Message ID | 20211129014007.286478-3-wefu@redhat.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | riscv: add RISC-V Svpbmt Standard Extension supports | expand |
On Mon, Nov 29, 2021 at 2:42 AM <wefu@redhat.com> wrote: > > From: Wei Fu <wefu@redhat.com> > > This patch follows the standard pure RISC-V Svpbmt extension in > privilege spec to solve the non-coherent SOC dma synchronization > issues. > > Here is the svpbmt PTE format: > | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > N MT RSW D A G U X W R V > ^ > > Of the Reserved bits [63:54] in a leaf PTE, the high bit is already > allocated (as the N bit), so bits [62:61] are used as the MT (aka > MemType) field. This field specifies one of three memory types that > are close equivalents (or equivalent in effect) to the three main x86 > and ARMv8 memory types - as shown in the following table. > > RISC-V > Encoding & > MemType RISC-V Description > ---------- ------------------------------------------------ > 00 - PMA Normal Cacheable, No change to implied PMA memory type > 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > 11 - Rsvd Reserved for future standard use > > The standard protection_map[] needn't be modified because the "PMA" > type keeps the highest bits zero. And the whole modification is > limited in the arch/riscv/* and using a global variable > (__svpbmt) as _PAGE_MASK/IO/NOCACHE for pgprot_noncached > (&writecombine) in pgtable.h. We also add _PAGE_CHG_MASK to filter > PFN than before. > > Enable it in devicetree - (Add "riscv,svpbmt" in the mmu of cpu node) > - mmu: > riscv,svpmbt > > Signed-off-by: Wei Fu <wefu@redhat.com> > Co-developed-by: Liu Shaohua <liush@allwinnertech.com> > Signed-off-by: Liu Shaohua <liush@allwinnertech.com> > Co-developed-by: Guo Ren <guoren@kernel.org> > Signed-off-by: Guo Ren <guoren@kernel.org> > Cc: Palmer Dabbelt <palmerdabbelt@google.com> > Cc: Christoph Hellwig <hch@lst.de> > Cc: Anup Patel <anup.patel@wdc.com> > Cc: Arnd Bergmann <arnd@arndb.de> > Cc: Atish Patra <atish.patra@wdc.com> > Cc: Drew Fustini <drew@beagleboard.org> > Cc: Wei Fu <wefu@redhat.com> > Cc: Wei Wu <lazyparser@gmail.com> > Cc: Chen-Yu Tsai <wens@csie.org> > Cc: Maxime Ripard <maxime@cerno.tech> > Cc: Daniel Lustig <dlustig@nvidia.com> > Cc: Greg Favor <gfavor@ventanamicro.com> > Cc: Andrea Mondelli <andrea.mondelli@huawei.com> > Cc: Jonathan Behrens <behrensj@mit.edu> > Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com> > Cc: Bill Huffman <huffman@cadence.com> > Cc: Nick Kossifidis <mick@ics.forth.gr> > Cc: Allen Baum <allen.baum@esperantotech.com> > Cc: Josh Scheid <jscheid@ventanamicro.com> > Cc: Richard Trauben <rtrauben@gmail.com> > --- > arch/riscv/include/asm/fixmap.h | 2 +- > arch/riscv/include/asm/pgtable-64.h | 21 ++++++++++++--- > arch/riscv/include/asm/pgtable-bits.h | 39 +++++++++++++++++++++++++-- > arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++------- > arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++ > arch/riscv/mm/init.c | 5 ++++ > 6 files changed, 126 insertions(+), 15 deletions(-) > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > index 54cbf07fb4e9..5acd99d08e74 100644 > --- a/arch/riscv/include/asm/fixmap.h > +++ b/arch/riscv/include/asm/fixmap.h > @@ -43,7 +43,7 @@ enum fixed_addresses { > __end_of_fixed_addresses > }; > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > +#define FIXMAP_PAGE_IO PAGE_IOREMAP > > #define __early_set_fixmap __set_fixmap > > diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h > index 228261aa9628..16d251282b1d 100644 > --- a/arch/riscv/include/asm/pgtable-64.h > +++ b/arch/riscv/include/asm/pgtable-64.h > @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) > set_pud(pudp, __pud(0)); > } > > +static inline unsigned long _chg_of_pmd(pmd_t pmd) > +{ > + return (pmd_val(pmd) & _PAGE_CHG_MASK); > +} > + > +static inline unsigned long _chg_of_pud(pud_t pud) > +{ > + return (pud_val(pud) & _PAGE_CHG_MASK); > +} > + > +static inline unsigned long _chg_of_pte(pte_t pte) > +{ > + return (pte_val(pte) & _PAGE_CHG_MASK); > +} Those functions are used to extract the pfn from a page table entry, IMO it would be clearer if those functions would look like that: static inline unsigned long pmd_to_pfn(pmd_t pmd) { return (pmd_val(pmd) & _PAGE_CHG_MASK) >> _PAGE_PFN_SHIFT; } > + > static inline pmd_t *pud_pgtable(pud_t pud) > { > - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); > + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > } > > static inline struct page *pud_page(pud_t pud) > { > - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); > + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > } > > static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > static inline unsigned long _pmd_pfn(pmd_t pmd) > { > - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; > + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; > } > Like this one actually, so if this exists for other levels, I would suggest to modify those functions to directly mask the PMA bits and use those in the whole code instead of manually extracting the pfn. > #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h > index 2ee413912926..e5b0fce4ddc5 100644 > --- a/arch/riscv/include/asm/pgtable-bits.h > +++ b/arch/riscv/include/asm/pgtable-bits.h > @@ -7,7 +7,7 @@ > #define _ASM_RISCV_PGTABLE_BITS_H > > /* > - * PTE format: > + * rv32 PTE format: > * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > * PFN reserved for SW D A G U X W R V > */ > @@ -24,6 +24,40 @@ > #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ > #define _PAGE_SOFT (1 << 8) /* Reserved for software */ > > +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) > +/* > + * rv64 PTE format: > + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > + * N MT RSV PFN reserved for SW D A G U X W R V > + * [62:61] Memory Type definitions: > + * 00 - PMA Normal Cacheable, No change to implied PMA memory type > + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > + * 11 - Rsvd Reserved for future standard use > + */ > +#define _SVPBMT_PMA 0UL > +#define _SVPBMT_NC (1UL << 61) > +#define _SVPBMT_IO (1UL << 62) > +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) > + > +extern struct __svpbmt_struct { > + unsigned long mask; > + unsigned long pma; > + unsigned long nocache; > + unsigned long io; > +} __svpbmt __cacheline_aligned; > + > +#define _PAGE_MASK __svpbmt.mask To me, _PAGE_MASK means something else: https://elixir.bootlin.com/linux/latest/source/arch/s390/include/asm/page.h#L16 Maybe something more explicit like _PAGE_SVPBMT_MASK? > +#define _PAGE_PMA __svpbmt.pma > +#define _PAGE_NOCACHE __svpbmt.nocache > +#define _PAGE_IO __svpbmt.io > +#else > +#define _PAGE_MASK 0 > +#define _PAGE_PMA 0 > +#define _PAGE_NOCACHE 0 > +#define _PAGE_IO 0 > +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ > + > #define _PAGE_SPECIAL _PAGE_SOFT > #define _PAGE_TABLE _PAGE_PRESENT > > @@ -38,7 +72,8 @@ > /* Set of bits to preserve across pte_modify() */ > #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ > _PAGE_WRITE | _PAGE_EXEC | \ > - _PAGE_USER | _PAGE_GLOBAL)) > + _PAGE_USER | _PAGE_GLOBAL | \ > + _PAGE_MASK)) > /* > * when all of R/W/X are zero, the PTE is a pointer to the next level > * of the page table; otherwise, it is a leaf PTE. > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > index bf204e7c1f74..0f7a6541015f 100644 > --- a/arch/riscv/include/asm/pgtable.h > +++ b/arch/riscv/include/asm/pgtable.h > @@ -138,7 +138,8 @@ > | _PAGE_PRESENT \ > | _PAGE_ACCESSED \ > | _PAGE_DIRTY \ > - | _PAGE_GLOBAL) > + | _PAGE_GLOBAL \ > + | _PAGE_PMA) > > #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) > #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) > @@ -148,11 +149,9 @@ > > #define PAGE_TABLE __pgprot(_PAGE_TABLE) > > -/* > - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't > - * change the properties of memory regions. > - */ > -#define _PAGE_IOREMAP _PAGE_KERNEL > +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) > + > +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) > > extern pgd_t swapper_pg_dir[]; > > @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) > > static inline struct page *pmd_page(pmd_t pmd) > { > - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > } > > static inline unsigned long pmd_page_vaddr(pmd_t pmd) > { > - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > } > > static inline pte_t pmd_pte(pmd_t pmd) > @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) > /* Yields the page frame number (PFN) of a page table entry */ > static inline unsigned long pte_pfn(pte_t pte) > { > - return (pte_val(pte) >> _PAGE_PFN_SHIFT); > + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); > } > > #define pte_page(x) pfn_to_page(pte_pfn(x)) > @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > return ptep_test_and_clear_young(vma, address, ptep); > } > > +#define pgprot_noncached pgprot_noncached > +static inline pgprot_t pgprot_noncached(pgprot_t _prot) > +{ > + unsigned long prot = pgprot_val(_prot); > + > + prot &= ~_PAGE_MASK; > + prot |= _PAGE_IO; > + > + return __pgprot(prot); > +} > + > +#define pgprot_writecombine pgprot_writecombine > +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) > +{ > + unsigned long prot = pgprot_val(_prot); > + > + prot &= ~_PAGE_MASK; > + prot |= _PAGE_NOCACHE; > + > + return __pgprot(prot); > +} > + > /* > * THP functions > */ > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > index d959d207a40d..fa7480cb8b87 100644 > --- a/arch/riscv/kernel/cpufeature.c > +++ b/arch/riscv/kernel/cpufeature.c > @@ -8,6 +8,7 @@ > > #include <linux/bitmap.h> > #include <linux/of.h> > +#include <linux/pgtable.h> > #include <asm/processor.h> > #include <asm/hwcap.h> > #include <asm/smp.h> > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > } > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > +static void __init mmu_supports_svpbmt(void) > +{ > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) > + struct device_node *node; > + const char *str; > + > + for_each_of_cpu_node(node) { > + if (of_property_read_string(node, "mmu-type", &str)) > + continue; > + > + if (!strncmp(str + 6, "none", 4)) > + continue; > + > + if (of_property_read_string(node, "mmu", &str)) > + continue; > + > + if (strncmp(str + 6, "svpmbt", 6)) > + continue; > + } > + > + __svpbmt.pma = _SVPBMT_PMA; > + __svpbmt.nocache = _SVPBMT_NC; > + __svpbmt.io = _SVPBMT_IO; > + __svpbmt.mask = _SVPBMT_MASK; > +#endif > +} > + > +static void __init mmu_supports(void) > +{ > + mmu_supports_svpbmt(); > +} > + > void __init riscv_fill_hwcap(void) > { > struct device_node *node; > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > size_t i, j, isa_len; > static unsigned long isa2hwcap[256] = {0}; > > + mmu_supports(); > + > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > index 24b2b8044602..e4e658165ee1 100644 > --- a/arch/riscv/mm/init.c > +++ b/arch/riscv/mm/init.c > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > return vmemmap_populate_basepages(start, end, node, NULL); > } > #endif > + > +#if defined(CONFIG_64BIT) > +struct __svpbmt_struct __svpbmt __ro_after_init; > +EXPORT_SYMBOL(__svpbmt); > +#endif > -- > 2.25.4 > > > _______________________________________________ > linux-riscv mailing list > linux-riscv@lists.infradead.org > http://lists.infradead.org/mailman/listinfo/linux-riscv
On Mon, 29 Nov 2021 09:40:07 +0800 wefu@redhat.com wrote: > From: Wei Fu <wefu@redhat.com> > > This patch follows the standard pure RISC-V Svpbmt extension in > privilege spec to solve the non-coherent SOC dma synchronization > issues. > > Here is the svpbmt PTE format: > | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > N MT RSW D A G U X W R V > ^ > > Of the Reserved bits [63:54] in a leaf PTE, the high bit is already > allocated (as the N bit), so bits [62:61] are used as the MT (aka > MemType) field. This field specifies one of three memory types that > are close equivalents (or equivalent in effect) to the three main x86 > and ARMv8 memory types - as shown in the following table. > > RISC-V > Encoding & > MemType RISC-V Description > ---------- ------------------------------------------------ > 00 - PMA Normal Cacheable, No change to implied PMA memory type > 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > 11 - Rsvd Reserved for future standard use > > The standard protection_map[] needn't be modified because the "PMA" > type keeps the highest bits zero. And the whole modification is > limited in the arch/riscv/* and using a global variable > (__svpbmt) as _PAGE_MASK/IO/NOCACHE for pgprot_noncached > (&writecombine) in pgtable.h. We also add _PAGE_CHG_MASK to filter > PFN than before. > > Enable it in devicetree - (Add "riscv,svpbmt" in the mmu of cpu node) > - mmu: > riscv,svpmbt > > Signed-off-by: Wei Fu <wefu@redhat.com> > Co-developed-by: Liu Shaohua <liush@allwinnertech.com> > Signed-off-by: Liu Shaohua <liush@allwinnertech.com> > Co-developed-by: Guo Ren <guoren@kernel.org> > Signed-off-by: Guo Ren <guoren@kernel.org> > Cc: Palmer Dabbelt <palmerdabbelt@google.com> > Cc: Christoph Hellwig <hch@lst.de> > Cc: Anup Patel <anup.patel@wdc.com> > Cc: Arnd Bergmann <arnd@arndb.de> > Cc: Atish Patra <atish.patra@wdc.com> > Cc: Drew Fustini <drew@beagleboard.org> > Cc: Wei Fu <wefu@redhat.com> > Cc: Wei Wu <lazyparser@gmail.com> > Cc: Chen-Yu Tsai <wens@csie.org> > Cc: Maxime Ripard <maxime@cerno.tech> > Cc: Daniel Lustig <dlustig@nvidia.com> > Cc: Greg Favor <gfavor@ventanamicro.com> > Cc: Andrea Mondelli <andrea.mondelli@huawei.com> > Cc: Jonathan Behrens <behrensj@mit.edu> > Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com> > Cc: Bill Huffman <huffman@cadence.com> > Cc: Nick Kossifidis <mick@ics.forth.gr> > Cc: Allen Baum <allen.baum@esperantotech.com> > Cc: Josh Scheid <jscheid@ventanamicro.com> > Cc: Richard Trauben <rtrauben@gmail.com> > --- > arch/riscv/include/asm/fixmap.h | 2 +- > arch/riscv/include/asm/pgtable-64.h | 21 ++++++++++++--- > arch/riscv/include/asm/pgtable-bits.h | 39 +++++++++++++++++++++++++-- > arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++------- > arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++ > arch/riscv/mm/init.c | 5 ++++ > 6 files changed, 126 insertions(+), 15 deletions(-) > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > index 54cbf07fb4e9..5acd99d08e74 100644 > --- a/arch/riscv/include/asm/fixmap.h > +++ b/arch/riscv/include/asm/fixmap.h > @@ -43,7 +43,7 @@ enum fixed_addresses { > __end_of_fixed_addresses > }; > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > +#define FIXMAP_PAGE_IO PAGE_IOREMAP > > #define __early_set_fixmap __set_fixmap > > diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h > index 228261aa9628..16d251282b1d 100644 > --- a/arch/riscv/include/asm/pgtable-64.h > +++ b/arch/riscv/include/asm/pgtable-64.h > @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) > set_pud(pudp, __pud(0)); > } > > +static inline unsigned long _chg_of_pmd(pmd_t pmd) > +{ > + return (pmd_val(pmd) & _PAGE_CHG_MASK); > +} > + > +static inline unsigned long _chg_of_pud(pud_t pud) > +{ > + return (pud_val(pud) & _PAGE_CHG_MASK); > +} > + > +static inline unsigned long _chg_of_pte(pte_t pte) > +{ > + return (pte_val(pte) & _PAGE_CHG_MASK); > +} > + > static inline pmd_t *pud_pgtable(pud_t pud) > { > - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); > + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > } > > static inline struct page *pud_page(pud_t pud) > { > - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); > + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > } > > static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > static inline unsigned long _pmd_pfn(pmd_t pmd) > { > - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; > + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; > } > > #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h > index 2ee413912926..e5b0fce4ddc5 100644 > --- a/arch/riscv/include/asm/pgtable-bits.h > +++ b/arch/riscv/include/asm/pgtable-bits.h > @@ -7,7 +7,7 @@ > #define _ASM_RISCV_PGTABLE_BITS_H > > /* > - * PTE format: > + * rv32 PTE format: > * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > * PFN reserved for SW D A G U X W R V > */ > @@ -24,6 +24,40 @@ > #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ > #define _PAGE_SOFT (1 << 8) /* Reserved for software */ > > +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) > +/* > + * rv64 PTE format: > + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > + * N MT RSV PFN reserved for SW D A G U X W R V > + * [62:61] Memory Type definitions: > + * 00 - PMA Normal Cacheable, No change to implied PMA memory type > + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > + * 11 - Rsvd Reserved for future standard use > + */ > +#define _SVPBMT_PMA 0UL > +#define _SVPBMT_NC (1UL << 61) > +#define _SVPBMT_IO (1UL << 62) > +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) > + > +extern struct __svpbmt_struct { > + unsigned long mask; > + unsigned long pma; > + unsigned long nocache; > + unsigned long io; > +} __svpbmt __cacheline_aligned; > + > +#define _PAGE_MASK __svpbmt.mask > +#define _PAGE_PMA __svpbmt.pma > +#define _PAGE_NOCACHE __svpbmt.nocache > +#define _PAGE_IO __svpbmt.io > +#else > +#define _PAGE_MASK 0 > +#define _PAGE_PMA 0 > +#define _PAGE_NOCACHE 0 > +#define _PAGE_IO 0 > +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ > + > #define _PAGE_SPECIAL _PAGE_SOFT > #define _PAGE_TABLE _PAGE_PRESENT > > @@ -38,7 +72,8 @@ > /* Set of bits to preserve across pte_modify() */ > #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ > _PAGE_WRITE | _PAGE_EXEC | \ > - _PAGE_USER | _PAGE_GLOBAL)) > + _PAGE_USER | _PAGE_GLOBAL | \ > + _PAGE_MASK)) > /* > * when all of R/W/X are zero, the PTE is a pointer to the next level > * of the page table; otherwise, it is a leaf PTE. > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > index bf204e7c1f74..0f7a6541015f 100644 > --- a/arch/riscv/include/asm/pgtable.h > +++ b/arch/riscv/include/asm/pgtable.h > @@ -138,7 +138,8 @@ > | _PAGE_PRESENT \ > | _PAGE_ACCESSED \ > | _PAGE_DIRTY \ > - | _PAGE_GLOBAL) > + | _PAGE_GLOBAL \ > + | _PAGE_PMA) > > #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) > #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) > @@ -148,11 +149,9 @@ > > #define PAGE_TABLE __pgprot(_PAGE_TABLE) > > -/* > - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't > - * change the properties of memory regions. > - */ > -#define _PAGE_IOREMAP _PAGE_KERNEL > +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) > + > +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) > > extern pgd_t swapper_pg_dir[]; > > @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) > > static inline struct page *pmd_page(pmd_t pmd) > { > - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > } > > static inline unsigned long pmd_page_vaddr(pmd_t pmd) > { > - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > } > > static inline pte_t pmd_pte(pmd_t pmd) > @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) > /* Yields the page frame number (PFN) of a page table entry */ > static inline unsigned long pte_pfn(pte_t pte) > { > - return (pte_val(pte) >> _PAGE_PFN_SHIFT); > + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); > } > > #define pte_page(x) pfn_to_page(pte_pfn(x)) > @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > return ptep_test_and_clear_young(vma, address, ptep); > } > > +#define pgprot_noncached pgprot_noncached > +static inline pgprot_t pgprot_noncached(pgprot_t _prot) > +{ > + unsigned long prot = pgprot_val(_prot); > + > + prot &= ~_PAGE_MASK; > + prot |= _PAGE_IO; > + > + return __pgprot(prot); > +} > + > +#define pgprot_writecombine pgprot_writecombine > +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) > +{ > + unsigned long prot = pgprot_val(_prot); > + > + prot &= ~_PAGE_MASK; > + prot |= _PAGE_NOCACHE; > + > + return __pgprot(prot); > +} > + > /* > * THP functions > */ > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > index d959d207a40d..fa7480cb8b87 100644 > --- a/arch/riscv/kernel/cpufeature.c > +++ b/arch/riscv/kernel/cpufeature.c > @@ -8,6 +8,7 @@ > > #include <linux/bitmap.h> > #include <linux/of.h> > +#include <linux/pgtable.h> > #include <asm/processor.h> > #include <asm/hwcap.h> > #include <asm/smp.h> > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > } > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > +static void __init mmu_supports_svpbmt(void) > +{ > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) IIRC, Christoph suggested a CONFIG_RISCV_SVPBMT when reviewing v3. What about that idea? > + struct device_node *node; > + const char *str; > + > + for_each_of_cpu_node(node) { > + if (of_property_read_string(node, "mmu-type", &str)) > + continue; > + > + if (!strncmp(str + 6, "none", 4)) > + continue; > + > + if (of_property_read_string(node, "mmu", &str)) > + continue; > + > + if (strncmp(str + 6, "svpmbt", 6)) > + continue; > + } > + > + __svpbmt.pma = _SVPBMT_PMA; > + __svpbmt.nocache = _SVPBMT_NC; > + __svpbmt.io = _SVPBMT_IO; > + __svpbmt.mask = _SVPBMT_MASK; > +#endif > +} > + > +static void __init mmu_supports(void) can we remove this function currently? Instead, directly call mmu_supports_svpbmt()? > +{ > + mmu_supports_svpbmt(); > +} > + > void __init riscv_fill_hwcap(void) > { > struct device_node *node; > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > size_t i, j, isa_len; > static unsigned long isa2hwcap[256] = {0}; > > + mmu_supports(); > + > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > index 24b2b8044602..e4e658165ee1 100644 > --- a/arch/riscv/mm/init.c > +++ b/arch/riscv/mm/init.c > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > return vmemmap_populate_basepages(start, end, node, NULL); > } > #endif > + > +#if defined(CONFIG_64BIT) > +struct __svpbmt_struct __svpbmt __ro_after_init; Added the structure for all RV64 including NOMMU case and those platforms which doen't want SVPBMT at all, I believe Christoph's CONFIG_RISCV_SVPBMT suggestion can solve this problem. > +EXPORT_SYMBOL(__svpbmt); > +#endif
Hi, We forgot fixmap, add below into your patch. diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h index 54cbf07fb4e9..899b59bdb9eb 100644 --- a/arch/riscv/include/asm/fixmap.h +++ b/arch/riscv/include/asm/fixmap.h @@ -43,8 +43,6 @@ enum fixed_addresses { __end_of_fixed_addresses }; -#define FIXMAP_PAGE_IO PAGE_KERNEL - #define __early_set_fixmap __set_fixmap #define __late_set_fixmap __set_fixmap diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index f3c9f9a1c1bb..9bb06384c57f 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -126,6 +126,8 @@ | _PAGE_SHARE \ | _PAGE_SO) +#define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP) On Mon, Nov 29, 2021 at 9:41 AM <wefu@redhat.com> wrote: > > From: Wei Fu <wefu@redhat.com> > > This patch follows the standard pure RISC-V Svpbmt extension in > privilege spec to solve the non-coherent SOC dma synchronization > issues. > > Here is the svpbmt PTE format: > | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > N MT RSW D A G U X W R V > ^ > > Of the Reserved bits [63:54] in a leaf PTE, the high bit is already > allocated (as the N bit), so bits [62:61] are used as the MT (aka > MemType) field. This field specifies one of three memory types that > are close equivalents (or equivalent in effect) to the three main x86 > and ARMv8 memory types - as shown in the following table. > > RISC-V > Encoding & > MemType RISC-V Description > ---------- ------------------------------------------------ > 00 - PMA Normal Cacheable, No change to implied PMA memory type > 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > 11 - Rsvd Reserved for future standard use > > The standard protection_map[] needn't be modified because the "PMA" > type keeps the highest bits zero. And the whole modification is > limited in the arch/riscv/* and using a global variable > (__svpbmt) as _PAGE_MASK/IO/NOCACHE for pgprot_noncached > (&writecombine) in pgtable.h. We also add _PAGE_CHG_MASK to filter > PFN than before. > > Enable it in devicetree - (Add "riscv,svpbmt" in the mmu of cpu node) > - mmu: > riscv,svpmbt > > Signed-off-by: Wei Fu <wefu@redhat.com> > Co-developed-by: Liu Shaohua <liush@allwinnertech.com> > Signed-off-by: Liu Shaohua <liush@allwinnertech.com> > Co-developed-by: Guo Ren <guoren@kernel.org> > Signed-off-by: Guo Ren <guoren@kernel.org> > Cc: Palmer Dabbelt <palmerdabbelt@google.com> > Cc: Christoph Hellwig <hch@lst.de> > Cc: Anup Patel <anup.patel@wdc.com> > Cc: Arnd Bergmann <arnd@arndb.de> > Cc: Atish Patra <atish.patra@wdc.com> > Cc: Drew Fustini <drew@beagleboard.org> > Cc: Wei Fu <wefu@redhat.com> > Cc: Wei Wu <lazyparser@gmail.com> > Cc: Chen-Yu Tsai <wens@csie.org> > Cc: Maxime Ripard <maxime@cerno.tech> > Cc: Daniel Lustig <dlustig@nvidia.com> > Cc: Greg Favor <gfavor@ventanamicro.com> > Cc: Andrea Mondelli <andrea.mondelli@huawei.com> > Cc: Jonathan Behrens <behrensj@mit.edu> > Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com> > Cc: Bill Huffman <huffman@cadence.com> > Cc: Nick Kossifidis <mick@ics.forth.gr> > Cc: Allen Baum <allen.baum@esperantotech.com> > Cc: Josh Scheid <jscheid@ventanamicro.com> > Cc: Richard Trauben <rtrauben@gmail.com> > --- > arch/riscv/include/asm/fixmap.h | 2 +- > arch/riscv/include/asm/pgtable-64.h | 21 ++++++++++++--- > arch/riscv/include/asm/pgtable-bits.h | 39 +++++++++++++++++++++++++-- > arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++------- > arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++ > arch/riscv/mm/init.c | 5 ++++ > 6 files changed, 126 insertions(+), 15 deletions(-) > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > index 54cbf07fb4e9..5acd99d08e74 100644 > --- a/arch/riscv/include/asm/fixmap.h > +++ b/arch/riscv/include/asm/fixmap.h > @@ -43,7 +43,7 @@ enum fixed_addresses { > __end_of_fixed_addresses > }; > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > +#define FIXMAP_PAGE_IO PAGE_IOREMAP > > #define __early_set_fixmap __set_fixmap > > diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h > index 228261aa9628..16d251282b1d 100644 > --- a/arch/riscv/include/asm/pgtable-64.h > +++ b/arch/riscv/include/asm/pgtable-64.h > @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) > set_pud(pudp, __pud(0)); > } > > +static inline unsigned long _chg_of_pmd(pmd_t pmd) > +{ > + return (pmd_val(pmd) & _PAGE_CHG_MASK); > +} > + > +static inline unsigned long _chg_of_pud(pud_t pud) > +{ > + return (pud_val(pud) & _PAGE_CHG_MASK); > +} > + > +static inline unsigned long _chg_of_pte(pte_t pte) > +{ > + return (pte_val(pte) & _PAGE_CHG_MASK); > +} > + > static inline pmd_t *pud_pgtable(pud_t pud) > { > - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); > + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > } > > static inline struct page *pud_page(pud_t pud) > { > - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); > + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > } > > static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > static inline unsigned long _pmd_pfn(pmd_t pmd) > { > - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; > + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; > } > > #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h > index 2ee413912926..e5b0fce4ddc5 100644 > --- a/arch/riscv/include/asm/pgtable-bits.h > +++ b/arch/riscv/include/asm/pgtable-bits.h > @@ -7,7 +7,7 @@ > #define _ASM_RISCV_PGTABLE_BITS_H > > /* > - * PTE format: > + * rv32 PTE format: > * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > * PFN reserved for SW D A G U X W R V > */ > @@ -24,6 +24,40 @@ > #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ > #define _PAGE_SOFT (1 << 8) /* Reserved for software */ > > +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) > +/* > + * rv64 PTE format: > + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > + * N MT RSV PFN reserved for SW D A G U X W R V > + * [62:61] Memory Type definitions: > + * 00 - PMA Normal Cacheable, No change to implied PMA memory type > + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > + * 11 - Rsvd Reserved for future standard use > + */ > +#define _SVPBMT_PMA 0UL > +#define _SVPBMT_NC (1UL << 61) > +#define _SVPBMT_IO (1UL << 62) > +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) > + > +extern struct __svpbmt_struct { > + unsigned long mask; > + unsigned long pma; > + unsigned long nocache; > + unsigned long io; > +} __svpbmt __cacheline_aligned; > + > +#define _PAGE_MASK __svpbmt.mask > +#define _PAGE_PMA __svpbmt.pma > +#define _PAGE_NOCACHE __svpbmt.nocache > +#define _PAGE_IO __svpbmt.io > +#else > +#define _PAGE_MASK 0 > +#define _PAGE_PMA 0 > +#define _PAGE_NOCACHE 0 > +#define _PAGE_IO 0 > +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ > + > #define _PAGE_SPECIAL _PAGE_SOFT > #define _PAGE_TABLE _PAGE_PRESENT > > @@ -38,7 +72,8 @@ > /* Set of bits to preserve across pte_modify() */ > #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ > _PAGE_WRITE | _PAGE_EXEC | \ > - _PAGE_USER | _PAGE_GLOBAL)) > + _PAGE_USER | _PAGE_GLOBAL | \ > + _PAGE_MASK)) > /* > * when all of R/W/X are zero, the PTE is a pointer to the next level > * of the page table; otherwise, it is a leaf PTE. > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > index bf204e7c1f74..0f7a6541015f 100644 > --- a/arch/riscv/include/asm/pgtable.h > +++ b/arch/riscv/include/asm/pgtable.h > @@ -138,7 +138,8 @@ > | _PAGE_PRESENT \ > | _PAGE_ACCESSED \ > | _PAGE_DIRTY \ > - | _PAGE_GLOBAL) > + | _PAGE_GLOBAL \ > + | _PAGE_PMA) > > #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) > #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) > @@ -148,11 +149,9 @@ > > #define PAGE_TABLE __pgprot(_PAGE_TABLE) > > -/* > - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't > - * change the properties of memory regions. > - */ > -#define _PAGE_IOREMAP _PAGE_KERNEL > +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) > + > +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) > > extern pgd_t swapper_pg_dir[]; > > @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) > > static inline struct page *pmd_page(pmd_t pmd) > { > - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > } > > static inline unsigned long pmd_page_vaddr(pmd_t pmd) > { > - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > } > > static inline pte_t pmd_pte(pmd_t pmd) > @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) > /* Yields the page frame number (PFN) of a page table entry */ > static inline unsigned long pte_pfn(pte_t pte) > { > - return (pte_val(pte) >> _PAGE_PFN_SHIFT); > + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); > } > > #define pte_page(x) pfn_to_page(pte_pfn(x)) > @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > return ptep_test_and_clear_young(vma, address, ptep); > } > > +#define pgprot_noncached pgprot_noncached > +static inline pgprot_t pgprot_noncached(pgprot_t _prot) > +{ > + unsigned long prot = pgprot_val(_prot); > + > + prot &= ~_PAGE_MASK; > + prot |= _PAGE_IO; > + > + return __pgprot(prot); > +} > + > +#define pgprot_writecombine pgprot_writecombine > +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) > +{ > + unsigned long prot = pgprot_val(_prot); > + > + prot &= ~_PAGE_MASK; > + prot |= _PAGE_NOCACHE; > + > + return __pgprot(prot); > +} > + > /* > * THP functions > */ > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > index d959d207a40d..fa7480cb8b87 100644 > --- a/arch/riscv/kernel/cpufeature.c > +++ b/arch/riscv/kernel/cpufeature.c > @@ -8,6 +8,7 @@ > > #include <linux/bitmap.h> > #include <linux/of.h> > +#include <linux/pgtable.h> > #include <asm/processor.h> > #include <asm/hwcap.h> > #include <asm/smp.h> > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > } > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > +static void __init mmu_supports_svpbmt(void) > +{ > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) > + struct device_node *node; > + const char *str; > + > + for_each_of_cpu_node(node) { > + if (of_property_read_string(node, "mmu-type", &str)) > + continue; > + > + if (!strncmp(str + 6, "none", 4)) > + continue; > + > + if (of_property_read_string(node, "mmu", &str)) > + continue; > + > + if (strncmp(str + 6, "svpmbt", 6)) > + continue; > + } > + > + __svpbmt.pma = _SVPBMT_PMA; > + __svpbmt.nocache = _SVPBMT_NC; > + __svpbmt.io = _SVPBMT_IO; > + __svpbmt.mask = _SVPBMT_MASK; > +#endif > +} > + > +static void __init mmu_supports(void) > +{ > + mmu_supports_svpbmt(); > +} > + > void __init riscv_fill_hwcap(void) > { > struct device_node *node; > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > size_t i, j, isa_len; > static unsigned long isa2hwcap[256] = {0}; > > + mmu_supports(); > + > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > index 24b2b8044602..e4e658165ee1 100644 > --- a/arch/riscv/mm/init.c > +++ b/arch/riscv/mm/init.c > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > return vmemmap_populate_basepages(start, end, node, NULL); > } > #endif > + > +#if defined(CONFIG_64BIT) > +struct __svpbmt_struct __svpbmt __ro_after_init; > +EXPORT_SYMBOL(__svpbmt); > +#endif > -- > 2.25.4 >
Am Montag, 29. November 2021, 02:40:07 CET schrieb wefu@redhat.com: > From: Wei Fu <wefu@redhat.com> > > This patch follows the standard pure RISC-V Svpbmt extension in > privilege spec to solve the non-coherent SOC dma synchronization > issues. > > Here is the svpbmt PTE format: > | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > N MT RSW D A G U X W R V > ^ > > Of the Reserved bits [63:54] in a leaf PTE, the high bit is already > allocated (as the N bit), so bits [62:61] are used as the MT (aka > MemType) field. This field specifies one of three memory types that > are close equivalents (or equivalent in effect) to the three main x86 > and ARMv8 memory types - as shown in the following table. > > RISC-V > Encoding & > MemType RISC-V Description > ---------- ------------------------------------------------ > 00 - PMA Normal Cacheable, No change to implied PMA memory type > 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > 11 - Rsvd Reserved for future standard use > > The standard protection_map[] needn't be modified because the "PMA" > type keeps the highest bits zero. And the whole modification is > limited in the arch/riscv/* and using a global variable > (__svpbmt) as _PAGE_MASK/IO/NOCACHE for pgprot_noncached > (&writecombine) in pgtable.h. We also add _PAGE_CHG_MASK to filter > PFN than before. > > Enable it in devicetree - (Add "riscv,svpbmt" in the mmu of cpu node) > - mmu: > riscv,svpmbt > > Signed-off-by: Wei Fu <wefu@redhat.com> > Co-developed-by: Liu Shaohua <liush@allwinnertech.com> > Signed-off-by: Liu Shaohua <liush@allwinnertech.com> > Co-developed-by: Guo Ren <guoren@kernel.org> > Signed-off-by: Guo Ren <guoren@kernel.org> > Cc: Palmer Dabbelt <palmerdabbelt@google.com> > Cc: Christoph Hellwig <hch@lst.de> > Cc: Anup Patel <anup.patel@wdc.com> > Cc: Arnd Bergmann <arnd@arndb.de> > Cc: Atish Patra <atish.patra@wdc.com> > Cc: Drew Fustini <drew@beagleboard.org> > Cc: Wei Fu <wefu@redhat.com> > Cc: Wei Wu <lazyparser@gmail.com> > Cc: Chen-Yu Tsai <wens@csie.org> > Cc: Maxime Ripard <maxime@cerno.tech> > Cc: Daniel Lustig <dlustig@nvidia.com> > Cc: Greg Favor <gfavor@ventanamicro.com> > Cc: Andrea Mondelli <andrea.mondelli@huawei.com> > Cc: Jonathan Behrens <behrensj@mit.edu> > Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com> > Cc: Bill Huffman <huffman@cadence.com> > Cc: Nick Kossifidis <mick@ics.forth.gr> > Cc: Allen Baum <allen.baum@esperantotech.com> > Cc: Josh Scheid <jscheid@ventanamicro.com> > Cc: Richard Trauben <rtrauben@gmail.com> > --- > arch/riscv/include/asm/fixmap.h | 2 +- > arch/riscv/include/asm/pgtable-64.h | 21 ++++++++++++--- > arch/riscv/include/asm/pgtable-bits.h | 39 +++++++++++++++++++++++++-- > arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++------- > arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++ > arch/riscv/mm/init.c | 5 ++++ > 6 files changed, 126 insertions(+), 15 deletions(-) > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > index 54cbf07fb4e9..5acd99d08e74 100644 > --- a/arch/riscv/include/asm/fixmap.h > +++ b/arch/riscv/include/asm/fixmap.h > @@ -43,7 +43,7 @@ enum fixed_addresses { > __end_of_fixed_addresses > }; > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > +#define FIXMAP_PAGE_IO PAGE_IOREMAP > > #define __early_set_fixmap __set_fixmap > > diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h > index 228261aa9628..16d251282b1d 100644 > --- a/arch/riscv/include/asm/pgtable-64.h > +++ b/arch/riscv/include/asm/pgtable-64.h > @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) > set_pud(pudp, __pud(0)); > } > > +static inline unsigned long _chg_of_pmd(pmd_t pmd) > +{ > + return (pmd_val(pmd) & _PAGE_CHG_MASK); > +} > + > +static inline unsigned long _chg_of_pud(pud_t pud) > +{ > + return (pud_val(pud) & _PAGE_CHG_MASK); > +} > + > +static inline unsigned long _chg_of_pte(pte_t pte) > +{ > + return (pte_val(pte) & _PAGE_CHG_MASK); > +} > + > static inline pmd_t *pud_pgtable(pud_t pud) > { > - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); > + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > } > > static inline struct page *pud_page(pud_t pud) > { > - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); > + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > } > > static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > static inline unsigned long _pmd_pfn(pmd_t pmd) > { > - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; > + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; > } > > #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h > index 2ee413912926..e5b0fce4ddc5 100644 > --- a/arch/riscv/include/asm/pgtable-bits.h > +++ b/arch/riscv/include/asm/pgtable-bits.h > @@ -7,7 +7,7 @@ > #define _ASM_RISCV_PGTABLE_BITS_H > > /* > - * PTE format: > + * rv32 PTE format: > * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > * PFN reserved for SW D A G U X W R V > */ > @@ -24,6 +24,40 @@ > #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ > #define _PAGE_SOFT (1 << 8) /* Reserved for software */ > > +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) > +/* > + * rv64 PTE format: > + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > + * N MT RSV PFN reserved for SW D A G U X W R V > + * [62:61] Memory Type definitions: > + * 00 - PMA Normal Cacheable, No change to implied PMA memory type > + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > + * 11 - Rsvd Reserved for future standard use > + */ > +#define _SVPBMT_PMA 0UL > +#define _SVPBMT_NC (1UL << 61) > +#define _SVPBMT_IO (1UL << 62) > +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) > + > +extern struct __svpbmt_struct { > + unsigned long mask; > + unsigned long pma; > + unsigned long nocache; > + unsigned long io; > +} __svpbmt __cacheline_aligned; > + > +#define _PAGE_MASK __svpbmt.mask > +#define _PAGE_PMA __svpbmt.pma > +#define _PAGE_NOCACHE __svpbmt.nocache > +#define _PAGE_IO __svpbmt.io > +#else > +#define _PAGE_MASK 0 > +#define _PAGE_PMA 0 > +#define _PAGE_NOCACHE 0 > +#define _PAGE_IO 0 > +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ > + > #define _PAGE_SPECIAL _PAGE_SOFT > #define _PAGE_TABLE _PAGE_PRESENT > > @@ -38,7 +72,8 @@ > /* Set of bits to preserve across pte_modify() */ > #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ > _PAGE_WRITE | _PAGE_EXEC | \ > - _PAGE_USER | _PAGE_GLOBAL)) > + _PAGE_USER | _PAGE_GLOBAL | \ > + _PAGE_MASK)) > /* > * when all of R/W/X are zero, the PTE is a pointer to the next level > * of the page table; otherwise, it is a leaf PTE. > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > index bf204e7c1f74..0f7a6541015f 100644 > --- a/arch/riscv/include/asm/pgtable.h > +++ b/arch/riscv/include/asm/pgtable.h > @@ -138,7 +138,8 @@ > | _PAGE_PRESENT \ > | _PAGE_ACCESSED \ > | _PAGE_DIRTY \ > - | _PAGE_GLOBAL) > + | _PAGE_GLOBAL \ > + | _PAGE_PMA) > > #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) > #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) > @@ -148,11 +149,9 @@ > > #define PAGE_TABLE __pgprot(_PAGE_TABLE) > > -/* > - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't > - * change the properties of memory regions. > - */ > -#define _PAGE_IOREMAP _PAGE_KERNEL > +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) > + > +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) > > extern pgd_t swapper_pg_dir[]; > > @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) > > static inline struct page *pmd_page(pmd_t pmd) > { > - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > } > > static inline unsigned long pmd_page_vaddr(pmd_t pmd) > { > - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > } > > static inline pte_t pmd_pte(pmd_t pmd) > @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) > /* Yields the page frame number (PFN) of a page table entry */ > static inline unsigned long pte_pfn(pte_t pte) > { > - return (pte_val(pte) >> _PAGE_PFN_SHIFT); > + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); > } > > #define pte_page(x) pfn_to_page(pte_pfn(x)) > @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > return ptep_test_and_clear_young(vma, address, ptep); > } > > +#define pgprot_noncached pgprot_noncached > +static inline pgprot_t pgprot_noncached(pgprot_t _prot) > +{ > + unsigned long prot = pgprot_val(_prot); > + > + prot &= ~_PAGE_MASK; > + prot |= _PAGE_IO; > + > + return __pgprot(prot); > +} > + > +#define pgprot_writecombine pgprot_writecombine > +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) > +{ > + unsigned long prot = pgprot_val(_prot); > + > + prot &= ~_PAGE_MASK; > + prot |= _PAGE_NOCACHE; > + > + return __pgprot(prot); > +} > + > /* > * THP functions > */ > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > index d959d207a40d..fa7480cb8b87 100644 > --- a/arch/riscv/kernel/cpufeature.c > +++ b/arch/riscv/kernel/cpufeature.c > @@ -8,6 +8,7 @@ > > #include <linux/bitmap.h> > #include <linux/of.h> > +#include <linux/pgtable.h> > #include <asm/processor.h> > #include <asm/hwcap.h> > #include <asm/smp.h> > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > } > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > +static void __init mmu_supports_svpbmt(void) > +{ > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) > + struct device_node *node; > + const char *str; > + > + for_each_of_cpu_node(node) { > + if (of_property_read_string(node, "mmu-type", &str)) > + continue; > + > + if (!strncmp(str + 6, "none", 4)) > + continue; > + > + if (of_property_read_string(node, "mmu", &str)) > + continue; > + > + if (strncmp(str + 6, "svpmbt", 6)) same here ... check for "svpbmt" [m seems to be at the wrong position] > + continue; > + } > + > + __svpbmt.pma = _SVPBMT_PMA; > + __svpbmt.nocache = _SVPBMT_NC; > + __svpbmt.io = _SVPBMT_IO; > + __svpbmt.mask = _SVPBMT_MASK; > +#endif > +} > + > +static void __init mmu_supports(void) > +{ > + mmu_supports_svpbmt(); > +} > + > void __init riscv_fill_hwcap(void) > { > struct device_node *node; > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > size_t i, j, isa_len; > static unsigned long isa2hwcap[256] = {0}; > > + mmu_supports(); > + > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > index 24b2b8044602..e4e658165ee1 100644 > --- a/arch/riscv/mm/init.c > +++ b/arch/riscv/mm/init.c > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > return vmemmap_populate_basepages(start, end, node, NULL); > } > #endif > + > +#if defined(CONFIG_64BIT) > +struct __svpbmt_struct __svpbmt __ro_after_init; > +EXPORT_SYMBOL(__svpbmt); > +#endif >
