CIP-dev Archive on lore.kernel.org
 help / color / Atom feed
From: "Lad Prabhakar" <prabhakar.mahadev-lad.rj@bp.renesas.com>
To: cip-dev@lists.cip-project.org,
	Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>,
	Pavel Machek <pavel@denx.de>
Cc: Biju Das <biju.das.jz@bp.renesas.com>,
	Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Subject: [cip-dev] [RFC PATCH 4.19.y-cip 35/50] PCI: endpoint: functions/pci-epf-test: Print throughput information
Date: Mon, 12 Oct 2020 15:19:18 +0100
Message-ID: <20201012141933.9652-36-prabhakar.mahadev-lad.rj@bp.renesas.com> (raw)
In-Reply-To: <20201012141933.9652-1-prabhakar.mahadev-lad.rj@bp.renesas.com>


[-- Attachment #1: Type: text/plain, Size: 3909 bytes --]

From: Kishon Vijay Abraham I <kishon@ti.com>

commit 5893c2e5353bb9a723d862d8b6ba8028a8f6a6eb upstream.

Print throughput information in KB/s after every completed transfer,
including information on whether DMA is used or not.

Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Tested-by: Alan Mikhak <alan.mikhak@sifive.com>
[PL: Applied changes to pci-epf-test.c manually, always pass dma variable
to pci_epf_test_print_rate() function as false since streaming DMA support
is missing in EPF]
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
---
 drivers/pci/endpoint/functions/pci-epf-test.c | 44 +++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index f6905c242194..8d9b5521ed50 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -73,6 +73,36 @@ static struct pci_epf_header test_header = {
 
 static size_t bar_size[] = { 512, 512, 1024, 16384, 131072, 1048576 };
 
+static void pci_epf_test_print_rate(const char *ops, u64 size,
+				    struct timespec64 *start,
+				    struct timespec64 *end, bool dma)
+{
+	struct timespec64 ts;
+	u64 rate, ns;
+
+	ts = timespec64_sub(*end, *start);
+
+	/* convert both size (stored in 'rate') and time in terms of 'ns' */
+	ns = timespec64_to_ns(&ts);
+	rate = size * NSEC_PER_SEC;
+
+	/* Divide both size (stored in 'rate') and ns by a common factor */
+	while (ns > UINT_MAX) {
+		rate >>= 1;
+		ns >>= 1;
+	}
+
+	if (!ns)
+		return;
+
+	/* calculate the rate */
+	do_div(rate, (uint32_t)ns);
+
+	pr_info("\n%s => Size: %llu bytes\t DMA: %s\t Time: %llu.%09u seconds\t"
+		"Rate: %llu KB/s\n", ops, size, dma ? "YES" : "NO",
+		(u64)ts.tv_sec, (u32)ts.tv_nsec, rate / 1024);
+}
+
 static int pci_epf_test_copy(struct pci_epf_test *epf_test)
 {
 	int ret;
@@ -80,6 +110,7 @@ static int pci_epf_test_copy(struct pci_epf_test *epf_test)
 	void __iomem *dst_addr;
 	phys_addr_t src_phys_addr;
 	phys_addr_t dst_phys_addr;
+	struct timespec64 start, end;
 	struct pci_epf *epf = epf_test->epf;
 	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
@@ -118,7 +149,10 @@ static int pci_epf_test_copy(struct pci_epf_test *epf_test)
 		goto err_dst_addr;
 	}
 
+	ktime_get_ts64(&start);
 	memcpy(dst_addr, src_addr, reg->size);
+	ktime_get_ts64(&end);
+	pci_epf_test_print_rate("COPY", reg->size, &start, &end, false);
 
 	pci_epc_unmap_addr(epc, epf->func_no, dst_phys_addr);
 
@@ -142,6 +176,7 @@ static int pci_epf_test_read(struct pci_epf_test *epf_test)
 	void *buf;
 	u32 crc32;
 	phys_addr_t phys_addr;
+	struct timespec64 start, end;
 	struct pci_epf *epf = epf_test->epf;
 	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
@@ -170,7 +205,11 @@ static int pci_epf_test_read(struct pci_epf_test *epf_test)
 		goto err_map_addr;
 	}
 
+	ktime_get_ts64(&start);
 	memcpy_fromio(buf, src_addr, reg->size);
+	ktime_get_ts64(&end);
+
+	pci_epf_test_print_rate("READ", reg->size, &start, &end, false);
 
 	crc32 = crc32_le(~0, buf, reg->size);
 	if (crc32 != reg->checksum)
@@ -194,6 +233,7 @@ static int pci_epf_test_write(struct pci_epf_test *epf_test)
 	void __iomem *dst_addr;
 	void *buf;
 	phys_addr_t phys_addr;
+	struct timespec64 start, end;
 	struct pci_epf *epf = epf_test->epf;
 	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
@@ -225,7 +265,11 @@ static int pci_epf_test_write(struct pci_epf_test *epf_test)
 	get_random_bytes(buf, reg->size);
 	reg->checksum = crc32_le(~0, buf, reg->size);
 
+	ktime_get_ts64(&start);
 	memcpy_toio(dst_addr, buf, reg->size);
+	ktime_get_ts64(&end);
+
+	pci_epf_test_print_rate("WRITE", reg->size, &start, &end, false);
 
 	/*
 	 * wait 1ms inorder for the write to complete. Without this delay L3
-- 
2.17.1


[-- Attachment #2: Type: text/plain, Size: 420 bytes --]


-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#5555): https://lists.cip-project.org/g/cip-dev/message/5555
Mute This Topic: https://lists.cip-project.org/mt/77461713/4520388
Group Owner: cip-dev+owner@lists.cip-project.org
Unsubscribe: https://lists.cip-project.org/g/cip-dev/leave/8129055/727948398/xyzzy [cip-dev@archiver.kernel.org]
-=-=-=-=-=-=-=-=-=-=-=-


  parent reply index

Thread overview: 73+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-12 14:18 [cip-dev] [RFC PATCH 4.19.y-cip 00/50] Add PCIe EP support for Renesas R-Car Gen3 and RZ/G2x Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 01/50] PCI: endpoint: Add new pci_epc_ops to get EPC features Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 02/50] PCI: dwc: Add ->get_features() callback function to dw_pcie_ep_ops Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 03/50] PCI: designware-plat: Populate ->get_features() dw_pcie_ep_ops Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 04/50] PCI: pci-dra7xx: " Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 05/50] PCI: rockchip: " Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 06/50] PCI: cadence: Populate ->get_features() cdns_pcie_epc_ops Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 07/50] PCI: endpoint: Add helper to get first unreserved BAR Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 08/50] PCI: endpoint: Fix pci_epf_alloc_space() to set correct MEM TYPE flags Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 09/50] PCI: pci-epf-test: Remove setting epf_bar flags in function driver Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 10/50] PCI: pci-epf-test: Do not allocate next BARs memory if current BAR is 64Bit Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 11/50] PCI: pci-epf-test: Use pci_epc_get_features() to get EPC features Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 12/50] PCI: cadence: Remove pci_epf_linkup() from Cadence EP driver Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 13/50] PCI: rockchip: Remove pci_epf_linkup() from Rockchip " Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 14/50] PCI: designware-plat: Remove setting epc->features in Designware plat " Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 15/50] PCI: endpoint: Remove features member in struct pci_epc Lad Prabhakar
2020-10-12 14:18 ` [cip-dev] [RFC PATCH 4.19.y-cip 16/50] PCI: endpoint: Fix a potential NULL pointer dereference Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 17/50] PCI: endpoint: Add support to specify alignment for buffers allocated to BARs Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 18/50] PCI: endpoint: Set endpoint controller pointer to NULL Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 19/50] PCI: endpoint: Allocate enough space for fixed size BAR Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 20/50] PCI: endpoint: Skip odd BAR when skipping 64bit BAR Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 21/50] PCI: endpoint: Clear BAR before freeing its space Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 22/50] PCI: endpoint: Cast the page number to phys_addr_t Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 23/50] PCI: endpoint: Use notification chain mechanism to notify EPC events to EPF Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 24/50] PCI: endpoint: Replace spinlock with mutex Lad Prabhakar
2020-10-20 20:43   ` Pavel Machek
2020-10-20 21:56     ` Lad Prabhakar
2020-10-21 18:34       ` Pavel Machek
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 25/50] PCI: endpoint: Protect concurrent access to pci_epf_ops " Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 26/50] PCI: endpoint: Assign function number for each PF in EPC core Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 27/50] PCI: endpoint: Add core init notifying feature Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 28/50] PCI: endpoint: Add notification for core init completion Lad Prabhakar
2020-10-21 19:00   ` Pavel Machek
2020-10-21 20:16     ` Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 29/50] PCI: pci-epf-test: Add support to defer core initialization Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 30/50] PCI: endpoint: Fix clearing start entry in configfs Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 31/50] PCI: endpoint: Fix ->set_msix() to take BIR and offset as arguments Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 32/50] PCI: dwc: Fix dw_pcie_ep_raise_msix_irq() to get correct MSI-X table address Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 33/50] PCI: endpoint: Pass page size as argument to pci_epc_mem_init() Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 34/50] PCI: endpoint: Add support to handle multiple base for mapping outbound memory Lad Prabhakar
2020-10-12 14:19 ` Lad Prabhakar [this message]
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 36/50] PCI: rcar: Rename pcie-rcar.c to pcie-rcar-host.c Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 37/50] arm64: defconfig: Enable CONFIG_PCIE_RCAR_HOST Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 38/50] PCI: rcar: Move shareable code to a common file Lad Prabhakar
2020-10-21 19:06   ` Pavel Machek
2020-10-21 20:28     ` Lad Prabhakar
2020-10-22 19:42       ` Pavel Machek
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 39/50] PCI: rcar: Fix calculating mask for PCIEPAMR register Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 40/50] dt-bindings: PCI: rcar: Add bindings for R-Car PCIe endpoint controller Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 41/50] PCI: rcar: Add endpoint mode support Lad Prabhakar
2020-10-14  9:22   ` Pavel Machek
2020-10-15 16:31     ` Lad Prabhakar
2020-10-15 18:01       ` Pavel Machek
2020-10-22 18:23         ` Pavel Machek
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 42/50] arm64: defconfig: Enable R-Car PCIe endpoint driver Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 43/50] dt-bindings: pci: rcar-pci-ep: Document r8a774a1 and r8a774b1 Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 44/50] arm64: dts: renesas: r8a774c0: Add PCIe EP node Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 45/50] arm64: dts: renesas: r8a774a1: Add PCIe EP nodes Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 46/50] arm64: dts: renesas: r8a774b1: " Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 47/50] misc: pci_endpoint_test: Add Device ID for RZ/G2E PCIe controller Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 48/50] misc: pci_endpoint_test: Add Device ID for RZ/G2M and RZ/G2N PCIe controllers Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 49/50] tools: PCI: Exit with error code when test fails Lad Prabhakar
2020-10-12 14:19 ` [cip-dev] [RFC PATCH 4.19.y-cip 50/50] tools: PCI: Fix fd leakage Lad Prabhakar
2020-10-14  9:39 ` [cip-dev] If you are using PCIe EP, speak up was Re: [RFC PATCH 4.19.y-cip 00/50] Add PCIe EP support for Renesas R-Car Gen3 and RZ/G2x Pavel Machek
2020-10-15 16:18   ` Lad Prabhakar
2020-10-20  7:16   ` Lad Prabhakar
2020-10-20 10:34     ` Pavel Machek
2020-10-20 12:01     ` Pavel Machek
2020-10-20 13:01       ` Lad Prabhakar
2020-10-20 20:48         ` Pavel Machek
2020-10-20 21:58           ` Lad Prabhakar
2020-10-14 10:07 ` [cip-dev] " Pavel Machek
2020-10-15 16:27   ` Lad Prabhakar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201012141933.9652-36-prabhakar.mahadev-lad.rj@bp.renesas.com \
    --to=prabhakar.mahadev-lad.rj@bp.renesas.com \
    --cc=biju.das.jz@bp.renesas.com \
    --cc=cip-dev@lists.cip-project.org \
    --cc=nobuhiro1.iwamatsu@toshiba.co.jp \
    --cc=pavel@denx.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

CIP-dev Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/cip-dev/0 cip-dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 cip-dev cip-dev/ https://lore.kernel.org/cip-dev \
		cip-dev@lists.cip-project.org
	public-inbox-index cip-dev

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.cip-project.lists.cip-dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git