Message ID | 20180917004451.174527-2-minchan@kernel.org (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | arm: support get_user_pages_fast | expand |
Hi Guys, Could you have a chance to review this patchset? Thanks! On Mon, Sep 17, 2018 at 09:44:49AM +0900, Minchan Kim wrote: > To use bit 5 in page table as L_PTE_SPECIAL, we need a room for that. > It seems we don't need 4 bits for the memory type with ARMv6+. > If it's true, let's reorder bits to make bit 5 free. > > We will use the bit for L_PTE_SPECIAL in next patch. > > A note from Catalin > " > > Anyway, on ARMv7 or ARMv6+LPAE, the non-shared device gets mapped to > > shared device in hardware. Looking through the arm32 code, it seems that > > MT_DEVICE_NONSHARED is used by arch/arm/mach-shmobile/setup-r8a7779.c > > and IIUC that's a v7 platform (R-Car H1, Cortex-A9). I think the above > > should be defined to L_PTE_MT_DEV_SHARED, unless I miss any place where > > DEV_NONSHARED is relevant on ARMv6 (adding Simon to confirm on shmbile). > " > > Cc: Russell King <linux@armlinux.org.uk> > Cc: Catalin Marinas <catalin.marinas@arm.com> > Cc: Will Deacon <will.deacon@arm.com> > Cc: Steve Capper <steve.capper@linaro.org> > Cc: Simon Horman <horms@verge.net.au> > Signed-off-by: Minchan Kim <minchan@kernel.org> > --- > arch/arm/include/asm/pgtable-2level.h | 19 +++++++++++++++---- > arch/arm/mm/proc-macros.S | 4 ++-- > 2 files changed, 17 insertions(+), 6 deletions(-) > > diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h > index 92fd2c8a9af0..514b13c27b43 100644 > --- a/arch/arm/include/asm/pgtable-2level.h > +++ b/arch/arm/include/asm/pgtable-2level.h > @@ -164,14 +164,25 @@ > #define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ > #define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ > #define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ > +#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ > +#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x05) << 2) /* 0101 */ > #define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ > #define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ > -#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ > -#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ > +#if defined(CONFIG_CPU_V7) || defined (CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) > +/* > + * On ARMv7 or ARMv6+LPAE, the non-shared device gets mapped to > + * shared device in hardware. > + */ > +#define L_PTE_MT_DEV_NONSHARED L_PTE_MT_DEV_SHARED > +#define L_PTE_MT_DEV_WC L_PTE_MT_BUFFERABLE > +#define L_PTE_MT_DEV_CACHED L_PTE_MT_WRITEBACK > +#define L_PTE_MT_MASK (_AT(pteval_t, 0x07) << 2) > +#else > #define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ > #define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ > -#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x0f) << 2) /* 1111 */ > -#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) > +#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ > +#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) > +#endif > > #ifndef __ASSEMBLY__ > > diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S > index 81d0efb055c6..367a89d5aeca 100644 > --- a/arch/arm/mm/proc-macros.S > +++ b/arch/arm/mm/proc-macros.S > @@ -138,7 +138,7 @@ > .long PTE_CACHEABLE @ L_PTE_MT_WRITETHROUGH > .long PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEBACK > .long PTE_BUFFERABLE @ L_PTE_MT_DEV_SHARED > - .long 0x00 @ unused > + .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS > .long 0x00 @ L_PTE_MT_MINICACHE (not present) > .long PTE_EXT_TEX(1) | PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEALLOC > .long 0x00 @ unused > @@ -148,7 +148,7 @@ > .long PTE_EXT_TEX(2) @ L_PTE_MT_DEV_NONSHARED > .long 0x00 @ unused > .long 0x00 @ unused > - .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS > + .long 0x00 @ unused > .endm > > .macro armv6_set_pte_ext pfx > -- > 2.19.0.397.gdd90340f6a-goog >