Hi Heiko, thanks , yup, my typo, fixed in my new version . On Wed, Dec 1, 2021 at 2:46 AM Heiko Stübner <heiko@sntech.de> wrote: > > Am Montag, 29. November 2021, 02:40:07 CET schrieb wefu@redhat.com: > > From: Wei Fu <wefu@redhat.com> > > > > This patch follows the standard pure RISC-V Svpbmt extension in > > privilege spec to solve the non-coherent SOC dma synchronization > > issues. > > > > Here is the svpbmt PTE format: > > | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > N MT RSW D A G U X W R V > > ^ > > > > Of the Reserved bits [63:54] in a leaf PTE, the high bit is already > > allocated (as the N bit), so bits [62:61] are used as the MT (aka > > MemType) field. This field specifies one of three memory types that > > are close equivalents (or equivalent in effect) to the three main x86 > > and ARMv8 memory types - as shown in the following table. > > > > RISC-V > > Encoding & > > MemType RISC-V Description > > ---------- ------------------------------------------------ > > 00 - PMA Normal Cacheable, No change to implied PMA memory type > > 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > 11 - Rsvd Reserved for future standard use > > > > The standard protection_map[] needn't be modified because the "PMA" > > type keeps the highest bits zero. And the whole modification is > > limited in the arch/riscv/* and using a global variable > > (__svpbmt) as _PAGE_MASK/IO/NOCACHE for pgprot_noncached > > (&writecombine) in pgtable.h. We also add _PAGE_CHG_MASK to filter > > PFN than before. > > > > Enable it in devicetree - (Add "riscv,svpbmt" in the mmu of cpu node) > > - mmu: > > riscv,svpmbt > > > > Signed-off-by: Wei Fu <wefu@redhat.com> > > Co-developed-by: Liu Shaohua <liush@allwinnertech.com> > > Signed-off-by: Liu Shaohua <liush@allwinnertech.com> > > Co-developed-by: Guo Ren <guoren@kernel.org> > > Signed-off-by: Guo Ren <guoren@kernel.org> > > Cc: Palmer Dabbelt <palmerdabbelt@google.com> > > Cc: Christoph Hellwig <hch@lst.de> > > Cc: Anup Patel <anup.patel@wdc.com> > > Cc: Arnd Bergmann <arnd@arndb.de> > > Cc: Atish Patra <atish.patra@wdc.com> > > Cc: Drew Fustini <drew@beagleboard.org> > > Cc: Wei Fu <wefu@redhat.com> > > Cc: Wei Wu <lazyparser@gmail.com> > > Cc: Chen-Yu Tsai <wens@csie.org> > > Cc: Maxime Ripard <maxime@cerno.tech> > > Cc: Daniel Lustig <dlustig@nvidia.com> > > Cc: Greg Favor <gfavor@ventanamicro.com> > > Cc: Andrea Mondelli <andrea.mondelli@huawei.com> > > Cc: Jonathan Behrens <behrensj@mit.edu> > > Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com> > > Cc: Bill Huffman <huffman@cadence.com> > > Cc: Nick Kossifidis <mick@ics.forth.gr> > > Cc: Allen Baum <allen.baum@esperantotech.com> > > Cc: Josh Scheid <jscheid@ventanamicro.com> > > Cc: Richard Trauben <rtrauben@gmail.com> > > --- > > arch/riscv/include/asm/fixmap.h | 2 +- > > arch/riscv/include/asm/pgtable-64.h | 21 ++++++++++++--- > > arch/riscv/include/asm/pgtable-bits.h | 39 +++++++++++++++++++++++++-- > > arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++------- > > arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++ > > arch/riscv/mm/init.c | 5 ++++ > > 6 files changed, 126 insertions(+), 15 deletions(-) > > > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > > index 54cbf07fb4e9..5acd99d08e74 100644 > > --- a/arch/riscv/include/asm/fixmap.h > > +++ b/arch/riscv/include/asm/fixmap.h > > @@ -43,7 +43,7 @@ enum fixed_addresses { > > __end_of_fixed_addresses > > }; > > > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > > +#define FIXMAP_PAGE_IO PAGE_IOREMAP > > > > #define __early_set_fixmap __set_fixmap > > > > diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h > > index 228261aa9628..16d251282b1d 100644 > > --- a/arch/riscv/include/asm/pgtable-64.h > > +++ b/arch/riscv/include/asm/pgtable-64.h > > @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) > > set_pud(pudp, __pud(0)); > > } > > > > +static inline unsigned long _chg_of_pmd(pmd_t pmd) > > +{ > > + return (pmd_val(pmd) & _PAGE_CHG_MASK); > > +} > > + > > +static inline unsigned long _chg_of_pud(pud_t pud) > > +{ > > + return (pud_val(pud) & _PAGE_CHG_MASK); > > +} > > + > > +static inline unsigned long _chg_of_pte(pte_t pte) > > +{ > > + return (pte_val(pte) & _PAGE_CHG_MASK); > > +} > > + > > static inline pmd_t *pud_pgtable(pud_t pud) > > { > > - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); > > + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > } > > > > static inline struct page *pud_page(pud_t pud) > > { > > - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); > > + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > } > > > > static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > > > static inline unsigned long _pmd_pfn(pmd_t pmd) > > { > > - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; > > + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; > > } > > > > #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) > > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h > > index 2ee413912926..e5b0fce4ddc5 100644 > > --- a/arch/riscv/include/asm/pgtable-bits.h > > +++ b/arch/riscv/include/asm/pgtable-bits.h > > @@ -7,7 +7,7 @@ > > #define _ASM_RISCV_PGTABLE_BITS_H > > > > /* > > - * PTE format: > > + * rv32 PTE format: > > * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > * PFN reserved for SW D A G U X W R V > > */ > > @@ -24,6 +24,40 @@ > > #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ > > #define _PAGE_SOFT (1 << 8) /* Reserved for software */ > > > > +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) > > +/* > > + * rv64 PTE format: > > + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > + * N MT RSV PFN reserved for SW D A G U X W R V > > + * [62:61] Memory Type definitions: > > + * 00 - PMA Normal Cacheable, No change to implied PMA memory type > > + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > + * 11 - Rsvd Reserved for future standard use > > + */ > > +#define _SVPBMT_PMA 0UL > > +#define _SVPBMT_NC (1UL << 61) > > +#define _SVPBMT_IO (1UL << 62) > > +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) > > + > > +extern struct __svpbmt_struct { > > + unsigned long mask; > > + unsigned long pma; > > + unsigned long nocache; > > + unsigned long io; > > +} __svpbmt __cacheline_aligned; > > + > > +#define _PAGE_MASK __svpbmt.mask > > +#define _PAGE_PMA __svpbmt.pma > > +#define _PAGE_NOCACHE __svpbmt.nocache > > +#define _PAGE_IO __svpbmt.io > > +#else > > +#define _PAGE_MASK 0 > > +#define _PAGE_PMA 0 > > +#define _PAGE_NOCACHE 0 > > +#define _PAGE_IO 0 > > +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ > > + > > #define _PAGE_SPECIAL _PAGE_SOFT > > #define _PAGE_TABLE _PAGE_PRESENT > > > > @@ -38,7 +72,8 @@ > > /* Set of bits to preserve across pte_modify() */ > > #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ > > _PAGE_WRITE | _PAGE_EXEC | \ > > - _PAGE_USER | _PAGE_GLOBAL)) > > + _PAGE_USER | _PAGE_GLOBAL | \ > > + _PAGE_MASK)) > > /* > > * when all of R/W/X are zero, the PTE is a pointer to the next level > > * of the page table; otherwise, it is a leaf PTE. > > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > > index bf204e7c1f74..0f7a6541015f 100644 > > --- a/arch/riscv/include/asm/pgtable.h > > +++ b/arch/riscv/include/asm/pgtable.h > > @@ -138,7 +138,8 @@ > > | _PAGE_PRESENT \ > > | _PAGE_ACCESSED \ > > | _PAGE_DIRTY \ > > - | _PAGE_GLOBAL) > > + | _PAGE_GLOBAL \ > > + | _PAGE_PMA) > > > > #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) > > #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) > > @@ -148,11 +149,9 @@ > > > > #define PAGE_TABLE __pgprot(_PAGE_TABLE) > > > > -/* > > - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't > > - * change the properties of memory regions. > > - */ > > -#define _PAGE_IOREMAP _PAGE_KERNEL > > +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) > > + > > +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) > > > > extern pgd_t swapper_pg_dir[]; > > > > @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) > > > > static inline struct page *pmd_page(pmd_t pmd) > > { > > - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > } > > > > static inline unsigned long pmd_page_vaddr(pmd_t pmd) > > { > > - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > } > > > > static inline pte_t pmd_pte(pmd_t pmd) > > @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) > > /* Yields the page frame number (PFN) of a page table entry */ > > static inline unsigned long pte_pfn(pte_t pte) > > { > > - return (pte_val(pte) >> _PAGE_PFN_SHIFT); > > + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); > > } > > > > #define pte_page(x) pfn_to_page(pte_pfn(x)) > > @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > > return ptep_test_and_clear_young(vma, address, ptep); > > } > > > > +#define pgprot_noncached pgprot_noncached > > +static inline pgprot_t pgprot_noncached(pgprot_t _prot) > > +{ > > + unsigned long prot = pgprot_val(_prot); > > + > > + prot &= ~_PAGE_MASK; > > + prot |= _PAGE_IO; > > + > > + return __pgprot(prot); > > +} > > + > > +#define pgprot_writecombine pgprot_writecombine > > +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) > > +{ > > + unsigned long prot = pgprot_val(_prot); > > + > > + prot &= ~_PAGE_MASK; > > + prot |= _PAGE_NOCACHE; > > + > > + return __pgprot(prot); > > +} > > + > > /* > > * THP functions > > */ > > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > > index d959d207a40d..fa7480cb8b87 100644 > > --- a/arch/riscv/kernel/cpufeature.c > > +++ b/arch/riscv/kernel/cpufeature.c > > @@ -8,6 +8,7 @@ > > > > #include <linux/bitmap.h> > > #include <linux/of.h> > > +#include <linux/pgtable.h> > > #include <asm/processor.h> > > #include <asm/hwcap.h> > > #include <asm/smp.h> > > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > > } > > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > > > +static void __init mmu_supports_svpbmt(void) > > +{ > > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) > > + struct device_node *node; > > + const char *str; > > + > > + for_each_of_cpu_node(node) { > > + if (of_property_read_string(node, "mmu-type", &str)) > > + continue; > > + > > + if (!strncmp(str + 6, "none", 4)) > > + continue; > > + > > + if (of_property_read_string(node, "mmu", &str)) > > + continue; > > + > > + if (strncmp(str + 6, "svpmbt", 6)) > > same here ... check for "svpbmt" [m seems to be at the wrong position] > > > > + continue; > > + } > > + > > + __svpbmt.pma = _SVPBMT_PMA; > > + __svpbmt.nocache = _SVPBMT_NC; > > + __svpbmt.io = _SVPBMT_IO; > > + __svpbmt.mask = _SVPBMT_MASK; > > +#endif > > +} > > + > > +static void __init mmu_supports(void) > > +{ > > + mmu_supports_svpbmt(); > > +} > > + > > void __init riscv_fill_hwcap(void) > > { > > struct device_node *node; > > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > > size_t i, j, isa_len; > > static unsigned long isa2hwcap[256] = {0}; > > > > + mmu_supports(); > > + > > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > > index 24b2b8044602..e4e658165ee1 100644 > > --- a/arch/riscv/mm/init.c > > +++ b/arch/riscv/mm/init.c > > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > > return vmemmap_populate_basepages(start, end, node, NULL); > > } > > #endif > > + > > +#if defined(CONFIG_64BIT) > > +struct __svpbmt_struct __svpbmt __ro_after_init; > > +EXPORT_SYMBOL(__svpbmt); > > +#endif > > > > > >
Thanks for reminding me, Guo Ren. :-) yes, I am working on the new version , yes, my bad, I am adding it in to my V5 On Tue, Nov 30, 2021 at 6:19 PM Guo Ren <guoren@kernel.org> wrote: > > Hi, > > We forgot fixmap, add below into your patch. > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > index 54cbf07fb4e9..899b59bdb9eb 100644 > --- a/arch/riscv/include/asm/fixmap.h > +++ b/arch/riscv/include/asm/fixmap.h > @@ -43,8 +43,6 @@ enum fixed_addresses { > __end_of_fixed_addresses > }; > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > - > #define __early_set_fixmap __set_fixmap > > #define __late_set_fixmap __set_fixmap > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > index f3c9f9a1c1bb..9bb06384c57f 100644 > --- a/arch/riscv/include/asm/pgtable.h > +++ b/arch/riscv/include/asm/pgtable.h > @@ -126,6 +126,8 @@ > | _PAGE_SHARE \ > | _PAGE_SO) > > +#define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP) > > On Mon, Nov 29, 2021 at 9:41 AM <wefu@redhat.com> wrote: > > > > From: Wei Fu <wefu@redhat.com> > > > > This patch follows the standard pure RISC-V Svpbmt extension in > > privilege spec to solve the non-coherent SOC dma synchronization > > issues. > > > > Here is the svpbmt PTE format: > > | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > N MT RSW D A G U X W R V > > ^ > > > > Of the Reserved bits [63:54] in a leaf PTE, the high bit is already > > allocated (as the N bit), so bits [62:61] are used as the MT (aka > > MemType) field. This field specifies one of three memory types that > > are close equivalents (or equivalent in effect) to the three main x86 > > and ARMv8 memory types - as shown in the following table. > > > > RISC-V > > Encoding & > > MemType RISC-V Description > > ---------- ------------------------------------------------ > > 00 - PMA Normal Cacheable, No change to implied PMA memory type > > 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > 11 - Rsvd Reserved for future standard use > > > > The standard protection_map[] needn't be modified because the "PMA" > > type keeps the highest bits zero. And the whole modification is > > limited in the arch/riscv/* and using a global variable > > (__svpbmt) as _PAGE_MASK/IO/NOCACHE for pgprot_noncached > > (&writecombine) in pgtable.h. We also add _PAGE_CHG_MASK to filter > > PFN than before. > > > > Enable it in devicetree - (Add "riscv,svpbmt" in the mmu of cpu node) > > - mmu: > > riscv,svpmbt > > > > Signed-off-by: Wei Fu <wefu@redhat.com> > > Co-developed-by: Liu Shaohua <liush@allwinnertech.com> > > Signed-off-by: Liu Shaohua <liush@allwinnertech.com> > > Co-developed-by: Guo Ren <guoren@kernel.org> > > Signed-off-by: Guo Ren <guoren@kernel.org> > > Cc: Palmer Dabbelt <palmerdabbelt@google.com> > > Cc: Christoph Hellwig <hch@lst.de> > > Cc: Anup Patel <anup.patel@wdc.com> > > Cc: Arnd Bergmann <arnd@arndb.de> > > Cc: Atish Patra <atish.patra@wdc.com> > > Cc: Drew Fustini <drew@beagleboard.org> > > Cc: Wei Fu <wefu@redhat.com> > > Cc: Wei Wu <lazyparser@gmail.com> > > Cc: Chen-Yu Tsai <wens@csie.org> > > Cc: Maxime Ripard <maxime@cerno.tech> > > Cc: Daniel Lustig <dlustig@nvidia.com> > > Cc: Greg Favor <gfavor@ventanamicro.com> > > Cc: Andrea Mondelli <andrea.mondelli@huawei.com> > > Cc: Jonathan Behrens <behrensj@mit.edu> > > Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com> > > Cc: Bill Huffman <huffman@cadence.com> > > Cc: Nick Kossifidis <mick@ics.forth.gr> > > Cc: Allen Baum <allen.baum@esperantotech.com> > > Cc: Josh Scheid <jscheid@ventanamicro.com> > > Cc: Richard Trauben <rtrauben@gmail.com> > > --- > > arch/riscv/include/asm/fixmap.h | 2 +- > > arch/riscv/include/asm/pgtable-64.h | 21 ++++++++++++--- > > arch/riscv/include/asm/pgtable-bits.h | 39 +++++++++++++++++++++++++-- > > arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++------- > > arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++ > > arch/riscv/mm/init.c | 5 ++++ > > 6 files changed, 126 insertions(+), 15 deletions(-) > > > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > > index 54cbf07fb4e9..5acd99d08e74 100644 > > --- a/arch/riscv/include/asm/fixmap.h > > +++ b/arch/riscv/include/asm/fixmap.h > > @@ -43,7 +43,7 @@ enum