[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20150519132307.GG4641@pd.tnic>
Date: Tue, 19 May 2015 15:23:07 +0200
From: Borislav Petkov <bp@...en8.de>
To: Toshi Kani <toshi.kani@...com>
Cc: akpm@...ux-foundation.org, hpa@...or.com, tglx@...utronix.de,
mingo@...hat.com, linux-mm@...ck.org, x86@...nel.org,
linux-kernel@...r.kernel.org, dave.hansen@...el.com,
Elliott@...com, pebolle@...cali.nl, mcgrof@...e.com
Subject: Re: [PATCH v5 6/6] mtrr, mm, x86: Enhance MTRR checks for KVA huge
page mapping
On Tue, May 19, 2015 at 01:44:37PM +0200, Borislav Petkov wrote:
> > Try with a smaller page size.
> >
> > The callers, pud_set_huge() and pmd_set_huge(), check if the given range
> > is safe with MTRRs for creating a huge page mapping. If not, they fail
> > the request, which leads their callers, ioremap_pud_range() and
> > ioremap_pmd_range(), to retry with a smaller page size, i.e. 1GB -> 2MB
> > -> 4KB. 4KB may not have overlap with MTRRs (hence no checking is
> > necessary), which will succeed as before.
Scratch that, I think I have it now. And I even have a good feeling
about it :-)
---
From: Toshi Kani <toshi.kani@...com>
Date: Fri, 15 May 2015 12:23:57 -0600
Subject: [PATCH] x86/mm: Enhance MTRR checks in kernel mapping helpers
This patch adds the argument 'uniform' to mtrr_type_lookup(), which gets
set to 1 when a given range is covered uniformly by MTRRs, i.e. the
range is fully covered by a single MTRR entry or the default type.
Change pud_set_huge() and pmd_set_huge() to honor the 'uniform' flag to
see if it is safe to create a huge page mapping in the range.
This allows them to create a huge page mapping in a range covered by
a single MTRR entry of any memory type. It also detects a non-optimal
request properly. They continue to check with the WB type since it does
not effectively change the uniform mapping even if a request spans
multiple MTRR entries.
pmd_set_huge() logs a warning message to a non-optimal request so that
driver writers will be aware of such a case. Drivers should make a
mapping request aligned to a single MTRR entry when the range is covered
by MTRRs.
Signed-off-by: Toshi Kani <toshi.kani@...com>
Cc: dave.hansen@...el.com
Cc: Elliott@...com
Cc: pebolle@...cali.nl
Cc: Luis R. Rodriguez <mcgrof@...e.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: H. Peter Anvin <hpa@...or.com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Ingo Molnar <mingo@...nel.org>
Cc: linux-mm <linux-mm@...ck.org>
Cc: x86-ml <x86@...nel.org>
Cc: lkml <linux-kernel@...r.kernel.org>
Link: http://lkml.kernel.org/r/1431714237-880-7-git-send-email-toshi.kani@hp.com
[ Realign, flesh out comments, improve warning message. ]
Signed-off-by: Borislav Petkov <bp@...e.de>
---
arch/x86/include/asm/mtrr.h | 4 ++--
arch/x86/kernel/cpu/mtrr/generic.c | 40 ++++++++++++++++++++++++++++----------
arch/x86/mm/pat.c | 4 ++--
arch/x86/mm/pgtable.c | 38 +++++++++++++++++++++++-------------
4 files changed, 58 insertions(+), 28 deletions(-)
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index bb03a547c1ab..a31759e1edd9 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -31,7 +31,7 @@
* arch_phys_wc_add and arch_phys_wc_del.
*/
# ifdef CONFIG_MTRR
-extern u8 mtrr_type_lookup(u64 addr, u64 end);
+extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform);
extern void mtrr_save_fixed_ranges(void *);
extern void mtrr_save_state(void);
extern int mtrr_add(unsigned long base, unsigned long size,
@@ -50,7 +50,7 @@ extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
extern int amd_special_default_mtrr(void);
extern int phys_wc_to_mtrr_index(int handle);
# else
-static inline u8 mtrr_type_lookup(u64 addr, u64 end)
+static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform)
{
/*
* Return no-MTRRs:
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index e51100c49eea..f782d9b62cb3 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -147,19 +147,24 @@ static u8 mtrr_type_lookup_fixed(u64 start, u64 end)
* Return Value:
* MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched)
*
- * Output Argument:
+ * Output Arguments:
* repeat - Set to 1 when [start:end] spanned across MTRR range and type
* returned corresponds only to [start:*partial_end]. Caller has
* to lookup again for [*partial_end:end].
+ *
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ * region is fully covered by a single MTRR entry or the default
+ * type.
