| Message ID | 20220613144550.3760857-3-ardb@kernel.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | arm64: refactor boot flow and add support for WXN | expand |
On 6/13/22 20:15, Ard Biesheuvel wrote: > Currently, we only support 52-bit virtual addressing on 64k pages But going forward, will support on 4K/16K pages as well via FEAT_LPA2. > configurations, and in all other cases, vabits_actual is guaranteed to > equal VA_BITS (== VA_BITS_MIN). So get rid of the variable entirely in > that case. The change here does not really get rid of vabit_actual in those cases either, it just makes it a build time constant AFAICS. --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -174,7 +174,11 @@ #include <linux/types.h> #include <asm/bug.h> +#if VA_BITS > 48 extern u64 vabits_actual; +#else +#define vabits_actual ((u64)VA_BITS) +#endif > > While at it, move the assignment out of the asm entry code - it has no > need to be there. This also changes when vabits_actual gets evaluated ? Then how would it know, that CPU needs to be stuck in kernel (CPU_STUCK_REASON_52_BIT_VA) in case all secondary CPUs do not support large VA feature ? Looking at the sequence... secondary_entry OR secondary_holding_pen secondary_startup __cpu_secondary_check52bitva primary_entry __create_page_tables <--- original position __primary_switch start_kernel setup_arch paging_init <--- new position It might still be possible for the secondary cpu start up sequence to validate LVA support across the platform, but still why even send vabits_actual evaluation down the line until paging_init(). Ideally should not it be evaluated as early as possible during boot. Hence, wondering - what is the real benefit here ? > > Signed-off-by: Ard Biesheuvel <ardb@kernel.org> > --- > arch/arm64/include/asm/memory.h | 4 ++++ > arch/arm64/kernel/head.S | 15 +-------------- > arch/arm64/mm/mmu.c | 15 ++++++++++++++- > 3 files changed, 19 insertions(+), 15 deletions(-) > > diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h > index 0af70d9abede..c751cd9b94f8 100644 > --- a/arch/arm64/include/asm/memory.h > +++ b/arch/arm64/include/asm/memory.h > @@ -174,7 +174,11 @@ > #include <linux/types.h> > #include <asm/bug.h> > > +#if VA_BITS > 48 > extern u64 vabits_actual; > +#else > +#define vabits_actual ((u64)VA_BITS) > +#endif > > extern s64 memstart_addr; > /* PHYS_OFFSET - the physical address of the start of memory. */ > diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S > index 1cdecce552bb..dc07858eb673 100644 > --- a/arch/arm64/kernel/head.S > +++ b/arch/arm64/kernel/head.S > @@ -293,19 +293,6 @@ SYM_FUNC_START_LOCAL(__create_page_tables) > adrp x0, idmap_pg_dir > adrp x3, __idmap_text_start // __pa(__idmap_text_start) > > -#ifdef CONFIG_ARM64_VA_BITS_52 > - mrs_s x6, SYS_ID_AA64MMFR2_EL1 > - and x6, x6, #(0xf << ID_AA64MMFR2_LVA_SHIFT) > - mov x5, #52 > - cbnz x6, 1f > -#endif > - mov x5, #VA_BITS_MIN > -1: > - adr_l x6, vabits_actual > - str x5, [x6] > - dmb sy > - dc ivac, x6 // Invalidate potentially stale cache line > - > /* > * VA_BITS may be too small to allow for an ID mapping to be created > * that covers system RAM if that is located sufficiently high in the > @@ -713,7 +700,7 @@ SYM_FUNC_START(__enable_mmu) > SYM_FUNC_END(__enable_mmu) > > SYM_FUNC_START(__cpu_secondary_check52bitva) > -#ifdef CONFIG_ARM64_VA_BITS_52 > +#if VA_BITS > 48 Just curious - why this is any better ? Although both (VA_BITS > 48) and CONFIG_ARM64_VA_BITS_52 are build time constants. > ldr_l x0, vabits_actual > cmp x0, #52 > b.ne 2f > diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c > index 7148928e3932..17b339c1a326 100644 > --- a/arch/arm64/mm/mmu.c > +++ b/arch/arm64/mm/mmu.c > @@ -46,8 +46,10 @@ > u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN); > u64 idmap_ptrs_per_pgd = PTRS_PER_PGD; > > -u64 __section(".mmuoff.data.write") vabits_actual; > +#if VA_BITS > 48 > +u64 vabits_actual __ro_after_init = VA_BITS_MIN; > EXPORT_SYMBOL(vabits_actual); > +#endif > > u64 kimage_vaddr __ro_after_init = (u64)&_text; > EXPORT_SYMBOL(kimage_vaddr); > @@ -772,6 +774,17 @@ void __init paging_init(void) > { > pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir)); > > +#if VA_BITS > 48 > + if (cpuid_feature_extract_unsigned_field( > + read_sysreg_s(SYS_ID_AA64MMFR2_EL1), > + ID_AA64MMFR2_LVA_SHIFT)) > + vabits_actual = VA_BITS; > + > + /* make the variable visible to secondaries with the MMU off */ > + dcache_clean_inval_poc((u64)&vabits_actual, > + (u64)&vabits_actual + sizeof(vabits_actual)); > +#endif > + > map_kernel(pgdp); > map_mem(pgdp); >
On Tue, 14 Jun 2022 at 10:25, Anshuman Khandual <anshuman.khandual@arm.com> wrote: > > > On 6/13/22 20:15, Ard Biesheuvel wrote: > > Currently, we only support 52-bit virtual addressing on 64k pages > > But going forward, will support on 4K/16K pages as well via FEAT_LPA2. > > > configurations, and in all other cases, vabits_actual is guaranteed to > > equal VA_BITS (== VA_BITS_MIN). So get rid of the variable entirely in > > that case. > > The change here does not really get rid of vabit_actual in those cases > either, it just makes it a build time constant AFAICS. > Indeed, and so it ceases to be a variable. > --- a/arch/arm64/include/asm/memory.h > +++ b/arch/arm64/include/asm/memory.h > @@ -174,7 +174,11 @@ > #include <linux/types.h> > #include <asm/bug.h> > > +#if VA_BITS > 48 > extern u64 vabits_actual; > +#else > +#define vabits_actual ((u64)VA_BITS) > +#endif > > > > > While at it, move the assignment out of the asm entry code - it has no > > need to be there. > > This also changes when vabits_actual gets evaluated ? Then how would it > know, that CPU needs to be stuck in kernel (CPU_STUCK_REASON_52_BIT_VA) > in case all secondary CPUs do not support large VA feature ? Looking at > the sequence... > > secondary_entry > OR > secondary_holding_pen > secondary_startup > __cpu_secondary_check52bitva > > primary_entry > __create_page_tables <--- original position > __primary_switch > start_kernel > setup_arch > paging_init <--- new position > > It might still be possible for the secondary cpu start up sequence to > validate LVA support across the platform, but still why even send > vabits_actual evaluation down the line until paging_init(). Ideally > should not it be evaluated as early as possible during boot. Hence, > wondering - what is the real benefit here ? > Why should it be evaluated as early as possible? The whole point is deferring it so we don't have to do it from asm code. But I suppose doing it as early as possible from C code (i.e., in setup_arch() before arm64_memblock_init() or even before early_fixmap_init()) might be better. > > > > Signed-off-by: Ard Biesheuvel <ardb@kernel.org> > > --- > > arch/arm64/include/asm/memory.h | 4 ++++ > > arch/arm64/kernel/head.S | 15 +-------------- > > arch/arm64/mm/mmu.c | 15 ++++++++++++++- > > 3 files changed, 19 insertions(+), 15 deletions(-) > > > > diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h > > index 0af70d9abede..c751cd9b94f8 100644 > > --- a/arch/arm64/include/asm/memory.h > > +++ b/arch/arm64/include/asm/memory.h > > @@ -174,7 +174,11 @@ > > #include <linux/types.h> > > #include <asm/bug.h> > > > > +#if VA_BITS > 48 > > extern u64 vabits_actual; > > +#else > > +#define vabits_actual ((u64)VA_BITS) > > +#endif > > > > extern s64 memstart_addr; > > /* PHYS_OFFSET - the physical address of the start of memory. */ > > diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S > > index 1cdecce552bb..dc07858eb673 100644 > > --- a/arch/arm64/kernel/head.S > > +++ b/arch/arm64/kernel/head.S > > @@ -293,19 +293,6 @@ SYM_FUNC_START_LOCAL(__create_page_tables) > > adrp x0, idmap_pg_dir > > adrp x3, __idmap_text_start // __pa(__idmap_text_start) > > > > -#ifdef CONFIG_ARM64_VA_BITS_52 > > - mrs_s x6, SYS_ID_AA64MMFR2_EL1 > > - and x6, x6, #(0xf << ID_AA64MMFR2_LVA_SHIFT) > > - mov x5, #52 > > - cbnz x6, 1f > > -#endif > > - mov x5, #VA_BITS_MIN > > -1: > > - adr_l x6, vabits_actual > > - str x5, [x6] > > - dmb sy > > - dc ivac, x6 // Invalidate potentially stale cache line > > - > > /* > > * VA_BITS may be too small to allow for an ID mapping to be created > > * that covers system RAM if that is located sufficiently high in the > > @@ -713,7 +700,7 @@ SYM_FUNC_START(__enable_mmu) > > SYM_FUNC_END(__enable_mmu) > > > > SYM_FUNC_START(__cpu_secondary_check52bitva) > > -#ifdef