fixed_addresses { > > __end_of_fixed_addresses > > }; > > > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > > +#define FIXMAP_PAGE_IO PAGE_IOREMAP > > > > #define __early_set_fixmap __set_fixmap > > > > diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h > > index 228261aa9628..16d251282b1d 100644 > > --- a/arch/riscv/include/asm/pgtable-64.h > > +++ b/arch/riscv/include/asm/pgtable-64.h > > @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) > > set_pud(pudp, __pud(0)); > > } > > > > +static inline unsigned long _chg_of_pmd(pmd_t pmd) > > +{ > > + return (pmd_val(pmd) & _PAGE_CHG_MASK); > > +} > > + > > +static inline unsigned long _chg_of_pud(pud_t pud) > > +{ > > + return (pud_val(pud) & _PAGE_CHG_MASK); > > +} > > + > > +static inline unsigned long _chg_of_pte(pte_t pte) > > +{ > > + return (pte_val(pte) & _PAGE_CHG_MASK); > > +} > > + > > static inline pmd_t *pud_pgtable(pud_t pud) > > { > > - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); > > + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > } > > > > static inline struct page *pud_page(pud_t pud) > > { > > - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); > > + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > } > > > > static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > > > static inline unsigned long _pmd_pfn(pmd_t pmd) > > { > > - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; > > + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; > > } > > > > #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) > > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h > > index 2ee413912926..e5b0fce4ddc5 100644 > > --- a/arch/riscv/include/asm/pgtable-bits.h > > +++ b/arch/riscv/include/asm/pgtable-bits.h > > @@ -7,7 +7,7 @@ > > #define _ASM_RISCV_PGTABLE_BITS_H > > > > /* > > - * PTE format: > > + * rv32 PTE format: > > * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > * PFN reserved for SW D A G U X W R V > > */ > > @@ -24,6 +24,40 @@ > > #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ > > #define _PAGE_SOFT (1 << 8) /* Reserved for software */ > > > > +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) > > +/* > > + * rv64 PTE format: > > + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > + * N MT RSV PFN reserved for SW D A G U X W R V > > + * [62:61] Memory Type definitions: > > + * 00 - PMA Normal Cacheable, No change to implied PMA memory type > > + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > + * 11 - Rsvd Reserved for future standard use > > + */ > > +#define _SVPBMT_PMA 0UL > > +#define _SVPBMT_NC (1UL << 61) > > +#define _SVPBMT_IO (1UL << 62) > > +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) > > + > > +extern struct __svpbmt_struct { > > + unsigned long mask; > > + unsigned long pma; > > + unsigned long nocache; > > + unsigned long io; > > +} __svpbmt __cacheline_aligned; > > + > > +#define _PAGE_MASK __svpbmt.mask > > +#define _PAGE_PMA __svpbmt.pma > > +#define _PAGE_NOCACHE __svpbmt.nocache > > +#define _PAGE_IO __svpbmt.io > > +#else > > +#define _PAGE_MASK 0 > > +#define _PAGE_PMA 0 > > +#define _PAGE_NOCACHE 0 > > +#define _PAGE_IO 0 > > +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ > > + > > #define _PAGE_SPECIAL _PAGE_SOFT > > #define _PAGE_TABLE _PAGE_PRESENT > > > > @@ -38,7 +72,8 @@ > > /* Set of bits to preserve across pte_modify() */ > > #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ > > _PAGE_WRITE | _PAGE_EXEC | \ > > - _PAGE_USER | _PAGE_GLOBAL)) > > + _PAGE_USER | _PAGE_GLOBAL | \ > > + _PAGE_MASK)) > > /* > > * when all of R/W/X are zero, the PTE is a pointer to the next level > > * of the page table; otherwise, it is a leaf PTE. > > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > > index bf204e7c1f74..0f7a6541015f 100644 > > --- a/arch/riscv/include/asm/pgtable.h > > +++ b/arch/riscv/include/asm/pgtable.h > > @@ -138,7 +138,8 @@ > > | _PAGE_PRESENT \ > > | _PAGE_ACCESSED \ > > | _PAGE_DIRTY \ > > - | _PAGE_GLOBAL) > > + | _PAGE_GLOBAL \ > > + | _PAGE_PMA) > > > > #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) > > #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) > > @@ -148,11 +149,9 @@ > > > > #define PAGE_TABLE __pgprot(_PAGE_TABLE) > > > > -/* > > - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't > > - * change the properties of memory regions. > > - */ > > -#define _PAGE_IOREMAP _PAGE_KERNEL > > +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) > > + > > +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) > > > > extern pgd_t swapper_pg_dir[]; > > > > @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) > > > > static inline struct page *pmd_page(pmd_t pmd) > > { > > - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > } > > > > static inline unsigned long pmd_page_vaddr(pmd_t pmd) > > { > > - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > } > > > > static inline pte_t pmd_pte(pmd_t pmd) > > @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) > > /* Yields the page frame number (PFN) of a page table entry */ > > static inline unsigned long pte_pfn(pte_t pte) > > { > > - return (pte_val(pte) >> _PAGE_PFN_SHIFT); > > + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); > > } > > > > #define pte_page(x) pfn_to_page(pte_pfn(x)) > > @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > > return ptep_test_and_clear_young(vma, address, ptep); > > } > > > > +#define pgprot_noncached pgprot_noncached > > +static inline pgprot_t pgprot_noncached(pgprot_t _prot) > > +{ > > + unsigned long prot = pgprot_val(_prot); > > + > > + prot &= ~_PAGE_MASK; > > + prot |= _PAGE_IO; > > + > > + return __pgprot(prot); > > +} > > + > > +#define pgprot_writecombine pgprot_writecombine > > +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) > > +{ > > + unsigned long prot = pgprot_val(_prot); > > + > > + prot &= ~_PAGE_MASK; > > + prot |= _PAGE_NOCACHE; > > + > > + return __pgprot(prot); > > +} > > + > > /* > > * THP functions > > */ > > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > > index d959d207a40d..fa7480cb8b87 100644 > > --- a/arch/riscv/kernel/cpufeature.c > > +++ b/arch/riscv/kernel/cpufeature.c > > @@ -8,6 +8,7 @@ > > > > #include <linux/bitmap.h> > > #include <linux/of.h> > > +#include <linux/pgtable.h> > > #include <asm/processor.h> > > #include <asm/hwcap.h> > > #include <asm/smp.h> > > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > > } > > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > > > +static void __init mmu_supports_svpbmt(void) > > +{ > > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) > > + struct device_node *node; > > + const char *str; > > + > > + for_each_of_cpu_node(node) { > > + if (of_property_read_string(node, "mmu-type", &str)) > > + continue; > > + > > + if (!strncmp(str + 6, "none", 4)) > > + continue; > > + > > + if (of_property_read_string(node, "mmu", &str)) > > + continue; > > + > > + if (strncmp(str + 6, "svpmbt", 6)) > > + continue; > > + } > > + > > + __svpbmt.pma = _SVPBMT_PMA; > > + __svpbmt.nocache = _SVPBMT_NC; > > + __svpbmt.io = _SVPBMT_IO; > > + __svpbmt.mask = _SVPBMT_MASK; > > +#endif > > +} > > + > > +static void __init mmu_supports(void) > > +{ > > + mmu_supports_svpbmt(); > > +} > > + > > void __init riscv_fill_hwcap(void) > > { > > struct device_node *node; > > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > > size_t i, j, isa_len; > > static unsigned long isa2hwcap[256] = {0}; > > > > + mmu_supports(); > > + > > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > > index 24b2b8044602..e4e658165ee1 100644 > > --- a/arch/riscv/mm/init.c > > +++ b/arch/riscv/mm/init.c > > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > > return vmemmap_populate_basepages(start, end, node, NULL); > > } > > #endif > > + > > +#if defined(CONFIG_64BIT) > > +struct __svpbmt_struct __svpbmt __ro_after_init; > > +EXPORT_SYMBOL(__svpbmt); > > +#endif > > -- > > 2.25.4 > > > > > -- > Best Regards > Guo Ren > > ML: https://lore.kernel.org/linux-csky/ >
Hi, Jisheng Zhang, On Mon, Nov 29, 2021 at 9:44 PM Jisheng Zhang <jszhang@kernel.org> wrote: > > On Mon, 29 Nov 2021 09:40:07 +0800 > wefu@redhat.com wrote: > > > From: Wei Fu <wefu@redhat.com> > > > > This patch follows the standard pure RISC-V Svpbmt extension in > > privilege spec to solve the non-coherent SOC dma synchronization > > issues. > > > > Here is the svpbmt PTE format: > > | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > N MT RSW D A G U X W R V > > ^ > > > > Of the Reserved bits [63:54] in a leaf PTE, the high bit is already > > allocated (as the N bit), so bits [62:61] are used as the MT (aka > > MemType) field. This field specifies one of three memory types that > > are close equivalents (or equivalent in effect) to the three main x86 > > and ARMv8 memory types - as shown in the following table. > > > > RISC-V > > Encoding & > > MemType RISC-V Description > > ---------- ------------------------------------------------ > > 00 - PMA Normal Cacheable, No change to implied PMA memory type > > 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > 11 - Rsvd Reserved for future standard use > > > > The standard protection_map[] needn't be modified because the "PMA" > > type keeps the highest bits zero. And the whole modification is > > limited in the arch/riscv/* and using a global variable > > (__svpbmt) as _PAGE_MASK/IO/NOCACHE for pgprot_noncached > > (&writecombine) in pgtable.h. We also add _PAGE_CHG_MASK to filter > > PFN than before. > > > > Enable it in devicetree - (Add "riscv,svpbmt" in the mmu of cpu node) > > - mmu: > > riscv,svpmbt > > > > Signed-off-by: Wei Fu <wefu@redhat.com> > > Co-developed-by: Liu Shaohua <liush@allwinnertech.com> > > Signed-off-by: Liu Shaohua <liush@allwinnertech.com> > > Co-developed-by: Guo Ren <guoren@kernel.org> > > Signed-off-by: Guo Ren <guoren@kernel.org> > > Cc: Palmer Dabbelt <palmerdabbelt@google.com> > > Cc: Christoph Hellwig <hch@lst.de> > > Cc: Anup Patel <anup.patel@wdc.com> > > Cc: Arnd Bergmann <arnd@arndb.de> > > Cc: Atish Patra <atish.patra@wdc.com> > > Cc: Drew Fustini <drew@beagleboard.org> > > Cc: Wei Fu <wefu@redhat.com> > > Cc: Wei Wu <lazyparser@gmail.com> > > Cc: Chen-Yu Tsai <wens@csie.org> > > Cc: Maxime Ripard <maxime@cerno.tech> > > Cc: Daniel Lustig <dlustig@nvidia.com> > > Cc: Greg Favor <gfavor@ventanamicro.com> > > Cc: Andrea Mondelli <andrea.mondelli@huawei.com> > > Cc: Jonathan Behrens <behrensj@mit.edu> > > Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com> > > Cc: Bill Huffman <huffman@cadence.com> > > Cc: Nick Kossifidis <mick@ics.forth.gr> > > Cc: Allen Baum <allen.baum@esperantotech.com> > > Cc: Josh Scheid <jscheid@ventanamicro.com> > > Cc: Richard Trauben <rtrauben@gmail.com> > > --- > > arch/riscv/include/asm/fixmap.h | 2 +- > > arch/riscv/include/asm/pgtable-64.h | 21 ++++++++++++--- > > arch/riscv/include/asm/pgtable-bits.h | 39 +++++++++++++++++++++++++-- > > arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++------- > > arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++ > > arch/riscv/mm/init.c | 5 ++++ > > 6 files changed, 126 insertions(+), 15 deletions(-) > > > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > > index 54cbf07fb4e9..5acd99d08e74 100644 > > --- a/arch/riscv/include/asm/fixmap.h > > +++ b/arch/riscv/include/asm/fixmap.h > > @@ -43,7 +43,7 @@ enum fixed_addresses { > > __end_of_fixed_addresses > > }; > > > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > > +#define FIXMAP_PAGE_IO PAGE_IOREMAP > > > > #define __early_set_fixmap __set_fixmap > > > > diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h > > index 228261aa9628..16d251282b1d 100644 > > --- a/arch/riscv/include/asm/pgtable-64.h > > +++ b/arch/riscv/include/asm/pgtable-64.h > > @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) > > set_pud(pudp, __pud(0)); > > } > > > > +static inline unsigned long _chg_of_pmd(pmd_t pmd) > > +{ > > + return (pmd_val(pmd) & _PAGE_CHG_MASK); > > +} > > + > > +static inline unsigned long _chg_of_pud(pud_t pud) > > +{ > > + return (pud_val(pud) & _PAGE_CHG_MASK); > > +} > > + > > +static inline unsigned long _chg_of_pte(pte_t pte) > > +{ > > + return (pte_val(pte) & _PAGE_CHG_MASK); > > +} > > + > > static inline pmd_t *pud_pgtable(pud_t pud) > > { > > - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); > > + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > } > > > > static inline struct page *pud_page(pud_t pud) > > { > > - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); > > + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > } > > > > static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > > > static inline unsigned long _pmd_pfn(pmd_t pmd) > > { > > - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; > > + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; > > } > > > > #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) > > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h > > index 2ee413912926..e5b0fce4ddc5 100644 > > --- a/arch/riscv/include/asm/pgtable-bits.h > > +++ b/arch/riscv/include/asm/pgtable-bits.h > > @@ -7,7 +7,7 @@ > > #define _ASM_RISCV_PGTABLE_BITS_H > > > > /* > > - * PTE format: > > + * rv32 PTE format: > > * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > * PFN reserved for SW D A G U X W R V > > */ > > @@ -24,6 +24,40 @@ > > #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ > > #define _PAGE_SOFT (1 << 8) /* Reserved for software */ > > > > +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) > > +/* > > + * rv64 PTE format: > > + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > + * N MT RSV PFN reserved for SW D A G U X W R V > > + * [62:61] Memory Type definitions: > > + * 00 - PMA Normal Cacheable, No change to implied PMA memory type > > + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > + * 11 - Rsvd Reserved for future standard use > > + */ > > +#define _SVPBMT_PMA 0UL > > +#define _SVPBMT_NC (1UL << 61) > > +#define _SVPBMT_IO (1UL << 62) > > +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) > > + > > +extern struct __svpbmt_struct { > > + unsigned long mask; > > + unsigned long pma; > > + unsigned long nocache; > > + unsigned long io; > > +} __svpbmt __cacheline_aligned; > > + > > +#define _PAGE_MASK __svpbmt.mask > > +#define _PAGE_PMA __svpbmt.pma > > +#define _PAGE_NOCACHE __svpbmt.nocache > > +#define _PAGE_IO __svpbmt.io > > +#else > > +#define _PAGE_MASK 0 > > +#define _PAGE_PMA 0 > > +#define _PAGE_NOCACHE 0 > > +#define _PAGE_IO 0 > > +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ > > + > > #define _PAGE_SPECIAL _PAGE_SOFT > > #define _PAGE_TABLE _PAGE_PRESENT > > > > @@ -38,7 +72,8 @@ > > /* Set of bits to preserve across pte_modify() */ > > #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ > > _PAGE_WRITE | _PAGE_EXEC | \ > > - _PAGE_USER | _PAGE_GLOBAL)) > > + _PAGE_USER | _PAGE_GLOBAL | \ > > + _PAGE_MASK)) > > /* > > * when all of R/W/X are zero, the PTE is a pointer to the next level > > * of the page table; otherwise, it is a leaf PTE. > > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > > index bf204e7c1f74..0f7a6541015f 100644 > > --- a/arch/riscv/include/asm/pgtable.h > > +++ b/arch/riscv/include/asm/pgtable.h > > @@ -138,7 +138,8 @@ > > | _PAGE_PRESENT \ > > | _PAGE_ACCESSED \ > > | _PAGE_DIRTY \ > > - | _PAGE_GLOBAL) > > + | _PAGE_GLOBAL \ > > + | _PAGE_PMA) > > > > #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) > > #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) > > @@ -148,11 +149,9 @@ > > > > #define PAGE_TABLE __pgprot(_PAGE_TABLE) > > > > -/* > > - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't > > - * change the properties of memory regions. > > - */ > > -#define _PAGE_IOREMAP _PAGE_KERNEL > > +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) > > + > > +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) > > > > extern pgd_t swapper_pg_dir[]; > > > > @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) > > > > static inline struct page *pmd_page(pmd_t pmd) > > { > > - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > } > > > > static inline unsigned long pmd_page_vaddr(pmd_t pmd) > > { > > - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > } > > > > static inline pte_t pmd_pte(pmd_t pmd) > > @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) > > /* Yields the page frame number (PFN) of a page table entry */ > > static inline unsigned long pte_pfn(pte_t pte) > > { > > - return (pte_val(pte) >> _PAGE_PFN_SHIFT); > > + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); > > } > > > > #define pte_page(x) pfn_to_page(pte_pfn(x)) > > @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > > return ptep_test_and_clear_young(vma, address, ptep); > > } > > > > +#define pgprot_noncached pgprot_noncached > > +static inline pgprot_t pgprot_noncached(pgprot_t _prot) > > +{ > > + unsigned long prot = pgprot_val(_prot); > > + > > + prot &= ~_PAGE_MASK; > > + prot |= _PAGE_IO; > > + > > + return __pgprot(prot); > > +} > > + > > +#define pgprot_writecombine pgprot_writecombine > > +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) > > +{ > > + unsigned long prot = pgprot_val(_prot); > > + > > + prot &= ~_PAGE_MASK; > > + prot |= _PAGE_NOCACHE; > > + > > + return __pgprot(prot); > > +} > > + > > /* > > * THP functions > > */ > > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > > index d959d207a40d..fa7480cb8b87 100644 > > --- a/arch/riscv/kernel/cpufeature.c > > +++ b/arch/riscv/kernel/cpufeature.c > > @@ -8,6 +8,7 @@ > > > > #include <linux/bitmap.h> > > #include <linux/of.h> > > +#include <linux/pgtable.h> > > #include <asm/processor.h> > > #include <asm/hwcap.h> > > #include <asm/smp.h> > > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > > } > > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > > > +static void __init mmu_supports_svpbmt(void) > > +{ > > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) > > IIRC, Christoph suggested a CONFIG_RISCV_SVPBMT when reviewing v3. What > about that idea? Yes, sorry for missing it, yes, I think we can have something like this config ARCH_HAS_RISCV_SVPBMT bool default n any platform which needs this support, can just select ARCH_HAS_RISCV_SVPBMT and which is the best name? ARCH_HAS_RISCV_SVPBMT or just ARCH_HAS_SVPBMT ? > > > + struct device_node *node; > > + const char *str; > > + > > + for_each_of_cpu_node(node) { > > + if (of_property_read_string(node, "mmu-type", &str)) > > + continue; > > + > > + if (!strncmp(str + 6, "none", 4)) > > + continue; > > + > > + if (of_property_read_string(node, "mmu", &str)) > > + continue; > > + > > + if (strncmp(str + 6, "svpmbt", 6)) > > + continue; > > + } > > + > > + __svpbmt.pma = _SVPBMT_PMA; > > + __svpbmt.nocache = _SVPBMT_NC; > > + __svpbmt.io = _SVPBMT_IO; > > + __svpbmt.mask = _SVPBMT_MASK; > > +#endif > > +} > > + > > +static void __init mmu_supports(void) > > can we remove this function currently? Instead, directly call > mmu_supports_svpbmt()? > > > +{ > > + mmu_supports_svpbmt(); > > +} > > + > > void __init riscv_fill_hwcap(void) > > { > > struct device_node *node; > > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > > size_t i, j, isa_len; > > static unsigned long isa2hwcap[256] = {0}; > > > > + mmu_supports(); > > + > > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > > index 24b2b8044602..e4e658165ee1 100644 > > --- a/arch/riscv/mm/init.c > > +++ b/arch/riscv/mm/init.c > > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > > return vmemmap_populate_basepages(start, end, node, NULL); > > } > > #endif > > + > > +#if defined(CONFIG_64BIT) > > +struct __svpbmt_struct __svpbmt __ro_after_init; > > Added the structure for all RV64 including NOMMU case and those platforms > which doen't want SVPBMT at all, I believe Christoph's CONFIG_RISCV_SVPBMT > suggestion can solve this problem. see ARCH_HAS_RISCV_SVPBMT above . :-) > > > +EXPORT_SYMBOL(__svpbmt); > > +#endif >
On Wed, Dec 1, 2021 at 10:35 AM Wei Fu <wefu@redhat.com> wrote: > > Hi, Jisheng Zhang, > > On Mon, Nov 29, 2021 at 9:44 PM Jisheng Zhang <jszhang@kernel.org> wrote: > > > > On Mon, 29 Nov 2021 09:40:07 +0800 > > wefu@redhat.com wrote: > > > > > From: Wei Fu <wefu@redhat.com> > > > > > > This patch follows the standard pure RISC-V Svpbmt extension in > > > privilege spec to solve the non-coherent SOC dma synchronization > > > issues. > > > > > > Here is the svpbmt PTE format: > > > | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > > N MT RSW D A G U X W R V > > > ^ > > > > > > Of the Reserved bits [63:54] in a leaf PTE, the high bit is already > > > allocated (as the N bit), so bits [62:61] are used as the MT (aka > > > MemType) field. This field specifies one of three memory types that > > > are close equivalents (or equivalent in effect) to the three main x86 > > > and ARMv8 memory types - as shown in the following table. > > > > > > RISC-V > > > Encoding & > > > MemType RISC-V Description > > > ---------- ------------------------------------------------ > > > 00 - PMA Normal Cacheable, No change to implied PMA memory type > > > 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > > 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > > 11 - Rsvd Reserved for future standard use > > > > > > The standard protection_map[] needn't be modified because the "PMA" > > > type keeps the highest bits zero. And the whole modification is > > > limited in the arch/riscv/* and using a global variable > > > (__svpbmt) as _PAGE_MASK/IO/NOCACHE for pgprot_noncached > > > (&writecombine) in pgtable.h. We also add _PAGE_CHG_MASK to filter > > > PFN than before. > > > > > > Enable it in devicetree - (Add "riscv,svpbmt" in the mmu of cpu node) > > > - mmu: > > > riscv,svpmbt > > > > > > Signed-off-by: Wei Fu <wefu@redhat.com> > > > Co-developed-by: Liu Shaohua <liush@allwinnertech.com> > > > Signed-off-by: Liu Shaohua <liush@allwinnertech.com> > > > Co-developed-by: Guo Ren <guoren@kernel.org> > > > Signed-off-by: Guo Ren <guoren@kernel.org> > > > Cc: Palmer Dabbelt <palmerdabbelt@google.com> > > > Cc: Christoph Hellwig <hch@lst.de> > > > Cc: Anup Patel <anup.patel@wdc.com> > > > Cc: Arnd Bergmann <arnd@arndb.de> > > > Cc: Atish Patra <atish.patra@wdc.com> > > > Cc: Drew Fustini <drew@beagleboard.org> > > > Cc: Wei Fu <wefu@redhat.com> > > > Cc: Wei Wu <lazyparser@gmail.com> > > > Cc: Chen-Yu Tsai <wens@csie.org> > > > Cc: Maxime Ripard <maxime@cerno.tech> > > > Cc: Daniel Lustig <dlustig@nvidia.com> > > > Cc: Greg Favor <gfavor@ventanamicro.com> > > > Cc: Andrea Mondelli <andrea.mondelli@huawei.com> > > > Cc: Jonathan Behrens <behrensj@mit.edu> > > > Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com> > > > Cc: Bill Huffman <huffman@cadence.com> > > > Cc: Nick Kossifidis <mick@ics.forth.gr> > > > Cc: Allen Baum <allen.baum@esperantotech.com> > > > Cc: Josh Scheid <jscheid@ventanamicro.com> > > > Cc: Richard Trauben <rtrauben@gmail.com> > > > --- > > > arch/riscv/include/asm/fixmap.h | 2 +- > > > arch/riscv/include/asm/pgtable-64.h | 21 ++++++++++++--- > > > arch/riscv/include/asm/pgtable-bits.h | 39 +++++++++++++++++++++++++-- > > > arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++------- > > > arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++ > > > arch/riscv/mm/init.c | 5 ++++ > > > 6 files changed, 126 insertions(+), 15 deletions(-) > > > > > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > > > index 54cbf07fb4e9..5acd99d08e74 100644 > > > --- a/arch/riscv/include/asm/fixmap.h > > > +++ b/arch/riscv/include/asm/fixmap.h > > > @@ -43,7 +43,7 @@ enum fixed_addresses { > > > __end_of_fixed_addresses > > > }; > > > > > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > > > +#define FIXMAP_PAGE_IO PAGE_IOREMAP > > > > > > #define __early_set_fixmap __set_fixmap > > > > > > diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h > > > index 228261aa9628..16d251282b1d 100644 > > > --- a/arch/riscv/include/asm/pgtable-64.h > > > +++ b/arch/riscv/include/asm/pgtable-64.h > > > @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) > > > set_pud(pudp, __pud(0)); > > > } > > > > > > +static inline unsigned long _chg_of_pmd(pmd_t pmd) > > > +{ > > > + return (pmd_val(pmd) & _PAGE_CHG_MASK); > > > +} > > > + > > > +static inline unsigned long _chg_of_pud(pud_t pud) > > > +{ > > > + return (pud_val(pud) & _PAGE_CHG_MASK); > > > +} > > > + > > > +static inline unsigned long _chg_of_pte(pte_t pte) > > > +{ > > > + return (pte_val(pte) & _PAGE_CHG_MASK); > > > +} > > > + > > > static inline pmd_t *pud_pgtable(pud_t pud) > > > { > > > - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); > > > + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > > } > > > > > > static inline struct page *pud_page(pud_t pud) > > > { > > > - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); > > > + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > > } > > > > > > static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > > @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > > > > > static inline unsigned long _pmd_pfn(pmd_t pmd) > > > { > > > - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; > > > + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; > > > } > > > > > > #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) > > > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h > > > index 2ee413912926..e5b0fce4ddc5 100644 > > > --- a/arch/riscv/include/asm/pgtable-bits.h > > > +++ b/arch/riscv/include/asm/pgtable-bits.h > > > @@ -7,7 +7,7 @@ > > > #define _ASM_RISCV_PGTABLE_BITS_H > > > > > > /* > > > - * PTE format: > > > + * rv32 PTE format: > > > * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > > * PFN reserved for SW D A G U X W R V > > > */ > > > @@ -24,6 +24,40 @@ > > > #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ > > > #define _PAGE_SOFT (1 << 8) /* Reserved for software */ > > > > > > +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) > > > +/* > > > + * rv64 PTE format: > > > + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > > + * N MT RSV PFN reserved for SW D A G U X W R V > > > + * [62:61] Memory Type definitions: > > > + * 00 - PMA Normal Cacheable, No change to implied PMA memory type > > > + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > > + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > > + * 11 - Rsvd Reserved for future standard use > > > + */ > > > +#define _SVPBMT_PMA 0UL > > > +#define _SVPBMT_NC (1UL << 61) > > > +#define _SVPBMT_IO (1UL << 62) > > > +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) > > > + > > > +extern struct __svpbmt_struct { > > > + unsigned long mask; > > > + unsigned long pma; > > > + unsigned long nocache; > > > + unsigned long io; > > > +} __svpbmt __cacheline_aligned; > > > + > > > +#define _PAGE_MASK __svpbmt.mask > > > +#define _PAGE_PMA __svpbmt.pma > > > +#define _PAGE_NOCACHE __svpbmt.nocache > > > +#define _PAGE_IO __svpbmt.io > > > +#else > > > +#define _PAGE_MASK 0 > > > +#define _PAGE_PMA 0 > > > +#define _PAGE_NOCACHE 0 > > > +#define _PAGE_IO 0 > > > +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ > > > + > > > #define _PAGE_SPECIAL _PAGE_SOFT > > > #define _PAGE_TABLE _PAGE_PRESENT > > > > > > @@ -38,7 +72,8 @@ > > > /* Set of bits to preserve across pte_modify() */ > > > #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ > > > _PAGE_WRITE | _PAGE_EXEC | \ > > > - _PAGE_USER | _PAGE_GLOBAL)) > > > + _PAGE_USER | _PAGE_GLOBAL | \ > > > + _PAGE_MASK)) > > > /* > > > * when all of R/W/X are zero, the PTE is a pointer to the next level > > > * of the page table; otherwise, it is a leaf PTE. > > > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > > > index bf204e7c1f74..0f7a6541015f 100644 > > > --- a/arch/riscv/include/asm/pgtable.h > > > +++ b/arch/riscv/include/asm/pgtable.h > > > @@ -138,7 +138,8 @@ > > > | _PAGE_PRESENT \ > > > | _PAGE_ACCESSED \ > > > | _PAGE_DIRTY \ > > > - | _PAGE_GLOBAL) > > > + | _PAGE_GLOBAL \ > > > + | _PAGE_PMA) > > > > > > #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) > > > #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) > > > @@ -148,11 +149,9 @@ > > > > > > #define PAGE_TABLE __pgprot(_PAGE_TABLE) > > > > > > -/* > > > - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't > > > - * change the properties of memory regions. > > > - */ > > > -#define _PAGE_IOREMAP _PAGE_KERNEL > > > +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) > > > + > > > +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) > > > > > > extern pgd_t swapper_pg_dir[]; > > > > > > @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) > > > > > > static inline struct page *pmd_page(pmd_t pmd) > > > { > > > - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > > + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > > } > > > > > > static inline unsigned long pmd_page_vaddr(pmd_t pmd) > > > { > > > - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > > + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > > } > > > > > > static inline pte_t pmd_pte(pmd_t pmd) > > > @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) > > > /* Yields the page frame number (PFN) of a page table entry */ > > > static inline unsigned long pte_pfn(pte_t pte) > > > { > > > - return (pte_val(pte) >> _PAGE_PFN_SHIFT); > > > + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); > > > } > > > > > > #define pte_page(x) pfn_to_page(pte_pfn(x)) > > > @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > > > return ptep_test_and_clear_young(vma, address, ptep); > > > } > > > > > > +#define pgprot_noncached pgprot_noncached > > > +static inline pgprot_t pgprot_noncached(pgprot_t _prot) > > > +{ > > > + unsigned long prot = pgprot_val(_prot); > > > + > > > + prot &= ~_PAGE_MASK; > > > + prot |= _PAGE_IO; > > > + > > > + return __pgprot(prot); > > > +} > > > + > > > +#define pgprot_writecombine pgprot_writecombine > > > +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) > > > +{ > > > + unsigned long prot = pgprot_val(_prot); > > > + > > > + prot &= ~_PAGE_MASK; > > > + prot |= _PAGE_NOCACHE; > > > + > > > + return __pgprot(prot); > > > +} > > > + > > > /* > > > * THP functions > > > */ > > > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > > > index d959d207a40d..fa7480cb8b87 100644 > > > --- a/arch/riscv/kernel/cpufeature.c > > > +++ b/arch/riscv/kernel/cpufeature.c > > > @@ -8,6 +8,7 @@ > > > > > > #include <linux/bitmap.h> > > > #include <linux/of.h> > > > +#include <linux/pgtable.h> > > > #include <asm/processor.h> > > > #include <asm/hwcap.h> > > > #include <asm/smp.h> > > > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > > > } > > > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > > > > > +static void __init mmu_supports_svpbmt(void) > > > +{ > > > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) > > > > IIRC, Christoph suggested a CONFIG_RISCV_SVPBMT when reviewing v3. What > > about that idea? > > Yes, sorry for missing it, yes, I think we can have something like this > > config ARCH_HAS_RISCV_SVPBMT > bool > default n > > any platform which needs this support, can just > > select ARCH_HAS_RISCV_SVPBMT > > and which is the best name? ARCH_HAS_RISCV_SVPBMT or just ARCH_HAS_SVPBMT ? > > > > > > + struct device_node *node; > > > + const char *str; > > > + > > > + for_each_of_cpu_node(node) { > > > + if (of_property_read_string(node, "mmu-type", &str)) > > > + continue; > > > + > > > + if (!strncmp(str + 6, "none", 4)) > > > + continue; > > > + > > > + if (of_property_read_string(node, "mmu", &str)) > > > + continue; > > > + > > > + if (strncmp(str + 6, "svpmbt", 6)) > > > + continue; > > > + } > > > + > > > + __svpbmt.pma = _SVPBMT_PMA; > > > + __svpbmt.nocache = _SVPBMT_NC; > > > + __svpbmt.io = _SVPBMT_IO; > > > + __svpbmt.mask = _SVPBMT_MASK; > > > +#endif > > > +} > > > + > > > +static void __init mmu_supports(void) > > > > can we remove this function currently? Instead, directly call > > mmu_supports_svpbmt()? > > > > > +{ > > > + mmu_supports_svpbmt(); > > > +} > > > + > > > void __init riscv_fill_hwcap(void) > > > { > > > struct device_node *node; > > > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > > > size_t i, j, isa_len; > > > static unsigned long isa2hwcap[256] = {0}; > > > > > > + mmu_supports(); > > > + > > > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > > > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > > > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > > > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > > > index 24b2b8044602..e4e658165ee1 100644 > > > --- a/arch/riscv/mm/init.c > > > +++ b/arch/riscv/mm/init.c > > > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > > > return vmemmap_populate_basepages(start, end, node, NULL); > > > } > > > #endif > > > + > > > +#if defined(CONFIG_64BIT) > > > +struct __svpbmt_struct __svpbmt __ro_after_init; > > > > Added the structure for all RV64 including NOMMU case and those platforms > > which doen't want SVPBMT at all, I believe Christoph's CONFIG_RISCV_SVPBMT > > suggestion can solve this problem. > > see ARCH_HAS_RISCV_SVPBMT above . :-) This config option will not align with the goal of having a unified kernel image which works on HW with/without Svpmbt. Better to explore code patching approaches which have zero overhead. Regards, Anup > > > > > > +EXPORT_SYMBOL(__svpbmt); > > > +#endif > > > > > _______________________________________________ > linux-riscv mailing list > linux-riscv@lists.infradead.org > http://lists.infradead.org/mailman/listinfo/linux-riscv
On Wed, 1 Dec 2021 11:48:44 +0530 Anup Patel <anup@brainfault.org> wrote: > > > > */ > > > > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > > > > index d959d207a40d..fa7480cb8b87 100644 > > > > --- a/arch/riscv/kernel/cpufeature.c > > > > +++ b/arch/riscv/kernel/cpufeature.c > > > > @@ -8,6 +8,7 @@ > > > > > > > > #include <linux/bitmap.h> > > > > #include <linux/of.h> > > > > +#include <linux/pgtable.h> > > > > #include <asm/processor.h> > > > > #include <asm/hwcap.h> > > > > #include <asm/smp.h> > > > > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > > > > } > > > > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > > > > > > > +static void __init mmu_supports_svpbmt(void) > > > > +{ > > > > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) > > > > > > IIRC, Christoph suggested a CONFIG_RISCV_SVPBMT when reviewing v3. What > > > about that idea? > > > > Yes, sorry for missing it, yes, I think we can have something like this > > > > config ARCH_HAS_RISCV_SVPBMT > > bool > > default n > > > > any platform which needs this support, can just > > > > select ARCH_HAS_RISCV_SVPBMT > > > > and which is the best name? ARCH_HAS_RISCV_SVPBMT or just ARCH_HAS_SVPBMT ? > > > > > > > > > + struct device_node *node; > > > > + const char *str; > > > > + > > > > + for_each_of_cpu_node(node) { > > > > + if (of_property_read_string(node, "mmu-type", &str)) > > > > + continue; > > > > + > > > > + if (!strncmp(str + 6, "none", 4)) > > > > + continue; > > > > + > > > > + if (of_property_read_string(node, "mmu", &str)) > > > > + continue; > > > > + > > > > + if (strncmp(str + 6, "svpmbt", 6)) > > > > + continue; > > > > + } > > > > + > > > > + __svpbmt.pma = _SVPBMT_PMA; > > > > + __svpbmt.nocache = _SVPBMT_NC; > > > > + __svpbmt.io = _SVPBMT_IO; > > > > + __svpbmt.mask = _SVPBMT_MASK; > > > > +#endif > > > > +} > > > > + > > > > +static void __init mmu_supports(void) > > > > > > can we remove this function currently? Instead, directly call > > > mmu_supports_svpbmt()? > > > > > > > +{ > > > > + mmu_supports_svpbmt(); > > > > +} > > > > + > > > > void __init riscv_fill_hwcap(void) > > > > { > > > > struct device_node *node; > > > > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > > > > size_t i, j, isa_len; > > > > static unsigned long isa2hwcap[256] = {0}; > > > > > > > > + mmu_supports(); > > > > + > > > > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > > > > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > > > > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > > > > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > > > > index 24b2b8044602..e4e658165ee1 100644 > > > > --- a/arch/riscv/mm/init.c > > > > +++ b/arch/riscv/mm/init.c > > > > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > > > > return vmemmap_populate_basepages(start, end, node, NULL); > > > > } > > > > #endif > > > > + > > > > +#if defined(CONFIG_64BIT) > > > > +struct __svpbmt_struct __svpbmt __ro_after_init; > > > > > > Added the structure for all RV64 including NOMMU case and those platforms > > > which doen't want SVPBMT at all, I believe Christoph's CONFIG_RISCV_SVPBMT > > > suggestion can solve this problem. > > > > see ARCH_HAS_RISCV_SVPBMT above . :-) > > This config option will not align with the goal of having a unified > kernel image which works on HW with/without Svpmbt. Just my thoughts: If disable this option, HW without Svpbmt can work as before; Hw with Svpbmt will only have a basic working, those DMA etc can't work. If enable this option, HW without Svpbmt can work as well, but with a bit overhead and waste. HW with Svpbmt can work. So this option gives those platforms which doesn't need Svpbmt a chance to totally disable it. But linux distributions which want a uniified Image usually enable features as much as possible, so IMHO, this config option can still meet unified kernel image requirement. > > Better to explore code patching approaches which have zero > overhead. It would be nice if the Svpbmt can be supported via. coding patching tech. Thanks
Hi Anup, On Wed, Dec 1, 2021 at 2:19 PM Anup Patel <anup@brainfault.org> wrote: > > On Wed, Dec 1, 2021 at 10:35 AM Wei Fu <wefu@redhat.com> wrote: > > > > Hi, Jisheng Zhang, > > > > On Mon, Nov 29, 2021 at 9:44 PM Jisheng Zhang <jszhang@kernel.org> wrote: > > > > > > On Mon, 29 Nov 2021 09:40:07 +0800 > > > wefu@redhat.com wrote: > > > > > > > From: Wei Fu <wefu@redhat.com> > > > > > > > > This patch follows the standard pure RISC-V Svpbmt extension in > > > > privilege spec to solve the non-coherent SOC dma synchronization > > > > issues. > > > > > > > > Here is the svpbmt PTE format: > > > > | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > > > N MT RSW D A G U X W R V > > > > ^ > > > > > > > > Of the Reserved bits [63:54] in a leaf PTE, the high bit is already > > > > allocated (as the N bit), so bits [62:61] are used as the MT (aka > > > > MemType) field. This field specifies one of three memory types that > > > > are close equivalents (or equivalent in effect) to the three main x86 > > > > and ARMv8 memory types - as shown in the following table. > > > > > > > > RISC-V > > > > Encoding & > > > > MemType RISC-V Description > > > > ---------- ------------------------------------------------ > > > > 00 - PMA Normal Cacheable, No change to implied PMA memory type > > > > 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > > > 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > > > 11 - Rsvd Reserved for future standard use > > > > > > > > The standard protection_map[] needn't be modified because the "PMA" > > > > type keeps the highest bits zero. And the whole modification is > > > > limited in the arch/riscv/* and using a global variable > > > > (__svpbmt) as _PAGE_MASK/IO/NOCACHE for pgprot_noncached > > > > (&writecombine) in pgtable.h. We also add _PAGE_CHG_MASK to filter > > > > PFN than before. > > > > > > > > Enable it in devicetree - (Add "riscv,svpbmt" in the mmu of cpu node) > > > > - mmu: > > > > riscv,svpmbt > > > > > > > > Signed-off-by: Wei Fu <wefu@redhat.com> > > > > Co-developed-by: Liu Shaohua <liush@allwinnertech.com> > > > > Signed-off-by: Liu Shaohua <liush@allwinnertech.com> > > > > Co-developed-by: Guo Ren <guoren@kernel.org> > > > > Signed-off-by: Guo Ren <guoren@kernel.org> > > > > Cc: Palmer Dabbelt <palmerdabbelt@google.com> > > > > Cc: Christoph Hellwig <hch@lst.de> > > > > Cc: Anup Patel <anup.patel@wdc.com> > > > > Cc: Arnd Bergmann <arnd@arndb.de> > > > > Cc: Atish Patra <atish.patra@wdc.com> > > > > Cc: Drew Fustini <drew@beagleboard.org> > > > > Cc: Wei Fu <wefu@redhat.com> > > > > Cc: Wei Wu <lazyparser@gmail.com> > > > > Cc: Chen-Yu Tsai <wens@csie.org> > > > > Cc: Maxime Ripard <maxime@cerno.tech> > > > > Cc: Daniel Lustig <dlustig@nvidia.com> > > > > Cc: Greg Favor <gfavor@ventanamicro.com> > > > > Cc: Andrea Mondelli <andrea.mondelli@huawei.com> > > > > Cc: Jonathan Behrens <behrensj@mit.edu> > > > > Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com> > > > > Cc: Bill Huffman <huffman@cadence.com> > > > > Cc: Nick Kossifidis <mick@ics.forth.gr> > > > > Cc: Allen Baum <allen.baum@esperantotech.com> > > > > Cc: Josh Scheid <jscheid@ventanamicro.com> > > > > Cc: Richard Trauben <rtrauben@gmail.com> > > > > --- > > > > arch/riscv/include/asm/fixmap.h | 2 +- > > > > arch/riscv/include/asm/pgtable-64.h | 21 ++++++++++++--- > > > > arch/riscv/include/asm/pgtable-bits.h | 39 +++++++++++++++++++++++++-- > > > > arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++------- > > > > arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++ > > > > arch/riscv/mm/init.c | 5 ++++ > > > > 6 files changed, 126 insertions(+), 15 deletions(-) > > > > > > > > diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h > > > > index 54cbf07fb4e9..5acd99d08e74 100644 > > > > --- a/arch/riscv/include/asm/fixmap.h > > > > +++ b/arch/riscv/include/asm/fixmap.h > > > > @@ -43,7 +43,7 @@ enum fixed_addresses { > > > > __end_of_fixed_addresses > > > > }; > > > > > > > > -#define FIXMAP_PAGE_IO PAGE_KERNEL > > > > +#define FIXMAP_PAGE_IO PAGE_IOREMAP > > > > > > > > #define __early_set_fixmap __set_fixmap > > > > > > > > diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h > > > > index 228261aa9628..16d251282b1d 100644 > > > > --- a/arch/riscv/include/asm/pgtable-64.h > > > > +++ b/arch/riscv/include/asm/pgtable-64.h > > > > @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) > > > > set_pud(pudp, __pud(0)); > > > > } > > > > > > > > +static inline unsigned long _chg_of_pmd(pmd_t pmd) > > > > +{ > > > > + return (pmd_val(pmd) & _PAGE_CHG_MASK); > > > > +} > > > > + > > > > +static inline unsigned long _chg_of_pud(pud_t pud) > > > > +{ > > > > + return (pud_val(pud) & _PAGE_CHG_MASK); > > > > +} > > > > + > > > > +static inline unsigned long _chg_of_pte(pte_t pte) > > > > +{ > > > > + return (pte_val(pte) & _PAGE_CHG_MASK); > > > > +} > > > > + > > > > static inline pmd_t *pud_pgtable(pud_t pud) > > > > { > > > > - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); > > > > + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > > > } > > > > > > > > static inline struct page *pud_page(pud_t pud) > > > > { > > > > - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); > > > > + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); > > > > } > > > > > > > > static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > > > @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) > > > > > > > > static inline unsigned long _pmd_pfn(pmd_t pmd) > > > > { > > > > - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; > > > > + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; > > > > } > > > > > > > > #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) > > > > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h > > > > index 2ee413912926..e5b0fce4ddc5 100644 > > > > --- a/arch/riscv/include/asm/pgtable-bits.h > > > > +++ b/arch/riscv/include/asm/pgtable-bits.h > > > > @@ -7,7 +7,7 @@ > > > > #define _ASM_RISCV_PGTABLE_BITS_H > > > > > > > > /* > > > > - * PTE format: > > > > + * rv32 PTE format: > > > > * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > > > * PFN reserved for SW D A G U X W R V > > > > */ > > > > @@ -24,6 +24,40 @@ > > > > #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ > > > > #define _PAGE_SOFT (1 << 8) /* Reserved for software */ > > > > > > > > +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) > > > > +/* > > > > + * rv64 PTE format: > > > > + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 > > > > + * N MT RSV PFN reserved for SW D A G U X W R V > > > > + * [62:61] Memory Type definitions: > > > > + * 00 - PMA Normal Cacheable, No change to implied PMA memory type > > > > + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory > > > > + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory > > > > + * 11 - Rsvd Reserved for future standard use > > > > + */ > > > > +#define _SVPBMT_PMA 0UL > > > > +#define _SVPBMT_NC (1UL << 61) > > > > +#define _SVPBMT_IO (1UL << 62) > > > > +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) > > > > + > > > > +extern struct __svpbmt_struct { > > > > + unsigned long mask; > > > > + unsigned long pma; > > > > + unsigned long nocache; > > > > + unsigned long io; > > > > +} __svpbmt __cacheline_aligned; > > > > + > > > > +#define _PAGE_MASK __svpbmt.mask > > > > +#define _PAGE_PMA __svpbmt.pma > > > > +#define _PAGE_NOCACHE __svpbmt.nocache > > > > +#define _PAGE_IO __svpbmt.io > > > > +#else > > > > +#define _PAGE_MASK 0 > > > > +#define _PAGE_PMA 0 > > > > +#define _PAGE_NOCACHE 0 > > > > +#define _PAGE_IO 0 > > > > +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ > > > > + > > > > #define _PAGE_SPECIAL _PAGE_SOFT > > > > #define _PAGE_TABLE _PAGE_PRESENT > > > > > > > > @@ -38,7 +72,8 @@ > > > > /* Set of bits to preserve across pte_modify() */ > > > > #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ > > > > _PAGE_WRITE | _PAGE_EXEC | \ > > > > - _PAGE_USER | _PAGE_GLOBAL)) > > > > + _PAGE_USER | _PAGE_GLOBAL | \ > > > > + _PAGE_MASK)) > > > > /* > > > > * when all of R/W/X are zero, the PTE is a pointer to the next level > > > > * of the page table; otherwise, it is a leaf PTE. > > > > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h > > > > index bf204e7c1f74..0f7a6541015f 100644 > > > > --- a/arch/riscv/include/asm/pgtable.h > > > > +++ b/arch/riscv/include/asm/pgtable.h > > > > @@ -138,7 +138,8 @@ > > > > | _PAGE_PRESENT \ > > > > | _PAGE_ACCESSED \ > > > > | _PAGE_DIRTY \ > > > > - | _PAGE_GLOBAL) > > > > + | _PAGE_GLOBAL \ > > > > + | _PAGE_PMA) > > > > > > > > #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) > > > > #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) > > > > @@ -148,11 +149,9 @@ > > > > > > > > #define PAGE_TABLE __pgprot(_PAGE_TABLE) > > > > > > > > -/* > > > > - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't > > > > - * change the properties of memory regions. > > > > - */ > > > > -#define _PAGE_IOREMAP _PAGE_KERNEL > > > > +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) > > > > + > > > > +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) > > > > > > > > extern pgd_t swapper_pg_dir[]; > > > > > > > > @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) > > > > > > > > static inline struct page *pmd_page(pmd_t pmd) > > > > { > > > > - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > > > + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > > > } > > > > > > > > static inline unsigned long pmd_page_vaddr(pmd_t pmd) > > > > { > > > > - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); > > > > + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); > > > > } > > > > > > > > static inline pte_t pmd_pte(pmd_t pmd) > > > > @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) > > > > /* Yields the page frame number (PFN) of a page table entry */ > > > > static inline unsigned long pte_pfn(pte_t pte) > > > > { > > > > - return (pte_val(pte) >> _PAGE_PFN_SHIFT); > > > > + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); > > > > } > > > > > > > > #define pte_page(x) pfn_to_page(pte_pfn(x)) > > > > @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > > > > return ptep_test_and_clear_young(vma, address, ptep); > > > > } > > > > > > > > +#define pgprot_noncached pgprot_noncached > > > > +static inline pgprot_t pgprot_noncached(pgprot_t _prot) > > > > +{ > > > > + unsigned long prot = pgprot_val(_prot); > > > > + > > > > + prot &= ~_PAGE_MASK; > > > > + prot |= _PAGE_IO; > > > > + > > > > + return __pgprot(prot); > > > > +} > > > > + > > > > +#define pgprot_writecombine pgprot_writecombine > > > > +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) > > > > +{ > > > > + unsigned long prot = pgprot_val(_prot); > > > > + > > > > + prot &= ~_PAGE_MASK; > > > > + prot |= _PAGE_NOCACHE; > > > > + > > > > + return __pgprot(prot); > > > > +} > > > > + > > > > /* > > > > * THP functions > > > > */ > > > > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c > > > > index d959d207a40d..fa7480cb8b87 100644 > > > > --- a/arch/riscv/kernel/cpufeature.c > > > > +++ b/arch/riscv/kernel/cpufeature.c > > > > @@ -8,6 +8,7 @@ > > > > > > > > #include <linux/bitmap.h> > > > > #include <linux/of.h> > > > > +#include <linux/pgtable.h> > > > > #include <asm/processor.h> > > > > #include <asm/hwcap.h> > > > > #include <asm/smp.h> > > > > @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) > > > > } > > > > EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); > > > > > > > > +static void __init mmu_supports_svpbmt(void) > > > > +{ > > > > +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) > > > > > > IIRC, Christoph suggested a CONFIG_RISCV_SVPBMT when reviewing v3. What > > > about that idea? > > > > Yes, sorry for missing it, yes, I think we can have something like this > > > > config ARCH_HAS_RISCV_SVPBMT > > bool > > default n > > > > any platform which needs this support, can just > > > > select ARCH_HAS_RISCV_SVPBMT > > > > and which is the best name? ARCH_HAS_RISCV_SVPBMT or just ARCH_HAS_SVPBMT ? > > > > > > > > > + struct device_node *node; > > > > + const char *str; > > > > + > > > > + for_each_of_cpu_node(node) { > > > > + if (of_property_read_string(node, "mmu-type", &str)) > > > > + continue; > > > > + > > > > + if (!strncmp(str + 6, "none", 4)) > > > > + continue; > > > > + > > > > + if (of_property_read_string(node, "mmu", &str)) > > > > + continue; > > > > + > > > > + if (strncmp(str + 6, "svpmbt", 6)) > > > > + continue; > > > > + } > > > > + > > > > + __svpbmt.pma = _SVPBMT_PMA; > > > > + __svpbmt.nocache = _SVPBMT_NC; > > > > + __svpbmt.io = _SVPBMT_IO; > > > > + __svpbmt.mask = _SVPBMT_MASK; > > > > +#endif > > > > +} > > > > + > > > > +static void __init mmu_supports(void) > > > > > > can we remove this function currently? Instead, directly call > > > mmu_supports_svpbmt()? > > > > > > > +{ > > > > + mmu_supports_svpbmt(); > > > > +} > > > > + > > > > void __init riscv_fill_hwcap(void) > > > > { > > > > struct device_node *node; > > > > @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) > > > > size_t i, j, isa_len; > > > > static unsigned long isa2hwcap[256] = {0}; > > > > > > > > + mmu_supports(); > > > > + > > > > isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; > > > > isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; > > > > isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; > > > > diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c > > > > index 24b2b8044602..e4e658165ee1 100644 > > > > --- a/arch/riscv/mm/init.c > > > > +++ b/arch/riscv/mm/init.c > > > > @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, > > > > return vmemmap_populate_basepages(start, end, node, NULL); > > > > } > > > > #endif > > > > + > > > > +#if defined(CONFIG_64BIT) > > > > +struct __svpbmt_struct __svpbmt __ro_after_init; > > > > > > Added the structure for all RV64 including NOMMU case and those platforms > > > which doen't want SVPBMT at all, I believe Christoph's CONFIG_RISCV_SVPBMT > > > suggestion can solve this problem. > > > > see ARCH_HAS_RISCV_SVPBMT above . :-) > > This config option will not align with the goal of having a unified > kernel image which works on HW with/without Svpmbt. > > Better to explore code patching approaches which have zero > overhead. Sure, I think Heiko has some Idea about code patching , and I will wait for his new patches for this mechanism > > Regards, > Anup > > > > > > > > > > +EXPORT_SYMBOL(__svpbmt); > > > > +#endif > > > > > > > > > _______________________________________________ > > linux-riscv mailing list > > linux-riscv@lists.infradead.org > > http://lists.infradead.org/mailman/listinfo/linux-riscv >
diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h index 54cbf07fb4e9..5acd99d08e74 100644 --- a/arch/riscv/include/asm/fixmap.h +++ b/arch/riscv/include/asm/fixmap.h @@ -43,7 +43,7 @@ enum fixed_addresses { __end_of_fixed_addresses }; -#define FIXMAP_PAGE_IO PAGE_KERNEL +#define FIXMAP_PAGE_IO PAGE_IOREMAP #define __early_set_fixmap __set_fixmap diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 228261aa9628..16d251282b1d 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -59,14 +59,29 @@ static inline void pud_clear(pud_t *pudp) set_pud(pudp, __pud(0)); } +static inline unsigned long _chg_of_pmd(pmd_t pmd) +{ + return (pmd_val(pmd) & _PAGE_CHG_MASK); +} + +static inline unsigned long _chg_of_pud(pud_t pud) +{ + return (pud_val(pud) & _PAGE_CHG_MASK); +} + +static inline unsigned long _chg_of_pte(pte_t pte) +{ + return (pte_val(pte) & _PAGE_CHG_MASK); +} + static inline pmd_t *pud_pgtable(pud_t pud) { - return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); + return (pmd_t *)pfn_to_virt(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); } static inline struct page *pud_page(pud_t pud) { - return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT); + return pfn_to_page(_chg_of_pud(pud) >> _PAGE_PFN_SHIFT); } static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) @@ -76,7 +91,7 @@ static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) static inline unsigned long _pmd_pfn(pmd_t pmd) { - return pmd_val(pmd) >> _PAGE_PFN_SHIFT; + return _chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT; } #define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h index 2ee413912926..e5b0fce4ddc5 100644 --- a/arch/riscv/include/asm/pgtable-bits.h +++ b/arch/riscv/include/asm/pgtable-bits.h @@ -7,7 +7,7 @@ #define _ASM_RISCV_PGTABLE_BITS_H /* - * PTE format: + * rv32 PTE format: * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 * PFN reserved for SW D A G U X W R V */ @@ -24,6 +24,40 @@ #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ #define _PAGE_SOFT (1 << 8) /* Reserved for software */ +#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) +/* + * rv64 PTE format: + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 + * N MT RSV PFN reserved for SW D A G U X W R V + * [62:61] Memory Type definitions: + * 00 - PMA Normal Cacheable, No change to implied PMA memory type + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory + * 11 - Rsvd Reserved for future standard use + */ +#define _SVPBMT_PMA 0UL +#define _SVPBMT_NC (1UL << 61) +#define _SVPBMT_IO (1UL << 62) +#define _SVPBMT_MASK (_SVPBMT_NC | _SVPBMT_IO) + +extern struct __svpbmt_struct { + unsigned long mask; + unsigned long pma; + unsigned long nocache; + unsigned long io; +} __svpbmt __cacheline_aligned; + +#define _PAGE_MASK __svpbmt.mask +#define _PAGE_PMA __svpbmt.pma +#define _PAGE_NOCACHE __svpbmt.nocache +#define _PAGE_IO __svpbmt.io +#else +#define _PAGE_MASK 0 +#define _PAGE_PMA 0 +#define _PAGE_NOCACHE 0 +#define _PAGE_IO 0 +#endif /* !__ASSEMBLY__ && CONFIG_64BIT */ + #define _PAGE_SPECIAL _PAGE_SOFT #define _PAGE_TABLE _PAGE_PRESENT @@ -38,7 +72,8 @@ /* Set of bits to preserve across pte_modify() */ #define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ _PAGE_WRITE | _PAGE_EXEC | \ - _PAGE_USER | _PAGE_GLOBAL)) + _PAGE_USER | _PAGE_GLOBAL | \ + _PAGE_MASK)) /* * when all of R/W/X are zero, the PTE is a pointer to the next level * of the page table; otherwise, it is a leaf PTE. diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index bf204e7c1f74..0f7a6541015f 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -138,7 +138,8 @@ | _PAGE_PRESENT \ | _PAGE_ACCESSED \ | _PAGE_DIRTY \ - | _PAGE_GLOBAL) + | _PAGE_GLOBAL \ + | _PAGE_PMA) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) @@ -148,11 +149,9 @@ #define PAGE_TABLE __pgprot(_PAGE_TABLE) -/* - * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't - * change the properties of memory regions. - */ -#define _PAGE_IOREMAP _PAGE_KERNEL +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MASK) | _PAGE_IO) + +#define PAGE_IOREMAP __pgprot(_PAGE_IOREMAP) extern pgd_t swapper_pg_dir[]; @@ -232,12 +231,12 @@ static inline unsigned long _pgd_pfn(pgd_t pgd) static inline struct page *pmd_page(pmd_t pmd) { - return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT); + return pfn_to_page(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { - return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); + return (unsigned long)pfn_to_virt(_chg_of_pmd(pmd) >> _PAGE_PFN_SHIFT); } static inline pte_t pmd_pte(pmd_t pmd) @@ -253,7 +252,7 @@ static inline pte_t pud_pte(pud_t pud) /* Yields the page frame number (PFN) of a page table entry */ static inline unsigned long pte_pfn(pte_t pte) { - return (pte_val(pte) >> _PAGE_PFN_SHIFT); + return (_chg_of_pte(pte) >> _PAGE_PFN_SHIFT); } #define pte_page(x) pfn_to_page(pte_pfn(x)) @@ -492,6 +491,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, return ptep_test_and_clear_young(vma, address, ptep); } +#define pgprot_noncached pgprot_noncached +static inline pgprot_t pgprot_noncached(pgprot_t _prot) +{ + unsigned long prot = pgprot_val(_prot); + + prot &= ~_PAGE_MASK; + prot |= _PAGE_IO; + + return __pgprot(prot); +} + +#define pgprot_writecombine pgprot_writecombine +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) +{ + unsigned long prot = pgprot_val(_prot); + + prot &= ~_PAGE_MASK; + prot |= _PAGE_NOCACHE; + + return __pgprot(prot); +} + /* * THP functions */ diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index d959d207a40d..fa7480cb8b87 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -8,6 +8,7 @@ #include <linux/bitmap.h> #include <linux/of.h> +#include <linux/pgtable.h> #include <asm/processor.h> #include <asm/hwcap.h> #include <asm/smp.h> @@ -59,6 +60,38 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) } EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); +static void __init mmu_supports_svpbmt(void) +{ +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) + struct device_node *node; + const char *str; + + for_each_of_cpu_node(node) { + if (of_property_read_string(node, "mmu-type", &str)) + continue; + + if (!strncmp(str + 6, "none", 4)) + continue; + + if (of_property_read_string(node, "mmu", &str)) + continue; + + if (strncmp(str + 6, "svpmbt", 6)) + continue; + } + + __svpbmt.pma = _SVPBMT_PMA; + __svpbmt.nocache = _SVPBMT_NC; + __svpbmt.io = _SVPBMT_IO; + __svpbmt.mask = _SVPBMT_MASK; +#endif +} + +static void __init mmu_supports(void) +{ + mmu_supports_svpbmt(); +} + void __init riscv_fill_hwcap(void) { struct device_node *node; @@ -67,6 +100,8 @@ void __init riscv_fill_hwcap(void) size_t i, j, isa_len; static unsigned long isa2hwcap[256] = {0}; + mmu_supports(); + isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 24b2b8044602..e4e658165ee1 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -854,3 +854,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, return vmemmap_populate_basepages(start, end, node, NULL); } #endif + +#if defined(CONFIG_64BIT) +struct __svpbmt_struct __svpbmt __ro_after_init; +EXPORT_SYMBOL(__svpbmt); +#endif