From 5c709e699881afd1cf9244c719eb063c3476a405 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 28 Feb 2012 12:56:06 +0000 Subject: ARM: nommu: define dummy TLB operations for nommu configurations nommu platforms do not perform address translation and therefore clearly don't have TLBs. However, some SMP code assumes the presence of the TLB flushing routines and will therefore fail to compile for a nommu system. This patch defines dummy local_* TLB operations and #defines tlb_ops_need_broadcast() as 0, therefore causing the usual ARM SMP TLB operations to call the local variants instead. Signed-off-by: Will Deacon CC: Lorenzo Pieralisi CC: Nicolas Pitre --- arch/arm/include/asm/smp_plat.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/arm/include/asm/smp_plat.h') diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h index aaa61b6f50f..1c7b6f8101a 100644 --- a/arch/arm/include/asm/smp_plat.h +++ b/arch/arm/include/asm/smp_plat.h @@ -26,6 +26,9 @@ static inline bool is_smp(void) } /* all SMP configurations have the extended CPUID registers */ +#ifndef CONFIG_MMU +#define tlb_ops_need_broadcast() 0 +#else static inline int tlb_ops_need_broadcast(void) { if (!is_smp()) @@ -33,6 +36,7 @@ static inline int tlb_ops_need_broadcast(void) return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2; } +#endif #if !defined(CONFIG_SMP) || __LINUX_ARM_ARCH__ >= 7 #define cache_ops_need_broadcast() 0 -- cgit v1.2.3-70-g09d2 From 8cf72172d739639f2699131821a3ebc291287cf2 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Thu, 16 May 2013 10:32:09 +0100 Subject: ARM: kernel: build MPIDR hash function data structure On ARM SMP systems, cores are identified by their MPIDR register. The MPIDR guidelines in the ARM ARM do not provide strict enforcement of MPIDR layout, only recommendations that, if followed, split the MPIDR on ARM 32 bit platforms in three affinity levels. In multi-cluster systems like big.LITTLE, if the affinity guidelines are followed, the MPIDR can not be considered an index anymore. This means that the association between logical CPU in the kernel and the HW CPU identifier becomes somewhat more complicated requiring methods like hashing to associate a given MPIDR to a CPU logical index, in order for the look-up to be carried out in an efficient and scalable way. This patch provides a function in the kernel that starting from the cpu_logical_map, implement collision-free hashing of MPIDR values by checking all significative bits of MPIDR affinity level bitfields. The hashing can then be carried out through bits shifting and ORing; the resulting hash algorithm is a collision-free though not minimal hash that can be executed with few assembly instructions. The mpidr is filtered through a mpidr mask that is built by checking all bits that toggle in the set of MPIDRs corresponding to possible CPUs. Bits that do not toggle do not carry information so they do not contribute to the resulting hash. Pseudo code: /* check all bits that toggle, so they are required */ for (i = 1, mpidr_mask = 0; i < num_possible_cpus(); i++) mpidr_mask |= (cpu_logical_map(i) ^ cpu_logical_map(0)); /* * Build shifts to be applied to aff0, aff1, aff2 values to hash the mpidr * fls() returns the last bit set in a word, 0 if none * ffs() returns the first bit set in a word, 0 if none */ fs0 = mpidr_mask[7:0] ? ffs(mpidr_mask[7:0]) - 1 : 0; fs1 = mpidr_mask[15:8] ? ffs(mpidr_mask[15:8]) - 1 : 0; fs2 = mpidr_mask[23:16] ? ffs(mpidr_mask[23:16]) - 1 : 0; ls0 = fls(mpidr_mask[7:0]); ls1 = fls(mpidr_mask[15:8]); ls2 = fls(mpidr_mask[23:16]); bits0 = ls0 - fs0; bits1 = ls1 - fs1; bits2 = ls2 - fs2; aff0_shift = fs0; aff1_shift = 8 + fs1 - bits0; aff2_shift = 16 + fs2 - (bits0 + bits1); u32 hash(u32 mpidr) { u32 l0, l1, l2; u32 mpidr_masked = mpidr & mpidr_mask; l0 = mpidr_masked & 0xff; l1 = mpidr_masked & 0xff00; l2 = mpidr_masked & 0xff0000; return (l0 >> aff0_shift | l1 >> aff1_shift | l2 >> aff2_shift); } The hashing algorithm relies on the inherent properties set in the ARM ARM recommendations for the MPIDR. Exotic configurations, where for instance the MPIDR values at a given affinity level have large holes, can end up requiring big hash tables since the compression of values that can be achieved through shifting is somewhat crippled when holes are present. Kernel warns if the number of buckets of the resulting hash table exceeds the number of possible CPUs by a factor of 4, which is a symptom of a very sparse HW MPIDR configuration. The hash algorithm is quite simple and can easily be implemented in assembly code, to be used in code paths where the kernel virtual address space is not set-up (ie cpu_resume) and instruction and data fetches are strongly ordered so code must be compact and must carry out few data accesses. Cc: Will Deacon Cc: Catalin Marinas Cc: Russell King Cc: Colin Cross Cc: Santosh Shilimkar Cc: Daniel Lezcano Cc: Amit Kucheria Signed-off-by: Lorenzo Pieralisi Reviewed-by: Dave Martin Reviewed-by: Nicolas Pitre Tested-by: Shawn Guo Tested-by: Kevin Hilman Tested-by: Stephen Warren --- arch/arm/include/asm/smp_plat.h | 12 ++++++++ arch/arm/kernel/setup.c | 67 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+) (limited to 'arch/arm/include/asm/smp_plat.h') diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h index 1c7b6f8101a..f75f8a234b3 100644 --- a/arch/arm/include/asm/smp_plat.h +++ b/arch/arm/include/asm/smp_plat.h @@ -70,4 +70,16 @@ static inline int get_logical_index(u32 mpidr) return -EINVAL; } +struct mpidr_hash { + u32 mask; + u32 shift_aff[3]; + u32 bits; +}; + +extern struct mpidr_hash mpidr_hash; + +static inline u32 mpidr_hash_size(void) +{ + return 1 << mpidr_hash.bits; +} #endif diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index ca34224f891..9048513cbe0 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -478,6 +478,72 @@ void __init smp_setup_processor_id(void) printk(KERN_INFO "Booting Linux on physical CPU 0x%x\n", mpidr); } +struct mpidr_hash mpidr_hash; +#ifdef CONFIG_SMP +/** + * smp_build_mpidr_hash - Pre-compute shifts required at each affinity + * level in order to build a linear index from an + * MPIDR value. Resulting algorithm is a collision + * free hash carried out through shifting and ORing + */ +static void __init smp_build_mpidr_hash(void) +{ + u32 i, affinity; + u32 fs[3], bits[3], ls, mask = 0; + /* + * Pre-scan the list of MPIDRS and filter out bits that do + * not contribute to affinity levels, ie they never toggle. + */ + for_each_possible_cpu(i) + mask |= (cpu_logical_map(i) ^ cpu_logical_map(0)); + pr_debug("mask of set bits 0x%x\n", mask); + /* + * Find and stash the last and first bit set at all affinity levels to + * check how many bits are required to represent them. + */ + for (i = 0; i < 3; i++) { + affinity = MPIDR_AFFINITY_LEVEL(mask, i); + /* + * Find the MSB bit and LSB bits position + * to determine how many bits are required + * to express the affinity level. + */ + ls = fls(affinity); + fs[i] = affinity ? ffs(affinity) - 1 : 0; + bits[i] = ls - fs[i]; + } + /* + * An index