On Mon, Sep 17, 2018 at 09:44:49AM +0900, Minchan Kim wrote: > To use bit 5 in page table as L_PTE_SPECIAL, we need a room for that. > It seems we don't need 4 bits for the memory type with ARMv6+. > If it's true, let's reorder bits to make bit 5 free. > > We will use the bit for L_PTE_SPECIAL in next patch. > > A note from Catalin > " > > Anyway, on ARMv7 or ARMv6+LPAE, the non-shared device gets mapped to I meant 'ARMv7+LPAE' since ARMv6 never had the LPAE feature (please correct the code comment below as well). I was wrong with the classic ARMv7, only ARMv7+LPAE makes all device memory shareable in hardware (even if not enabled). With classic ARMv7 (that is pre-Cortex-A7/A15), the shareable bit in combination with PRRR allows the Device Non-shareable configuration. Anyway, it doesn't matter here since the L_PTE_SHARED bit is set separately in the mem_types[] array, the L_PTE_MT_* definitions are just for the actual memory type ignoring shareability. We just need to make sure the comments are correct. > > shared device in hardware. Looking through the arm32 code, it seems that > > MT_DEVICE_NONSHARED is used by arch/arm/mach-shmobile/setup-r8a7779.c > > and IIUC that's a v7 platform (R-Car H1, Cortex-A9). I think the above > > should be defined to L_PTE_MT_DEV_SHARED, unless I miss any place where > > DEV_NONSHARED is relevant on ARMv6 (adding Simon to confirm on shmbile). It would be good to figure out the DEV_NONSHARED on ARMv6 relevance. I don't think we break R-Car H1 since the shareability bit wouldn't be set for DEV_NONSHARED. > diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h > index 92fd2c8a9af0..514b13c27b43 100644 > --- a/arch/arm/include/asm/pgtable-2level.h > +++ b/arch/arm/include/asm/pgtable-2level.h > @@ -164,14 +164,25 @@ > #define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ > #define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ > #define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ > +#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ > +#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x05) << 2) /* 0101 */ > #define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ > #define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ > -#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ > -#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ > +#if defined(CONFIG_CPU_V7) || defined (CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) > +/* > + * On ARMv7 or ARMv6+LPAE, the non-shared device gets mapped to > + * shared device in hardware. > + */ I would change this to something like: /* * On ARMv7 or ARMv7+LPAE, the non-shared and shared device types get * mapped to the same TEX remapping index. On classic ARMv7, the * shareability is controlled by the PRRR[17:16] field, indexed by * L_PTE_SHARED. On ARMv7+LPAE the device mapping is always shareable. */ > +#define L_PTE_MT_DEV_NONSHARED L_PTE_MT_DEV_SHARED > +#define L_PTE_MT_DEV_WC L_PTE_MT_BUFFERABLE > +#define L_PTE_MT_DEV_CACHED L_PTE_MT_WRITEBACK > +#define L_PTE_MT_MASK (_AT(pteval_t, 0x07) << 2) > +#else > #define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ > #define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ > -#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x0f) << 2) /* 1111 */ > -#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) > +#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ > +#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) > +#endif > > #ifndef __ASSEMBLY__ > > diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S > index 81d0efb055c6..367a89d5aeca 100644 > --- a/arch/arm/mm/proc-macros.S > +++ b/arch/arm/mm/proc-macros.S > @@ -138,7 +138,7 @@ > .long PTE_CACHEABLE @ L_PTE_MT_WRITETHROUGH > .long PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEBACK > .long PTE_BUFFERABLE @ L_PTE_MT_DEV_SHARED > - .long 0x00 @ unused > + .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS > .long 0x00 @ L_PTE_MT_MINICACHE (not present) > .long PTE_EXT_TEX(1) | PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEALLOC > .long 0x00 @ unused > @@ -148,7 +148,7 @@ > .long PTE_EXT_TEX(2) @ L_PTE_MT_DEV_NONSHARED > .long 0x00 @ unused > .long 0x00 @ unused > - .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS > + .long 0x00 @ unused > .endm Looking at the L_PTE_MT_VECTORS uses, I don't think this gives you what you intended. vecs_pgprot in build_mem_type_table() actually combines the cache policy bits with L_PTE_MT_VECTORS and this might have been the reason why it was on the last position (all bits 1). So the default cachepolicy of L_PTE_MT_WRITEBACK or'ed with the new L_PTE_MT_VECTORS gives you 0b0111 which is position 7 instead of 5. This would map onto L_PTE_MT_WRITEALLOC (which is not that bad) but misses the APX bit which marks the vectors page r/w for kernel and ro for user. I don't think this matters since the kernel no longer writes to the vectors page at run-time but it needs cleaning up a bit (and testing in case I missed something). IOW, do we still need a dedicated mapping type for the vectors or we can simply use the read-only user page attributes?
