diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-05 11:36:44 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-05 11:36:44 -0700 |
commit | 7246f60068840847bdcf595be5f0b5ca632736e0 (patch) | |
tree | fd9a963a03c2655f3ba9d1ced3c87a2775f5b166 /arch/powerpc/mm/slice.c | |
parent | e579dde654fc2c6b0d3e4b77a9a4b2d2405c510e (diff) | |
parent | 700b7eadd5625d22b8235fb21259b3d7d564c000 (diff) |
Merge tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Highlights include:
- Larger virtual address space on 64-bit server CPUs. By default we
use a 128TB virtual address space, but a process can request access
to the full 512TB by passing a hint to mmap().
- Support for the new Power9 "XIVE" interrupt controller.
- TLB flushing optimisations for the radix MMU on Power9.
- Support for CAPI cards on Power9, using the "Coherent Accelerator
Interface Architecture 2.0".
- The ability to configure the mmap randomisation limits at build and
runtime.
- Several small fixes and cleanups to the kprobes code, as well as
support for KPROBES_ON_FTRACE.
- Major improvements to handling of system reset interrupts,
correctly treating them as NMIs, giving them a dedicated stack and
using a new hypervisor call to trigger them, all of which should
aid debugging and robustness.
- Many fixes and other minor enhancements.
Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Alistair Popple,
Andrew Donnellan, Aneesh Kumar K.V, Anshuman Khandual, Anton
Blanchard, Balbir Singh, Ben Hutchings, Benjamin Herrenschmidt,
Bhupesh Sharma, Chris Packham, Christian Zigotzky, Christophe Leroy,
Christophe Lombard, Daniel Axtens, David Gibson, Gautham R. Shenoy,
Gavin Shan, Geert Uytterhoeven, Guilherme G. Piccoli, Hamish Martin,
Hari Bathini, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Mahesh J
Salgaonkar, Mahesh Salgaonkar, Masami Hiramatsu, Matt Brown, Matthew
R. Ochs, Michael Neuling, Naveen N. Rao, Nicholas Piggin, Oliver
O'Halloran, Pan Xinhui, Paul Mackerras, Rashmica Gupta, Russell
Currey, Sukadev Bhattiprolu, Thadeu Lima de Souza Cascardo, Tobin C.
Harding, Tyrel Datwyler, Uma Krishnan, Vaibhav Jain, Vipin K Parashar,
Yang Shi"
* tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (214 commits)
powerpc/64s: Power9 has no LPCR[VRMASD] field so don't set it
powerpc/powernv: Fix TCE kill on NVLink2
powerpc/mm/radix: Drop support for CPUs without lockless tlbie
powerpc/book3s/mce: Move add_taint() later in virtual mode
powerpc/sysfs: Move #ifdef CONFIG_HOTPLUG_CPU out of the function body
powerpc/smp: Document irq enable/disable after migrating IRQs
powerpc/mpc52xx: Don't select user-visible RTAS_PROC
powerpc/powernv: Document cxl dependency on special case in pnv_eeh_reset()
powerpc/eeh: Clean up and document event handling functions
powerpc/eeh: Avoid use after free in eeh_handle_special_event()
cxl: Mask slice error interrupts after first occurrence
cxl: Route eeh events to all drivers in cxl_pci_error_detected()
cxl: Force context lock during EEH flow
powerpc/64: Allow CONFIG_RELOCATABLE if COMPILE_TEST
powerpc/xmon: Teach xmon oops about radix vectors
powerpc/mm/hash: Fix off-by-one in comment about kernel contexts ids
powerpc/pseries: Enable VFIO
powerpc/powernv: Fix iommu table size calculation hook for small tables
powerpc/powernv: Check kzalloc() return value in pnv_pci_table_alloc
powerpc: Add arch/powerpc/tools directory
...