CONFIG_ARM64_VA_BITS_52 > > +#if VA_BITS > 48 > > Just curious - why this is any better ? Although both (VA_BITS > 48) > and CONFIG_ARM64_VA_BITS_52 are build time constants. > VA_BITS > 48 is a bit more readable, and more likely to remain accurate. > > ldr_l x0, vabits_actual > > cmp x0, #52 > > b.ne 2f > > diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c > > index 7148928e3932..17b339c1a326 100644 > > --- a/arch/arm64/mm/mmu.c > > +++ b/arch/arm64/mm/mmu.c > > @@ -46,8 +46,10 @@ > > u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN); > > u64 idmap_ptrs_per_pgd = PTRS_PER_PGD; > > > > -u64 __section(".mmuoff.data.write") vabits_actual; > > +#if VA_BITS > 48 > > +u64 vabits_actual __ro_after_init = VA_BITS_MIN; > > EXPORT_SYMBOL(vabits_actual); > > +#endif > > > > u64 kimage_vaddr __ro_after_init = (u64)&_text; > > EXPORT_SYMBOL(kimage_vaddr); > > @@ -772,6 +774,17 @@ void __init paging_init(void) > > { > > pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir)); > > > > +#if VA_BITS > 48 > > + if (cpuid_feature_extract_unsigned_field( > > + read_sysreg_s(SYS_ID_AA64MMFR2_EL1), > > + ID_AA64MMFR2_LVA_SHIFT)) > > + vabits_actual = VA_BITS; > > + > > + /* make the variable visible to secondaries with the MMU off */ > > + dcache_clean_inval_poc((u64)&vabits_actual, > > + (u64)&vabits_actual + sizeof(vabits_actual)); > > +#endif > > + > > map_kernel(pgdp); > > map_mem(pgdp); > >
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 0af70d9abede..c751cd9b94f8 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -174,7 +174,11 @@ #include <linux/types.h> #include <asm/bug.h> +#if VA_BITS > 48 extern u64 vabits_actual; +#else +#define vabits_actual ((u64)VA_BITS) +#endif extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 1cdecce552bb..dc07858eb673 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -293,19 +293,6 @@ SYM_FUNC_START_LOCAL(__create_page_tables) adrp x0, idmap_pg_dir adrp x3, __idmap_text_start // __pa(__idmap_text_start) -#ifdef CONFIG_ARM64_VA_BITS_52 - mrs_s x6, SYS_ID_AA64MMFR2_EL1 - and x6, x6, #(0xf << ID_AA64MMFR2_LVA_SHIFT) - mov x5, #52 - cbnz x6, 1f -#endif - mov x5, #VA_BITS_MIN -1: - adr_l x6, vabits_actual - str x5, [x6] - dmb sy - dc ivac, x6 // Invalidate potentially stale cache line - /* * VA_BITS may be too small to allow for an ID mapping to be created * that covers system RAM if that is located sufficiently high in the @@ -713,7 +700,7 @@ SYM_FUNC_START(__enable_mmu) SYM_FUNC_END(__enable_mmu) SYM_FUNC_START(__cpu_secondary_check52bitva) -#ifdef CONFIG_ARM64_VA_BITS_52 +#if VA_BITS > 48 ldr_l x0, vabits_actual cmp x0, #52 b.ne 2f diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 7148928e3932..17b339c1a326 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -46,8 +46,10 @@ u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN); u64 idmap_ptrs_per_pgd = PTRS_PER_PGD; -u64 __section(".mmuoff.data.write") vabits_actual; +#if VA_BITS > 48 +u64 vabits_actual __ro_after_init = VA_BITS_MIN; EXPORT_SYMBOL(vabits_actual); +#endif u64 kimage_vaddr __ro_after_init = (u64)&_text; EXPORT_SYMBOL(kimage_vaddr); @@ -772,6 +774,17 @@ void __init paging_init(void) { pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir)); +#if VA_BITS > 48 + if (cpuid_feature_extract_unsigned_field( + read_sysreg_s(SYS_ID_AA64MMFR2_EL1), + ID_AA64MMFR2_LVA_SHIFT)) + vabits_actual = VA_BITS; + + /* make the variable visible to secondaries with the MMU off */ + dcache_clean_inval_poc((u64)&vabits_actual, + (u64)&vabits_actual + sizeof(vabits_actual)); +#endif + map_kernel(pgdp); map_mem(pgdp);
Currently, we only support 52-bit virtual addressing on 64k pages configurations, and in all other cases, vabits_actual is guaranteed to equal VA_BITS (== VA_BITS_MIN). So get rid of the variable entirely in that case. While at it, move the assignment out of the asm entry code - it has no need to be there. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> --- arch/arm64/include/asm/memory.h | 4 ++++ arch/arm64/kernel/head.S | 15 +-------------- arch/arm64/mm/mmu.c | 15 ++++++++++++++- 3 files changed, 19 insertions(+), 15 deletions(-)