public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Robert Richter <robert.richter@amd.com>
To: Barry Kasindorf <barry.kasindorf@amd.com>, Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>,
	oprofile-list <oprofile-list@lists.sourceforge.net>,
	LKML <linux-kernel@vger.kernel.org>,
	Jason Yeh <jason.yeh@amd.com>
Subject: Re: [PATCH 11/24] x86/oprofile: Add IBS support for AMD CPUs, model specific code
Date: Thu, 24 Jul 2008 16:39:53 +0200	[thread overview]
Message-ID: <20080724143953.GS17134@erda.amd.com> (raw)
In-Reply-To: <1216753748-11261-12-git-send-email-robert.richter@amd.com>

On 22.07.08 21:08:55, Robert Richter wrote:
> From: Barry Kasindorf <barry.kasindorf@amd.com>
> 
> This patchset supports the new profiling hardware available in the
> latest AMD CPUs in the oProfile driver.
> 
> Signed-off-by: Barry Kasindorf <barry.kasindorf@amd.com>
> Signed-off-by: Robert Richter <robert.richter@amd.com>
> ---
>  arch/x86/oprofile/op_model_athlon.c |  257 +++++++++++++++++++++++++++++++++++
>  1 files changed, 257 insertions(+), 0 deletions(-)
> 
> diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c
> index 40ecb02..229e0b4 100644

[...]

> @@ -181,6 +345,99 @@ static void op_amd_shutdown(struct op_msrs const * const msrs)
>  	}
>  }
>  
> +static inline void apic_init_ibs_nmi_per_cpu(void *arg)
> +{
> +	setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0);
> +}
> +
> +static inline void apic_clear_ibs_nmi_per_cpu(void *arg)
> +{
> +	setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
> +}
> +
> +/*
> + * initialize the APIC for the IBS interrupts
> + * if needed on AMD Family10h rev B0 and later
> + */
> +static void setup_ibs(void)
> +{
> +	struct pci_dev *gh_device = NULL;
> +	u32 low, high;
> +	u8 vector;
> +
> +	ibs_allowed = boot_cpu_has(X86_FEATURE_IBS);
> +
> +	if (!ibs_allowed)
> +		return;
> +
> +	/* This gets the APIC_EILVT_LVTOFF_IBS value */
> +	vector = setup_APIC_eilvt_ibs(0, 0, 1);
> +
> +	/*see if the IBS control register is already set correctly*/
> +	/*remove this when we know for sure it is done
> +	  in the kernel init*/
> +	rdmsr(MSR_AMD64_IBSCTL, low, high);
> +	if ((low & (IBS_CTL_LVT_OFFSET_VALID_BIT | vector)) !=
> +		(IBS_CTL_LVT_OFFSET_VALID_BIT | vector)) {
> +
> +		/**** Be sure to run loop until NULL is returned to
> +		decrement reference count on any pci_dev structures
> +		returned ****/
> +		while ((gh_device = pci_get_device(PCI_VENDOR_ID_AMD,
> +			PCI_DEVICE_ID_AMD_10H_NB_MISC, gh_device))
> +			!= NULL) {
> +			/* This code may change if we can find a proper
> +			* way to get at the PCI extended config space */
> +			pci_write_config_dword(
> +				gh_device, IBS_LVT_OFFSET_PCI,
> +				(vector | IBS_CTL_LVT_OFFSET_VALID_BIT));
> +		}
> +	}
> +	on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1, 1);
> +}
> +
> +
> +/*
> + * unitialize the APIC for the IBS interrupts if needed on AMD Family10h
> + * rev B0 and later */
> +static void clear_ibs_nmi(void)
> +{
> +	if (ibs_allowed)
> +		on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1, 1);
> +}
> +
> +static void setup_ibs_files(struct super_block *sb, struct dentry *root)
> +{
> +	char buf[12];
> +	struct dentry *dir;
> +
> +	if (!ibs_allowed)
> +		return;
> +
> +	/* setup some reasonable defaults */
> +	ibs_config.max_cnt_fetch = 250000;
> +	ibs_config.fetch_enabled = 0;
> +	ibs_config.max_cnt_op = 250000;
> +	ibs_config.op_enabled = 0;
> +	ibs_config.dispatched_ops = 1;
> +	snprintf(buf,  sizeof(buf), "ibs_fetch");
> +	dir = oprofilefs_mkdir(sb, root, buf);
> +	oprofilefs_create_ulong(sb, dir, "rand_enable",
> +				&ibs_config.rand_en);
> +	oprofilefs_create_ulong(sb, dir, "enable",
> +		&ibs_config.fetch_enabled);
> +	oprofilefs_create_ulong(sb, dir, "max_count",
> +		&ibs_config.max_cnt_fetch);
> +	snprintf(buf,  sizeof(buf), "ibs_uops");

This should be renamed to "ibs_op" to be close to the register
specification in the BKDG.

-Robert

> +	dir = oprofilefs_mkdir(sb, root, buf);
> +	oprofilefs_create_ulong(sb, dir, "enable",
> +		&ibs_config.op_enabled);
> +	oprofilefs_create_ulong(sb, dir, "max_count",
> +		&ibs_config.max_cnt_op);
> +	oprofilefs_create_ulong(sb, dir, "dispatched_ops",
> +		&ibs_config.dispatched_ops);
> +}
> +
>  static int op_amd_init(struct oprofile_operations *ops)
>  {
>  	return 0;
> -- 
> 1.5.5.4
> 

-- 
Advanced Micro Devices, Inc.
Operating System Research Center
email: robert.richter@amd.com


  parent reply	other threads:[~2008-07-24 14:40 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-07-22 19:08 [PATCH 0/24] oprofile: Add IBS support for AMD CPUs Robert Richter
2008-07-22 19:08 ` [PATCH 01/24] x86: Add PCI IDs for AMD Barcelona PCI devices Robert Richter
2008-07-22 19:08 ` [PATCH 02/24] x86: apic_*.c: Add description to AMD's extended LVT functions Robert Richter
2008-07-22 19:08 ` [PATCH 03/24] oprofile: Add support for AMD Family 11h Robert Richter
2008-07-26 17:32   ` Daniel K.
2008-07-28 15:35     ` Ingo Molnar
2008-07-22 19:08 ` [PATCH 04/24] x86/oprofile: Introduce model specific init/exit functions Robert Richter
2008-07-22 19:08 ` [PATCH 05/24] x86/oprofile: Minor changes in op_model_athlon.c Robert Richter
2008-07-22 19:08 ` [PATCH 06/24] x86/oprofile: Renaming athlon_*() into op_amd_*() Robert Richter
2008-07-26  9:55   ` Ingo Molnar
2008-07-22 19:08 ` [PATCH 07/24] drivers/oprofile: Coding style fixes in buffer_sync.c Robert Richter
2008-07-22 19:08 ` [PATCH 08/24] OProfile: Moving increment_tail() " Robert Richter
2008-07-26  9:56   ` Ingo Molnar
2008-07-22 19:08 ` [PATCH 09/24] OProfile: Add IBS code macros Robert Richter
2008-07-22 19:08 ` [PATCH 10/24] x86/oprofile: Add IBS support for AMD CPUs, IBS buffer handling routines Robert Richter
2008-07-23 19:20   ` Maynard Johnson
2008-07-23 19:46     ` Robert Richter
2008-07-23 20:01   ` Carl Love
2008-07-23 20:19     ` Robert Richter
2008-07-26  9:58   ` Ingo Molnar
2008-07-22 19:08 ` [PATCH 11/24] x86/oprofile: Add IBS support for AMD CPUs, model specific code Robert Richter
2008-07-24 14:15   ` Maynard Johnson
2008-07-24 14:36     ` Robert Richter
2008-07-24 14:39   ` Robert Richter [this message]
2008-07-26 10:03   ` Ingo Molnar
2008-07-22 19:08 ` [PATCH 12/24] x86/oprofile: Separating the IBS handler Robert Richter
2008-07-22 19:08 ` [PATCH 13/24] OProfile: Change IBS interrupt initialization Robert Richter
2008-07-26 10:05   ` Ingo Molnar
2008-07-22 19:08 ` [PATCH 14/24] OProfile: Fix build error in op_model_athlon.c Robert Richter
2008-07-26 10:05   ` Ingo Molnar
2008-07-22 19:08 ` [PATCH 15/24] OProfile: on_each_cpu(): kill unused retry parameter Robert Richter
2008-07-22 19:09 ` [PATCH 16/24] OProfile: Fix setup_ibs_files() function interface Robert Richter
2008-07-22 19:09 ` [PATCH 17/24] OProfile: Enable IBS for AMD CPUs Robert Richter
2008-07-26 10:09   ` Ingo Molnar
2008-07-22 19:09 ` [PATCH 18/24] OProfile: Fix IBS build error for UP Robert Richter
2008-07-22 19:09 ` [PATCH 19/24] x86/oprofile: Macro definition cleanup in op_model_athlon.c Robert Richter
2008-07-22 19:09 ` [PATCH 20/24] x86/oprofile: op_model_athlon.c: Fix counter reset when reenabling IBS OP Robert Richter
2008-07-22 19:09 ` [PATCH 21/24] x86: apic: Export symbols for extended interrupt LVT functions Robert Richter
2008-07-22 19:53   ` Arjan van de Ven
2008-07-23 13:28     ` [PATCH] x86: apic: Changing export symbols to *_GPL Robert Richter
2008-07-23 19:29       ` linux-os (Dick Johnson)
2008-07-23 20:01         ` Robert Richter
2008-07-24  8:16           ` Stefan Richter
2008-07-22 19:09 ` [PATCH 22/24] x86/oprofile: Add CONFIG_OPROFILE_IBS option Robert Richter
2008-07-26 10:15   ` Ingo Molnar
2008-07-22 19:09 ` [PATCH 23/24] oprofile: Fix printk in cpu_buffer.c Robert Richter
2008-07-22 19:09 ` [PATCH 24/24] x86/oprofile: Reanaming op_model_athlon.c to op_model_amd.c Robert Richter
2008-07-26 10:17   ` Ingo Molnar
2008-07-23 12:24 ` [PATCH 0/24] oprofile: Add IBS support for AMD CPUs Maynard Johnson
2008-07-26  9:52 ` Ingo Molnar
2008-07-28 14:02   ` Robert Richter
2008-07-31 10:32     ` Ingo Molnar

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=20080724143953.GS17134@erda.amd.com \
    --to=robert.richter@amd.com \
    --cc=barry.kasindorf@amd.com \
    --cc=jason.yeh@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=oprofile-list@lists.sourceforge.net \
    --cc=tglx@linutronix.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
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