Diffstat (limited to 'arch/powerpc/mm/slice.c')
-rw-r--r-- | arch/powerpc/mm/slice.c | 258 |
1 files changed, 157 insertions, 101 deletions
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 2b27458902ee..966b9fccfa66 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -36,38 +36,29 @@ #include <asm/copro.h> #include <asm/hugetlb.h> -/* some sanity checks */ -#if (H_PGTABLE_RANGE >> 43) > SLICE_MASK_SIZE -#error H_PGTABLE_RANGE exceeds slice_mask high_slices size -#endif - static DEFINE_SPINLOCK(slice_convert_lock); - +/* + * One bit per slice. We have lower slices which cover 256MB segments + * upto 4G range. That gets us 16 low slices. For the rest we track slices + * in 1TB size. + */ +struct slice_mask { + u64 low_slices; + DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH); +}; #ifdef DEBUG int _slice_debug = 1; static void slice_print_mask(const char *label, struct slice_mask mask) { - char *p, buf[16 + 3 + 64 + 1]; - int i; - if (!_slice_debug) return; - p = buf; - for (i = 0; i < SLICE_NUM_LOW; i++) - *(p++) = (mask.low_slices & (1 << i)) ? '1' : '0'; - *(p++) = ' '; - *(p++) = '-'; - *(p++) = ' '; - for (i = 0; i < SLICE_NUM_HIGH; i++) - *(p++) = (mask.high_slices & (1ul << i)) ? '1' : '0'; - *(p++) = 0; - - printk(KERN_DEBUG "%s:%s\n", label, buf); + pr_devel("%s low_slice: %*pbl\n", label, (int)SLICE_NUM_LOW, &mask.low_slices); + pr_devel("%s high_slice: %*pbl\n", label, (int)SLICE_NUM_HIGH, mask.high_slices); } -#define slice_dbg(fmt...) do { if (_slice_debug) pr_debug(fmt); } while(0) +#define slice_dbg(fmt...) do { if (_slice_debug) pr_devel(fmt); } while (0) #else @@ -76,25 +67,28 @@ static void slice_print_mask(const char *label, struct slice_mask mask) {} #endif -static struct slice_mask slice_range_to_mask(unsigned long start, - unsigned long len) +static void slice_range_to_mask(unsigned long start, unsigned long len, + struct slice_mask *ret) { unsigned long end = start + len - 1; - struct slice_mask ret = { 0, 0 }; + + ret->low_slices = 0; + bitmap_zero(ret->high_slices, SLICE_NUM_HIGH); if (start < SLICE_LOW_TOP) { - unsigned long mend = min(end, SLICE_LOW_TOP); - unsigned long mstart = min(start, SLICE_LOW_TOP); + unsigned long mend = min(end, (SLICE_LOW_TOP - 1)); - ret.low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1)) - - (1u << GET_LOW_SLICE_INDEX(mstart)); + ret->low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1)) + - (1u << GET_LOW_SLICE_INDEX(start)); } - if ((start + len) > SLICE_LOW_TOP) - ret.high_slices = (1ul << (GET_HIGH_SLICE_INDEX(end) + 1)) - - (1ul << GET_HIGH_SLICE_INDEX(start)); + if ((start + len) > SLICE_LOW_TOP) { + unsigned long start_index = GET_HIGH_SLICE_INDEX(start); + unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT)); + unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index; - return ret; + bitmap_set(ret->high_slices, start_index, count); + } } static int slice_area_is_free(struct mm_struct *mm, unsigned long addr, @@ -128,53 +122,60 @@ static int slice_high_has_vma(struct mm_struct *mm, unsigned long slice) return !slice_area_is_free(mm, start, end - start); } -static struct slice_mask slice_mask_for_free(struct mm_struct *mm) +static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret) { - struct slice_mask ret = { 0, 0 }; unsigned long i; + ret->low_slices = 0; + bitmap_zero(ret->high_slices, SLICE_NUM_HIGH); + for (i = 0; i < SLICE_NUM_LOW; i++) if (!slice_low_has_vma(mm, i)) - ret.low_slices |= 1u << i; + ret->low_slices |= 1u << i; if (mm->task_size <= SLICE_LOW_TOP) - return ret; + return; - for (i = 0; i < SLICE_NUM_HIGH; i++) + for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) if (!slice_high_has_vma(mm, i)) - ret.high_slices |= 1ul << i; - - return ret; + __set_bit(i, ret->high_slices); } -static struct slice_mask slice_mask_for_size(struct mm_struct *mm, int psize) +static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret) { unsigned char *hpsizes; int index, mask_index; - struct slice_mask ret = { 0, 0 }; unsigned long i; u64 lpsizes; + ret->low_slices = 0; + bitmap_zero(ret->high_slices, SLICE_NUM_HIGH); + lpsizes = mm->context.low_slices_psize; for (i = 0; i < SLICE_NUM_LOW; i++) if (((lpsizes >> (i * 4)) & 0xf) == psize) - ret.low_slices |= 1u << i; + ret->low_slices |= 1u << i; hpsizes = mm->context.high_slices_psize; - for (i = 0; i < SLICE_NUM_HIGH; i++) { + for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) { mask_index = i & 0x1; index = i >> 1; if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == psize) - ret.high_slices |= 1ul << i; + __set_bit(i, ret->high_slices); } - - return ret; } -static int slice_check_fit(struct slice_mask mask, struct slice_mask available) +static int slice_check_fit(struct mm_struct *mm, + struct slice_mask mask, struct slice_mask available) { + DECLARE_BITMAP(result, SLICE_NUM_HIGH); + unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.addr_limit); + + bitmap_and(result, mask.high_slices, + available.high_slices, slice_count); + return (mask.low_slices & available.low_slices) == mask.low_slices && - (mask.high_slices & available.high_slices) == mask.high_slices; + bitmap_equal(result, mask.high_slices, slice_count); } static void slice_flush_segments(void *parm) @@ -185,7 +186,7 @@ static void slice_flush_segments(void *parm) if (mm != current->active_mm) return; - copy_mm_to_paca(¤t->active_mm->context); + copy_mm_to_paca(current->active_mm); local_irq_save(flags); slb_flush_and_rebolt(); @@ -218,18 +219,18 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz mm->context.low_slices_psize = lpsizes; hpsizes = mm->context.high_slices_psize; - for (i = 0; i < SLICE_NUM_HIGH; i++) { + for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) { mask_index = i & 0x1; index = i >> 1; - if (mask.high_slices & (1ul << i)) + if (test_bit(i, mask.high_slices)) hpsizes[index] = (hpsizes[index] & ~(0xf << (mask_index * 4))) | (((unsigned long)psize) << (mask_index * 4)); } slice_dbg(" lsps=%lx, hsps=%lx\n", - mm->context.low_slices_psize, - mm->context.high_slices_psize); + (unsigned long)mm->context.low_slices_psize, + (unsigned long)mm->context.high_slices_psize); spin_unlock_irqrestore(&slice_convert_lock, flags); @@ -257,14 +258,14 @@ static bool slice_scan_available(unsigned long addr, slice = GET_HIGH_SLICE_INDEX(addr); *boundary_addr = (slice + end) ? ((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP; - return !!(available.high_slices & (1ul << slice)); + return !!test_bit(slice, available.high_slices); } } static unsigned long slice_find_area_bottomup(struct mm_struct *mm, unsigned long len, struct slice_mask available, - int psize) + int psize, unsigned long high_limit) { int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); unsigned long addr, found, next_end; @@ -276,7 +277,10 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm, info.align_offset = 0; addr = TASK_UNMAPPED_BASE; - while (addr < TASK_SIZE) { + /* + * Check till the allow max value for this mmap request + */ + while (addr < high_limit) { info.low_limit = addr; if (!slice_scan_available(addr, available, 1, &addr)) continue; @@ -288,8 +292,8 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm, * Check if we need to reduce the range, or if we can * extend it to cover the next available slice. */ - if (addr >= TASK_SIZE) - addr = TASK_SIZE; + if (addr >= high_limit) + addr = high_limit; else if (slice_scan_available(addr, available, 1, &next_end)) { addr = next_end; goto next_slice; @@ -307,7 +311,7 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm, static unsigned long slice_find_area_topdown(struct mm_struct *mm, unsigned long len, struct slice_mask available, - int psize) + int psize, unsigned long high_limit) { int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); unsigned long addr, found, prev; @@ -319,6 +323,15 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, info.align_offset = 0; addr = mm->mmap_base; + /* + * If we are trying to allocate above DEFAULT_MAP_WINDOW + * Add the different to the mmap_base. + * Only for that request for which high_limit is above + * DEFAULT_MAP_WINDOW we should apply this. + */ + if (high_limit > DEFAULT_MAP_WINDOW) + addr += mm->context.addr_limit - DEFAULT_MAP_WINDOW; + while (addr > PAGE_SIZE) { info.high_limit = addr; if (!slice_scan_available(addr - 1, available, 0, &addr)) @@ -350,29 +363,38 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, * can happen with large stack limits and large mmap() * allocations. */ - return slice_find_area_bottomup(mm, len, available, psize); + return slice_find_area_bottomup(mm, len, available, psize, high_limit); } static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len, struct slice_mask mask, int psize, - int topdown) + int topdown, unsigned long high_limit) { if (topdown) - return slice_find_area_topdown(mm, len, mask, psize); + return slice_find_area_topdown(mm, len, mask, psize, high_limit); else - return slice_find_area_bottomup(mm, len, mask, psize); + return slice_find_area_bottomup(mm, len, mask, psize, high_limit); } -#define or_mask(dst, src) do { \ - (dst).low_slices |= (src).low_slices; \ - (dst).high_slices |= (src).high_slices; \ -} while (0) +static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src) +{ + DECLARE_BITMAP(result, SLICE_NUM_HIGH); + + dst->low_slices |= src->low_slices; + bitmap_or(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH); + bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH); +} -#define andnot_mask(dst, src) do { \ - (dst).low_slices &= ~(src).low_slices; \ - (dst).high_slices &= ~(src).high_slices; \ -} while (0) +static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *src) +{ + DECLARE_BITMAP(result, SLICE_NUM_HIGH); + + dst->low_slices &= ~src->low_slices; + + bitmap_andnot(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH); + bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH); +} #ifdef CONFIG_PPC_64K_PAGES #define MMU_PAGE_BASE MMU_PAGE_64K @@ -384,14 +406,43 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, unsigned long flags, unsigned int psize, int topdown) { - struct slice_mask mask = {0, 0}; + struct slice_mask mask; struct slice_mask good_mask; - struct slice_mask potential_mask = {0,0} /* silence stupid warning */; - struct slice_mask compat_mask = {0, 0}; + struct slice_mask potential_mask; + struct slice_mask compat_mask; int fixed = (flags & MAP_FIXED); int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); struct mm_struct *mm = current->mm; unsigned long newaddr; + unsigned long high_limit; + + /* + * Check if we need to expland slice area. + */ + if (unlikely(addr > mm->context.addr_limit && + mm->context.addr_limit != TASK_SIZE)) { + mm->context.addr_limit = TASK_SIZE; + on_each_cpu(slice_flush_segments, mm, 1); + } + /* + * This mmap request can allocate upt to 512TB + */ + if (addr > DEFAULT_MAP_WINDOW) + high_limit = mm->context.addr_limit; + else + high_limit = DEFAULT_MAP_WINDOW; + /* + * init different masks + */ + mask.low_slices = 0; + bitmap_zero(mask.high_slices, SLICE_NUM_HIGH); + + /* silence stupid warning */; + potential_mask.low_slices = 0; + bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH); + + compat_mask.low_slices = 0; + bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH); /* Sanity checks */ BUG_ON(mm->task_size == 0); @@ -423,7 +474,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* First make up a "good" mask of slices that have the right size * already */ - good_mask = slice_mask_for_size(mm, psize); + slice_mask_for_size(mm, psize, &good_mask); slice_print_mask(" good_mask", good_mask); /* @@ -448,22 +499,22 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, #ifdef CONFIG_PPC_64K_PAGES /* If we support combo pages, we can allow 64k pages in 4k slices */ if (psize == MMU_PAGE_64K) { - compat_mask = slice_mask_for_size(mm, MMU_PAGE_4K); + slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask); if (fixed) - or_mask(good_mask, compat_mask); + slice_or_mask(&good_mask, &compat_mask); } #endif /* First check hint if it's valid or if we have MAP_FIXED */ if (addr != 0 || fixed) { /* Build a mask for the requested range */ - mask = slice_range_to_mask(addr, len); + slice_range_to_mask(addr, len, &mask); slice_print_mask(" mask", mask); /* Check if we fit in the good mask. If we do, we just return, * nothing else to do */ - if (slice_check_fit(mask, good_mask)) { + if (slice_check_fit(mm, mask, good_mask)) { slice_dbg(" fits good !