mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: andreas.herrmann3@amd.com, tglx@linutronix.de, mingo@elte.hu,
	linux-kernel@vger.kernel.org
Subject: [PATCH] [3/7] Add set_memory_4k to pageattr.c
Date: Wed, 12 Mar 2008 03:53:29 +0100 (CET)	[thread overview]
Message-ID: <20080312025329.A74C71B41D1@basil.firstfloor.org> (raw)
In-Reply-To: <20080312353.598285931@firstfloor.org>


Add a new function to force split large pages into 4k pages.
This is needed for some followup optimizations.

I had to add a new field to cpa_data to pass down the information
that try_preserve_large_page should not run.

Right now no set_page_4k() because I didn't need it and all the
specialized users I have in mind would be more comfortable with
pure addresses. I also didn't export it because it's unlikely
external code needs it.

Signed-off-by: Andi Kleen <ak@suse.de>

Index: linux/arch/x86/mm/pageattr.c
===================================================================
--- linux.orig/arch/x86/mm/pageattr.c
+++ linux/arch/x86/mm/pageattr.c
@@ -28,6 +28,7 @@ struct cpa_data {
 	int		numpages;
 	int		flushtlb;
 	unsigned long	pfn;
+	unsigned	force_split : 1;
 };
 
 #ifdef CONFIG_X86_64
@@ -259,6 +260,9 @@ try_preserve_large_page(pte_t *kpte, uns
 	int i, do_split = 1;
 	unsigned int level;
 
+	if (cpa->force_split)
+		return 1;
+
 	spin_lock_irqsave(&pgd_lock, flags);
 	/*
 	 * Check for races, another CPU might have split this page
@@ -693,7 +697,8 @@ static inline int cache_attr(pgprot_t at
 }
 
 static int change_page_attr_set_clr(unsigned long addr, int numpages,
-				    pgprot_t mask_set, pgprot_t mask_clr)
+				    pgprot_t mask_set, pgprot_t mask_clr,
+				    int force_split)
 {
 	struct cpa_data cpa;
 	int ret, cache, checkalias;
@@ -704,7 +709,7 @@ static int change_page_attr_set_clr(unsi
 	 */
 	mask_set = canon_pgprot(mask_set);
 	mask_clr = canon_pgprot(mask_clr);
-	if (!pgprot_val(mask_set) && !pgprot_val(mask_clr))
+	if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split)
 		return 0;
 
 	/* Ensure we are PAGE_SIZE aligned */
@@ -721,6 +726,7 @@ static int change_page_attr_set_clr(unsi
 	cpa.mask_set = mask_set;
 	cpa.mask_clr = mask_clr;
 	cpa.flushtlb = 0;
+	cpa.force_split = force_split;
 
 	/* No alias checking for _NX bit modifications */
 	checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;
@@ -759,13 +765,13 @@ out:
 static inline int change_page_attr_set(unsigned long addr, int numpages,
 				       pgprot_t mask)
 {
-	return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0));
+	return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0);
 }
 
 static inline int change_page_attr_clear(unsigned long addr, int numpages,
 					 pgprot_t mask)
 {
-	return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask);
+	return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0);
 }
 
 int set_memory_uc(unsigned long addr, int numpages)
@@ -809,6 +815,12 @@ int set_memory_np(unsigned long addr, in
 	return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_PRESENT));
 }
 
+int set_memory_4k(unsigned long addr, int numpages)
+{
+	return change_page_attr_set_clr(addr, numpages, __pgprot(0),
+					__pgprot(0), 1);
+}
+
 int set_pages_uc(struct page *page, int numpages)
 {
 	unsigned long addr = (unsigned long)page_address(page);
Index: linux/include/asm-x86/cacheflush.h
===================================================================
--- linux.orig/include/asm-x86/cacheflush.h
+++ linux/include/asm-x86/cacheflush.h
@@ -41,6 +41,7 @@ int set_memory_nx(unsigned long addr, in
 int set_memory_ro(unsigned long addr, int numpages);
 int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_np(unsigned long addr, int numpages);
+int set_memory_4k(unsigned long addr, int numpages);
 
 void clflush_cache_range(void *addr, unsigned int size);
 

  parent reply	other threads:[~2008-03-12  2:54 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-12  2:53 [PATCH] [1/7] Implement true end_pfn_mapped for 32bit Andi Kleen
2008-03-12  2:53 ` [PATCH] [2/7] Account overlapped mappings in end_pfn_map Andi Kleen
2008-03-12  2:53 ` Andi Kleen [this message]
2008-03-12  2:53 ` [PATCH] [4/7] Don't use large pages to map the first 2/4MB of memory Andi Kleen
2008-03-12  5:38   ` Eric Dumazet
2008-03-12  9:19     ` Andi Kleen
2008-03-21 17:45   ` Thomas Gleixner
2008-03-21 17:59     ` Andi Kleen
2008-03-21 18:03       ` Thomas Gleixner
2008-03-21 18:44         ` Andi Kleen
2008-03-25 11:31   ` Joerg Roedel
2008-03-25 11:39     ` Andi Kleen
2008-03-12  2:53 ` [PATCH] [5/7] Readd rdmsrl_safe Andi Kleen
2008-03-21 17:06   ` Thomas Gleixner
2008-03-21 17:16     ` Andi Kleen
2008-03-21 17:58       ` Thomas Gleixner
2008-03-21 18:06         ` Andi Kleen
2008-03-21 18:14           ` Thomas Gleixner
2008-03-21 18:46             ` Andi Kleen
2008-03-21 18:48               ` [PATCH] [5/7] Readd rdmsrl_safe II Andi Kleen
2008-03-22  9:59     ` [PATCH] Readd rdmsrl_safe v2 Andi Kleen
2008-03-12  2:53 ` [PATCH] [6/7] Split large page mapping for AMD TSEG Andi Kleen
2008-03-21 17:55   ` Thomas Gleixner
2008-03-25 11:56   ` Joerg Roedel
2008-03-25 16:44   ` Thomas Gleixner
2008-03-25 16:54     ` Andi Kleen
2008-03-12  2:53 ` [PATCH] [7/7] CPA: Add statistics about state of direct mapping v2 Andi Kleen
2008-03-21 17:41   ` Thomas Gleixner
2008-03-21 17:55     ` Andi Kleen
2008-03-22  9:50       ` [PATCH] CPA: Add statistics about state of direct mapping v3 Andi Kleen
2008-03-25 15:40         ` Thomas Gleixner
2008-03-25 16:14           ` Andi Kleen
2008-03-25 16:16             ` Thomas Gleixner
2008-03-25 17:01               ` [PATCH] CPA: Add statistics about state of direct mapping v4 Andi Kleen

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=20080312025329.A74C71B41D1@basil.firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=andreas.herrmann3@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --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

all inboxes | Powered by JetHome®