Hi Catalin, Sorry for the late response. It was big holiday here. I will correct what you pointed out and resubmit patch next week. Thanks for the review! On Mon, Sep 24, 2018 at 05:22:03PM +0100, Catalin Marinas wrote: > On Mon, Sep 17, 2018 at 09:44:49AM +0900, Minchan Kim wrote: > > To use bit 5 in page table as L_PTE_SPECIAL, we need a room for that. > > It seems we don't need 4 bits for the memory type with ARMv6+. > > If it's true, let's reorder bits to make bit 5 free. > > > > We will use the bit for L_PTE_SPECIAL in next patch. > > > > A note from Catalin > > " > > > Anyway, on ARMv7 or ARMv6+LPAE, the non-shared device gets mapped to > > I meant 'ARMv7+LPAE' since ARMv6 never had the LPAE feature (please > correct the code comment below as well). > > I was wrong with the classic ARMv7, only ARMv7+LPAE makes all device > memory shareable in hardware (even if not enabled). With classic ARMv7 > (that is pre-Cortex-A7/A15), the shareable bit in combination with PRRR > allows the Device Non-shareable configuration. > > Anyway, it doesn't matter here since the L_PTE_SHARED bit is set > separately in the mem_types[] array, the L_PTE_MT_* definitions are just > for the actual memory type ignoring shareability. We just need to make > sure the comments are correct. > > > > shared device in hardware. Looking through the arm32 code, it seems that > > > MT_DEVICE_NONSHARED is used by arch/arm/mach-shmobile/setup-r8a7779.c > > > and IIUC that's a v7 platform (R-Car H1, Cortex-A9). I think the above > > > should be defined to L_PTE_MT_DEV_SHARED, unless I miss any place where > > > DEV_NONSHARED is relevant on ARMv6 (adding Simon to confirm on shmbile). > > It would be good to figure out the DEV_NONSHARED on ARMv6 relevance. I > don't think we break R-Car H1 since the shareability bit wouldn't be set > for DEV_NONSHARED. > > > diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h > > index 92fd2c8a9af0..514b13c27b43 100644 > > --- a/arch/arm/include/asm/pgtable-2level.h > > +++ b/arch/arm/include/asm/pgtable-2level.h > > @@ -164,14 +164,25 @@ > > #define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ > > #define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ > > #define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ > > +#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ > > +#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x05) << 2) /* 0101 */ > > #define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ > > #define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ > > -#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ > > -#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ > > +#if defined(CONFIG_CPU_V7) || defined (CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) > > +/* > > + * On ARMv7 or ARMv6+LPAE, the non-shared device gets mapped to > > + * shared device in hardware. > > + */ > > I would change this to something like: > > /* > * On ARMv7 or ARMv7+LPAE, the non-shared and shared device types get > * mapped to the same TEX remapping index. On classic ARMv7, the > * shareability is controlled by the PRRR[17:16] field, indexed by > * L_PTE_SHARED. On ARMv7+LPAE the device mapping is always shareable. > */ > > > +#define L_PTE_MT_DEV_NONSHARED L_PTE_MT_DEV_SHARED > > +#define L_PTE_MT_DEV_WC L_PTE_MT_BUFFERABLE > > +#define L_PTE_MT_DEV_CACHED L_PTE_MT_WRITEBACK > > +#define L_PTE_MT_MASK (_AT(pteval_t, 0x07) << 2) > > +#else > > #define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ > > #define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ > > -#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x0f) << 2) /* 1111 */ > > -#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) > > +#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ > > +#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) > > +#endif > > > > #ifndef __ASSEMBLY__ > > > > diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S > > index 81d0efb055c6..367a89d5aeca 100644 > > --- a/arch/arm/mm/proc-macros.S > > +++ b/arch/arm/mm/proc-macros.S > > @@ -138,7 +138,7 @@ > > .long PTE_CACHEABLE @ L_PTE_MT_WRITETHROUGH > > .long PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEBACK > > .long PTE_BUFFERABLE @ L_PTE_MT_DEV_SHARED > > - .long 0x00 @ unused > > + .