From: David Daney <ddaney@caviumnetworks.com>
To: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Cc: Ralf Baechle <ralf@linux-mips.org>, <linux-mips@linux-mips.org>,
David Daney <ddaney@cavium.com>, <ddaney.cavm@gmail.com>,
"ext Daney, David" <David.Daney@caviumnetworks.com>,
Rob Herring <robh@kernel.org>, Jiri Kosina <jkosina@suse.cz>,
Randy Dunlap <rdunlap@infradead.org>,
Masanari Iida <standby24x7@gmail.com>,
Bjorn Helgaas <bhelgaas@google.com>,
"Rulf, Mathias (Nokia - DE/Ulm)" <mathias.rulf@nokia.com>
Subject: Re: [PATCH] pci: octeon: Remove udelay() causing huge IRQ latency
Date: Wed, 18 Mar 2015 09:11:08 -0700 [thread overview]
Message-ID: <5509A39C.6010707@caviumnetworks.com> (raw)
In-Reply-To: <55097811.8050003@nokia.com>
On 03/18/2015 06:05 AM, Alexander Sverdlin wrote:
> udelay() in PCI/PCIe read/write callbacks cause 30ms IRQ latency on Octeon
> platforms because these operations are called from PCI_OP_READ() and
> PCI_OP_WRITE() under raw_spin_lock_irqsave().
>
> Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Can you say how it was tested. In principle I have no objections, but
it would be nice to know how it was validated.
Thanks,
David Daney
> ---
> arch/mips/include/asm/octeon/pci-octeon.h | 3 ---
> arch/mips/pci/pci-octeon.c | 6 ------
> arch/mips/pci/pcie-octeon.c | 8 --------
> 3 files changed, 0 insertions(+), 17 deletions(-)
>
> diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h
> index 64ba56a..1884609 100644
> --- a/arch/mips/include/asm/octeon/pci-octeon.h
> +++ b/arch/mips/include/asm/octeon/pci-octeon.h
> @@ -11,9 +11,6 @@
>
> #include <linux/pci.h>
>
> -/* Some PCI cards require delays when accessing config space. */
> -#define PCI_CONFIG_SPACE_DELAY 10000
> -
> /*
> * The physical memory base mapped by BAR1. 256MB at the end of the
> * first 4GB.
> diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
> index a04af55..01c604a 100644
> --- a/arch/mips/pci/pci-octeon.c
> +++ b/arch/mips/pci/pci-octeon.c
> @@ -271,9 +271,6 @@ static int octeon_read_config(struct pci_bus *bus, unsigned int devfn,
> pci_addr.s.func = devfn & 0x7;
> pci_addr.s.reg = reg;
>
> -#if PCI_CONFIG_SPACE_DELAY
> - udelay(PCI_CONFIG_SPACE_DELAY);
> -#endif
> switch (size) {
> case 4:
> *val = le32_to_cpu(cvmx_read64_uint32(pci_addr.u64));
> @@ -308,9 +305,6 @@ static int octeon_write_config(struct pci_bus *bus, unsigned int devfn,
> pci_addr.s.func = devfn & 0x7;
> pci_addr.s.reg = reg;
>
> -#if PCI_CONFIG_SPACE_DELAY
> - udelay(PCI_CONFIG_SPACE_DELAY);
> -#endif
> switch (size) {
> case 4:
> cvmx_write64_uint32(pci_addr.u64, cpu_to_le32(val));
> diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
> index 1bb0b2b..99f3db4 100644
> --- a/arch/mips/pci/pcie-octeon.c
> +++ b/arch/mips/pci/pcie-octeon.c
> @@ -1762,14 +1762,6 @@ static int octeon_pcie_write_config(unsigned int pcie_port, struct pci_bus *bus,
> default:
> return PCIBIOS_FUNC_NOT_SUPPORTED;
> }
> -#if PCI_CONFIG_SPACE_DELAY
> - /*
> - * Delay on writes so that devices have time to come up. Some
> - * bridges need this to allow time for the secondary busses to
> - * work
> - */
> - udelay(PCI_CONFIG_SPACE_DELAY);
> -#endif
> return PCIBIOS_SUCCESSFUL;
> }
>
>
WARNING: multiple messages have this Message-ID (diff)
From: David Daney <ddaney@caviumnetworks.com>
To: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Cc: Ralf Baechle <ralf@linux-mips.org>,
linux-mips@linux-mips.org, David Daney <ddaney@cavium.com>,
ddaney.cavm@gmail.com, "ext Daney,
David" <David.Daney@caviumnetworks.com>,
Rob Herring <robh@kernel.org>, Jiri Kosina <jkosina@suse.cz>,
Randy Dunlap <rdunlap@infradead.org>,
Masanari Iida <standby24x7@gmail.com>,
Bjorn Helgaas <bhelgaas@google.com>,
"Rulf, Mathias (Nokia - DE/Ulm)" <mathias.rulf@nokia.com>
Subject: Re: [PATCH] pci: octeon: Remove udelay() causing huge IRQ latency
Date: Wed, 18 Mar 2015 09:11:08 -0700 [thread overview]
Message-ID: <5509A39C.6010707@caviumnetworks.com> (raw)
Message-ID: <20150318161108.MtjISLq06KHBwK-PCAl9PxNu2L4vy2lpUc6scM0Wp2I@z> (raw)
In-Reply-To: <55097811.8050003@nokia.com>
On 03/18/2015 06:05 AM, Alexander Sverdlin wrote:
> udelay() in PCI/PCIe read/write callbacks cause 30ms IRQ latency on Octeon
> platforms because these operations are called from PCI_OP_READ() and
> PCI_OP_WRITE() under raw_spin_lock_irqsave().
>
> Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Can you say how it was tested. In principle I have no objections, but
it would be nice to know how it was validated.
Thanks,
David Daney
> ---
> arch/mips/include/asm/octeon/pci-octeon.h | 3 ---
> arch/mips/pci/pci-octeon.c | 6 ------
> arch/mips/pci/pcie-octeon.c | 8 --------
> 3 files changed, 0 insertions(+), 17 deletions(-)
>
> diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h
> index 64ba56a..1884609 100644
> --- a/arch/mips/include/asm/octeon/pci-octeon.h
> +++ b/arch/mips/include/asm/octeon/pci-octeon.h
> @@ -11,9 +11,6 @@
>
> #include <linux/pci.h>
>
> -/* Some PCI cards require delays when accessing config space. */
> -#define PCI_CONFIG_SPACE_DELAY 10000
> -
> /*
> * The physical memory base mapped by BAR1. 256MB at the end of the
> * first 4GB.
> diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
> index a04af55..01c604a 100644
> --- a/arch/mips/pci/pci-octeon.c
> +++ b/arch/mips/pci/pci-octeon.c
> @@ -271,9 +271,6 @@ static int octeon_read_config(struct pci_bus *bus, unsigned int devfn,
> pci_addr.s.func = devfn & 0x7;
> pci_addr.s.reg = reg;
>
> -#if PCI_CONFIG_SPACE_DELAY
> - udelay(PCI_CONFIG_SPACE_DELAY);
> -#endif
> switch (size) {
> case 4:
> *val = le32_to_cpu(cvmx_read64_uint32(pci_addr.u64));
> @@ -308,9 +305,6 @@ static int octeon_write_config(struct pci_bus *bus, unsigned int devfn,
> pci_addr.s.func = devfn & 0x7;
> pci_addr.s.reg = reg;
>
> -#if PCI_CONFIG_SPACE_DELAY
> - udelay(PCI_CONFIG_SPACE_DELAY);
> -#endif
> switch (size) {
> case 4:
> cvmx_write64_uint32(pci_addr.u64, cpu_to_le32(val));
> diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
> index 1bb0b2b..99f3db4 100644
> --- a/arch/mips/pci/pcie-octeon.c
> +++ b/arch/mips/pci/pcie-octeon.c
> @@ -1762,14 +1762,6 @@ static int octeon_pcie_write_config(unsigned int pcie_port, struct pci_bus *bus,
> default:
> return PCIBIOS_FUNC_NOT_SUPPORTED;
> }
> -#if PCI_CONFIG_SPACE_DELAY
> - /*
> - * Delay on writes so that devices have time to come up. Some
> - * bridges need this to allow time for the secondary busses to
> - * work
> - */
> - udelay(PCI_CONFIG_SPACE_DELAY);
> -#endif
> return PCIBIOS_SUCCESSFUL;
> }
>
>
next prev parent reply other threads:[~2015-03-18 16:11 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-03-18 13:05 [PATCH] pci: octeon: Remove udelay() causing huge IRQ latency Alexander Sverdlin
2015-03-18 13:11 ` Jiri Kosina
2015-03-18 14:15 ` Alexander Sverdlin
2015-03-18 16:11 ` David Daney [this message]
2015-03-18 16:11 ` David Daney
2015-03-18 16:17 ` Alexander Sverdlin
2015-03-18 18:06 ` Aaro Koskinen
2015-03-19 14:55 ` Alexander Sverdlin
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=5509A39C.6010707@caviumnetworks.com \
--to=ddaney@caviumnetworks.com \
--cc=David.Daney@caviumnetworks.com \
--cc=alexander.sverdlin@nokia.com \
--cc=bhelgaas@google.com \
--cc=ddaney.cavm@gmail.com \
--cc=ddaney@cavium.com \
--cc=jkosina@suse.cz \
--cc=linux-mips@linux-mips.org \
--cc=mathias.rulf@nokia.com \
--cc=ralf@linux-mips.org \
--cc=rdunlap@infradead.org \
--cc=robh@kernel.org \
--cc=standby24x7@gmail.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox