page, 0);
+skip_dma_unmap:
+ /* This may be the last page returned, releasing the pool, so
+ * it is not safe to reference pool afterwards.
+ */
+ count = atomic_inc_return(&pool->pages_state_release_cnt);
+ trace_page_pool_state_release(pool, page, count);
+}
+EXPORT_SYMBOL(page_pool_release_page);
+
+/* Return a page to the page allocator, cleaning up our state */
+static void page_pool_return_page(struct page_pool *pool, struct page *page)
+{
+ page_pool_release_page(pool, page);
+
put_page(page);
/* An optimization would be to call __free_pages(page, pool->p.order)
* knowing page is not part of page-cache (thus avoiding a
@@ -195,8 +322,7 @@
*/
}
-static bool __page_pool_recycle_into_ring(struct page_pool *pool,
- struct page *page)
+static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page)
{
int ret;
/* BH protection not needed if current is serving softirq */
@@ -213,7 +339,7 @@
*
* Caller must provide appropriate safe context.
*/
-static bool __page_pool_recycle_direct(struct page *page,
+static bool page_pool_recycle_in_cache(struct page *page,
struct page_pool *pool)
{
if (unlikely(pool->alloc.count == PP_ALLOC_CACHE_SIZE))
@@ -224,8 +350,22 @@
return true;
}
-void __page_pool_put_page(struct page_pool *pool,
- struct page *page, bool allow_direct)
+/* page is NOT reusable when:
+ * 1) allocated when system is under some pressure. (page_is_pfmemalloc)
+ */
+static bool pool_page_reusable(struct page_pool *pool, struct page *page)
+{
+ return !page_is_pfmemalloc(page);
+}
+
+/* If the page refcnt == 1, this will try to recycle the page.
+ * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for
+ * the configured size min(dma_sync_size, pool->max_len).
+ * If the page refcnt != 1, then the page will be returned to memory
+ * subsystem.
+ */
+void page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
{
/* This allocator is optimized for the XDP mode that uses
* one-frame-per-page, but have fallbacks that act like the
@@ -233,16 +373,21 @@
*
* refcnt == 1 means page_pool owns page, and can recycle it.
*/
- if (likely(page_ref_count(page) == 1)) {
+ if (likely(page_ref_count(page) == 1 &&
+ pool_page_reusable(pool, page))) {
/* Read barrier done in page_ref_count / READ_ONCE */
+ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+ page_pool_dma_sync_for_device(pool, page,
+ dma_sync_size);
+
if (allow_direct && in_serving_softirq())
- if (__page_pool_recycle_direct(page, pool))
+ if (page_pool_recycle_in_cache(page, pool))
return;
- if (!__page_pool_recycle_into_ring(pool, page)) {
+ if (!page_pool_recycle_in_ring(pool, page)) {
/* Cache full, fallback to free pages */
- __page_pool_return_page(pool, page);
+ page_pool_return_page(pool, page);
}
return;
}
@@ -259,12 +404,13 @@
* doing refcnt based recycle tricks, meaning another process
* will be invoking put_page.
*/
- __page_pool_clean_page(pool, page);
+ /* Do not replace this with page_pool_return_page() */
+ page_pool_release_page(pool, page);
put_page(page);
}
-EXPORT_SYMBOL(__page_pool_put_page);
+EXPORT_SYMBOL(page_pool_put_page);
-static void __page_pool_empty_ring(struct page_pool *pool)
+static void page_pool_empty_ring(struct page_pool *pool)
{
struct page *page;
@@ -275,27 +421,29 @@
pr_crit("%s() page_pool refcnt %d violation\n",
__func__, page_ref_count(page));
- __page_pool_return_page(pool, page);
+ page_pool_return_page(pool, page);
}
}
-static void __page_pool_destroy_rcu(struct rcu_head *rcu)
+static void page_pool_free(struct page_pool *pool)
{
- struct page_pool *pool;
+ if (pool->disconnect)
+ pool->disconnect(pool);
- pool = container_of(rcu, struct page_pool, rcu);
-
- WARN(pool->alloc.count, "API usage violation");
-
- __page_pool_empty_ring(pool);
ptr_ring_cleanup(&pool->ring, NULL);
+
+ if (pool->p.flags & PP_FLAG_DMA_MAP)
+ put_device(pool->p.dev);
+
kfree(pool);
}
-/* Cleanup and release resources */
-void page_pool_destroy(struct page_pool *pool)
+static void page_pool_empty_alloc_cache_once(struct page_pool *pool)
{
struct page *page;
+
+ if (pool->destroy_cnt)
+ return;
/* Empty alloc cache, assume caller made sure this is
* no-longer in use, and page_pool_alloc_pages() cannot be
@@ -303,15 +451,93 @@
*/
while (pool->alloc.count) {
page = pool->alloc.cache[--pool->alloc.count];
- __page_pool_return_page(pool, page);
+ page_pool_return_page(pool, page);
}
+}
+
+static void page_pool_scrub(struct page_pool *pool)
+{
+ page_pool_empty_alloc_cache_once(pool);
+ pool->destroy_cnt++;
/* No more consumers should exist, but producers could still
* be in-flight.
*/
- __page_pool_empty_ring(pool);
+ page_pool_empty_ring(pool);
+}
- /* An xdp_mem_allocator can still ref page_pool pointer */
- call_rcu(&pool->rcu, __page_pool_destroy_rcu);
+static int page_pool_release(struct page_pool *pool)
+{
+ int inflight;
+
+ page_pool_scrub(pool);
+ inflight = page_pool_inflight(pool);
+ if (!inflight)
+ page_pool_free(pool);
+
+ return inflight;
+}
+
+static void page_pool_release_retry(struct work_struct *wq)
+{
+ struct delayed_work *dwq = to_delayed_work(wq);
+ struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw);
+ int inflight;
+
+ inflight = page_pool_release(pool);
+ if (!inflight)
+ return;
+
+ /* Periodic warning */
+ if (time_after_eq(jiffies, pool->defer_warn)) {
+ int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ;
+
+ pr_warn("%s() stalled pool shutdown %d inflight %d sec\n",
+ __func__, inflight, sec);
+ pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
+ }
+
+ /* Still not ready to be disconnected, retry later */
+ schedule_delayed_work(&pool->release_dw, DEFER_TIME);
+}
+
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *))
+{
+ refcount_inc(&pool->user_cnt);
+ pool->disconnect = disconnect;
+}
+
+void page_pool_destroy(struct page_pool *pool)
+{
+ if (!pool)
+ return;
+
+ if (!page_pool_put(pool))
+ return;
+
+ if (!page_pool_release(pool))
+ return;
+
+ pool->defer_start = jiffies;
+ pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
+
+ INIT_DELAYED_WORK(&pool->release_dw, page_pool_release_retry);
+ schedule_delayed_work(&pool->release_dw, DEFER_TIME);
}
EXPORT_SYMBOL(page_pool_destroy);
+
+/* Caller must provide appropriate safe context, e.g. NAPI. */
+void page_pool_update_nid(struct page_pool *pool, int new_nid)
+{
+ struct page *page;
+
+ trace_page_pool_update_nid(pool, new_nid);
+ pool->p.nid = new_nid;
+
+ /* Flush pool alloc cache, as refill will check NUMA node */
+ while (pool->alloc.count) {
+ page = pool->alloc.cache[--pool->alloc.count];
+ page_pool_return_page(pool, page);
+ }
+}
+EXPORT_SYMBOL(page_pool_update_nid);
--
Gitblit v1.6.2