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS > > .long 0x00 @ L_PTE_MT_MINICACHE (not present) > > .long PTE_EXT_TEX(1) | PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEALLOC > > .long 0x00 @ unused > > @@ -148,7 +148,7 @@ > > .long PTE_EXT_TEX(2) @ L_PTE_MT_DEV_NONSHARED > > .long 0x00 @ unused > > .long 0x00 @ unused > > - .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS > > + .long 0x00 @ unused > > .endm > > Looking at the L_PTE_MT_VECTORS uses, I don't think this gives you what > you intended. vecs_pgprot in build_mem_type_table() actually combines > the cache policy bits with L_PTE_MT_VECTORS and this might have been the > reason why it was on the last position (all bits 1). So the default > cachepolicy of L_PTE_MT_WRITEBACK or'ed with the new L_PTE_MT_VECTORS > gives you 0b0111 which is position 7 instead of 5. This would map onto > L_PTE_MT_WRITEALLOC (which is not that bad) but misses the APX bit which > marks the vectors page r/w for kernel and ro for user. > > I don't think this matters since the kernel no longer writes to the > vectors page at run-time but it needs cleaning up a bit (and testing in > case I missed something). IOW, do we still need a dedicated mapping type > for the vectors or we can simply use the read-only user page attributes? > > -- > Catalin
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 92fd2c8a9af0..514b13c27b43 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -164,14 +164,25 @@ #define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ #define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ #define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ +#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ +#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x05) << 2) /* 0101 */ #define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ #define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ -#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ -#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ +#if defined(CONFIG_CPU_V7) || defined (CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) +/* + * On ARMv7 or ARMv6+LPAE, the non-shared device gets mapped to + * shared device in hardware. + */ +#define L_PTE_MT_DEV_NONSHARED L_PTE_MT_DEV_SHARED +#define L_PTE_MT_DEV_WC L_PTE_MT_BUFFERABLE +#define L_PTE_MT_DEV_CACHED L_PTE_MT_WRITEBACK +#define L_PTE_MT_MASK (_AT(pteval_t, 0x07) << 2) +#else #define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ #define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ -#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x0f) << 2) /* 1111 */ -#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) +#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ +#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) +#endif #ifndef __ASSEMBLY__ diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 81d0efb055c6..367a89d5aeca 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -138,7 +138,7 @@ .long PTE_CACHEABLE @ L_PTE_MT_WRITETHROUGH .long PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEBACK .long PTE_BUFFERABLE @ L_PTE_MT_DEV_SHARED - .long 0x00 @ unused + .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS .long 0x00 @ L_PTE_MT_MINICACHE (not present) .long PTE_EXT_TEX(1) | PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEALLOC .long 0x00 @ unused @@ -148,7 +148,7 @@ .long PTE_EXT_TEX(2) @ L_PTE_MT_DEV_NONSHARED .long 0x00 @ unused .long 0x00 @ unused - .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS + .long 0x00 @ unused .endm .macro armv6_set_pte_ext pfx