\n"); return addr; } @@ -471,7 +522,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* Now let's see if we can find something in the existing * slices for that size */ - newaddr = slice_find_area(mm, len, good_mask, psize, topdown); + newaddr = slice_find_area(mm, len, good_mask, + psize, topdown, high_limit); if (newaddr != -ENOMEM) { /* Found within the good mask, we don't have to setup, * we thus return directly @@ -484,11 +536,11 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* We don't fit in the good mask, check what other slices are * empty and thus can be converted */ - potential_mask = slice_mask_for_free(mm); - or_mask(potential_mask, good_mask); + slice_mask_for_free(mm, &potential_mask); + slice_or_mask(&potential_mask, &good_mask); slice_print_mask(" potential", potential_mask); - if ((addr != 0 || fixed) && slice_check_fit(mask, potential_mask)) { + if ((addr != 0 || fixed) && slice_check_fit(mm, mask, potential_mask)) { slice_dbg(" fits potential !\n"); goto convert; } @@ -503,7 +555,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, * anywhere in the good area. */ if (addr) { - addr = slice_find_area(mm, len, good_mask, psize, topdown); + addr = slice_find_area(mm, len, good_mask, + psize, topdown, high_limit); if (addr != -ENOMEM) { slice_dbg(" found area at 0x%lx\n", addr); return addr; @@ -513,28 +566,29 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* Now let's see if we can find something in the existing slices * for that size plus free slices */ - addr = slice_find_area(mm, len, potential_mask, psize, topdown); + addr = slice_find_area(mm, len, potential_mask, + psize, topdown, high_limit); #ifdef CONFIG_PPC_64K_PAGES if (addr == -ENOMEM && psize == MMU_PAGE_64K) { /* retry the search with 4k-page slices included */ - or_mask(potential_mask, compat_mask); - addr = slice_find_area(mm, len, potential_mask, psize, - topdown); + slice_or_mask(&potential_mask, &compat_mask); + addr = slice_find_area(mm, len, potential_mask, + psize, topdown, high_limit); } #endif if (addr == -ENOMEM) return -ENOMEM; - mask = slice_range_to_mask(addr, len); + slice_range_to_mask(addr, len, &mask); slice_dbg(" found potential area at 0x%lx\n", addr); slice_print_mask(" mask", mask); convert: - andnot_mask(mask, good_mask); - andnot_mask(mask, compat_mask); - if (mask.low_slices || mask.high_slices) { + slice_andnot_mask(&mask, &good_mask); + slice_andnot_mask(&mask, &compat_mask); + if (mask.low_slices || !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH)) { slice_convert(mm, mask, psize); if (psize > MMU_PAGE_BASE) on_each_cpu(slice_flush_segments, mm, 1); @@ -649,8 +703,8 @@ void slice_set_user_psize(struct mm_struct *mm, unsigned int psize) slice_dbg(" lsps=%lx, hsps=%lx\n", - mm->context.low_slices_psize, - mm->context.high_slices_psize); + (unsigned long)mm->context.low_slices_psize, + (unsigned long)mm->context.high_slices_psize); bail: spin_unlock_irqrestore(&slice_convert_lock, flags); @@ -659,9 +713,11 @@ void slice_set_user_psize(struct mm_struct *mm, unsigned int psize) void slice_set_range_psize(struct mm_struct *mm, unsigned long start, unsigned long len, unsigned int psize) { - struct slice_mask mask = slice_range_to_mask(start, len); + struct slice_mask mask; VM_BUG_ON(radix_enabled()); + + slice_range_to_mask(start, len, &mask); slice_convert(mm, mask, psize); } @@ -694,14 +750,14 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, if (radix_enabled()) return 0; - mask = slice_range_to_mask(addr, len); - available = slice_mask_for_size(mm, psize); + slice_range_to_mask(addr, len, &mask); + slice_mask_for_size(mm, psize, &available); #ifdef CONFIG_PPC_64K_PAGES /* We need to account for 4k slices too */ if (psize == MMU_PAGE_64K) { struct slice_mask compat_mask; - compat_mask = slice_mask_for_size(mm, MMU_PAGE_4K); - or_mask(available, compat_mask); + slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask); + slice_or_mask(&available, &compat_mask); } #endif @@ -711,6 +767,6 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, slice_print_mask(" mask", mask); slice_print_mask(" available", available); #endif - return !slice_check_fit(mask, available); + return !slice_check_fit(mm, mask, available); } #endif |