Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:1 as permitted sender) client-ip=2620:137:e000::3:1;
From:   Pasha Tatashin <pasha.tatashin@soleen.com>
To:     akpm@linux-foundation.org, alex.williamson@redhat.com,
        alim.akhtar@samsung.com, alyssa@rosenzweig.io,
        asahi@lists.linux.dev, baolu.lu@linux.intel.com,
        bhelgaas@google.com, cgroups@vger.kernel.org, corbet@lwn.net,
        david@redhat.com, dwmw2@infradead.org, hannes@cmpxchg.org,
        heiko@sntech.de, iommu@lists.linux.dev, jasowang@redhat.com,
        jernej.skrabec@gmail.com, jgg@ziepe.ca, jonathanh@nvidia.com,
        joro@8bytes.org, kevin.tian@intel.com,
        krzysztof.kozlowski@linaro.org, kvm@vger.kernel.org,
        linux-arm-kernel@lists.infradead.org, linux-doc@vger.kernel.org,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org, linux-rockchip@lists.infradead.org,
        linux-samsung-soc@vger.kernel.org, linux-sunxi@lists.linux.dev,
        linux-tegra@vger.kernel.org, lizefan.x@bytedance.com,
        marcan@marcan.st, mhiramat@kernel.org, mst@redhat.com,
        m.szyprowski@samsung.com, netdev@vger.kernel.org,
        pasha.tatashin@soleen.com, paulmck@kernel.org,
        rdunlap@infradead.org, robin.murphy@arm.com, samuel@sholland.org,
        suravee.suthikulpanit@amd.com, sven@svenpeter.dev,
        thierry.reding@gmail.com, tj@kernel.org, tomas.mudrunka@gmail.com,
        vdumpa@nvidia.com, virtualization@lists.linux.dev, wens@csie.org,
        will@kernel.org, yu-cheng.yu@intel.com
Subject: [PATCH 13/16] iommu: observability of the IOMMU allocations
Date:   Tue, 28 Nov 2023 20:49:35 +0000
Message-ID: <20231128204938.1453583-14-pasha.tatashin@soleen.com>
In-Reply-To: <20231128204938.1453583-1-pasha.tatashin@soleen.com>
References: <20231128204938.1453583-1-pasha.tatashin@soleen.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add NR_IOMMU_PAGES into node_stat_item that counts number of pages
that are allocated by the IOMMU subsystem.

The allocations can be view per-node via:
/sys/devices/system/node/nodeN/vmstat.

For example:

$ grep iommu /sys/devices/system/node/node*/vmstat
/sys/devices/system/node/node0/vmstat:nr_iommu_pages 106025
/sys/devices/system/node/node1/vmstat:nr_iommu_pages 3464

The value is in page-count, therefore, in the above example
the iommu allocations amount to ~428M.

Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
 drivers/iommu/iommu-pages.h | 30 ++++++++++++++++++++++++++++++
 include/linux/mmzone.h      |  3 +++
 mm/vmstat.c                 |  3 +++
 3 files changed, 36 insertions(+)

diff --git a/drivers/iommu/iommu-pages.h b/drivers/iommu/iommu-pages.h
index 2332f807d514..69895a355c0c 100644
--- a/drivers/iommu/iommu-pages.h
+++ b/drivers/iommu/iommu-pages.h
@@ -17,6 +17,30 @@
  * state can be rather large, i.e. multiple gigabytes in size.
  */
 
+/**
+ * __iommu_alloc_account - account for newly allocated page.
+ * @pages: head struct page of the page.
+ * @order: order of the page
+ */
+static inline void __iommu_alloc_account(struct page *pages, int order)
+{
+	const long pgcnt = 1l << order;
+
+	mod_node_page_state(page_pgdat(pages), NR_IOMMU_PAGES, pgcnt);
+}
+
+/**
+ * __iommu_free_account - account a page that is about to be freed.
+ * @pages: head struct page of the page.
+ * @order: order of the page
+ */
+static inline void __iommu_free_account(struct page *pages, int order)
+{
+	const long pgcnt = 1l << order;
+
+	mod_node_page_state(page_pgdat(pages), NR_IOMMU_PAGES, -pgcnt);
+}
+
 /**
  * __iommu_alloc_pages_node - allocate a zeroed page of a given order from
  * specific NUMA node.
@@ -35,6 +59,8 @@ static inline struct page *__iommu_alloc_pages_node(int nid, gfp_t gfp,
 	if (!pages)
 		return NULL;
 
+	__iommu_alloc_account(pages, order);
+
 	return pages;
 }
 
@@ -53,6 +79,8 @@ static inline struct page *__iommu_alloc_pages(gfp_t gfp, int order)
 	if (!pages)
 		return NULL;
 
+	__iommu_alloc_account(pages, order);
+
 	return pages;
 }
 
@@ -89,6 +117,7 @@ static inline void __iommu_free_pages(struct page *pages, int order)
 	if (!pages)
 		return;
 
+	__iommu_free_account(pages, order);
 	__free_pages(pages, order);
 }
 
@@ -192,6 +221,7 @@ static inline void iommu_free_pages_list(struct list_head *pages)
 		struct page *p = list_entry(pages->prev, struct page, lru);
 
 		list_del(&p->lru);
+		__iommu_free_account(p, 0);
 		put_page(p);
 	}
 }
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3c25226beeed..1a4d0bba3e8b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -200,6 +200,9 @@ enum node_stat_item {
 #endif
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */
+#ifdef CONFIG_IOMMU_SUPPORT
+	NR_IOMMU_PAGES,		/* # of pages allocated by IOMMU */
+#endif
 #ifdef CONFIG_SWAP
 	NR_SWAPCACHE,
 #endif
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 359460deb377..801b58890b6c 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1242,6 +1242,9 @@ const char * const vmstat_text[] = {
 #endif
 	"nr_page_table_pages",
 	"nr_sec_page_table_pages",
+#ifdef CONFIG_IOMMU_SUPPORT
+	"nr_iommu_pages",
+#endif
 #ifdef CONFIG_SWAP
 	"nr_swapcached",
 #endif
-- 
2.43.0.rc2.451.g8631bc7472-goog