can be created from the MPIDR by isolating the + * significant bits at each affinity level and by shifting + * them in order to compress the 24 bits values space to a + * compressed set of values. This is equivalent to hashing + * the MPIDR through shifting and ORing. It is a collision free + * hash though not minimal since some levels might contain a number + * of CPUs that is not an exact power of 2 and their bit + * representation might contain holes, eg MPIDR[7:0] = {0x2, 0x80}. + */ + mpidr_hash.shift_aff[0] = fs[0]; + mpidr_hash.shift_aff[1] = MPIDR_LEVEL_BITS + fs[1] - bits[0]; + mpidr_hash.shift_aff[2] = 2*MPIDR_LEVEL_BITS + fs[2] - + (bits[1] + bits[0]); + mpidr_hash.mask = mask; + mpidr_hash.bits = bits[2] + bits[1] + bits[0]; + pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] mask[0x%x] bits[%u]\n", + mpidr_hash.shift_aff[0], + mpidr_hash.shift_aff[1], + mpidr_hash.shift_aff[2], + mpidr_hash.mask, + mpidr_hash.bits); + /* + * 4x is an arbitrary value used to warn on a hash table much bigger + * than expected on most systems. + */ + if (mpidr_hash_size() > 4 * num_possible_cpus()) + pr_warn("Large number of MPIDR hash buckets detected\n"); + sync_cache_w(&mpidr_hash); +} +#endif + static void __init setup_processor(void) { struct proc_info_list *list; @@ -825,6 +891,7 @@ void __init setup_arch(char **cmdline_p) smp_set_ops(mdesc->smp); } smp_init_cpus(); + smp_build_mpidr_hash(); } #endif -- cgit v1.2.3-70-g09d2 From 7604537bbb5720376e8c9e6bc74a8e6305e3094d Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Thu, 16 May 2013 10:34:30 +0100 Subject: ARM: kernel: implement stack pointer save array through MPIDR hashing Current implementation of cpu_{suspend}/cpu_{resume} relies on the MPIDR to index the array of pointers where the context is saved and restored. The current approach works as long as the MPIDR can be considered a linear index, so that the pointers array can simply be dereferenced by using the MPIDR[7:0] value. On ARM multi-cluster systems, where the MPIDR may not be a linear index, to properly dereference the stack pointer array, a mapping function should be applied to it so that it can be used for arrays look-ups. This patch adds code in the cpu_{suspend}/cpu_{resume} implementation that relies on shifting and ORing hashing method to map a MPIDR value to a set of buckets precomputed at boot to have a collision free mapping from MPIDR to context pointers. The hashing algorithm must be simple, fast, and implementable with few instructions since in the cpu_resume path the mapping is carried out with the MMU off and the I-cache off, hence code and data are fetched from DRAM with no-caching available. Simplicity is counterbalanced with a little increase of memory (allocated dynamically) for stack pointers buckets, that should be anyway fairly limited on most systems. Memory for context pointers is allocated in a early_initcall with size precomputed and stashed previously in kernel data structures. Memory for context pointers is allocated through kmalloc; this guarantees contiguous physical addresses for the allocated memory which is fundamental to the correct functioning of the resume mechanism that relies on the context pointer array to be a chunk of contiguous physical memory. Virtual to physical address conversion for the context pointer array base is carried out at boot to avoid fiddling with virt_to_phys conversions in the cpu_resume path which is quite fragile and should be optimized to execute as few instructions as possible. Virtual and physical context pointer base array addresses are stashed in a struct that is accessible from assembly using values generated through the asm-offsets.c mechanism. Cc: Will Deacon Cc: Catalin Marinas Cc: Russell King Cc: Colin Cross Cc: Santosh Shilimkar Cc: Daniel Lezcano Cc: Amit Kucheria Signed-off-by: Lorenzo Pieralisi Reviewed-by: Dave Martin Reviewed-by: Nicolas Pitre Tested-by: Shawn Guo Tested-by: Kevin Hilman Tested-by: Stephen Warren --- arch/arm/include/asm/smp_plat.h | 10 ++++- arch/arm/include/asm/suspend.h | 5 +++ arch/arm/kernel/asm-offsets.c | 6 +++ arch/arm/kernel/sleep.S | 97 +++++++++++++++++++++++++++++++++-------- arch/arm/kernel/suspend.c | 20 +++++++++ 5 files changed, 118 insertions(+), 20 deletions(-) (limited to 'arch/arm/include/asm/smp_plat.h') diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h index f75f8a234b3..6e63f29f41b 100644 --- a/arch/arm/include/asm/smp_plat.h +++ b/arch/arm/include/asm/smp_plat.h @@ -70,9 +70,15 @@ static inline int get_logical_index(u32 mpidr) return -EINVAL; } +/* + * NOTE ! Assembly code relies on the following + * structure memory layout in order to carry out load + * multiple from its base address. For more + * information check arch/arm/kernel/sleep.S + */ struct mpidr_hash { - u32 mask; - u32 shift_aff[3]; + u32 mask; /* used by sleep.S */ + u32 shift_aff[3]; /* used by sleep.S */ u32 bits; }; diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h index 1c0a551ae37..cd20029bcd9 100644 --- a/arch/arm/include/asm/suspend.h +++ b/arch/arm/include/asm/suspend.h @@ -1,6 +1,11 @@ #ifndef __ASM_ARM_SUSPEND_H #define __ASM_ARM_SUSPEND_H +struct sleep_save_sp { + u32 *save_ptr_stash; + u32 save_ptr_stash_phys; +}; + extern void cpu_resume(void); extern int cpu_suspend(unsigned long, int (*)(unsigned long)); diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index ee68cce6b48..ded041711be 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -144,6 +145,11 @@ int main(void) #endif #ifdef MULTI_CACHE DEFINE(CACHE_FLUSH_KERN_ALL, offsetof(struct cpu_cache_fns, flush_kern_all)); +#endif +#ifdef CONFIG_ARM_CPU_SUSPEND + DEFINE(SLEEP_SAVE_SP_SZ, sizeof(struct sleep_save_sp)); + DEFINE(SLEEP_SAVE_SP_PHYS, offsetof(struct sleep_save_sp, save_ptr_stash_phys)); + DEFINE(SLEEP_SAVE_SP_VIRT, offsetof(struct sleep_save_sp, save_ptr_stash)); #endif BLANK(); DEFINE(DMA_BIDIRECTIONAL, DMA_BIDIRECTIONAL); diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 987dcf33415..db1536b8b30 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -6,6 +6,49 @@ #include .text +/* + * Implementation of MPIDR hash algorithm through shifting + * and OR'ing. + * + * @dst: register containing hash result + * @rs0: register containing affinity level 0 bit shift + * @rs1: register containing affinity level 1 bit shift + * @rs2: register containing affinity level 2 bit shift + * @mpidr: register containing MPIDR value + * @mask: register containing MPIDR mask + * + * Pseudo C-code: + * + *u32 dst; + * + *compute_mpidr_hash(u32 rs0, u32 rs1, u32 rs2, u32 mpidr, u32 mask) { + * u32 aff0, aff1, aff2; + * u32 mpidr_masked = mpidr & mask; + * aff0 = mpidr_masked & 0xff; + * aff1 = mpidr_masked & 0xff00; + * aff2 = mpidr_masked & 0xff0000; + * dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2); + *} + * Input registers: rs0, rs1, rs2, mpidr, mask + * Output register: dst + * Note: input and output registers must be disjoint register sets + (eg: a macro instance with mpidr = r1 and dst = r1 is invalid) + */ + .macro compute_mpidr_hash dst, rs0, rs1, rs2, mpidr, mask + and \mpidr, \mpidr, \mask @ mask out MPIDR bits + and \dst, \mpidr, #0xff @ mask=aff0 + ARM( mov \dst, \dst, lsr \rs0 ) @ dst=aff0>>rs0 + THUMB( lsr \dst, \dst, \rs0 ) + and \mask, \mpidr, #0xff00 @ mask = aff1 + ARM( orr \dst, \dst, \mask, lsr \rs1 ) @ dst|=(aff1>>rs1) + THUMB( lsr \mask, \mask, \rs1 ) + THUMB( orr \dst, \dst, \mask ) + and \mask, \mpidr, #0xff0000 @ mask = aff2 + ARM( orr \dst, \dst, \mask, lsr \rs2 ) @ dst|=(aff2>>rs2) + THUMB( lsr \mask, \mask, \rs2 ) + THUMB( orr \dst, \dst, \mask ) + .endm + /* * Save CPU state for a suspend. This saves the CPU general purpose * registers, and allocates space on the kernel stack to save the CPU @@ -29,12 +72,18 @@ ENTRY(__cpu_suspend) mov r1, r4 @ size of save block mov r2, r5 @ virtual SP ldr r3, =sleep_save_sp -#ifdef CONFIG_SMP - ALT_SMP(mrc p15, 0, lr, c0, c0, 5) - ALT_UP(mov lr, #0) - and lr, lr, #15 + ldr r3, [r3, #SLEEP_SAVE_SP_VIRT] + ALT_SMP(mrc p15, 0, r9, c0, c0, 5) + ALT_UP_B(1f) + ldr r8, =mpidr_hash + /* + * This ldmia relies on the memory layout of the mpidr_hash + * struct mpidr_hash. + */ + ldmia r8, {r4-r7} @ r4 = mpidr mask (r5,r6,r7) = l[0,1,2] shifts + compute_mpidr_hash lr, r5, r6, r7, r9, r4 add r3, r3, lr, lsl #2 -#endif +1: bl __cpu_suspend_save adr lr, BSYM(cpu_suspend_abort) ldmfd sp!, {r0, pc} @ call suspend fn @@ -81,15 +130,23 @@ ENDPROC(cpu_resume_after_mmu) .data .align ENTRY(cpu_resume) -#ifdef CONFIG_SMP - adr r0, sleep_save_sp - ALT_SMP(mrc p15, 0, r1, c0, c0, 5) - ALT_UP(mov r1, #0) - and r1, r1, #15 - ldr r0, [r0, r1, lsl #2] @ stack phys addr -#else - ldr r0, sleep_save_sp @ stack phys addr -#endif + mov r1, #0 + ALT_SMP(mrc p15, 0, r0, c0, c0, 5) + ALT_UP_B(1f) + adr r2, mpidr_hash_ptr + ldr r3, [r2] + add r2, r2, r3 @ r2 = struct mpidr_hash phys address + /* + * This ldmia relies on the memory layout of the mpidr_hash + * struct mpidr_hash. + */ + ldmia r2, { r3-r6 } @ r3 = mpidr mask (r4,r5,r6) = l[0,1,2] shifts + compute_mpidr_hash r1, r4, r5, r6, r0, r3 +1: + adr r0, _sleep_save_sp + ldr r0, [r0, #SLEEP_SAVE_SP_PHYS] + ldr r0, [r0, r1, lsl #2] + setmode PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1 @ set SVC, irqs off @ load phys pgd, stack, resume fn ARM( ldmia r0!, {r1, sp, pc} ) @@ -98,7 +155,11 @@ THUMB( mov sp, r2 ) THUMB( bx r3 ) ENDPROC(cpu_resume) -sleep_save_sp: - .rept CONFIG_NR_CPUS - .long 0 @ preserve stack phys ptr here - .endr + .align 2 +mpidr_hash_ptr: + .long mpidr_hash - . @ mpidr_hash struct offset + + .type sleep_save_sp, #object +ENTRY(sleep_save_sp) +_sleep_save_sp: + .space SLEEP_SAVE_SP_SZ @ struct sleep_save_sp diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c index 38a50676213..41cf3cbf756 100644 --- a/arch/arm/kernel/suspend.c +++ b/arch/arm/kernel/suspend.c @@ -1,9 +1,12 @@ #include +#include +#include #include #include #include #include +#include #include #include @@ -82,3 +85,20 @@ void __cpu_suspend_save(u32 *ptr, u32 ptrsz, u32 sp, u32 *save_ptr) outer_clean_range(virt_to_phys(save_ptr), virt_to_phys(save_ptr) + sizeof(*save_ptr)); } + +extern struct sleep_save_sp sleep_save_sp; + +static int cpu_suspend_alloc_sp(void) +{ + void *ctx_ptr; + /* ctx_ptr is an array of physical addresses */ + ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(u32), GFP_KERNEL); + + if (WARN_ON(!ctx_ptr)) + return -ENOMEM; + sleep_save_sp.save_ptr_stash = ctx_ptr; + sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr); + sync_cache_w(&sleep_save_sp); + return 0; +} +early_initcall(cpu_suspend_alloc_sp); -- cgit v1.2.3-70-g09d2