*/
static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
- int *repeat)
+ int *repeat, u8 *uniform)
{
int i;
u64 base, mask;
u8 prev_match, curr_match;
*repeat = 0;
+ *uniform = 1;
/* Make end inclusive instead of exclusive */
end--;
@@ -214,6 +219,7 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
end = *partial_end - 1; /* end is inclusive */
*repeat = 1;
+ *uniform = 0;
}
if ((start & mask) != (base & mask))
@@ -225,6 +231,7 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
continue;
}
+ *uniform = 0;
if (check_type_overlap(&prev_match, &curr_match))
return curr_match;
}
@@ -241,10 +248,15 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
* Return Values:
* MTRR_TYPE_(type) - The effective MTRR type for the region
* MTRR_TYPE_INVALID - MTRR is disabled
+ *
+ * Output Argument:
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ * region is fully covered by a single MTRR entry or the default
+ * type.
*/
-u8 mtrr_type_lookup(u64 start, u64 end)
+u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
{
- u8 type, prev_type;
+ u8 type, prev_type, is_uniform = 1, dummy;
int repeat;
u64 partial_end;
@@ -260,14 +272,18 @@ u8 mtrr_type_lookup(u64 start, u64 end)
*/
if ((start < 0x100000) &&
(mtrr_state.have_fixed) &&
- (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED))
- return mtrr_type_lookup_fixed(start, end);
+ (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
+ is_uniform = 0;
+ type = mtrr_type_lookup_fixed(start, end);
+ goto out;
+ }
/*
* Look up the variable ranges. Look of multiple ranges matching
* this address and pick type as per MTRR precedence.
*/
- type = mtrr_type_lookup_variable(start, end, &partial_end, &repeat);
+ type = mtrr_type_lookup_variable(start, end, &partial_end,
+ &repeat, &is_uniform);
/*
* Common path is with repeat = 0.
@@ -278,15 +294,19 @@ u8 mtrr_type_lookup(u64 start, u64 end)
while (repeat) {
prev_type = type;
start = partial_end;
- type = mtrr_type_lookup_variable(start, end, &partial_end, &repeat);
+ is_uniform = 0;
+ type = mtrr_type_lookup_variable(start, end, &partial_end,
+ &repeat, &dummy);
if (check_type_overlap(&prev_type, &type))
- return type;
+ goto out;
}
if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2))
- return MTRR_TYPE_WRBACK;
+ type = MTRR_TYPE_WRBACK;
+out:
+ *uniform = is_uniform;
return type;
}
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 35af6771a95a..372ad422c2c3 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -267,9 +267,9 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end,
* request is for WB.
*/
if (req_type == _PAGE_CACHE_MODE_WB) {
- u8 mtrr_type;
+ u8 mtrr_type, uniform;
- mtrr_type = mtrr_type_lookup(start, end);
+ mtrr_type = mtrr_type_lookup(start, end, &uniform);
if (mtrr_type != MTRR_TYPE_WRBACK)
return _PAGE_CACHE_MODE_UC_MINUS;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index c30f9819786b..df2f8a587438 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -566,19 +566,28 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
/**
* pud_set_huge - setup kernel PUD mapping
*
- * MTRR can override PAT memory types with 4KiB granularity. Therefore,
- * this function does not set up a huge page when the range is covered
- * by a non-WB type of MTRR. MTRR_TYPE_INVALID indicates that MTRR are
- * disabled.
+ * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this
+ * function sets up a huge page only if any of the following conditions are met:
+ *
+ * - MTRRs are disabled, or
+ *
+ * - MTRRs are enabled and the range is completely covered by a single MTRR, or
+ *
+ * - MTRRs are enabled and the range is not completely covered by a single MTRR
+ * but the memory type of the range is WB, even if covered by multiple MTRRs.
+ *
+ * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger
+ * page mapping attempt fails.
*
* Returns 1 on success and 0 on failure.
*/
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
- u8 mtrr;
+ u8 mtrr, uniform;
- mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE);
- if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != MTRR_TYPE_INVALID))
+ mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform);
+ if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+ (mtrr != MTRR_TYPE_WRBACK))
return 0;
prot = pgprot_4k_2_large(prot);
@@ -593,20 +602,21 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
/**
* pmd_set_huge - setup kernel PMD mapping
*
- * MTRR can override PAT memory types with 4KiB granularity. Therefore,
- * this function does not set up a huge page when the range is covered
- * by a non-WB type of MTRR. MTRR_TYPE_INVALID indicates that MTRR are
- * disabled.
+ * See text over pud_set_huge() above.
*
* Returns 1 on success and 0 on failure.
*/
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
{
- u8 mtrr;
+ u8 mtrr, uniform;
- mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE);
- if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != MTRR_TYPE_INVALID))
+ mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform);
+ if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+ (mtrr != MTRR_TYPE_WRBACK)) {
+ pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n",
+ __func__, addr, addr + PMD_SIZE);
return 0;
+ }
prot = pgprot_4k_2_large(prot);
--
2.3.5
--
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists