From 9848e49a9a9aab075d79c5d2856abb879495f97f Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Thu, 16 Jan 2014 03:38:58 +0400 Subject: xtensa: fix warning '"CONFIG_OF" is not defined' The warning only shows up when building MMUv3 configuration with OF support disabled. Signed-off-by: Max Filippov --- arch/xtensa/include/asm/io.h | 2 +- arch/xtensa/include/asm/vectors.h | 2 +- arch/xtensa/mm/mmu.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h index 2a042d430c25..74944207167e 100644 --- a/arch/xtensa/include/asm/io.h +++ b/arch/xtensa/include/asm/io.h @@ -25,7 +25,7 @@ #ifdef CONFIG_MMU -#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF +#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF) extern unsigned long xtensa_kio_paddr; static inline unsigned long xtensa_get_kio_paddr(void) diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h index 5791b45d5a5d..f74ddfbb92ef 100644 --- a/arch/xtensa/include/asm/vectors.h +++ b/arch/xtensa/include/asm/vectors.h @@ -25,7 +25,7 @@ #define XCHAL_KIO_DEFAULT_PADDR 0xf0000000 #define XCHAL_KIO_SIZE 0x10000000 -#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF +#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF) #define XCHAL_KIO_PADDR xtensa_get_kio_paddr() #else #define XCHAL_KIO_PADDR XCHAL_KIO_DEFAULT_PADDR diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c index 36ec171698b8..861203e958da 100644 --- a/arch/xtensa/mm/mmu.c +++ b/arch/xtensa/mm/mmu.c @@ -39,7 +39,7 @@ void init_mmu(void) set_itlbcfg_register(0); set_dtlbcfg_register(0); #endif -#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF +#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF) /* * Update the IO area mapping in case xtensa_kio_paddr has changed */ -- cgit v1.2.3 From 45ec8860be2f681b2e3e521a3fb4554ec29fbaac Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Sun, 19 Jan 2014 20:00:48 +0400 Subject: xtensa: export ccount_freq Now that ccount_freq is used in udelay and ndelay it needs to be exported in order to be available to modules. Signed-off-by: Max Filippov --- arch/xtensa/kernel/time.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 08b769d3b3a1..2a1823de69cc 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -30,6 +30,7 @@ #include unsigned long ccount_freq; /* ccount Hz */ +EXPORT_SYMBOL(ccount_freq); static cycle_t ccount_read(struct clocksource *cs) { -- cgit v1.2.3 From b8989db9d82465bf38a48a4d3ef32e7d8afc4d08 Mon Sep 17 00:00:00 2001 From: Alan Date: Mon, 20 Jan 2014 18:01:56 +0000 Subject: x86, doc, kconfig: Fix dud URL for Microcode data The actual data lives in the Intel download center, and that ought to also be a reliable way to continue to find it. Unfortunately the actual URL needed for doing it directly is about a foot long so give instructions. Signed-off-by: Alan Cox Link: http://lkml.kernel.org/r/20140120180056.7173.62222.stgit@alan.etchedpixels.co.uk Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0952ecd60eca..64199bc08d66 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1064,9 +1064,9 @@ config MICROCODE_INTEL This options enables microcode patch loading support for Intel processors. - For latest news and information on obtaining all the required - Intel ingredients for this driver, check: - . + For the current Intel microcode data package go to + and search for + 'Linux Processor Microcode Data File'. config MICROCODE_AMD bool "AMD microcode loading support" -- cgit v1.2.3 From fb53a1ab88d14848dc292842e35c3bda3a665997 Mon Sep 17 00:00:00 2001 From: Aravind Gopalakrishnan Date: Thu, 23 Jan 2014 16:13:32 -0600 Subject: x86/quirks: Add workaround for AMD F16h Erratum792 The workaround for this Erratum is included in AGESA. But BIOSes spun only after Jan2014 will have the fix (atleast server versions of the chip). The erratum affects both embedded and server platforms and since we cannot say with certainity that ALL BIOSes on systems out in the field will have the fix, we should probably insulate ourselves in case BIOS does not do the right thing or someone is using old BIOSes. Refer to Revision Guide for AMD F16h models 00h-0fh, document 51810 Rev. 3.04, November2013 for details on the Erratum. Tested the patch on Fam16h server platform and it works fine. Signed-off-by: Aravind Gopalakrishnan Cc: Cc: Cc: Cc: Cc: Link: http://lkml.kernel.org/r/1390515212-1824-1-git-send-email-Aravind.Gopalakrishnan@amd.com [ Minor edits. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/quirks.c | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 04ee1e2e4c02..7c6acd4b8995 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -571,3 +571,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5, quirk_amd_nb_node); #endif + +#ifdef CONFIG_PCI +/* + * Processor does not ensure DRAM scrub read/write sequence + * is atomic wrt accesses to CC6 save state area. Therefore + * if a concurrent scrub read/write access is to same address + * the entry may appear as if it is not written. This quirk + * applies to Fam16h models 00h-0Fh + * + * See "Revision Guide" for AMD F16h models 00h-0fh, + * document 51810 rev. 3.04, Nov 2013 + */ +static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev) +{ + u32 val; + + /* + * Suggested workaround: + * set D18F3x58[4:0] = 00h and set D18F3x5C[0] = 0b + */ + pci_read_config_dword(dev, 0x58, &val); + if (val & 0x1F) { + val &= ~(0x1F); + pci_write_config_dword(dev, 0x58, val); + } + + pci_read_config_dword(dev, 0x5C, &val); + if (val & BIT(0)) { + val &= ~BIT(0); + pci_write_config_dword(dev, 0x5c, val); + } +} + +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3, + amd_disable_seq_and_redirect_scrub); + +#endif -- cgit v1.2.3 From 2993ae3305ad10b41e0d0bc2662f7754ee8e30fa Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 21 Jan 2014 10:22:09 +0300 Subject: x86/AMD/NB: Fix amd_set_subcaches() parameter type This is under CAP_SYS_ADMIN, but Smatch complains that mask comes from the user and the test for "mask > 0xf" can underflow. The fix is simple: amd_set_subcaches() should hand down not an 'int' but an 'unsigned long' like it was originally indended to do. Signed-off-by: Dan Carpenter Acked-by: Borislav Petkov Cc: Borislav Petkov Cc: Daniel J Blueman Link: http://lkml.kernel.org/r/20140121072209.GA22095@elgon.mountain Signed-off-by: Ingo Molnar --- arch/x86/include/asm/amd_nb.h | 2 +- arch/x86/kernel/amd_nb.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index a54ee1d054d9..aaac3b2fb746 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -19,7 +19,7 @@ extern int amd_cache_northbridges(void); extern void amd_flush_garts(void); extern int amd_numa_init(void); extern int amd_get_subcaches(int); -extern int amd_set_subcaches(int, int); +extern int amd_set_subcaches(int, unsigned long); struct amd_l3_cache { unsigned indices; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 59554dca96ec..dec8de4e1663 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -179,7 +179,7 @@ int amd_get_subcaches(int cpu) return (mask >> (4 * cuid)) & 0xf; } -int amd_set_subcaches(int cpu, int mask) +int amd_set_subcaches(int cpu, unsigned long mask) { static unsigned int reset, ban; struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu)); -- cgit v1.2.3 From ec65993443736a5091b68e80ff1734548944a4b8 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:16 -0800 Subject: mm, x86: Account for TLB flushes only when debugging Bisection between 3.11 and 3.12 fingered commit 9824cf97 ("mm: vmstats: tlb flush counters") to cause overhead problems. The counters are undeniably useful but how often do we really need to debug TLB flush related issues? It does not justify taking the penalty everywhere so make it a debugging option. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Hugh Dickins Cc: Alex Shi Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-XzxjntugxuwpxXhcrxqqh53b@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/tlbflush.h | 6 +++--- arch/x86/kernel/cpu/mtrr/generic.c | 4 ++-- arch/x86/mm/tlb.c | 14 +++++++------- include/linux/vm_event_item.h | 4 +++- include/linux/vmstat.h | 8 ++++++++ mm/vmstat.c | 4 +++- 6 files changed, 26 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index e6d90babc245..04905bfc508b 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void) static inline void __flush_tlb_one(unsigned long addr) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr) */ static inline void __flush_tlb_up(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); } static inline void flush_tlb_all(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb_all(); } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index ce2d0a2c3e4f..0e25a1bc5ab5 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) } /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Save MTRR state */ @@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) static void post_set(void) __releases(set_atomicity_lock) { /* Flush TLBs (no need to flush caches - they are disabled) */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Intel (P6) standard MTRRs */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index ae699b3bbac8..05446c1cccfe 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -103,7 +103,7 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; - count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { if (f->flush_end == TLB_FLUSH_ALL) local_flush_tlb(); @@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, info.flush_start = start; info.flush_end = end; - count_vm_event(NR_TLB_REMOTE_FLUSH); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); if (is_uv_system()) { unsigned int cpu; @@ -151,7 +151,7 @@ void flush_tlb_current_task(void) preempt_disable(); - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -215,7 +215,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, /* tlb_flushall_shift is on balance point, details in commit log */ if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { if (has_large_page(mm, start, end)) { @@ -224,7 +224,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, } /* flush range by one by one 'invlpg' */ for (addr = start; addr < end; addr += PAGE_SIZE) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -262,7 +262,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) static void do_flush_tlb_all(void *info) { - count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); __flush_tlb_all(); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) leave_mm(smp_processor_id()); @@ -270,7 +270,7 @@ static void do_flush_tlb_all(void *info) void flush_tlb_all(void) { - count_vm_event(NR_TLB_REMOTE_FLUSH); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); on_each_cpu(do_flush_tlb_all, NULL, 1); } diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index c557c6d096de..3a712e2e7d76 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -71,12 +71,14 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif +#ifdef CONFIG_DEBUG_TLBFLUSH #ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif +#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, +#endif /* CONFIG_DEBUG_TLBFLUSH */ NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index e4b948080d20..80ebba9c2e87 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -83,6 +83,14 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_DEBUG_TLBFLUSH +#define count_vm_tlb_event(x) count_vm_event(x) +#define count_vm_tlb_events(x, y) count_vm_events(x, y) +#else +#define count_vm_tlb_event(x) do {} while (0) +#define count_vm_tlb_events(x, y) do { (void)(y); } while (0) +#endif + #define __count_zone_vm_events(item, zone, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + \ zone_idx(zone), delta) diff --git a/mm/vmstat.c b/mm/vmstat.c index 72496140ac08..def5dd2fbe61 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -851,12 +851,14 @@ const char * const vmstat_text[] = { "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif +#ifdef CONFIG_DEBUG_TLBFLUSH #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", -#endif +#endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", +#endif /* CONFIG_DEBUG_TLBFLUSH */ #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; -- cgit v1.2.3 From 15aa368255f249df0b2af630c9487bb5471bd7da Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:18 -0800 Subject: x86/mm: Clean up inconsistencies when flushing TLB ranges NR_TLB_LOCAL_FLUSH_ALL is not always accounted for correctly and the comparison with total_vm is done before taking tlb_flushall_shift into account. Clean it up. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Alex Shi Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Hugh Dickins Link: http://lkml.kernel.org/n/tip-Iz5gcahrgskIldvukulzi0hh@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/tlb.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 05446c1cccfe..5176526ddd59 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -189,6 +189,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, { unsigned long addr; unsigned act_entries, tlb_entries = 0; + unsigned long nr_base_pages; preempt_disable(); if (current->active_mm != mm) @@ -210,18 +211,17 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, tlb_entries = tlb_lli_4k[ENTRIES]; else tlb_entries = tlb_lld_4k[ENTRIES]; + /* Assume all of TLB entries was occupied by this task */ - act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm; + act_entries = tlb_entries >> tlb_flushall_shift; + act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm; + nr_base_pages = (end - start) >> PAGE_SHIFT; /* tlb_flushall_shift is on balance point, details in commit log */ - if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) { + if (nr_base_pages > act_entries || has_large_page(mm, start, end)) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { - if (has_large_page(mm, start, end)) { - local_flush_tlb(); - goto flush_all; - } /* flush range by one by one 'invlpg' */ for (addr = start; addr < end; addr += PAGE_SIZE) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); -- cgit v1.2.3 From 71b54f8263860a37dd9f50f81880a9d681fd9c10 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:19 -0800 Subject: x86/mm: Eliminate redundant page table walk during TLB range flushing When choosing between doing an address space or ranged flush, the x86 implementation of flush_tlb_mm_range takes into account whether there are any large pages in the range. A per-page flush typically requires fewer entries than would covered by a single large page and the check is redundant. There is one potential exception. THP migration flushes single THP entries and it conceivably would benefit from flushing a single entry instead of the mm. However, this flush is after a THP allocation, copy and page table update potentially with any other threads serialised behind it. In comparison to that, the flush is noise. It makes more sense to optimise balancing to require fewer flushes than to optimise the flush itself. This patch deletes the redundant huge page check. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Alex Shi Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-sgei1drpOcburujPsfh6ovmo@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/tlb.c | 28 +--------------------------- 1 file changed, 1 insertion(+), 27 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5176526ddd59..dd8dda167a24 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -158,32 +158,6 @@ void flush_tlb_current_task(void) preempt_enable(); } -/* - * It can find out the THP large page, or - * HUGETLB page in tlb_flush when THP disabled - */ -static inline unsigned long has_large_page(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - unsigned long addr = ALIGN(start, HPAGE_SIZE); - for (; addr < end; addr += HPAGE_SIZE) { - pgd = pgd_offset(mm, addr); - if (likely(!pgd_none(*pgd))) { - pud = pud_offset(pgd, addr); - if (likely(!pud_none(*pud))) { - pmd = pmd_offset(pud, addr); - if (likely(!pmd_none(*pmd))) - if (pmd_large(*pmd)) - return addr; - } - } - } - return 0; -} - void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { @@ -218,7 +192,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, nr_base_pages = (end - start) >> PAGE_SHIFT; /* tlb_flushall_shift is on balance point, details in commit log */ - if (nr_base_pages > act_entries || has_large_page(mm, start, end)) { + if (nr_base_pages > act_entries) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { -- cgit v1.2.3 From f98b7a772ab51b52ca4d2a14362fc0e0c8a2e0f3 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:21 -0800 Subject: x86: mm: change tlb_flushall_shift for IvyBridge There was a large performance regression that was bisected to commit 611ae8e3 ("x86/tlb: enable tlb flush range support for x86"). This patch simply changes the default balance point between a local and global flush for IvyBridge. In the interest of allowing the tests to be reproduced, this patch was tested using mmtests 0.15 with the following configurations configs/config-global-dhp__tlbflush-performance configs/config-global-dhp__scheduler-performance configs/config-global-dhp__network-performance Results are from two machines Ivybridge 4 threads: Intel(R) Core(TM) i3-3240 CPU @ 3.40GHz Ivybridge 8 threads: Intel(R) Core(TM) i7-3770 CPU @ 3.40GHz Page fault microbenchmark showed nothing interesting. Ebizzy was configured to run multiple iterations and threads. Thread counts ranged from 1 to NR_CPUS*2. For each thread count, it ran 100 iterations and each iteration lasted 10 seconds. Ivybridge 4 threads 3.13.0-rc7 3.13.0-rc7 vanilla altshift-v3 Mean 1 6395.44 ( 0.00%) 6789.09 ( 6.16%) Mean 2 7012.85 ( 0.00%) 8052.16 ( 14.82%) Mean 3 6403.04 ( 0.00%) 6973.74 ( 8.91%) Mean 4 6135.32 ( 0.00%) 6582.33 ( 7.29%) Mean 5 6095.69 ( 0.00%) 6526.68 ( 7.07%) Mean 6 6114.33 ( 0.00%) 6416.64 ( 4.94%) Mean 7 6085.10 ( 0.00%) 6448.51 ( 5.97%) Mean 8 6120.62 ( 0.00%) 6462.97 ( 5.59%) Ivybridge 8 threads 3.13.0-rc7 3.13.0-rc7 vanilla altshift-v3 Mean 1 7336.65 ( 0.00%) 7787.02 ( 6.14%) Mean 2 8218.41 ( 0.00%) 9484.13 ( 15.40%) Mean 3 7973.62 ( 0.00%) 8922.01 ( 11.89%) Mean 4 7798.33 ( 0.00%) 8567.03 ( 9.86%) Mean 5 7158.72 ( 0.00%) 8214.23 ( 14.74%) Mean 6 6852.27 ( 0.00%) 7952.45 ( 16.06%) Mean 7 6774.65 ( 0.00%) 7536.35 ( 11.24%) Mean 8 6510.50 ( 0.00%) 6894.05 ( 5.89%) Mean 12 6182.90 ( 0.00%) 6661.29 ( 7.74%) Mean 16 6100.09 ( 0.00%) 6608.69 ( 8.34%) Ebizzy hits the worst case scenario for TLB range flushing every time and it shows for these Ivybridge CPUs at least that the default choice is a poor on. The patch addresses the problem. Next was a tlbflush microbenchmark written by Alex Shi at http://marc.info/?l=linux-kernel&m=133727348217113 . It measures access costs while the TLB is being flushed. The expectation is that if there are always full TLB flushes that the benchmark would suffer and it benefits from range flushing There are 320 iterations of the test per thread count. The number of entries is randomly selected with a min of 1 and max of 512. To ensure a reasonably even spread of entries, the full range is broken up into 8 sections and a random number selected within that section. iteration 1, random number between 0-64 iteration 2, random number between 64-128 etc This is still a very weak methodology. When you do not know what are typical ranges, random is a reasonable choice but it can be easily argued that the opimisation was for smaller ranges and an even spread is not representative of any workload that matters. To improve this, we'd need to know the probability distribution of TLB flush range sizes for a set of workloads that are considered "common", build a synthetic trace and feed that into this benchmark. Even that is not perfect because it would not account for the time between flushes but there are limits of what can be reasonably done and still be doing something useful. If a representative synthetic trace is provided then this benchmark could be revisited and the shift values retuned. Ivybridge 4 threads 3.13.0-rc7 3.13.0-rc7 vanilla altshift-v3 Mean 1 10.50 ( 0.00%) 10.50 ( 0.03%) Mean 2 17.59 ( 0.00%) 17.18 ( 2.34%) Mean 3 22.98 ( 0.00%) 21.74 ( 5.41%) Mean 5 47.13 ( 0.00%) 46.23 ( 1.92%) Mean 8 43.30 ( 0.00%) 42.56 ( 1.72%) Ivybridge 8 threads 3.13.0-rc7 3.13.0-rc7 vanilla altshift-v3 Mean 1 9.45 ( 0.00%) 9.36 ( 0.93%) Mean 2 9.37 ( 0.00%) 9.70 ( -3.54%) Mean 3 9.36 ( 0.00%) 9.29 ( 0.70%) Mean 5 14.49 ( 0.00%) 15.04 ( -3.75%) Mean 8 41.08 ( 0.00%) 38.73 ( 5.71%) Mean 13 32.04 ( 0.00%) 31.24 ( 2.49%) Mean 16 40.05 ( 0.00%) 39.04 ( 2.51%) For both CPUs, average access time is reduced which is good as this is the benchmark that was used to tune the shift values in the first place albeit it is now known *how* the benchmark was used. The scheduler benchmarks were somewhat inconclusive. They showed gains and losses and makes me reconsider how stable those benchmarks really are or if something else might be interfering with the test results recently. Network benchmarks were inconclusive. Almost all results were flat except for netperf-udp tests on the 4 thread machine. These results were unstable and showed large variations between reboots. It is unknown if this is a recent problems but I've noticed before that netperf-udp results tend to vary. Based on these results, changing the default for Ivybridge seems like a logical choice. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Alex Shi Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-cqnadffh1tiqrshthRj3Esge@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ea04b342c026..bbe1b8b1f1c4 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -628,7 +628,7 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) tlb_flushall_shift = 5; break; case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 1; + tlb_flushall_shift = 2; break; default: tlb_flushall_shift = 6; -- cgit v1.2.3 From b9a3b4c976c1209957326537ad5c0bb633dfd764 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:22 -0800 Subject: mm, x86: Revisit tlb_flushall_shift tuning for page flushes except on IvyBridge There was a large ebizzy performance regression that was bisected to commit 611ae8e3 (x86/tlb: enable tlb flush range support for x86). The problem was related to the tlb_flushall_shift tuning for IvyBridge which was altered. The problem is that it is not clear if the tuning values for each CPU family is correct as the methodology used to tune the values is unclear. This patch uses a conservative tlb_flushall_shift value for all CPU families except IvyBridge so the decision can be revisited if any regression is found as a result of this change. IvyBridge is an exception as testing with one methodology determined that the value of 2 is acceptable. Details are in the changelog for the patch "x86: mm: Change tlb_flushall_shift for IvyBridge". One important aspect of this to watch out for is Xen. The original commit log mentioned large performance gains on Xen. It's possible Xen is more sensitive to this value if it flushes small ranges of pages more frequently than workloads on bare metal typically do. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Alex Shi Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-dyzMww3fqugnhbhgo6Gxmtkw@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/amd.c | 5 +---- arch/x86/kernel/cpu/intel.c | 10 +++------- 2 files changed, 4 insertions(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 59bfebc8c805..96abccaada33 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -768,10 +768,7 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) { - tlb_flushall_shift = 5; - - if (c->x86 <= 0x11) - tlb_flushall_shift = 4; + tlb_flushall_shift = 6; } static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index bbe1b8b1f1c4..d358a3928b8f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -615,21 +615,17 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) case 0x61d: /* six-core 45 nm xeon "Dunnington" */ tlb_flushall_shift = -1; break; + case 0x63a: /* Ivybridge */ + tlb_flushall_shift = 2; + break; case 0x61a: /* 45 nm nehalem, "Bloomfield" */ case 0x61e: /* 45 nm nehalem, "Lynnfield" */ case 0x625: /* 32 nm nehalem, "Clarkdale" */ case 0x62c: /* 32 nm nehalem, "Gulftown" */ case 0x62e: /* 45 nm nehalem-ex, "Beckton" */ case 0x62f: /* 32 nm Xeon E7 */ - tlb_flushall_shift = 6; - break; case 0x62a: /* SandyBridge */ case 0x62d: /* SandyBridge, "Romely-EP" */ - tlb_flushall_shift = 5; - break; - case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 2; - break; default: tlb_flushall_shift = 6; } -- cgit v1.2.3 From a85eba8814631d0d48361c8b9a7ee0984e80c03c Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Tue, 21 Jan 2014 14:33:15 -0800 Subject: arch/x86/mm/srat: Skip NUMA_NO_NODE while parsing SLIT When ACPI SLIT table has an I/O locality (i.e. a locality unique to an I/O device), numa_set_distance() emits this warning message: NUMA: Warning: node ids are out of bound, from=-1 to=-1 distance=10 acpi_numa_slit_init() calls numa_set_distance() with pxm_to_node(), which assumes that all localities have been parsed with SRAT previously. SRAT does not list I/O localities, where as SLIT lists all localities including I/Os. Hence, pxm_to_node() returns NUMA_NO_NODE (-1) for an I/O locality. I/O localities are not supported and are ignored today, but emitting such warning message leads to unnecessary confusion. Change acpi_numa_slit_init() to avoid calling numa_set_distance() with NUMA_NO_NODE. Signed-off-by: Toshi Kani Acked-by: David Rientjes Signed-off-by: Andrew Morton Cc: Yinghai Lu Link: http://lkml.kernel.org/n/tip-dSvpjjvp8aMzs1ybkftxohlh@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/srat.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 266ca912f62e..5ecf65117e6f 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -42,15 +42,25 @@ static __init inline int srat_disabled(void) return acpi_numa < 0; } -/* Callback for SLIT parsing */ +/* + * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for + * I/O localities since SRAT does not list them. I/O localities are + * not supported at this point. + */ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) { int i, j; - for (i = 0; i < slit->locality_count; i++) - for (j = 0; j < slit->locality_count; j++) + for (i = 0; i < slit->locality_count; i++) { + if (pxm_to_node(i) == NUMA_NO_NODE) + continue; + for (j = 0; j < slit->locality_count; j++) { + if (pxm_to_node(j) == NUMA_NO_NODE) + continue; numa_set_distance(pxm_to_node(i), pxm_to_node(j), slit->entry[slit->locality_count * i + j]); + } + } } /* Callback for Proximity Domain -> x2APIC mapping */ -- cgit v1.2.3 From edc6bc784028f2ef80dff0ff697363ff5a06e3a3 Mon Sep 17 00:00:00 2001 From: David Cohen Date: Tue, 21 Jan 2014 10:41:39 -0800 Subject: x86/intel/mid: Fix X86_INTEL_MID dependencies This patch fixes the following warning: warning: (X86_INTEL_MID) selects INTEL_SCU_IPC which has unmet direct dependencies (X86 && X86_PLATFORM_DEVICES && X86_INTEL_MID) It happens because when selected, X86_INTEL_MID tries to select INTEL_SCU_IPC regardless all its dependencies are met or not. This patch fixes it by adding the missing X86_PLATFORM_DEVICES dependency to X86_INTEL_MID. Reported-by: kbuild test robot Signed-off-by: David Cohen Link: http://lkml.kernel.org/r/1390329699-20782-1-git-send-email-david.a.cohen@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cb9af474dfca..3b6922ebf170 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -443,6 +443,7 @@ config X86_INTEL_MID bool "Intel MID platform support" depends on X86_32 depends on X86_EXTENDED_PLATFORM + depends on X86_PLATFORM_DEVICES depends on PCI depends on PCI_GOANY depends on X86_IO_APIC -- cgit v1.2.3 From e2fd1374c705abe4661df3fb6fadb3879c7c1846 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 22 Jan 2014 08:04:43 +0400 Subject: xtensa: introduce spill_registers_kernel macro Most in-kernel users want registers spilled on the kernel stack and don't require PS.EXCM to be set. That means that they don't need fixup routine and could reuse regular window overflow mechanism for that, which makes spill routine very simple. Cc: stable@vger.kernel.org Suggested-by: Chris Zankel Signed-off-by: Max Filippov --- arch/xtensa/include/asm/traps.h | 44 +++++++++++++++++++----------- arch/xtensa/kernel/entry.S | 60 ++++++++++++++++++++++++++++++++--------- 2 files changed, 76 insertions(+), 28 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h index 8c194f6af45e..677bfcf4ee5d 100644 --- a/arch/xtensa/include/asm/traps.h +++ b/arch/xtensa/include/asm/traps.h @@ -23,25 +23,37 @@ void secondary_trap_init(void); static inline void spill_registers(void) { - +#if XCHAL_NUM_AREGS > 16 __asm__ __volatile__ ( - "movi a14, "__stringify((1 << PS_EXCM_BIT) | LOCKLEVEL)"\n\t" - "mov a12, a0\n\t" - "rsr a13, sar\n\t" - "xsr a14, ps\n\t" - "movi a0, _spill_registers\n\t" - "rsync\n\t" - "callx0 a0\n\t" - "mov a0, a12\n\t" - "wsr a13, sar\n\t" - "wsr a14, ps\n\t" - : : -#if defined(CONFIG_FRAME_POINTER) - : "a2", "a3", "a4", "a11", "a12", "a13", "a14", "a15", + " call12 1f\n" + " _j 2f\n" + " retw\n" + " .align 4\n" + "1:\n" + " _entry a1, 48\n" + " addi a12, a0, 3\n" +#if XCHAL_NUM_AREGS > 32 + " .rept (" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n" + " _entry a1, 48\n" + " mov a12, a0\n" + " .endr\n" +#endif + " _entry a1, 48\n" +#if XCHAL_NUM_AREGS % 12 == 0 + " mov a8, a8\n" +#elif XCHAL_NUM_AREGS % 12 == 4 + " mov a12, a12\n" +#elif XCHAL_NUM_AREGS % 12 == 8 + " mov a4, a4\n" +#endif + " retw\n" + "2:\n" + : : : "a12", "a13", "memory"); #else - : "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15", + __asm__ __volatile__ ( + " mov a12, a12\n" + : : : "memory"); #endif - "memory"); } #endif /* _XTENSA_TRAPS_H */ diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index 21dbe6bdb8ed..0489918e40d2 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1794,6 +1794,43 @@ ENTRY(system_call) ENDPROC(system_call) +/* + * Spill live registers on the kernel stack macro. + * + * Entry condition: ps.woe is set, ps.excm is cleared + * Exit condition: windowstart has single bit set + * May clobber: a12, a13 + */ + .macro spill_registers_kernel + +#if XCHAL_NUM_AREGS > 16 + call12 1f + _j 2f + retw + .align 4 +1: + _entry a1, 48 + addi a12, a0, 3 +#if XCHAL_NUM_AREGS > 32 + .rept (XCHAL_NUM_AREGS - 32) / 12 + _entry a1, 48 + mov a12, a0 + .endr +#endif + _entry a1, 48 +#if XCHAL_NUM_AREGS % 12 == 0 + mov a8, a8 +#elif XCHAL_NUM_AREGS % 12 == 4 + mov a12, a12 +#elif XCHAL_NUM_AREGS % 12 == 8 + mov a4, a4 +#endif + retw +2: +#else + mov a12, a12 +#endif + .endm /* * Task switch. @@ -1806,21 +1843,20 @@ ENTRY(_switch_to) entry a1, 16 - mov a12, a2 # preserve 'prev' (a2) - mov a13, a3 # and 'next' (a3) + mov a10, a2 # preserve 'prev' (a2) + mov a11, a3 # and 'next' (a3) l32i a4, a2, TASK_THREAD_INFO l32i a5, a3, TASK_THREAD_INFO - save_xtregs_user a4 a6 a8 a9 a10 a11 THREAD_XTREGS_USER + save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER - s32i a0, a12, THREAD_RA # save return address - s32i a1, a12, THREAD_SP # save stack pointer + s32i a0, a10, THREAD_RA # save return address + s32i a1, a10, THREAD_SP # save stack pointer /* Disable ints while we manipulate the stack pointer. */ - movi a14, (1 << PS_EXCM_BIT) | LOCKLEVEL - xsr a14, ps + rsil a14, LOCKLEVEL rsr a3, excsave1 rsync s32i a3, a3, EXC_TABLE_FIXUP /* enter critical section */ @@ -1835,7 +1871,7 @@ ENTRY(_switch_to) /* Flush register file. */ - call0 _spill_registers # destroys a3, a4, and SAR + spill_registers_kernel /* Set kernel stack (and leave critical section) * Note: It's save to set it here. The stack will not be overwritten @@ -1851,13 +1887,13 @@ ENTRY(_switch_to) /* restore context of the task 'next' */ - l32i a0, a13, THREAD_RA # restore return address - l32i a1, a13, THREAD_SP # restore stack pointer + l32i a0, a11, THREAD_RA # restore return address + l32i a1, a11, THREAD_SP # restore stack pointer - load_xtregs_user a5 a6 a8 a9 a10 a11 THREAD_XTREGS_USER + load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER wsr a14, ps - mov a2, a12 # return 'prev' + mov a2, a10 # return 'prev' rsync retw -- cgit v1.2.3 From 3251f1e27a5a17f0efd436cfd1e7b9896cfab0a0 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 30 Oct 2013 16:18:25 +0400 Subject: xtensa: save current register frame in fast_syscall_spill_registers_fixup We need it saved because it contains a3 where we track which register windows we still need to spill, and fixup handler may call C exception handlers. Also fix comments. Cc: stable@vger.kernel.org Signed-off-by: Max Filippov --- arch/xtensa/kernel/entry.S | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'arch') diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index 0489918e40d2..b61e25146a2f 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1117,6 +1117,13 @@ ENDPROC(fast_syscall_spill_registers) * We basically restore WINDOWBASE and WINDOWSTART to the condition when * we entered the spill routine and jump to the user exception handler. * + * Note that we only need to restore the bits in windowstart that have not + * been spilled yet by the _spill_register routine. Luckily, a3 contains a + * rotated windowstart with only those bits set for frames that haven't been + * spilled yet. Because a3 is rotated such that bit 0 represents the register + * frame for the current windowbase - 1, we need to rotate a3 left by the + * value of the current windowbase + 1 and move it to windowstart. + * * a0: value of depc, original value in depc * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE * a3: exctable, original value in excsave1 @@ -1131,10 +1138,15 @@ ENTRY(fast_syscall_spill_registers_fixup) /* We need to make sure the current registers (a0-a3) are preserved. * To do this, we simply set the bit for the current window frame * in WS, so that the exception handlers save them to the task stack. + * + * Note: we use a3 to set the windowbase, so we take a special care + * of it, saving it in the original _spill_registers frame across + * the exception handler call. */ xsr a3, excsave1 # get spill-mask slli a3, a3, 1 # shift left by one + addi a3, a3, 1 # set the bit for the current window frame slli a2, a3, 32-WSBITS src a2, a3, a2 # a2 = xxwww1yyxxxwww1yy...... -- cgit v1.2.3 From 7de8246eba58c6f4c315b8c69fb29e445ccf3c80 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 28 Jan 2014 09:38:37 -0800 Subject: [IA64] Wire up new sched_setattr and sched_getattr syscalls New syscalls for v3.14 Signed-off-by: Tony Luck --- arch/ia64/include/asm/unistd.h | 2 +- arch/ia64/include/uapi/asm/unistd.h | 2 ++ arch/ia64/kernel/entry.S | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h index afd45e0d552e..ae763d8bf55a 100644 --- a/arch/ia64/include/asm/unistd.h +++ b/arch/ia64/include/asm/unistd.h @@ -11,7 +11,7 @@ -#define NR_syscalls 312 /* length of syscall table */ +#define NR_syscalls 314 /* length of syscall table */ /* * The following defines stop scripts/checksyscalls.sh from complaining about diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h index 34fd6fe46da1..715e85f858de 100644 --- a/arch/ia64/include/uapi/asm/unistd.h +++ b/arch/ia64/include/uapi/asm/unistd.h @@ -325,5 +325,7 @@ #define __NR_process_vm_writev 1333 #define __NR_accept4 1334 #define __NR_finit_module 1335 +#define __NR_sched_setattr 1336 +#define __NR_sched_getattr 1337 #endif /* _UAPI_ASM_IA64_UNISTD_H */ diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index ddea607f948a..fa8d61a312a7 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1773,6 +1773,8 @@ sys_call_table: data8 sys_process_vm_writev data8 sys_accept4 data8 sys_finit_module // 1335 + data8 sys_sched_setattr + data8 sys_sched_getattr .org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */ -- cgit v1.2.3 From 6b5a1f74e50170e64104135490dc32b657483594 Mon Sep 17 00:00:00 2001 From: Chris Zankel Date: Tue, 28 Jan 2014 22:09:51 -0800 Subject: xtensa: fix fast_syscall_spill_registers The original implementation could clobber registers under certain conditions. The Xtensa processor architecture uses windowed registers and the original implementation was using a4 as a temporary register, which under certain conditions could be register a0 of the oldest window frame, and didn't always restore the content correctly. By moving the _spill_registers routine inside the fast system call, it frees up one more register (the return address is not required anymore) for the spill routine. Signed-off-by: Chris Zankel --- arch/xtensa/kernel/entry.S | 383 ++++++++++++++++++++------------------------- 1 file changed, 174 insertions(+), 209 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index b61e25146a2f..ef7f4990722b 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1081,34 +1081,202 @@ ENTRY(fast_syscall_spill_registers) rsr a0, sar s32i a3, a2, PT_AREG3 - s32i a4, a2, PT_AREG4 - s32i a0, a2, PT_AREG5 # store SAR to PT_AREG5 + s32i a0, a2, PT_SAR - /* The spill routine might clobber a7, a11, and a15. */ + /* The spill routine might clobber a4, a7, a8, a11, a12, and a15. */ + s32i a4, a2, PT_AREG4 s32i a7, a2, PT_AREG7 + s32i a8, a2, PT_AREG8 s32i a11, a2, PT_AREG11 + s32i a12, a2, PT_AREG12 s32i a15, a2, PT_AREG15 - call0 _spill_registers # destroys a3, a4, and SAR + /* + * Rotate ws so that the current windowbase is at bit 0. + * Assume ws = xxxwww1yy (www1 current window frame). + * Rotate ws right so that a4 = yyxxxwww1. + */ + + rsr a0, windowbase + rsr a3, windowstart # a3 = xxxwww1yy + ssr a0 # holds WB + slli a0, a3, WSBITS + or a3, a3, a0 # a3 = xxxwww1yyxxxwww1yy + srl a3, a3 # a3 = 00xxxwww1yyxxxwww1 + + /* We are done if there are no more than the current register frame. */ + + extui a3, a3, 1, WSBITS-1 # a3 = 0yyxxxwww + movi a0, (1 << (WSBITS-1)) + _beqz a3, .Lnospill # only one active frame? jump + + /* We want 1 at the top, so that we return to the current windowbase */ + + or a3, a3, a0 # 1yyxxxwww + + /* Skip empty frames - get 'oldest' WINDOWSTART-bit. */ + + wsr a3, windowstart # save shifted windowstart + neg a0, a3 + and a3, a0, a3 # first bit set from right: 000010000 + + ffs_ws a0, a3 # a0: shifts to skip empty frames + movi a3, WSBITS + sub a0, a3, a0 # WSBITS-a0:number of 0-bits from right + ssr a0 # save in SAR for later. + + rsr a3, windowbase + add a3, a3, a0 + wsr a3, windowbase + rsync + + rsr a3, windowstart + srl a3, a3 # shift windowstart + + /* WB is now just one frame below the oldest frame in the register + window. WS is shifted so the oldest frame is in bit 0, thus, WB + and WS differ by one 4-register frame. */ + + /* Save frames. Depending what call was used (call4, call8, call12), + * we have to save 4,8. or 12 registers. + */ + + +.Lloop: _bbsi.l a3, 1, .Lc4 + _bbci.l a3, 2, .Lc12 + +.Lc8: s32e a4, a13, -16 + l32e a4, a5, -12 + s32e a8, a4, -32 + s32e a5, a13, -12 + s32e a6, a13, -8 + s32e a7, a13, -4 + s32e a9, a4, -28 + s32e a10, a4, -24 + s32e a11, a4, -20 + srli a11, a3, 2 # shift windowbase by 2 + rotw 2 + _bnei a3, 1, .Lloop + j .Lexit + +.Lc4: s32e a4, a9, -16 + s32e a5, a9, -12 + s32e a6, a9, -8 + s32e a7, a9, -4 + + srli a7, a3, 1 + rotw 1 + _bnei a3, 1, .Lloop + j .Lexit + +.Lc12: _bbci.l a3, 3, .Linvalid_mask # bit 2 shouldn't be zero! + + /* 12-register frame (call12) */ + + l32e a0, a5, -12 + s32e a8, a0, -48 + mov a8, a0 + + s32e a9, a8, -44 + s32e a10, a8, -40 + s32e a11, a8, -36 + s32e a12, a8, -32 + s32e a13, a8, -28 + s32e a14, a8, -24 + s32e a15, a8, -20 + srli a15, a3, 3 + + /* The stack pointer for a4..a7 is out of reach, so we rotate the + * window, grab the stackpointer, and rotate back. + * Alternatively, we could also use the following approach, but that + * makes the fixup routine much more complicated: + * rotw 1 + * s32e a0, a13, -16 + * ... + * rotw 2 + */ + + rotw 1 + mov a4, a13 + rotw -1 + + s32e a4, a8, -16 + s32e a5, a8, -12 + s32e a6, a8, -8 + s32e a7, a8, -4 + + rotw 3 + + _beqi a3, 1, .Lexit + j .Lloop + +.Lexit: + + /* Done. Do the final rotation and set WS */ + + rotw 1 + rsr a3, windowbase + ssl a3 + movi a3, 1 + sll a3, a3 + wsr a3, windowstart +.Lnospill: /* Advance PC, restore registers and SAR, and return from exception. */ - l32i a3, a2, PT_AREG5 - l32i a4, a2, PT_AREG4 + l32i a3, a2, PT_SAR l32i a0, a2, PT_AREG0 wsr a3, sar l32i a3, a2, PT_AREG3 /* Restore clobbered registers. */ + l32i a4, a2, PT_AREG4 l32i a7, a2, PT_AREG7 + l32i a8, a2, PT_AREG8 l32i a11, a2, PT_AREG11 + l32i a12, a2, PT_AREG12 l32i a15, a2, PT_AREG15 movi a2, 0 rfe +.Linvalid_mask: + + /* We get here because of an unrecoverable error in the window + * registers, so set up a dummy frame and kill the user application. + * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer. + */ + + movi a0, 1 + movi a1, 0 + + wsr a0, windowstart + wsr a1, windowbase + rsync + + movi a0, 0 + + rsr a3, excsave1 + l32i a1, a3, EXC_TABLE_KSTK + + movi a4, (1 << PS_WOE_BIT) | LOCKLEVEL + wsr a4, ps + rsync + + movi a6, SIGSEGV + movi a4, do_exit + callx4 a4 + + /* shouldn't return, so panic */ + + wsr a0, excsave1 + movi a0, unrecoverable_exception + callx0 a0 # should not return +1: j 1b + + ENDPROC(fast_syscall_spill_registers) /* Fixup handler. @@ -1232,209 +1400,6 @@ ENTRY(fast_syscall_spill_registers_fixup_return) ENDPROC(fast_syscall_spill_registers_fixup_return) -/* - * spill all registers. - * - * This is not a real function. The following conditions must be met: - * - * - must be called with call0. - * - uses a3, a4 and SAR. - * - the last 'valid' register of each frame are clobbered. - * - the caller must have registered a fixup handler - * (or be inside a critical section) - * - PS_EXCM must be set (PS_WOE cleared?) - */ - -ENTRY(_spill_registers) - - /* - * Rotate ws so that the current windowbase is at bit 0. - * Assume ws = xxxwww1yy (www1 current window frame). - * Rotate ws right so that a4 = yyxxxwww1. - */ - - rsr a4, windowbase - rsr a3, windowstart # a3 = xxxwww1yy - ssr a4 # holds WB - slli a4, a3, WSBITS - or a3, a3, a4 # a3 = xxxwww1yyxxxwww1yy - srl a3, a3 # a3 = 00xxxwww1yyxxxwww1 - - /* We are done if there are no more than the current register frame. */ - - extui a3, a3, 1, WSBITS-1 # a3 = 0yyxxxwww - movi a4, (1 << (WSBITS-1)) - _beqz a3, .Lnospill # only one active frame? jump - - /* We want 1 at the top, so that we return to the current windowbase */ - - or a3, a3, a4 # 1yyxxxwww - - /* Skip empty frames - get 'oldest' WINDOWSTART-bit. */ - - wsr a3, windowstart # save shifted windowstart - neg a4, a3 - and a3, a4, a3 # first bit set from right: 000010000 - - ffs_ws a4, a3 # a4: shifts to skip empty frames - movi a3, WSBITS - sub a4, a3, a4 # WSBITS-a4:number of 0-bits from right - ssr a4 # save in SAR for later. - - rsr a3, windowbase - add a3, a3, a4 - wsr a3, windowbase - rsync - - rsr a3, windowstart - srl a3, a3 # shift windowstart - - /* WB is now just one frame below the oldest frame in the register - window. WS is shifted so the oldest frame is in bit 0, thus, WB - and WS differ by one 4-register frame. */ - - /* Save frames. Depending what call was used (call4, call8, call12), - * we have to save 4,8. or 12 registers. - */ - - _bbsi.l a3, 1, .Lc4 - _bbsi.l a3, 2, .Lc8 - - /* Special case: we have a call12-frame starting at a4. */ - - _bbci.l a3, 3, .Lc12 # bit 3 shouldn't be zero! (Jump to Lc12 first) - - s32e a4, a1, -16 # a1 is valid with an empty spill area - l32e a4, a5, -12 - s32e a8, a4, -48 - mov a8, a4 - l32e a4, a1, -16 - j .Lc12c - -.Lnospill: - ret - -.Lloop: _bbsi.l a3, 1, .Lc4 - _bbci.l a3, 2, .Lc12 - -.Lc8: s32e a4, a13, -16 - l32e a4, a5, -12 - s32e a8, a4, -32 - s32e a5, a13, -12 - s32e a6, a13, -8 - s32e a7, a13, -4 - s32e a9, a4, -28 - s32e a10, a4, -24 - s32e a11, a4, -20 - - srli a11, a3, 2 # shift windowbase by 2 - rotw 2 - _bnei a3, 1, .Lloop - -.Lexit: /* Done. Do the final rotation, set WS, and return. */ - - rotw 1 - rsr a3, windowbase - ssl a3 - movi a3, 1 - sll a3, a3 - wsr a3, windowstart - ret - -.Lc4: s32e a4, a9, -16 - s32e a5, a9, -12 - s32e a6, a9, -8 - s32e a7, a9, -4 - - srli a7, a3, 1 - rotw 1 - _bnei a3, 1, .Lloop - j .Lexit - -.Lc12: _bbci.l a3, 3, .Linvalid_mask # bit 2 shouldn't be zero! - - /* 12-register frame (call12) */ - - l32e a2, a5, -12 - s32e a8, a2, -48 - mov a8, a2 - -.Lc12c: s32e a9, a8, -44 - s32e a10, a8, -40 - s32e a11, a8, -36 - s32e a12, a8, -32 - s32e a13, a8, -28 - s32e a14, a8, -24 - s32e a15, a8, -20 - srli a15, a3, 3 - - /* The stack pointer for a4..a7 is out of reach, so we rotate the - * window, grab the stackpointer, and rotate back. - * Alternatively, we could also use the following approach, but that - * makes the fixup routine much more complicated: - * rotw 1 - * s32e a0, a13, -16 - * ... - * rotw 2 - */ - - rotw 1 - mov a5, a13 - rotw -1 - - s32e a4, a9, -16 - s32e a5, a9, -12 - s32e a6, a9, -8 - s32e a7, a9, -4 - - rotw 3 - - _beqi a3, 1, .Lexit - j .Lloop - -.Linvalid_mask: - - /* We get here because of an unrecoverable error in the window - * registers. If we are in user space, we kill the application, - * however, this condition is unrecoverable in kernel space. - */ - - rsr a0, ps - _bbci.l a0, PS_UM_BIT, 1f - - /* User space: Setup a dummy frame and kill application. - * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer. - */ - - movi a0, 1 - movi a1, 0 - - wsr a0, windowstart - wsr a1, windowbase - rsync - - movi a0, 0 - - rsr a3, excsave1 - l32i a1, a3, EXC_TABLE_KSTK - - movi a4, (1 << PS_WOE_BIT) | LOCKLEVEL - wsr a4, ps - rsync - - movi a6, SIGSEGV - movi a4, do_exit - callx4 a4 - -1: /* Kernel space: PANIC! */ - - wsr a0, excsave1 - movi a0, unrecoverable_exception - callx0 a0 # should not return -1: j 1b - -ENDPROC(_spill_registers) - #ifdef CONFIG_MMU /* * We should never get here. Bail out! -- cgit v1.2.3 From b7c5b1aa2836c933ab03f90391619ebdc9112e46 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Tue, 28 Jan 2014 18:40:12 +0100 Subject: s390/appldata: restore missing init_virt_timer() Commit 27f6b416 "s390/vtimer: rework virtual timer interface" removed the call to init_virt_timer() by mistake, which is added again by this patch. Signed-off-by: Gerald Schaefer Signed-off-by: Martin Schwidefsky --- arch/s390/appldata/appldata_base.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 4c4a1cef5208..47c8630c93cd 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -529,6 +529,7 @@ static int __init appldata_init(void) { int rc; + init_virt_timer(&appldata_timer); appldata_timer.function = appldata_timer_function; appldata_timer.data = (unsigned long) &appldata_work; -- cgit v1.2.3 From c0e50d41126e4786d9cf1105bdf783e55c99f915 Mon Sep 17 00:00:00 2001 From: Chris Zankel Date: Tue, 28 Jan 2014 22:09:51 -0800 Subject: xtensa: fix fast_syscall_spill_registers The original implementation could clobber registers under certain conditions. The Xtensa processor architecture uses windowed registers and the original implementation was using a4 as a temporary register, which under certain conditions could be register a0 of the oldest window frame, and didn't always restore the content correctly. By moving the _spill_registers routine inside the fast system call, it frees up one more register (the return address is not required anymore) for the spill routine. Signed-off-by: Chris Zankel --- arch/xtensa/kernel/vectors.S | 2 +- arch/xtensa/kernel/xtensa_ksyms.c | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S index cb8fd44caabc..f9e1ec346e35 100644 --- a/arch/xtensa/kernel/vectors.S +++ b/arch/xtensa/kernel/vectors.S @@ -235,7 +235,7 @@ ENTRY(_DoubleExceptionVector) /* Check for overflow/underflow exception, jump if overflow. */ - _bbci.l a0, 6, _DoubleExceptionVector_WindowOverflow + bbci.l a0, 6, _DoubleExceptionVector_WindowOverflow /* * Restart window underflow exception. diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 74a60c7e085e..80b33ed51f31 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -122,9 +122,7 @@ EXPORT_SYMBOL(insw); EXPORT_SYMBOL(insl); extern long common_exception_return; -extern long _spill_registers; EXPORT_SYMBOL(common_exception_return); -EXPORT_SYMBOL(_spill_registers); #ifdef CONFIG_FUNCTION_TRACER EXPORT_SYMBOL(_mcount); -- cgit v1.2.3 From 0519e9ad89e5cd6e6b08398f57c6a71d9580564c Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Thu, 16 Jan 2014 16:01:11 +0100 Subject: crypto: s390 - fix concurrency issue in aes-ctr mode The aes-ctr mode uses one preallocated page without any concurrency protection. When multiple threads run aes-ctr encryption or decryption this can lead to data corruption. The patch introduces locking for the page and a fallback solution with slower en/decryption performance in concurrency situations. Cc: stable@vger.kernel.org Signed-off-by: Harald Freudenberger Signed-off-by: Herbert Xu --- arch/s390/crypto/aes_s390.c | 65 ++++++++++++++++++++++++++++++++------------- 1 file changed, 46 insertions(+), 19 deletions(-) (limited to 'arch') diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index b3feabd39f31..cf3c0089bef2 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "crypt_s390.h" #define AES_KEYLEN_128 1 @@ -32,6 +33,7 @@ #define AES_KEYLEN_256 4 static u8 *ctrblk; +static DEFINE_SPINLOCK(ctrblk_lock); static char keylen_flag; struct s390_aes_ctx { @@ -758,43 +760,67 @@ static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, return aes_set_key(tfm, in_key, key_len); } +static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes) +{ + unsigned int i, n; + + /* only use complete blocks, max. PAGE_SIZE */ + n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1); + for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) { + memcpy(ctrptr + i, ctrptr + i - AES_BLOCK_SIZE, + AES_BLOCK_SIZE); + crypto_inc(ctrptr + i, AES_BLOCK_SIZE); + } + return n; +} + static int ctr_aes_crypt(struct blkcipher_desc *desc, long func, struct s390_aes_ctx *sctx, struct blkcipher_walk *walk) { int ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE); - unsigned int i, n, nbytes; - u8 buf[AES_BLOCK_SIZE]; - u8 *out, *in; + unsigned int n, nbytes; + u8 buf[AES_BLOCK_SIZE], ctrbuf[AES_BLOCK_SIZE]; + u8 *out, *in, *ctrptr = ctrbuf; if (!walk->nbytes) return ret; - memcpy(ctrblk, walk->iv, AES_BLOCK_SIZE); + if (spin_trylock(&ctrblk_lock)) + ctrptr = ctrblk; + + memcpy(ctrptr, walk->iv, AES_BLOCK_SIZE); while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { out = walk->dst.virt.addr; in = walk->src.virt.addr; while (nbytes >= AES_BLOCK_SIZE) { - /* only use complete blocks, max. PAGE_SIZE */ - n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : - nbytes & ~(AES_BLOCK_SIZE - 1); - for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) { - memcpy(ctrblk + i, ctrblk + i - AES_BLOCK_SIZE, - AES_BLOCK_SIZE); - crypto_inc(ctrblk + i, AES_BLOCK_SIZE); - } - ret = crypt_s390_kmctr(func, sctx->key, out, in, n, ctrblk); - if (ret < 0 || ret != n) + if (ctrptr == ctrblk) + n = __ctrblk_init(ctrptr, nbytes); + else + n = AES_BLOCK_SIZE; + ret = crypt_s390_kmctr(func, sctx->key, out, in, + n, ctrptr); + if (ret < 0 || ret != n) { + if (ctrptr == ctrblk) + spin_unlock(&ctrblk_lock); return -EIO; + } if (n > AES_BLOCK_SIZE) - memcpy(ctrblk, ctrblk + n - AES_BLOCK_SIZE, + memcpy(ctrptr, ctrptr + n - AES_BLOCK_SIZE, AES_BLOCK_SIZE); - crypto_inc(ctrblk, AES_BLOCK_SIZE); + crypto_inc(ctrptr, AES_BLOCK_SIZE); out += n; in += n; nbytes -= n; } ret = blkcipher_walk_done(desc, walk, nbytes); } + if (ctrptr == ctrblk) { + if (nbytes) + memcpy(ctrbuf, ctrptr, AES_BLOCK_SIZE); + else + memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE); + spin_unlock(&ctrblk_lock); + } /* * final block may be < AES_BLOCK_SIZE, copy only nbytes */ @@ -802,14 +828,15 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func, out = walk->dst.virt.addr; in = walk->src.virt.addr; ret = crypt_s390_kmctr(func, sctx->key, buf, in, - AES_BLOCK_SIZE, ctrblk); + AES_BLOCK_SIZE, ctrbuf); if (ret < 0 || ret != AES_BLOCK_SIZE) return -EIO; memcpy(out, buf, nbytes); - crypto_inc(ctrblk, AES_BLOCK_SIZE); + crypto_inc(ctrbuf, AES_BLOCK_SIZE); ret = blkcipher_walk_done(desc, walk, 0); + memcpy(walk->iv, ctrbuf, AES_BLOCK_SIZE); } - memcpy(walk->iv, ctrblk, AES_BLOCK_SIZE); + return ret; } -- cgit v1.2.3 From adc3fcf1552b6e406d172fd9690bbd1395053d13 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 22 Jan 2014 13:00:04 +0100 Subject: crypto: s390 - fix des and des3_ede cbc concurrency issue In s390 des and des3_ede cbc mode the iv value is not protected against concurrency access and modifications from another running en/decrypt operation which is using the very same tfm struct instance. This fix copies the iv to the local stack before the crypto operation and stores the value back when done. Cc: stable@vger.kernel.org Signed-off-by: Harald Freudenberger Signed-off-by: Herbert Xu --- arch/s390/crypto/des_s390.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 200f2a1b599d..82a0a2ad2494 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -105,29 +105,35 @@ static int ecb_desall_crypt(struct blkcipher_desc *desc, long func, } static int cbc_desall_crypt(struct blkcipher_desc *desc, long func, - u8 *iv, struct blkcipher_walk *walk) + struct blkcipher_walk *walk) { + struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); int ret = blkcipher_walk_virt(desc, walk); unsigned int nbytes = walk->nbytes; + struct { + u8 iv[DES_BLOCK_SIZE]; + u8 key[DES3_KEY_SIZE]; + } param; if (!nbytes) goto out; - memcpy(iv, walk->iv, DES_BLOCK_SIZE); + memcpy(param.iv, walk->iv, DES_BLOCK_SIZE); + memcpy(param.key, ctx->key, DES3_KEY_SIZE); do { /* only use complete blocks */ unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1); u8 *out = walk->dst.virt.addr; u8 *in = walk->src.virt.addr; - ret = crypt_s390_kmc(func, iv, out, in, n); + ret = crypt_s390_kmc(func, ¶m, out, in, n); if (ret < 0 || ret != n) return -EIO; nbytes &= DES_BLOCK_SIZE - 1; ret = blkcipher_walk_done(desc, walk, nbytes); } while ((nbytes = walk->nbytes)); - memcpy(walk->iv, iv, DES_BLOCK_SIZE); + memcpy(walk->iv, param.iv, DES_BLOCK_SIZE); out: return ret; @@ -179,22 +185,20 @@ static int cbc_des_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, ctx->iv, &walk); + return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, &walk); } static int cbc_des_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, ctx->iv, &walk); + return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, &walk); } static struct crypto_alg cbc_des_alg = { @@ -327,22 +331,20 @@ static int cbc_des3_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, ctx->iv, &walk); + return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, &walk); } static int cbc_des3_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, ctx->iv, &walk); + return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, &walk); } static struct crypto_alg cbc_des3_alg = { -- cgit v1.2.3 From ee97dc7db4cbda33e4241c2d85b42d1835bc8a35 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 22 Jan 2014 13:01:33 +0100 Subject: crypto: s390 - fix des and des3_ede ctr concurrency issue In s390 des and 3des ctr mode there is one preallocated page used to speed up the en/decryption. This page is not protected against concurrent usage and thus there is a potential of data corruption with multiple threads. The fix introduces locking/unlocking the ctr page and a slower fallback solution at concurrency situations. Cc: stable@vger.kernel.org Signed-off-by: Harald Freudenberger Signed-off-by: Herbert Xu --- arch/s390/crypto/des_s390.c | 69 +++++++++++++++++++++++++++++++-------------- 1 file changed, 48 insertions(+), 21 deletions(-) (limited to 'arch') diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 82a0a2ad2494..0a5aac8a9412 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -25,6 +25,7 @@ #define DES3_KEY_SIZE (3 * DES_KEY_SIZE) static u8 *ctrblk; +static DEFINE_SPINLOCK(ctrblk_lock); struct s390_des_ctx { u8 iv[DES_BLOCK_SIZE]; @@ -368,54 +369,80 @@ static struct crypto_alg cbc_des3_alg = { } }; +static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes) +{ + unsigned int i, n; + + /* align to block size, max. PAGE_SIZE */ + n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(DES_BLOCK_SIZE - 1); + for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) { + memcpy(ctrptr + i, ctrptr + i - DES_BLOCK_SIZE, DES_BLOCK_SIZE); + crypto_inc(ctrptr + i, DES_BLOCK_SIZE); + } + return n; +} + static int ctr_desall_crypt(struct blkcipher_desc *desc, long func, - struct s390_des_ctx *ctx, struct blkcipher_walk *walk) + struct s390_des_ctx *ctx, + struct blkcipher_walk *walk) { int ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE); - unsigned int i, n, nbytes; - u8 buf[DES_BLOCK_SIZE]; - u8 *out, *in; + unsigned int n, nbytes; + u8 buf[DES_BLOCK_SIZE], ctrbuf[DES_BLOCK_SIZE]; + u8 *out, *in, *ctrptr = ctrbuf; + + if (!walk->nbytes) + return ret; - memcpy(ctrblk, walk->iv, DES_BLOCK_SIZE); + if (spin_trylock(&ctrblk_lock)) + ctrptr = ctrblk; + + memcpy(ctrptr, walk->iv, DES_BLOCK_SIZE); while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) { out = walk->dst.virt.addr; in = walk->src.virt.addr; while (nbytes >= DES_BLOCK_SIZE) { - /* align to block size, max. PAGE_SIZE */ - n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : - nbytes & ~(DES_BLOCK_SIZE - 1); - for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) { - memcpy(ctrblk + i, ctrblk + i - DES_BLOCK_SIZE, - DES_BLOCK_SIZE); - crypto_inc(ctrblk + i, DES_BLOCK_SIZE); - } - ret = crypt_s390_kmctr(func, ctx->key, out, in, n, ctrblk); - if (ret < 0 || ret != n) + if (ctrptr == ctrblk) + n = __ctrblk_init(ctrptr, nbytes); + else + n = DES_BLOCK_SIZE; + ret = crypt_s390_kmctr(func, ctx->key, out, in, + n, ctrptr); + if (ret < 0 || ret != n) { + if (ctrptr == ctrblk) + spin_unlock(&ctrblk_lock); return -EIO; + } if (n > DES_BLOCK_SIZE) - memcpy(ctrblk, ctrblk + n - DES_BLOCK_SIZE, + memcpy(ctrptr, ctrptr + n - DES_BLOCK_SIZE, DES_BLOCK_SIZE); - crypto_inc(ctrblk, DES_BLOCK_SIZE); + crypto_inc(ctrptr, DES_BLOCK_SIZE); out += n; in += n; nbytes -= n; } ret = blkcipher_walk_done(desc, walk, nbytes); } - + if (ctrptr == ctrblk) { + if (nbytes) + memcpy(ctrbuf, ctrptr, DES_BLOCK_SIZE); + else + memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE); + spin_unlock(&ctrblk_lock); + } /* final block may be < DES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { out = walk->dst.virt.addr; in = walk->src.virt.addr; ret = crypt_s390_kmctr(func, ctx->key, buf, in, - DES_BLOCK_SIZE, ctrblk); + DES_BLOCK_SIZE, ctrbuf); if (ret < 0 || ret != DES_BLOCK_SIZE) return -EIO; memcpy(out, buf, nbytes); - crypto_inc(ctrblk, DES_BLOCK_SIZE); + crypto_inc(ctrbuf, DES_BLOCK_SIZE); ret = blkcipher_walk_done(desc, walk, 0); + memcpy(walk->iv, ctrbuf, DES_BLOCK_SIZE); } - memcpy(walk->iv, ctrblk, DES_BLOCK_SIZE); return ret; } -- cgit v1.2.3 From 39424e89d64661faa0a2e00c5ad1e6dbeebfa972 Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Tue, 28 Jan 2014 08:22:11 -0500 Subject: x86, cpu hotplug: Fix stack frame warning in check_irq_vectors_for_cpu_disable() Further discussion here: http://marc.info/?l=linux-kernel&m=139073901101034&w=2 kbuild, 0day kernel build service, outputs the warning: arch/x86/kernel/irq.c:333:1: warning: the frame size of 2056 bytes is larger than 2048 bytes [-Wframe-larger-than=] because check_irq_vectors_for_cpu_disable() allocates two cpumasks on the stack. Fix this by moving the two cpumasks to a global file context. Reported-by: Fengguang Wu Tested-by: David Rientjes Signed-off-by: Prarit Bhargava Link: http://lkml.kernel.org/r/1390915331-27375-1-git-send-email-prarit@redhat.com Cc: Andi Kleen Cc: Michel Lespinasse Cc: Seiji Aguchi Cc: Yang Zhang Cc: Paul Gortmaker Cc: Janet Morgan Cc: Tony Luck Cc: Ruiv Wang Cc: Gong Chen Cc: Yinghai Lu Signed-off-by: H. Peter Anvin --- arch/x86/kernel/irq.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index dbb60878b744..d99f31d9a750 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -266,6 +266,14 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs) EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU + +/* These two declarations are only used in check_irq_vectors_for_cpu_disable() + * below, which is protected by stop_machine(). Putting them on the stack + * results in a stack frame overflow. Dynamically allocating could result in a + * failure so declare these two cpumasks as global. + */ +static struct cpumask affinity_new, online_new; + /* * This cpu is going to be removed and its vectors migrated to the remaining * online cpus. Check to see if there are enough vectors in the remaining cpus. @@ -277,7 +285,6 @@ int check_irq_vectors_for_cpu_disable(void) unsigned int this_cpu, vector, this_count, count; struct irq_desc *desc; struct irq_data *data; - struct cpumask affinity_new, online_new; this_cpu = smp_processor_id(); cpumask_copy(&online_new, cpu_online_mask); -- cgit v1.2.3 From 85fc73a2cdf10cf42bc36fb3bca3896b2095a1c2 Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Sat, 1 Feb 2014 13:30:19 +0100 Subject: x86: Fix the initialization of physnode_map With DISCONTIGMEM, the mapping between a pfn and its owning node is initialized using data provided by the BIOS. However, the initialization may fail if the extents are not aligned to section boundary (64M). The symptom of this bug is an early boot failure in pfn_to_page(), as it tries to access NODE_DATA(__nid) using index from an unitialized element of the physnode_map[] array. While the bug is always present, it is more likely to be hit in kdump kernels on large machines, because: 1. The memory map for a kdump kernel is specified as exactmap, and exactmap is more likely to be unaligned. 2. Large reservations are more likely to span across a 64M boundary. [ hpa: fixed incorrect use of "pfn" instead of "start" ] Signed-off-by: Petr Tesarik Link: http://lkml.kernel.org/r/20140201133019.32e56f86@hananiah.suse.cz Acked-by: David Rientjes Signed-off-by: H. Peter Anvin --- arch/x86/mm/numa_32.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 0342d27ca798..47b6436e41c2 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -52,6 +52,8 @@ void memory_present(int nid, unsigned long start, unsigned long end) nid, start, end); printk(KERN_DEBUG " Setting physnode_map array to node %d for pfns:\n", nid); printk(KERN_DEBUG " "); + start = round_down(start, PAGES_PER_SECTION); + end = round_up(end, PAGES_PER_SECTION); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) { physnode_map[pfn / PAGES_PER_SECTION] = nid; printk(KERN_CONT "%lx ", pfn); -- cgit v1.2.3 From 57789d69c5e7cdfdad6c0f1c54ab17240d800ac2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sat, 1 Feb 2014 16:35:42 -0600 Subject: ARM: hisi: fix kconfig warning on HAVE_ARM_TWD Commit "ARM: hisi: don't select SMP" introduced a kconfig warning: warning: (ARCH_HI3xxx) selects HAVE_ARM_TWD which has unmet direct dependencies (SMP) Fix HAVE_ARM_TWD to depend on SMP. Signed-off-by: Rob Herring Signed-off-by: Olof Johansson --- arch/arm/mach-hisi/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/mach-hisi/Kconfig b/arch/arm/mach-hisi/Kconfig index 8f4649b301b2..1abae5f6a418 100644 --- a/arch/arm/mach-hisi/Kconfig +++ b/arch/arm/mach-hisi/Kconfig @@ -8,7 +8,7 @@ config ARCH_HI3xxx select CLKSRC_OF select GENERIC_CLOCKEVENTS select HAVE_ARM_SCU - select HAVE_ARM_TWD + select HAVE_ARM_TWD if SMP select HAVE_SMP select PINCTRL select PINCTRL_SINGLE -- cgit v1.2.3 From e803d988662ff365c2ed3c2d10a0aad811c1f492 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sat, 1 Feb 2014 16:35:43 -0600 Subject: ARM: moxart: move DMA_OF selection to driver Move the DMA_OF selection to the DMA driver to fix kconfig warning: warning: (ARCH_MOXART) selects DMA_OF which has unmet direct dependencies (DMADEVICES && OF) Signed-off-by: Rob Herring Signed-off-by: Olof Johansson --- arch/arm/mach-moxart/Kconfig | 1 - drivers/dma/Kconfig | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig index ba470d64493b..3795ae28a613 100644 --- a/arch/arm/mach-moxart/Kconfig +++ b/arch/arm/mach-moxart/Kconfig @@ -2,7 +2,6 @@ config ARCH_MOXART bool "MOXA ART SoC" if ARCH_MULTI_V4T select CPU_FA526 select ARM_DMA_MEM_BUFFERABLE - select DMA_OF select USE_OF select CLKSRC_OF select CLKSRC_MMIO diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 9bed1a2a67a1..605b016bcea4 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -346,6 +346,7 @@ config MOXART_DMA tristate "MOXART DMA support" depends on ARCH_MOXART select DMA_ENGINE + select DMA_OF select DMA_VIRTUAL_CHANNELS help Enable support for the MOXA ART SoC DMA controller. -- cgit v1.2.3 From 8b7dfa7dc701a27ac8ea4c4dfc0dbc8dce4825de Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sat, 1 Feb 2014 16:35:44 -0600 Subject: ARM: fix HAVE_ARM_TWD selection for OMAP and shmobile The selection of HAVE_ARM_TWD for OMAP and shmobile depend on LOCAL_TIMER which no longer exists. They should depend on SMP instead. Cc: Tony Lindgren Cc: Simon Horman Cc: Magnus Damm Signed-off-by: Rob Herring Signed-off-by: Olof Johansson --- arch/arm/mach-omap2/Kconfig | 2 +- arch/arm/mach-shmobile/Kconfig | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 653b489479e0..e2ce4f8366a7 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -54,7 +54,7 @@ config SOC_OMAP5 select ARM_GIC select CPU_V7 select HAVE_ARM_SCU if SMP - select HAVE_ARM_TWD if LOCAL_TIMERS + select HAVE_ARM_TWD if SMP select HAVE_SMP select HAVE_ARM_ARCH_TIMER select ARM_ERRATA_798181 if SMP diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig index 338640631e08..05fa505df585 100644 --- a/arch/arm/mach-shmobile/Kconfig +++ b/arch/arm/mach-shmobile/Kconfig @@ -8,7 +8,7 @@ config ARCH_SHMOBILE_MULTI select CPU_V7 select GENERIC_CLOCKEVENTS select HAVE_ARM_SCU if SMP - select HAVE_ARM_TWD if LOCAL_TIMERS + select HAVE_ARM_TWD if SMP select HAVE_SMP select ARM_GIC select MIGHT_HAVE_CACHE_L2X0 -- cgit v1.2.3 From e85fc9805591a17ca8af50023ee8e2b61d9a123b Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Mon, 3 Feb 2014 06:43:59 -0500 Subject: Revert "xen/grant-table: Avoid m2p_override during mapping" This reverts commit 08ece5bb2312b4510b161a6ef6682f37f4eac8a1. As it breaks ARM builds and needs more attention on the ARM side. Acked-by: David Vrabel Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/include/asm/xen/page.h | 5 +-- arch/x86/xen/p2m.c | 17 ++++++- drivers/block/xen-blkback/blkback.c | 15 ++++--- drivers/xen/gntdev.c | 13 +++--- drivers/xen/grant-table.c | 89 ++++++------------------------------- include/xen/grant_table.h | 8 +--- 6 files changed, 46 insertions(+), 101 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 787e1bb5aafc..3e276eb23d1b 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -52,8 +52,7 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s, extern int m2p_add_override(unsigned long mfn, struct page *page, struct gnttab_map_grant_ref *kmap_op); extern int m2p_remove_override(struct page *page, - struct gnttab_map_grant_ref *kmap_op, - unsigned long mfn); + struct gnttab_map_grant_ref *kmap_op); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); @@ -122,7 +121,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) pfn = m2p_find_override_pfn(mfn, ~0); } - /* + /* * pfn is ~0 if there are no entries in the m2p for mfn or if the * entry doesn't map back to the mfn and m2p_override doesn't have a * valid entry for it. diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 8009acbe41e4..696c694986d0 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -899,6 +899,13 @@ int m2p_add_override(unsigned long mfn, struct page *page, "m2p_add_override: pfn %lx not mapped", pfn)) return -EINVAL; } + WARN_ON(PagePrivate(page)); + SetPagePrivate(page); + set_page_private(page, mfn); + page->index = pfn_to_mfn(pfn); + + if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) + return -ENOMEM; if (kmap_op != NULL) { if (!PageHighMem(page)) { @@ -937,16 +944,19 @@ int m2p_add_override(unsigned long mfn, struct page *page, } EXPORT_SYMBOL_GPL(m2p_add_override); int m2p_remove_override(struct page *page, - struct gnttab_map_grant_ref *kmap_op, - unsigned long mfn) + struct gnttab_map_grant_ref *kmap_op) { unsigned long flags; + unsigned long mfn; unsigned long pfn; unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; pfn = page_to_pfn(page); + mfn = get_phys_to_machine(pfn); + if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) + return -EINVAL; if (!PageHighMem(page)) { address = (unsigned long)__va(pfn << PAGE_SHIFT); @@ -960,7 +970,10 @@ int m2p_remove_override(struct page *page, spin_lock_irqsave(&m2p_override_lock, flags); list_del(&page->lru); spin_unlock_irqrestore(&m2p_override_lock, flags); + WARN_ON(!PagePrivate(page)); + ClearPagePrivate(page); + set_phys_to_machine(pfn, page->index); if (kmap_op != NULL) { if (!PageHighMem(page)) { struct multicall_space mcs; diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 875025f299b6..6620b73d0490 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -285,7 +285,8 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root, if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST || !rb_next(&persistent_gnt->node)) { - ret = gnttab_unmap_refs(unmap, pages, segs_to_unmap); + ret = gnttab_unmap_refs(unmap, NULL, pages, + segs_to_unmap); BUG_ON(ret); put_free_pages(blkif, pages, segs_to_unmap); segs_to_unmap = 0; @@ -320,7 +321,8 @@ static void unmap_purged_grants(struct work_struct *work) pages[segs_to_unmap] = persistent_gnt->page; if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) { - ret = gnttab_unmap_refs(unmap, pages, segs_to_unmap); + ret = gnttab_unmap_refs(unmap, NULL, pages, + segs_to_unmap); BUG_ON(ret); put_free_pages(blkif, pages, segs_to_unmap); segs_to_unmap = 0; @@ -328,7 +330,7 @@ static void unmap_purged_grants(struct work_struct *work) kfree(persistent_gnt); } if (segs_to_unmap > 0) { - ret = gnttab_unmap_refs(unmap, pages, segs_to_unmap); + ret = gnttab_unmap_refs(unmap, NULL, pages, segs_to_unmap); BUG_ON(ret); put_free_pages(blkif, pages, segs_to_unmap); } @@ -668,14 +670,15 @@ static void xen_blkbk_unmap(struct xen_blkif *blkif, GNTMAP_host_map, pages[i]->handle); pages[i]->handle = BLKBACK_INVALID_HANDLE; if (++invcount == BLKIF_MAX_SEGMENTS_PER_REQUEST) { - ret = gnttab_unmap_refs(unmap, unmap_pages, invcount); + ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, + invcount); BUG_ON(ret); put_free_pages(blkif, unmap_pages, invcount); invcount = 0; } } if (invcount) { - ret = gnttab_unmap_refs(unmap, unmap_pages, invcount); + ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount); BUG_ON(ret); put_free_pages(blkif, unmap_pages, invcount); } @@ -737,7 +740,7 @@ again: } if (segs_to_map) { - ret = gnttab_map_refs(map, pages_to_gnt, segs_to_map); + ret = gnttab_map_refs(map, NULL, pages_to_gnt, segs_to_map); BUG_ON(ret); } diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 34a2704fbc88..073b4a19a8b0 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -284,10 +284,8 @@ static int map_grant_pages(struct grant_map *map) } pr_debug("map %d+%d\n", map->index, map->count); - err = gnttab_map_refs_userspace(map->map_ops, - use_ptemod ? map->kmap_ops : NULL, - map->pages, - map->count); + err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL, + map->pages, map->count); if (err) return err; @@ -317,10 +315,9 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages) } } - err = gnttab_unmap_refs_userspace(map->unmap_ops + offset, - use_ptemod ? map->kmap_ops + offset : NULL, - map->pages + offset, - pages); + err = gnttab_unmap_refs(map->unmap_ops + offset, + use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset, + pages); if (err) return err; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 8ee13e2e45e2..b84e3ab839aa 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -928,17 +928,15 @@ void gnttab_batch_copy(struct gnttab_copy *batch, unsigned count) } EXPORT_SYMBOL_GPL(gnttab_batch_copy); -int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, +int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count, - bool m2p_override) + struct page **pages, unsigned int count) { int i, ret; bool lazy = false; pte_t *pte; - unsigned long mfn, pfn; + unsigned long mfn; - BUG_ON(kmap_ops && !m2p_override); ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count); if (ret) return ret; @@ -957,12 +955,10 @@ int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT, map_ops[i].dev_bus_addr >> PAGE_SHIFT); } - return 0; + return ret; } - if (m2p_override && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { + if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { arch_enter_lazy_mmu_mode(); lazy = true; } @@ -979,20 +975,8 @@ int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, } else { mfn = PFN_DOWN(map_ops[i].dev_bus_addr); } - pfn = page_to_pfn(pages[i]); - - WARN_ON(PagePrivate(pages[i])); - SetPagePrivate(pages[i]); - set_page_private(pages[i], mfn); - - pages[i]->index = pfn_to_mfn(pfn); - if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { - ret = -ENOMEM; - goto out; - } - if (m2p_override) - ret = m2p_add_override(mfn, pages[i], kmap_ops ? - &kmap_ops[i] : NULL); + ret = m2p_add_override(mfn, pages[i], kmap_ops ? + &kmap_ops[i] : NULL); if (ret) goto out; } @@ -1003,32 +987,15 @@ int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, return ret; } - -int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_map_refs(map_ops, NULL, pages, count, false); -} EXPORT_SYMBOL_GPL(gnttab_map_refs); -int gnttab_map_refs_userspace(struct gnttab_map_grant_ref *map_ops, - struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_map_refs(map_ops, kmap_ops, pages, count, true); -} -EXPORT_SYMBOL_GPL(gnttab_map_refs_userspace); - -int __gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, +int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count, - bool m2p_override) + struct page **pages, unsigned int count) { int i, ret; bool lazy = false; - unsigned long pfn, mfn; - BUG_ON(kmap_ops && !m2p_override); ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count); if (ret) return ret; @@ -1039,33 +1006,17 @@ int __gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT, INVALID_P2M_ENTRY); } - return 0; + return ret; } - if (m2p_override && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { + if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { arch_enter_lazy_mmu_mode(); lazy = true; } for (i = 0; i < count; i++) { - pfn = page_to_pfn(pages[i]); - mfn = get_phys_to_machine(pfn); - if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) { - ret = -EINVAL; - goto out; - } - - set_page_private(pages[i], INVALID_P2M_ENTRY); - WARN_ON(!PagePrivate(pages[i])); - ClearPagePrivate(pages[i]); - set_phys_to_machine(pfn, pages[i]->index); - if (m2p_override) - ret = m2p_remove_override(pages[i], - kmap_ops ? - &kmap_ops[i] : NULL, - mfn); + ret = m2p_remove_override(pages[i], kmap_ops ? + &kmap_ops[i] : NULL); if (ret) goto out; } @@ -1076,22 +1027,8 @@ int __gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, return ret; } - -int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *map_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_unmap_refs(map_ops, NULL, pages, count, false); -} EXPORT_SYMBOL_GPL(gnttab_unmap_refs); -int gnttab_unmap_refs_userspace(struct gnttab_unmap_grant_ref *map_ops, - struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_unmap_refs(map_ops, kmap_ops, pages, count, true); -} -EXPORT_SYMBOL_GPL(gnttab_unmap_refs_userspace); - static unsigned nr_status_frames(unsigned nr_grant_frames) { BUG_ON(grefs_per_grant_frame == 0); diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 7ad033dbc845..a5af2a26d94f 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -191,15 +191,11 @@ void gnttab_free_auto_xlat_frames(void); #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count); -int gnttab_map_refs_userspace(struct gnttab_map_grant_ref *map_ops, - struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count); int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_map_grant_ref *kunmap_ops, struct page **pages, unsigned int count); -int gnttab_unmap_refs_userspace(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kunmap_ops, - struct page **pages, unsigned int count); /* Perform a batch of grant map/copy operations. Retry every batch slot * for which the hypervisor returns GNTST_eagain. This is typically due -- cgit v1.2.3 From 1ff6bbfd13ca2c114a5cb58e1a92d1e5d68ce0b7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 28 Jan 2014 18:10:37 -0500 Subject: arm, pm, vmpressure: add missing slab.h includes arch/arm/mach-tegra/pm.c, kernel/power/console.c and mm/vmpressure.c were somehow getting slab.h indirectly through cgroup.h which in turn was getting it indirectly through xattr.h. A scheduled cgroup change drops xattr.h inclusion from cgroup.h and breaks compilation of these three files. Add explicit slab.h includes to the three files. A pending cgroup patch depends on this change and it'd be great if this can be routed through cgroup/for-3.14-fixes branch. Signed-off-by: Tejun Heo Acked-by: Stephen Warren Cc: Thierry Reding Cc: linux-tegra@vger.kernel.org Cc: "Rafael J. Wysocki" Cc: linux-pm@vger.kernel.org Cc: Johannes Weiner Cc: Michal Hocko Cc: Balbir Singh Cc: KAMEZAWA Hiroyuki Cc: cgroups@vger.kernel.org --- arch/arm/mach-tegra/pm.c | 1 + kernel/power/console.c | 1 + mm/vmpressure.c | 1 + 3 files changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/arm/mach-tegra/pm.c b/arch/arm/mach-tegra/pm.c index 4ae0286b468d..f55b05a29b55 100644 --- a/arch/arm/mach-tegra/pm.c +++ b/arch/arm/mach-tegra/pm.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include diff --git a/kernel/power/console.c b/kernel/power/console.c index eacb8bd8cab4..aba9c545a0e3 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "power.h" #define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1) diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 196970a4541f..d4042e75f7c7 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From afca50132cfa7bfc5646676d8c67dc18454f38f8 Mon Sep 17 00:00:00 2001 From: Mukesh Rathor Date: Wed, 29 Jan 2014 16:15:18 -0800 Subject: xen/pvh: set CR4 flags for APs During bootup in the 'probe_page_size_mask' these CR4 flags are set in there. But for AP processors they are not set as we do not use 'secondary_startup_64' which the baremetal kernels uses. Instead do it in this function which we use in Xen PVH during our startup for AP processors. As such fix it up to make sure we have that flag set. Signed-off-by: Mukesh Rathor Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/enlighten.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'arch') diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a4d7b647867f..201d09a7c46b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1473,6 +1473,18 @@ static void xen_pvh_set_cr_flags(int cpu) * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */ write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM); + + if (!cpu) + return; + /* + * For BSP, PSE PGE are set in probe_page_size_mask(), for APs + * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init. + */ + if (cpu_has_pse) + set_in_cr4(X86_CR4_PSE); + + if (cpu_has_pge) + set_in_cr4(X86_CR4_PGE); } /* -- cgit v1.2.3 From 4294ad1c52caad3239404cea9e0cbfeb435e3a25 Mon Sep 17 00:00:00 2001 From: Manuel Lauss Date: Wed, 29 Jan 2014 19:11:46 +0100 Subject: MIPS: Alchemy: Fix DB1100 GPIO registration With CONFIG_GPIOLIB=y gpios need to be requested before they can be modified. Request the SD carddetect pins, and drop the SPI direction setup, as the driver does that for us anyway. This gets rid of a lot of WARN_ON()s triggered by GPIO core, and restores functionality of the touschreen controller. Signed-off-by: Manuel Lauss Cc: Linux-MIPS Patchwork: https://patchwork.linux-mips.org/patch/6497/ Signed-off-by: Ralf Baechle --- arch/mips/alchemy/devboards/db1000.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c index 11f3ad20321c..5483906e0f86 100644 --- a/arch/mips/alchemy/devboards/db1000.c +++ b/arch/mips/alchemy/devboards/db1000.c @@ -534,13 +534,10 @@ static int __init db1000_dev_init(void) s0 = AU1100_GPIO1_INT; s1 = AU1100_GPIO4_INT; + gpio_request(19, "sd0_cd"); + gpio_request(20, "sd1_cd"); gpio_direction_input(19); /* sd0 cd# */ gpio_direction_input(20); /* sd1 cd# */ - gpio_direction_input(21); /* touch pendown# */ - gpio_direction_input(207); /* SPI MISO */ - gpio_direction_output(208, 0); /* SPI MOSI */ - gpio_direction_output(209, 1); /* SPI SCK */ - gpio_direction_output(210, 1); /* SPI CS# */ /* spi_gpio on SSI0 pins */ pfc = __raw_readl((void __iomem *)SYS_PINFUNC); -- cgit v1.2.3 From 6776254b1c28fece9535d42baf2db88756121fe7 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Tue, 4 Feb 2014 12:29:01 +0000 Subject: MIPS: Wire up sched_setattr/sched_getattr syscalls Wire up for MIPS the new sched_setattr and sched_getattr system calls added in commit d50dde5a10f3 (sched: Add new scheduler syscalls to support an extended scheduling parameters ABI) merged in v3.14-rc1. Signed-off-by: James Hogan Reviewed-by: Markos Chandras Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/6502/ Signed-off-by: Ralf Baechle --- arch/mips/include/uapi/asm/unistd.h | 18 ++++++++++++------ arch/mips/kernel/scall32-o32.S | 2 ++ arch/mips/kernel/scall64-64.S | 2 ++ arch/mips/kernel/scall64-n32.S | 2 ++ arch/mips/kernel/scall64-o32.S | 2 ++ 5 files changed, 20 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h index 1dee279f9665..d6e154a9e6a5 100644 --- a/arch/mips/include/uapi/asm/unistd.h +++ b/arch/mips/include/uapi/asm/unistd.h @@ -369,16 +369,18 @@ #define __NR_process_vm_writev (__NR_Linux + 346) #define __NR_kcmp (__NR_Linux + 347) #define __NR_finit_module (__NR_Linux + 348) +#define __NR_sched_setattr (__NR_Linux + 349) +#define __NR_sched_getattr (__NR_Linux + 350) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 348 +#define __NR_Linux_syscalls 350 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 348 +#define __NR_O32_Linux_syscalls 350 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -695,16 +697,18 @@ #define __NR_kcmp (__NR_Linux + 306) #define __NR_finit_module (__NR_Linux + 307) #define __NR_getdents64 (__NR_Linux + 308) +#define __NR_sched_setattr (__NR_Linux + 309) +#define __NR_sched_getattr (__NR_Linux + 310) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 308 +#define __NR_Linux_syscalls 310 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 308 +#define __NR_64_Linux_syscalls 310 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -1025,15 +1029,17 @@ #define __NR_process_vm_writev (__NR_Linux + 310) #define __NR_kcmp (__NR_Linux + 311) #define __NR_finit_module (__NR_Linux + 312) +#define __NR_sched_setattr (__NR_Linux + 313) +#define __NR_sched_getattr (__NR_Linux + 314) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 312 +#define __NR_Linux_syscalls 314 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 312 +#define __NR_N32_Linux_syscalls 314 #endif /* _UAPI_ASM_UNISTD_H */ diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index e8e541b40d86..a5b14f48e1af 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -563,3 +563,5 @@ EXPORT(sys_call_table) PTR sys_process_vm_writev PTR sys_kcmp PTR sys_finit_module + PTR sys_sched_setattr + PTR sys_sched_getattr /* 4350 */ diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 57e3742fec59..b56e254beb15 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -425,4 +425,6 @@ EXPORT(sys_call_table) PTR sys_kcmp PTR sys_finit_module PTR sys_getdents64 + PTR sys_sched_setattr + PTR sys_sched_getattr /* 5310 */ .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 2f48f5934399..f7e5b72cf481 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -418,4 +418,6 @@ EXPORT(sysn32_call_table) PTR compat_sys_process_vm_writev /* 6310 */ PTR sys_kcmp PTR sys_finit_module + PTR sys_sched_setattr + PTR sys_sched_getattr .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index f1acdb429f4f..6788727d91af 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -541,4 +541,6 @@ EXPORT(sys32_call_table) PTR compat_sys_process_vm_writev PTR sys_kcmp PTR sys_finit_module + PTR sys_sched_setattr + PTR sys_sched_getattr /* 4350 */ .size sys32_call_table,.-sys32_call_table -- cgit v1.2.3 From d7736ff5be31edaa4fe5ab62810c64529a24b149 Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Thu, 30 Jan 2014 16:14:02 +0100 Subject: s390/dump: Fix dump memory detection Dumps created by kdump or zfcpdump can contain invalid memory holes when dumping z/VM systems that have memory pressure. For example: # zgetdump -i /proc/vmcore. Memory map: 0000000000000000 - 0000000000bfffff (12 MB) 0000000000e00000 - 00000000014fffff (7 MB) 000000000bd00000 - 00000000f3bfffff (3711 MB) The memory detection function find_memory_chunks() issues tprot to find valid memory chunks. In case of CMM it can happen that pages are marked as unstable via set_page_unstable() in arch_free_page(). If z/VM has released that pages, tprot returns -EFAULT and indicates a memory hole. So fix this and switch off CMM in case of kdump or zfcpdump. Cc: Signed-off-by: Michael Holzheu Signed-off-by: Martin Schwidefsky --- arch/s390/mm/page-states.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'arch') diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c index a90d45e9dfb0..27c50f4d90cb 100644 --- a/arch/s390/mm/page-states.c +++ b/arch/s390/mm/page-states.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #define ESSA_SET_STABLE 1 #define ESSA_SET_UNUSED 2 @@ -41,6 +43,14 @@ void __init cmma_init(void) if (!cmma_flag) return; + /* + * Disable CMM for dump, otherwise the tprot based memory + * detection can fail because of unstable pages. + */ + if (OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP) { + cmma_flag = 0; + return; + } asm volatile( " .insn rrf,0xb9ab0000,%1,%1,0,0\n" "0: la %0,0\n" -- cgit v1.2.3 From 40507403485fcb56b83d6ddfc954e9b08305054c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 4 Feb 2014 14:41:26 +0000 Subject: arm64: vdso: prevent ld from aligning PT_LOAD segments to 64k Whilst the text segment for our VDSO is marked as PT_LOAD in the ELF headers, it is mapped by the kernel and not actually subject to demand-paging. ld doesn't realise this, and emits a p_align field of 64k (the maximum supported page size), which conflicts with the load address picked by the kernel on 4k systems, which will be 4k aligned. This causes GDB to fail with "Failed to read a valid object file image from memory" when attempting to load the VDSO. This patch passes the -n option to ld, which prevents it from aligning PT_LOAD segments to the maximum page size. Cc: Reported-by: Kyle McMartin Acked-by: Kyle McMartin Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/kernel/vdso/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index d8064af42e62..6d20b7d162d8 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -48,7 +48,7 @@ $(obj-vdso): %.o: %.S # Actual build commands quiet_cmd_vdsold = VDSOL $@ - cmd_vdsold = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@ quiet_cmd_vdsoas = VDSOA $@ cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $< -- cgit v1.2.3 From 14cfa4bd74be31e5502dcb5c98de86db63fddb65 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Sun, 12 Jan 2014 13:09:24 +0100 Subject: ARM: mvebu: dt: add missing alias 'eth3' on Armada XP mv78260 It was correctly set on mv78460 but not on mv78260, resulting in my OpenBlocks AX3-4 retrieving only 3 of its 4 MAC addresses from the boot loader. Cc: Thomas Petazzoni Cc: Gregory CLEMENT Signed-off-by: Willy Tarreau Acked-by: Gregory CLEMENT Signed-off-by: Jason Cooper --- arch/arm/boot/dts/armada-xp-mv78260.dtsi | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi index 66609684d41b..9480cf891f8c 100644 --- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi +++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi @@ -23,6 +23,7 @@ gpio0 = &gpio0; gpio1 = &gpio1; gpio2 = &gpio2; + eth3 = ð3; }; cpus { @@ -291,7 +292,7 @@ interrupts = <91>; }; - ethernet@34000 { + eth3: ethernet@34000 { compatible = "marvell,armada-370-neta"; reg = <0x34000 0x4000>; interrupts = <14>; -- cgit v1.2.3 From 8d7f6690cedb83456edd41c9bd583783f0703bf0 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 3 Feb 2014 17:37:15 +0100 Subject: s390: fix kernel crash due to linkage stack instructions The kernel currently crashes with a low-address-protection exception if a user space process executes an instruction that tries to use the linkage stack. Set the base-ASTE origin and the subspace-ASTE origin of the dispatchable-unit-control-table to point to a dummy ASTE. Set up control register 15 to point to an empty linkage stack with no room left. A user space process with a linkage stack instruction will still crash but with a different exception which is correctly translated to a segmentation fault instead of a kernel oops. Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/head64.S | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index b9e25ae2579c..d7c00507568a 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -59,7 +59,7 @@ ENTRY(startup_continue) .quad 0 # cr12: tracing off .quad 0 # cr13: home space segment table .quad 0xc0000000 # cr14: machine check handling off - .quad 0 # cr15: linkage stack operations + .quad .Llinkage_stack # cr15: linkage stack operations .Lpcmsk:.quad 0x0000000180000000 .L4malign:.quad 0xffffffffffc00000 .Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8 @@ -67,12 +67,15 @@ ENTRY(startup_continue) .Lparmaddr: .quad PARMAREA .align 64 -.Lduct: .long 0,0,0,0,.Lduald,0,0,0 +.Lduct: .long 0,.Laste,.Laste,0,.Lduald,0,0,0 .long 0,0,0,0,0,0,0,0 +.Laste: .quad 0,0xffffffffffffffff,0,0,0,0,0,0 .align 128 .Lduald:.rept 8 .long 0x80000000,0,0,0 # invalid access-list entries .endr +.Llinkage_stack: + .long 0,0,0x89000000,0,0,0,0x8a000000,0 ENTRY(_ehead) -- cgit v1.2.3 From 5044bad43ee573d0b6d90e3ccb7a40c2c7d25eb4 Mon Sep 17 00:00:00 2001 From: Vinayak Kale Date: Wed, 5 Feb 2014 09:34:36 +0000 Subject: arm64: add DSB after icache flush in __flush_icache_all() Add DSB after icache flush to complete the cache maintenance operation. The function __flush_icache_all() is used only for user space mappings and an ISB is not required because of an exception return before executing user instructions. An exception return would behave like an ISB. Signed-off-by: Vinayak Kale Acked-by: Will Deacon Cc: Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cacheflush.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index fea9ee327206..889324981aa4 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -116,6 +116,7 @@ extern void flush_dcache_page(struct page *); static inline void __flush_icache_all(void) { asm("ic ialluis"); + dsb(); } #define flush_dcache_mmap_lock(mapping) \ -- cgit v1.2.3 From ccc9e244eb1b9654915634827322932cbafd8244 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 4 Feb 2014 23:08:57 +0000 Subject: arm64: Align CMA sizes to PAGE_SIZE dma_alloc_from_contiguous takes number of pages for a size. Align up the dma size passed in to page size to avoid truncation and allocation failures on sizes less than PAGE_SIZE. Cc: Will Deacon Signed-off-by: Laura Abbott Signed-off-by: Catalin Marinas --- arch/arm64/mm/dma-mapping.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 45b5ab54c9ee..fbd76785c5db 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -45,6 +45,7 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_DMA_CMA)) { struct page *page; + size = PAGE_ALIGN(size); page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, get_order(size)); if (!page) -- cgit v1.2.3 From a55f9929a9b257f84b6cc7b2397379cabd744a22 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 4 Feb 2014 16:01:31 +0000 Subject: arm64: Invalidate the TLB when replacing pmd entries during boot With the 64K page size configuration, __create_page_tables in head.S maps enough memory to get started but using 64K pages rather than 512M sections with a single pgd/pud/pmd entry pointing to a pte table. create_mapping() may override the pgd/pud/pmd table entry with a block (section) one if the RAM size is more than 512MB and aligned correctly. For the end of this block to be accessible, the old TLB entry must be invalidated. Cc: Reported-by: Mark Salter Tested-by: Mark Salter Signed-off-by: Catalin Marinas --- arch/arm64/mm/mmu.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index f557ebbe7013..f8dc7e8fce6f 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -203,10 +203,18 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, do { next = pmd_addr_end(addr, end); /* try section mapping first */ - if (((addr | next | phys) & ~SECTION_MASK) == 0) + if (((addr | next | phys) & ~SECTION_MASK) == 0) { + pmd_t old_pmd =*pmd; set_pmd(pmd, __pmd(phys | prot_sect_kernel)); - else + /* + * Check for previous table entries created during + * boot (__create_page_tables) and flush them. + */ + if (!pmd_none(old_pmd)) + flush_tlb_all(); + } else { alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys)); + } phys += next - addr; } while (pmd++, addr = next, addr != end); } -- cgit v1.2.3 From bfb67a5606376bb32cb6f93dc05cda2e8c2038a5 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 5 Feb 2014 10:24:12 +0000 Subject: arm64: fix typo: s/SERRROR/SERROR/ Somehow SERROR has acquired an additional 'R' in a couple of headers. This patch removes them before they spread further. As neither instance is in use yet, no other sites need to be fixed up. Signed-off-by: Mark Rutland Acked-by: Marc Zyngier Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/esr.h | 2 +- arch/arm64/include/asm/kvm_arm.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 78834123a32e..c4a7f940b387 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -42,7 +42,7 @@ #define ESR_EL1_EC_SP_ALIGN (0x26) #define ESR_EL1_EC_FP_EXC32 (0x28) #define ESR_EL1_EC_FP_EXC64 (0x2C) -#define ESR_EL1_EC_SERRROR (0x2F) +#define ESR_EL1_EC_SERROR (0x2F) #define ESR_EL1_EC_BREAKPT_EL0 (0x30) #define ESR_EL1_EC_BREAKPT_EL1 (0x31) #define ESR_EL1_EC_SOFTSTP_EL0 (0x32) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index c98ef4771c73..0eb398655378 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -231,7 +231,7 @@ #define ESR_EL2_EC_SP_ALIGN (0x26) #define ESR_EL2_EC_FP_EXC32 (0x28) #define ESR_EL2_EC_FP_EXC64 (0x2C) -#define ESR_EL2_EC_SERRROR (0x2F) +#define ESR_EL2_EC_SERROR (0x2F) #define ESR_EL2_EC_BREAKPT (0x30) #define ESR_EL2_EC_BREAKPT_HYP (0x31) #define ESR_EL2_EC_SOFTSTP (0x32) -- cgit v1.2.3 From 883d50a0ed403446437444a495356ce31e1197a3 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 5 Feb 2014 10:24:13 +0000 Subject: arm64: simplify pgd_alloc Currently pgd_alloc has a redundant NULL check in its return path that can be removed with no ill effects. With that removed it's also possible to return early and eliminate the new_pgd temporary variable. This patch applies said modifications, making the logic of pgd_alloc correspond 1-1 with that of pgd_free. Signed-off-by: Mark Rutland Cc: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/mm/pgd.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 7083cdada657..62c6101df260 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -32,17 +32,10 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *new_pgd; - if (PGD_SIZE == PAGE_SIZE) - new_pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL); + return (pgd_t *)get_zeroed_page(GFP_KERNEL); else - new_pgd = kzalloc(PGD_SIZE, GFP_KERNEL); - - if (!new_pgd) - return NULL; - - return new_pgd; + return kzalloc(PGD_SIZE, GFP_KERNEL); } void pgd_free(struct mm_struct *mm, pgd_t *pgd) -- cgit v1.2.3 From 069b918623e1510e58dacf178905a72c3baa3ae4 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Wed, 5 Feb 2014 05:53:04 +0000 Subject: arm64: vdso: fix coarse clock handling When __kernel_clock_gettime is called with a CLOCK_MONOTONIC_COARSE or CLOCK_REALTIME_COARSE clock id, it returns incorrectly to whatever the caller has placed in x2 ("ret x2" to return from the fast path). Fix this by saving x30/LR to x2 only in code that will call __do_get_tspec, restoring x30 afterward, and using a plain "ret" to return from the routine. Also: while the resulting tv_nsec value for CLOCK_REALTIME and CLOCK_MONOTONIC must be computed using intermediate values that are left-shifted by cs_shift (x12, set by __do_get_tspec), the results for coarse clocks should be calculated using unshifted values (xtime_coarse_nsec is in units of actual nanoseconds). The current code shifts intermediate values by x12 unconditionally, but x12 is uninitialized when servicing a coarse clock. Fix this by setting x12 to 0 once we know we are dealing with a coarse clock id. Signed-off-by: Nathan Lynch Acked-by: Will Deacon Cc: Signed-off-by: Catalin Marinas --- arch/arm64/kernel/vdso/gettimeofday.S | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index f0a6d10b5211..fe652ffd34c2 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -103,6 +103,8 @@ ENTRY(__kernel_clock_gettime) bl __do_get_tspec seqcnt_check w9, 1b + mov x30, x2 + cmp w0, #CLOCK_MONOTONIC b.ne 6f @@ -118,6 +120,9 @@ ENTRY(__kernel_clock_gettime) ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne b.ne 8f + /* xtime_coarse_nsec is already right-shifted */ + mov x12, #0 + /* Get coarse timespec. */ adr vdso_data, _vdso_data 3: seqcnt_acquire @@ -156,7 +161,7 @@ ENTRY(__kernel_clock_gettime) lsr x11, x11, x12 stp x10, x11, [x1, #TSPEC_TV_SEC] mov x0, xzr - ret x2 + ret 7: mov x30, x2 8: /* Syscall fallback. */ -- cgit v1.2.3 From d4022a335271a48cce49df35d825897914fbffe3 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Mon, 3 Feb 2014 19:48:52 +0000 Subject: arm64: vdso: update wtm fields for CLOCK_MONOTONIC_COARSE Update wall-to-monotonic fields in the VDSO data page unconditionally. These are used to service CLOCK_MONOTONIC_COARSE, which is not guarded by use_syscall. Signed-off-by: Nathan Lynch Acked-by: Will Deacon Cc: Signed-off-by: Catalin Marinas --- arch/arm64/kernel/vdso.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 65d40cf6945a..a7149cae1615 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -238,6 +238,8 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->use_syscall = use_syscall; vdso_data->xtime_coarse_sec = xtime_coarse.tv_sec; vdso_data->xtime_coarse_nsec = xtime_coarse.tv_nsec; + vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec; + vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { vdso_data->cs_cycle_last = tk->clock->cycle_last; @@ -245,8 +247,6 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->xtime_clock_nsec = tk->xtime_nsec; vdso_data->cs_mult = tk->mult; vdso_data->cs_shift = tk->shift; - vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec; - vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; } smp_wmb(); -- cgit v1.2.3 From 6290b53de025dd08a79257ee84173ef7b6d926f7 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Wed, 5 Feb 2014 12:03:52 +0000 Subject: arm64: compat: Wire up new AArch32 syscalls This patch enables sys_compat, sys_finit_module, sys_sched_setattr and sys_sched_getattr for compat (AArch32) applications. Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/unistd32.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 58125bf008d3..bb8eb8a78e67 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -399,7 +399,10 @@ __SYSCALL(374, compat_sys_sendmmsg) __SYSCALL(375, sys_setns) __SYSCALL(376, compat_sys_process_vm_readv) __SYSCALL(377, compat_sys_process_vm_writev) -__SYSCALL(378, sys_ni_syscall) /* 378 for kcmp */ +__SYSCALL(378, sys_kcmp) +__SYSCALL(379, sys_finit_module) +__SYSCALL(380, sys_sched_setattr) +__SYSCALL(381, sys_sched_getattr) #define __NR_compat_syscalls 379 -- cgit v1.2.3 From c4ad8f98bef77c7356aa6a9ad9188a6acc6b849d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 5 Feb 2014 12:54:53 -0800 Subject: execve: use 'struct filename *' for executable name passing This changes 'do_execve()' to get the executable name as a 'struct filename', and to free it when it is done. This is what the normal users want, and it simplifies and streamlines their error handling. The controlled lifetime of the executable name also fixes a use-after-free problem with the trace_sched_process_exec tracepoint: the lifetime of the passed-in string for kernel users was not at all obvious, and the user-mode helper code used UMH_WAIT_EXEC to serialize the pathname allocation lifetime with the execve() having finished, which in turn meant that the trace point that happened after mm_release() of the old process VM ended up using already free'd memory. To solve the kernel string lifetime issue, this simply introduces "getname_kernel()" that works like the normal user-space getname() function, except with the source coming from kernel memory. As Oleg points out, this also means that we could drop the tcomm[] array from 'struct linux_binprm', since the pathname lifetime now covers setup_new_exec(). That would be a separate cleanup. Reported-by: Igor Zhbanov Tested-by: Steven Rostedt Cc: Oleg Nesterov Cc: Al Viro Signed-off-by: Linus Torvalds --- arch/parisc/hpux/fs.c | 15 +-------------- fs/exec.c | 45 +++++++++++++++++++++------------------------ fs/namei.c | 30 ++++++++++++++++++++++++++++++ include/linux/binfmts.h | 1 - include/linux/fs.h | 1 + include/linux/sched.h | 3 ++- init/main.c | 2 +- kernel/auditsc.c | 2 +- kernel/kmod.c | 2 +- 9 files changed, 58 insertions(+), 43 deletions(-) (limited to 'arch') diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c index 88d0962de65a..2bedafea3d94 100644 --- a/arch/parisc/hpux/fs.c +++ b/arch/parisc/hpux/fs.c @@ -33,22 +33,9 @@ int hpux_execve(struct pt_regs *regs) { - int error; - struct filename *filename; - - filename = getname((const char __user *) regs->gr[26]); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - - error = do_execve(filename->name, + return do_execve(getname((const char __user *) regs->gr[26]), (const char __user *const __user *) regs->gr[25], (const char __user *const __user *) regs->gr[24]); - - putname(filename); - -out: - return error; } struct hpux_dirent { diff --git a/fs/exec.c b/fs/exec.c index e1529b4c79b1..3d78fccdd723 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -748,11 +748,10 @@ EXPORT_SYMBOL(setup_arg_pages); #endif /* CONFIG_MMU */ -struct file *open_exec(const char *name) +static struct file *do_open_exec(struct filename *name) { struct file *file; int err; - struct filename tmp = { .name = name }; static const struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC | MAY_OPEN, @@ -760,7 +759,7 @@ struct file *open_exec(const char *name) .lookup_flags = LOOKUP_FOLLOW, }; - file = do_filp_open(AT_FDCWD, &tmp, &open_exec_flags); + file = do_filp_open(AT_FDCWD, name, &open_exec_flags); if (IS_ERR(file)) goto out; @@ -784,6 +783,12 @@ exit: fput(file); return ERR_PTR(err); } + +struct file *open_exec(const char *name) +{ + struct filename tmp = { .name = name }; + return do_open_exec(&tmp); +} EXPORT_SYMBOL(open_exec); int kernel_read(struct file *file, loff_t offset, @@ -1162,7 +1167,7 @@ int prepare_bprm_creds(struct linux_binprm *bprm) return -ENOMEM; } -void free_bprm(struct linux_binprm *bprm) +static void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { @@ -1432,7 +1437,7 @@ static int exec_binprm(struct linux_binprm *bprm) /* * sys_execve() executes a new program. */ -static int do_execve_common(const char *filename, +static int do_execve_common(struct filename *filename, struct user_arg_ptr argv, struct user_arg_ptr envp) { @@ -1441,6 +1446,9 @@ static int do_execve_common(const char *filename, struct files_struct *displaced; int retval; + if (IS_ERR(filename)) + return PTR_ERR(filename); + /* * We move the actual failure in case of RLIMIT_NPROC excess from * set*uid() to execve() because too many poorly written programs @@ -1473,7 +1481,7 @@ static int do_execve_common(const char *filename, check_unsafe_exec(bprm); current->in_execve = 1; - file = open_exec(filename); + file = do_open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) goto out_unmark; @@ -1481,8 +1489,7 @@ static int do_execve_common(const char *filename, sched_exec(); bprm->file = file; - bprm->filename = filename; - bprm->interp = filename; + bprm->filename = bprm->interp = filename->name; retval = bprm_mm_init(bprm); if (retval) @@ -1523,6 +1530,7 @@ static int do_execve_common(const char *filename, acct_update_integrals(current); task_numa_free(current); free_bprm(bprm); + putname(filename); if (displaced) put_files_struct(displaced); return retval; @@ -1544,10 +1552,11 @@ out_files: if (displaced) reset_files_struct(displaced); out_ret: + putname(filename); return retval; } -int do_execve(const char *filename, +int do_execve(struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp) { @@ -1557,7 +1566,7 @@ int do_execve(const char *filename, } #ifdef CONFIG_COMPAT -static int compat_do_execve(const char *filename, +static int compat_do_execve(struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp) { @@ -1607,25 +1616,13 @@ SYSCALL_DEFINE3(execve, const char __user *const __user *, argv, const char __user *const __user *, envp) { - struct filename *path = getname(filename); - int error = PTR_ERR(path); - if (!IS_ERR(path)) { - error = do_execve(path->name, argv, envp); - putname(path); - } - return error; + return do_execve(getname(filename), argv, envp); } #ifdef CONFIG_COMPAT asmlinkage long compat_sys_execve(const char __user * filename, const compat_uptr_t __user * argv, const compat_uptr_t __user * envp) { - struct filename *path = getname(filename); - int error = PTR_ERR(path); - if (!IS_ERR(path)) { - error = compat_do_execve(path->name, argv, envp); - putname(path); - } - return error; + return compat_do_execve(getname(filename), argv, envp); } #endif diff --git a/fs/namei.c b/fs/namei.c index d580df2e6804..385f7817bfcc 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -196,6 +196,7 @@ recopy: goto error; result->uptr = filename; + result->aname = NULL; audit_getname(result); return result; @@ -210,6 +211,35 @@ getname(const char __user * filename) return getname_flags(filename, 0, NULL); } +/* + * The "getname_kernel()" interface doesn't do pathnames longer + * than EMBEDDED_NAME_MAX. Deal with it - you're a kernel user. + */ +struct filename * +getname_kernel(const char * filename) +{ + struct filename *result; + char *kname; + int len; + + len = strlen(filename); + if (len >= EMBEDDED_NAME_MAX) + return ERR_PTR(-ENAMETOOLONG); + + result = __getname(); + if (unlikely(!result)) + return ERR_PTR(-ENOMEM); + + kname = (char *)result + sizeof(*result); + result->name = kname; + result->uptr = NULL; + result->aname = NULL; + result->separate = false; + + strlcpy(kname, filename, EMBEDDED_NAME_MAX); + return result; +} + #ifdef CONFIG_AUDITSYSCALL void putname(struct filename *name) { diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index fd8bf3219ef7..b4a745d7d9a9 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -115,7 +115,6 @@ extern int copy_strings_kernel(int argc, const char *const *argv, extern int prepare_bprm_creds(struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); -extern void free_bprm(struct linux_binprm *); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); #endif /* _LINUX_BINFMTS_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 09f553c59813..d79678c188ad 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2079,6 +2079,7 @@ extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname(const char __user *); +extern struct filename *getname_kernel(const char *); enum { FILE_CREATED = 1, diff --git a/include/linux/sched.h b/include/linux/sched.h index 68a0e84463a0..a781dec1cd0b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -128,6 +128,7 @@ struct bio_list; struct fs_struct; struct perf_event_context; struct blk_plug; +struct filename; /* * List of flags we want to share for kernel threads, @@ -2311,7 +2312,7 @@ extern void do_group_exit(int); extern int allow_signal(int); extern int disallow_signal(int); -extern int do_execve(const char *, +extern int do_execve(struct filename *, const char __user * const __user *, const char __user * const __user *); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); diff --git a/init/main.c b/init/main.c index 2fd9cef70ee8..eb03090cdced 100644 --- a/init/main.c +++ b/init/main.c @@ -812,7 +812,7 @@ void __init load_default_modules(void) static int run_init_process(const char *init_filename) { argv_init[0] = init_filename; - return do_execve(init_filename, + return do_execve(getname_kernel(init_filename), (const char __user *const __user *)argv_init, (const char __user *const __user *)envp_init); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 10176cd5956a..7aef2f4b6c64 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1719,7 +1719,7 @@ void audit_putname(struct filename *name) struct audit_context *context = current->audit_context; BUG_ON(!context); - if (!context->in_syscall) { + if (!name->aname || !context->in_syscall) { #if AUDIT_DEBUG == 2 printk(KERN_ERR "%s:%d(:%d): final_putname(%p)\n", __FILE__, __LINE__, context->serial, name); diff --git a/kernel/kmod.c b/kernel/kmod.c index b086006c59e7..6b375af4958d 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -239,7 +239,7 @@ static int ____call_usermodehelper(void *data) commit_creds(new); - retval = do_execve(sub_info->path, + retval = do_execve(getname_kernel(sub_info->path), (const char __user *const __user *)sub_info->argv, (const char __user *const __user *)sub_info->envp); if (!retval) -- cgit v1.2.3 From f8f202348208fa8a2d817b42f250e145fa885620 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 5 Feb 2014 06:51:37 +0100 Subject: x86: Disable CONFIG_X86_DECODER_SELFTEST in allmod/allyesconfigs It can take some time to validate the image, make sure {allyes|allmod}config doesn't enable it. I'd say randconfig will cover it often enough, and the failure is also borderline build coverage related: you cannot really make the decoder test fail via source level changes, only with changes in the build environment, so I agree with Andi that we can disable this one too. Signed-off-by: Ingo Molnar Acked-by: Paul Gortmaker paul.gortmaker@windriver.com> Suggested-and-acked-by: Andi Kleen andi@firstfloor.org> Signed-off-by: Linus Torvalds --- arch/x86/Kconfig.debug | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 0f3621ed1db6..321a52ccf63a 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -184,6 +184,7 @@ config HAVE_MMIOTRACE_SUPPORT config X86_DECODER_SELFTEST bool "x86 instruction decoder selftest" depends on DEBUG_KERNEL && KPROBES + depends on !COMPILE_TEST ---help--- Perform x86 instruction decoder selftests at build time. This option is useful for checking the sanity of x86 instruction -- cgit v1.2.3 From 081cd62a010f97b5bc1d2b0cd123c5abc692b68a Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Tue, 14 Jan 2014 12:40:09 +0000 Subject: x86/efi: Allow mapping BGRT on x86-32 CONFIG_X86_32 doesn't map the boot services regions into the EFI memory map (see commit 700870119f49 ("x86, efi: Don't map Boot Services on i386")), and so efi_lookup_mapped_addr() will fail to return a valid address. Executing the ioremap() path in efi_bgrt_init() causes the following warning on x86-32 because we're trying to ioremap() RAM, WARNING: CPU: 0 PID: 0 at arch/x86/mm/ioremap.c:102 __ioremap_caller+0x2ad/0x2c0() Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.13.0-0.rc5.git0.1.2.fc21.i686 #1 Hardware name: DellInc. Venue 8 Pro 5830/09RP78, BIOS A02 10/17/2013 00000000 00000000 c0c0df08 c09a5196 00000000 c0c0df38 c0448c1e c0b41310 00000000 00000000 c0b37bc1 00000066 c043bbfd c043bbfd 00e7dfe0 00073eff 00073eff c0c0df48 c0448ce2 00000009 00000000 c0c0df9c c043bbfd 00078d88 Call Trace: [] dump_stack+0x41/0x52 [] warn_slowpath_common+0x7e/0xa0 [] ? __ioremap_caller+0x2ad/0x2c0 [] ? __ioremap_caller+0x2ad/0x2c0 [] warn_slowpath_null+0x22/0x30 [] __ioremap_caller+0x2ad/0x2c0 [] ? acpi_tb_verify_table+0x1c/0x43 [] ? acpi_get_table_with_size+0x63/0xb5 [] ? efi_lookup_mapped_addr+0xe/0xf0 [] ioremap_nocache+0x1b/0x20 [] ? efi_bgrt_init+0x83/0x10c [] efi_bgrt_init+0x83/0x10c [] efi_late_init+0x8/0xa [] start_kernel+0x3ae/0x3c3 [] ? repair_env_string+0x51/0x51 [] i386_start_kernel+0x12e/0x131 Switch to using early_memremap(), which won't trigger this warning, and has the added benefit of more accurately conveying what we're trying to do - map a chunk of memory. This patch addresses the following bug report, https://bugzilla.kernel.org/show_bug.cgi?id=67911 Reported-by: Adam Williamson Cc: Josh Triplett Cc: Matthew Garrett Cc: Rafael J. Wysocki Signed-off-by: Matt Fleming --- arch/x86/platform/efi/efi-bgrt.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index 7145ec63c520..4df9591eadad 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -49,7 +49,8 @@ void __init efi_bgrt_init(void) image = efi_lookup_mapped_addr(bgrt_tab->image_address); if (!image) { - image = ioremap(bgrt_tab->image_address, sizeof(bmp_header)); + image = early_memremap(bgrt_tab->image_address, + sizeof(bmp_header)); ioremapped = true; if (!image) return; @@ -57,7 +58,7 @@ void __init efi_bgrt_init(void) memcpy_fromio(&bmp_header, image, sizeof(bmp_header)); if (ioremapped) - iounmap(image); + early_iounmap(image, sizeof(bmp_header)); bgrt_image_size = bmp_header.size; bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL); @@ -65,7 +66,8 @@ void __init efi_bgrt_init(void) return; if (ioremapped) { - image = ioremap(bgrt_tab->image_address, bmp_header.size); + image = early_memremap(bgrt_tab->image_address, + bmp_header.size); if (!image) { kfree(bgrt_image); bgrt_image = NULL; @@ -75,5 +77,5 @@ void __init efi_bgrt_init(void) memcpy_fromio(bgrt_image, image, bgrt_image_size); if (ioremapped) - iounmap(image); + early_iounmap(image, bmp_header.size); } -- cgit v1.2.3 From 4a7ac12eedd190cdf071e61145defa73df1675c0 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 6 Feb 2014 11:30:48 +0000 Subject: arm64: barriers: allow dsb macro to take option parameter The dsb instruction takes an option specifying both the target access types and shareability domain. This patch allows such an option to be passed to the dsb macro, resulting in potentially more efficient code. Currently the option is ignored until all callers are updated (unlike ARM, the option is mandated by the assembler). Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/barrier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 78e20ba8806b..409ca370cfe2 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -25,7 +25,7 @@ #define wfi() asm volatile("wfi" : : : "memory") #define isb() asm volatile("isb" : : : "memory") -#define dsb() asm volatile("dsb sy" : : : "memory") +#define dsb(opt) asm volatile("dsb sy" : : : "memory") #define mb() dsb() #define rmb() asm volatile("dsb ld" : : : "memory") -- cgit v1.2.3 From 97b8b16bfcb7f5ccc1b3c10c08580f9f1acb61ac Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Wed, 5 Feb 2014 22:05:44 +0200 Subject: MIPS: fpu.h: Fix build when CONFIG_BUG is not set __enable_fpu produces a build failure when CONFIG_BUG is not set: In file included from arch/mips/kernel/cpu-probe.c:24:0: arch/mips/include/asm/fpu.h: In function '__enable_fpu': arch/mips/include/asm/fpu.h:77:1: error: control reaches end of non-void function [-Werror=return-type] This is regression introduced in 3.14-rc1. Fix that. Signed-off-by: Aaro Koskinen Acked-by: Paul Burton Cc: John Crispin Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/6504/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/fpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index cfe092fc720d..6b9749540edf 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -74,6 +74,8 @@ static inline int __enable_fpu(enum fpu_mode mode) default: BUG(); } + + return SIGFPE; } #define __disable_fpu() \ -- cgit v1.2.3 From 75a1ba5b2c529db60ca49626bcaf0bddf4548438 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 3 Feb 2014 21:41:44 +0100 Subject: x86, microcode, AMD: Unify valid container checks For additional coverage, BorisO and friends unknowlingly did swap AMD microcode with Intel microcode blobs in order to see what happens. What did happen on 32-bit was [ 5.722656] BUG: unable to handle kernel paging request at be3a6008 [ 5.722693] IP: [] load_microcode_amd+0x24/0x3f0 [ 5.722716] *pdpt = 0000000000000000 *pde = 0000000000000000 because there was a valid initrd there but without valid microcode in it and the container check happened *after* the relocated ramdisk handling on 32-bit, which was clearly wrong. While at it, take care of the ramdisk relocation on both 32- and 64-bit as it is done on both. Also, comment what we're doing because this code is a bit tricky. Reported-and-tested-by: Boris Ostrovsky Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1391460104-7261-1-git-send-email-bp@alien8.de Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/microcode/amd_early.c | 43 +++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 8384c0fa206f..617a9e284245 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -285,6 +285,15 @@ static void __init collect_cpu_sig_on_bsp(void *arg) uci->cpu_sig.sig = cpuid_eax(0x00000001); } + +static void __init get_bsp_sig(void) +{ + unsigned int bsp = boot_cpu_data.cpu_index; + struct ucode_cpu_info *uci = ucode_cpu_info + bsp; + + if (!uci->cpu_sig.sig) + smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); +} #else void load_ucode_amd_ap(void) { @@ -337,31 +346,37 @@ void load_ucode_amd_ap(void) int __init save_microcode_in_initrd_amd(void) { + unsigned long cont; enum ucode_state ret; u32 eax; -#ifdef CONFIG_X86_32 - unsigned int bsp = boot_cpu_data.cpu_index; - struct ucode_cpu_info *uci = ucode_cpu_info + bsp; - - if (!uci->cpu_sig.sig) - smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); + if (!container) + return -EINVAL; +#ifdef CONFIG_X86_32 + get_bsp_sig(); + cont = (unsigned long)container; +#else /* - * Take into account the fact that the ramdisk might get relocated - * and therefore we need to recompute the container's position in - * virtual memory space. + * We need the physical address of the container for both bitness since + * boot_params.hdr.ramdisk_image is a physical address. */ - container = (u8 *)(__va((u32)relocated_ramdisk) + - ((u32)container - boot_params.hdr.ramdisk_image)); + cont = __pa(container); #endif + + /* + * Take into account the fact that the ramdisk might get relocated and + * therefore we need to recompute the container's position in virtual + * memory space. + */ + if (relocated_ramdisk) + container = (u8 *)(__va(relocated_ramdisk) + + (cont - boot_params.hdr.ramdisk_image)); + if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", ucode_new_rev); - if (!container) - return -EINVAL; - eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); -- cgit v1.2.3 From 017c217a26e9bf6948482f751b30d0507e30a7d0 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Thu, 6 Feb 2014 12:04:25 -0800 Subject: arch/x86/mm/numa.c: initialize numa_kernel_nodes in numa_clear_kernel_node_hotplug() On-stack variable numa_kernel_nodes in numa_clear_kernel_node_hotplug() was not initialized. So we need to initialize it. [akpm@linux-foundation.org: use NODE_MASK_NONE, per David] Signed-off-by: Tang Chen Tested-by: Gu Zheng Reported-by: Dave Jones Reported-by: David Rientjes Tested-by: Dave Jones Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/numa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 81b2750f3666..45ec9d72b6dd 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -565,7 +565,7 @@ static void __init numa_init_array(void) static void __init numa_clear_kernel_node_hotplug(void) { int i, nid; - nodemask_t numa_kernel_nodes; + nodemask_t numa_kernel_nodes = NODE_MASK_NONE; unsigned long start, end; struct memblock_type *type = &memblock.reserved; -- cgit v1.2.3 From 7bc35fdde6724549a0239b71e08b9f33d8bf2bfb Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Thu, 6 Feb 2014 12:04:27 -0800 Subject: arch/x86/mm/numa.c: fix array index overflow when synchronizing nid to memblock.reserved. The following path will cause array out of bound. memblock_add_region() will always set nid in memblock.reserved to MAX_NUMNODES. In numa_register_memblks(), after we set all nid to correct valus in memblock.reserved, we called setup_node_data(), and used memblock_alloc_nid() to allocate memory, with nid set to MAX_NUMNODES. The nodemask_t type can be seen as a bit array. And the index is 0 ~ MAX_NUMNODES-1. After that, when we call node_set() in numa_clear_kernel_node_hotplug(), the nodemask_t got an index of value MAX_NUMNODES, which is out of [0 ~ MAX_NUMNODES-1]. See below: numa_init() |---> numa_register_memblks() | |---> memblock_set_node(memory) set correct nid in memblock.memory | |---> memblock_set_node(reserved) set correct nid in memblock.reserved | |...... | |---> setup_node_data() | |---> memblock_alloc_nid() here, nid is set to MAX_NUMNODES (1024) |...... |---> numa_clear_kernel_node_hotplug() |---> node_set() here, we have an index 1024, and overflowed This patch moves nid setting to numa_clear_kernel_node_hotplug() to fix this problem. Reported-by: Dave Jones Signed-off-by: Tang Chen Tested-by: Gu Zheng Reported-by: Dave Jones Cc: David Rientjes Tested-by: Dave Jones Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/numa.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 45ec9d72b6dd..27aa0455fab3 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -493,14 +493,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) struct numa_memblk *mb = &mi->blk[i]; memblock_set_node(mb->start, mb->end - mb->start, &memblock.memory, mb->nid); - - /* - * At this time, all memory regions reserved by memblock are - * used by the kernel. Set the nid in memblock.reserved will - * mark out all the nodes the kernel resides in. - */ - memblock_set_node(mb->start, mb->end - mb->start, - &memblock.reserved, mb->nid); } /* @@ -569,6 +561,17 @@ static void __init numa_clear_kernel_node_hotplug(void) unsigned long start, end; struct memblock_type *type = &memblock.reserved; + /* + * At this time, all memory regions reserved by memblock are + * used by the kernel. Set the nid in memblock.reserved will + * mark out all the nodes the kernel resides in. + */ + for (i = 0; i < numa_meminfo.nr_blks; i++) { + struct numa_memblk *mb = &numa_meminfo.blk[i]; + memblock_set_node(mb->start, mb->end - mb->start, + &memblock.reserved, mb->nid); + } + /* Mark all kernel nodes. */ for (i = 0; i < type->cnt; i++) node_set(type->regions[i].nid, numa_kernel_nodes); -- cgit v1.2.3 From 1c70e099ac80ee779ffac66a6169ad936425fe41 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Sun, 2 Feb 2014 14:49:13 +0100 Subject: ARM: sunxi: dt: Convert to the new net compatibles Switch the device tree to the new compatibles introduced in the ethernet and mdio drivers to have a common pattern accross all Allwinner SoCs. Signed-off-by: Maxime Ripard Signed-off-by: David S. Miller --- arch/arm/boot/dts/sun4i-a10.dtsi | 4 ++-- arch/arm/boot/dts/sun5i-a10s.dtsi | 4 ++-- arch/arm/boot/dts/sun7i-a20.dtsi | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index 040bb0eba152..10666ca8aee1 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -315,7 +315,7 @@ ranges; emac: ethernet@01c0b000 { - compatible = "allwinner,sun4i-emac"; + compatible = "allwinner,sun4i-a10-emac"; reg = <0x01c0b000 0x1000>; interrupts = <55>; clocks = <&ahb_gates 17>; @@ -323,7 +323,7 @@ }; mdio@01c0b080 { - compatible = "allwinner,sun4i-mdio"; + compatible = "allwinner,sun4i-a10-mdio"; reg = <0x01c0b080 0x14>; status = "disabled"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index ea16054857a4..64961595e8d6 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -278,7 +278,7 @@ ranges; emac: ethernet@01c0b000 { - compatible = "allwinner,sun4i-emac"; + compatible = "allwinner,sun4i-a10-emac"; reg = <0x01c0b000 0x1000>; interrupts = <55>; clocks = <&ahb_gates 17>; @@ -286,7 +286,7 @@ }; mdio@01c0b080 { - compatible = "allwinner,sun4i-mdio"; + compatible = "allwinner,sun4i-a10-mdio"; reg = <0x01c0b080 0x14>; status = "disabled"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 119f066f0d98..9ff09484847b 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -340,7 +340,7 @@ ranges; emac: ethernet@01c0b000 { - compatible = "allwinner,sun4i-emac"; + compatible = "allwinner,sun4i-a10-emac"; reg = <0x01c0b000 0x1000>; interrupts = <0 55 4>; clocks = <&ahb_gates 17>; @@ -348,7 +348,7 @@ }; mdio@01c0b080 { - compatible = "allwinner,sun4i-mdio"; + compatible = "allwinner,sun4i-a10-mdio"; reg = <0x01c0b080 0x14>; status = "disabled"; #address-cells = <1>; -- cgit v1.2.3 From 821003ba4b9ffbf020a12177f0ea3d27826463c3 Mon Sep 17 00:00:00 2001 From: Jean-Jacques Hiblot Date: Wed, 15 Jan 2014 11:24:46 +0100 Subject: ARM: at91/dt: sam9263: fix compatibility string for the I2C Signed-off-by: Jean-Jacques Hiblot Signed-off-by: Nicolas Ferre --- arch/arm/boot/dts/at91sam9263.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index 0042f73068b0..fece8665fb63 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -523,7 +523,7 @@ }; i2c0: i2c@fff88000 { - compatible = "atmel,at91sam9263-i2c"; + compatible = "atmel,at91sam9260-i2c"; reg = <0xfff88000 0x100>; interrupts = <13 IRQ_TYPE_LEVEL_HIGH 6>; #address-cells = <1>; -- cgit v1.2.3 From 5f877518775a681b516dde700b511641fb3e4f9b Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Thu, 16 Jan 2014 16:25:34 +0100 Subject: ARM: at91/dt: fix sama5d3 ohci hclk clock reference The hclk clock of the ohci node is referencing udphs_clk instead of uhphs_clk. Signed-off-by: Boris BREZILLON Signed-off-by: Nicolas Ferre --- arch/arm/boot/dts/sama5d3.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi index 52447c17537a..3d5faf85f51b 100644 --- a/arch/arm/boot/dts/sama5d3.dtsi +++ b/arch/arm/boot/dts/sama5d3.dtsi @@ -1228,7 +1228,7 @@ compatible = "atmel,at91rm9200-ohci", "usb-ohci"; reg = <0x00600000 0x100000>; interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>, + clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>; clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck"; status = "disabled"; -- cgit v1.2.3 From d7e67ee8b2ce27f4481d3cf2ac6ba8febcc3d888 Mon Sep 17 00:00:00 2001 From: Bo Shen Date: Tue, 14 Jan 2014 14:34:44 +0800 Subject: ARM: at91: enable USB host on at91sam9n12ek board Enable USB host on at91sam9n12ek board. Signed-off-by: Bo Shen Signed-off-by: Nicolas Ferre --- arch/arm/boot/dts/at91sam9n12ek.dts | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch') diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index e9487f6f0166..924a6a6ffd0f 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -124,6 +124,10 @@ nand-on-flash-bbt; status = "okay"; }; + + usb0: ohci@00500000 { + status = "okay"; + }; }; leds { -- cgit v1.2.3 From b7c2b6157079811586180d13c44a1095b57c2d47 Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Tue, 4 Feb 2014 15:05:55 +0100 Subject: ARM: at91: add Atmel's SAMA5D3 Xplained board Add DT file for new SAMA5D3 Xplained board. This board is based on Atmel's SAMA5D36 Cortex-A5 SoC. Signed-off-by: Nicolas Ferre --- arch/arm/boot/dts/Makefile | 1 + arch/arm/boot/dts/at91-sama5d3_xplained.dts | 229 ++++++++++++++++++++++++++++ 2 files changed, 230 insertions(+) create mode 100644 arch/arm/boot/dts/at91-sama5d3_xplained.dts (limited to 'arch') diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index b9d6a8b485e0..6d1e43d46187 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -38,6 +38,7 @@ dtb-$(CONFIG_ARCH_AT91) += at91sam9g35ek.dtb dtb-$(CONFIG_ARCH_AT91) += at91sam9x25ek.dtb dtb-$(CONFIG_ARCH_AT91) += at91sam9x35ek.dtb # sama5d3 +dtb-$(CONFIG_ARCH_AT91) += at91-sama5d3_xplained.dtb dtb-$(CONFIG_ARCH_AT91) += sama5d31ek.dtb dtb-$(CONFIG_ARCH_AT91) += sama5d33ek.dtb dtb-$(CONFIG_ARCH_AT91) += sama5d34ek.dtb diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts new file mode 100644 index 000000000000..ce1375595e5f --- /dev/null +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -0,0 +1,229 @@ +/* + * at91-sama5d3_xplained.dts - Device Tree file for the SAMA5D3 Xplained board + * + * Copyright (C) 2014 Atmel, + * 2014 Nicolas Ferre + * + * Licensed under GPLv2 or later. + */ +/dts-v1/; +#include "sama5d36.dtsi" + +/ { + model = "SAMA5D3 Xplained"; + compatible = "atmel,sama5d3-xplained", "atmel,sama5d3", "atmel,sama5"; + + chosen { + bootargs = "console=ttyS0,115200"; + }; + + memory { + reg = <0x20000000 0x10000000>; + }; + + ahb { + apb { + mmc0: mmc@f0000000 { + pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0 &pinctrl_mmc0_dat1_3 &pinctrl_mmc0_dat4_7 &pinctrl_mmc0_cd>; + status = "okay"; + slot@0 { + reg = <0>; + bus-width = <8>; + cd-gpios = <&pioE 0 GPIO_ACTIVE_LOW>; + }; + }; + + spi0: spi@f0004000 { + cs-gpios = <&pioD 13 0>; + status = "okay"; + }; + + can0: can@f000c000 { + status = "okay"; + }; + + i2c0: i2c@f0014000 { + status = "okay"; + }; + + i2c1: i2c@f0018000 { + status = "okay"; + }; + + macb0: ethernet@f0028000 { + phy-mode = "rgmii"; + status = "okay"; + }; + + usart0: serial@f001c000 { + status = "okay"; + }; + + usart1: serial@f0020000 { + pinctrl-0 = <&pinctrl_usart1 &pinctrl_usart1_rts_cts>; + status = "okay"; + }; + + uart0: serial@f0024000 { + status = "okay"; + }; + + mmc1: mmc@f8000000 { + pinctrl-0 = <&pinctrl_mmc1_clk_cmd_dat0 &pinctrl_mmc1_dat1_3 &pinctrl_mmc1_cd>; + status = "okay"; + slot@0 { + reg = <0>; + bus-width = <4>; + cd-gpios = <&pioE 1 GPIO_ACTIVE_HIGH>; + }; + }; + + spi1: spi@f8008000 { + cs-gpios = <&pioC 25 0>, <0>, <0>, <&pioD 16 0>; + status = "okay"; + }; + + adc0: adc@f8018000 { + pinctrl-0 = < + &pinctrl_adc0_adtrg + &pinctrl_adc0_ad0 + &pinctrl_adc0_ad1 + &pinctrl_adc0_ad2 + &pinctrl_adc0_ad3 + &pinctrl_adc0_ad4 + &pinctrl_adc0_ad5 + &pinctrl_adc0_ad6 + &pinctrl_adc0_ad7 + &pinctrl_adc0_ad8 + &pinctrl_adc0_ad9 + >; + status = "okay"; + }; + + i2c2: i2c@f801c000 { + dmas = <0>, <0>; /* Do not use DMA for i2c2 */ + status = "okay"; + }; + + macb1: ethernet@f802c000 { + phy-mode = "rmii"; + status = "okay"; + }; + + dbgu: serial@ffffee00 { + status = "okay"; + }; + + pinctrl@fffff200 { + board { + pinctrl_mmc0_cd: mmc0_cd { + atmel,pins = + ; + }; + + pinctrl_mmc1_cd: mmc1_cd { + atmel,pins = + ; + }; + + pinctrl_usba_vbus: usba_vbus { + atmel,pins = + ; /* PE9, conflicts with A9 */ + }; + }; + }; + + pmc: pmc@fffffc00 { + main: mainck { + clock-frequency = <12000000>; + }; + }; + }; + + nand0: nand@60000000 { + nand-bus-width = <8>; + nand-ecc-mode = "hw"; + atmel,has-pmecc; + atmel,pmecc-cap = <4>; + atmel,pmecc-sector-size = <512>; + nand-on-flash-bbt; + status = "okay"; + + at91bootstrap@0 { + label = "at91bootstrap"; + reg = <0x0 0x40000>; + }; + + bootloader@40000 { + label = "bootloader"; + reg = <0x40000 0x80000>; + }; + + bootloaderenv@c0000 { + label = "bootloader env"; + reg = <0xc0000 0xc0000>; + }; + + dtb@180000 { + label = "device tree"; + reg = <0x180000 0x80000>; + }; + + kernel@200000 { + label = "kernel"; + reg = <0x200000 0x600000>; + }; + + rootfs@800000 { + label = "rootfs"; + reg = <0x800000 0x0f800000>; + }; + }; + + usb0: gadget@00500000 { + atmel,vbus-gpio = <&pioE 9 GPIO_ACTIVE_HIGH>; /* PE9, conflicts with A9 */ + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usba_vbus>; + status = "okay"; + }; + + usb1: ohci@00600000 { + num-ports = <3>; + atmel,vbus-gpio = <0 + &pioE 3 GPIO_ACTIVE_LOW + &pioE 4 GPIO_ACTIVE_LOW + >; + status = "okay"; + }; + + usb2: ehci@00700000 { + status = "okay"; + }; + }; + + gpio_keys { + compatible = "gpio-keys"; + + bp3 { + label = "PB_USER"; + gpios = <&pioE 29 GPIO_ACTIVE_LOW>; + linux,code = <0x104>; + gpio-key,wakeup; + }; + }; + + leds { + compatible = "gpio-leds"; + + d2 { + label = "d2"; + gpios = <&pioE 23 GPIO_ACTIVE_LOW>; /* PE23, conflicts with A23, CTS2 */ + linux,default-trigger = "heartbeat"; + }; + + d3 { + label = "d3"; + gpios = <&pioE 24 GPIO_ACTIVE_HIGH>; + }; + }; +}; -- cgit v1.2.3 From 8e86f0b409a44193f1587e87b69c5dcf8f65be67 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 4 Feb 2014 12:29:12 +0000 Subject: arm64: atomics: fix use of acquire + release for full barrier semantics Linux requires a number of atomic operations to provide full barrier semantics, that is no memory accesses after the operation can be observed before any accesses up to and including the operation in program order. On arm64, these operations have been incorrectly implemented as follows: // A, B, C are independent memory locations // atomic_op (B) 1: ldaxr x0, [B] // Exclusive load with acquire stlxr w1, x0, [B] // Exclusive store with release cbnz w1, 1b The assumption here being that two half barriers are equivalent to a full barrier, so the only permitted ordering would be A -> B -> C (where B is the atomic operation involving both a load and a store). Unfortunately, this is not the case by the letter of the architecture and, in fact, the accesses to A and C are permitted to pass their nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the store-release on B). This is a clear violation of the full barrier requirement. The simple way to fix this is to implement the same algorithm as ARMv7 using explicit barriers: // atomic_op (B) dmb ish // Full barrier 1: ldxr x0, [B] // Exclusive load stxr w1, x0, [B] // Exclusive store cbnz w1, 1b dmb ish // Full barrier but this has the undesirable effect of introducing *two* full barrier instructions. A better approach is actually the following, non-intuitive sequence: // atomic_op (B) 1: ldxr x0, [B] // Exclusive load stlxr w1, x0, [B] // Exclusive store with release cbnz w1, 1b dmb ish // Full barrier The simple observations here are: - The dmb ensures that no subsequent accesses (e.g. the access to C) can enter or pass the atomic sequence. - The dmb also ensures that no prior accesses (e.g. the access to A) can pass the atomic sequence. - Therefore, no prior access can pass a subsequent access, or vice-versa (i.e. A is strictly ordered before C). - The stlxr ensures that no prior access can pass the store component of the atomic operation. The only tricky part remaining is the ordering between the ldxr and the access to A, since the absence of the first dmb means that we're now permitting re-ordering between the ldxr and any prior accesses. From an (arbitrary) observer's point of view, there are two scenarios: 1. We have observed the ldxr. This means that if we perform a store to [B], the ldxr will still return older data. If we can observe the ldxr, then we can potentially observe the permitted re-ordering with the access to A, which is clearly an issue when compared to the dmb variant of the code. Thankfully, the exclusive monitor will save us here since it will be cleared as a result of the store and the ldxr will retry. Notice that any use of a later memory observation to imply observation of the ldxr will also imply observation of the access to A, since the stlxr/dmb ensure strict ordering. 2. We have not observed the ldxr. This means we can perform a store and influence the later ldxr. However, that doesn't actually tell us anything about the access to [A], so we've not lost anything here either when compared to the dmb variant. This patch implements this solution for our barriered atomic operations, ensuring that we satisfy the full barrier requirements where they are needed. Cc: Cc: Peter Zijlstra Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/atomic.h | 29 ++++++++++++++++++++--------- arch/arm64/include/asm/cmpxchg.h | 9 +++++---- arch/arm64/include/asm/futex.h | 6 ++++-- arch/arm64/kernel/kuser32.S | 6 ++++-- arch/arm64/lib/bitops.S | 3 ++- 5 files changed, 35 insertions(+), 18 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 01de5aaa3edc..e32893e005d4 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -64,7 +64,7 @@ static inline int atomic_add_return(int i, atomic_t *v) int result; asm volatile("// atomic_add_return\n" -"1: ldaxr %w0, %2\n" +"1: ldxr %w0, %2\n" " add %w0, %w0, %w3\n" " stlxr %w1, %w0, %2\n" " cbnz %w1, 1b" @@ -72,6 +72,7 @@ static inline int atomic_add_return(int i, atomic_t *v) : "Ir" (i) : "cc", "memory"); + smp_mb(); return result; } @@ -96,7 +97,7 @@ static inline int atomic_sub_return(int i, atomic_t *v) int result; asm volatile("// atomic_sub_return\n" -"1: ldaxr %w0, %2\n" +"1: ldxr %w0, %2\n" " sub %w0, %w0, %w3\n" " stlxr %w1, %w0, %2\n" " cbnz %w1, 1b" @@ -104,6 +105,7 @@ static inline int atomic_sub_return(int i, atomic_t *v) : "Ir" (i) : "cc", "memory"); + smp_mb(); return result; } @@ -112,17 +114,20 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new) unsigned long tmp; int oldval; + smp_mb(); + asm volatile("// atomic_cmpxchg\n" -"1: ldaxr %w1, %2\n" +"1: ldxr %w1, %2\n" " cmp %w1, %w3\n" " b.ne 2f\n" -" stlxr %w0, %w4, %2\n" +" stxr %w0, %w4, %2\n" " cbnz %w0, 1b\n" "2:" : "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter) : "Ir" (old), "r" (new) : "cc", "memory"); + smp_mb(); return oldval; } @@ -183,7 +188,7 @@ static inline long atomic64_add_return(long i, atomic64_t *v) unsigned long tmp; asm volatile("// atomic64_add_return\n" -"1: ldaxr %0, %2\n" +"1: ldxr %0, %2\n" " add %0, %0, %3\n" " stlxr %w1, %0, %2\n" " cbnz %w1, 1b" @@ -191,6 +196,7 @@ static inline long atomic64_add_return(long i, atomic64_t *v) : "Ir" (i) : "cc", "memory"); + smp_mb(); return result; } @@ -215,7 +221,7 @@ static inline long atomic64_sub_return(long i, atomic64_t *v) unsigned long tmp; asm volatile("// atomic64_sub_return\n" -"1: ldaxr %0, %2\n" +"1: ldxr %0, %2\n" " sub %0, %0, %3\n" " stlxr %w1, %0, %2\n" " cbnz %w1, 1b" @@ -223,6 +229,7 @@ static inline long atomic64_sub_return(long i, atomic64_t *v) : "Ir" (i) : "cc", "memory"); + smp_mb(); return result; } @@ -231,17 +238,20 @@ static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new) long oldval; unsigned long res; + smp_mb(); + asm volatile("// atomic64_cmpxchg\n" -"1: ldaxr %1, %2\n" +"1: ldxr %1, %2\n" " cmp %1, %3\n" " b.ne 2f\n" -" stlxr %w0, %4, %2\n" +" stxr %w0, %4, %2\n" " cbnz %w0, 1b\n" "2:" : "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter) : "Ir" (old), "r" (new) : "cc", "memory"); + smp_mb(); return oldval; } @@ -253,11 +263,12 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) unsigned long tmp; asm volatile("// atomic64_dec_if_positive\n" -"1: ldaxr %0, %2\n" +"1: ldxr %0, %2\n" " subs %0, %0, #1\n" " b.mi 2f\n" " stlxr %w1, %0, %2\n" " cbnz %w1, 1b\n" +" dmb ish\n" "2:" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) : diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 56166d7f4a25..189390ce8653 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -29,7 +29,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size switch (size) { case 1: asm volatile("// __xchg1\n" - "1: ldaxrb %w0, %2\n" + "1: ldxrb %w0, %2\n" " stlxrb %w1, %w3, %2\n" " cbnz %w1, 1b\n" : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) @@ -38,7 +38,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size break; case 2: asm volatile("// __xchg2\n" - "1: ldaxrh %w0, %2\n" + "1: ldxrh %w0, %2\n" " stlxrh %w1, %w3, %2\n" " cbnz %w1, 1b\n" : "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr) @@ -47,7 +47,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size break; case 4: asm volatile("// __xchg4\n" - "1: ldaxr %w0, %2\n" + "1: ldxr %w0, %2\n" " stlxr %w1, %w3, %2\n" " cbnz %w1, 1b\n" : "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr) @@ -56,7 +56,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size break; case 8: asm volatile("// __xchg8\n" - "1: ldaxr %0, %2\n" + "1: ldxr %0, %2\n" " stlxr %w1, %3, %2\n" " cbnz %w1, 1b\n" : "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr) @@ -67,6 +67,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size BUILD_BUG(); } + smp_mb(); return ret; } diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 78cc3aba5d69..572193d0005d 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -24,10 +24,11 @@ #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \ asm volatile( \ -"1: ldaxr %w1, %2\n" \ +"1: ldxr %w1, %2\n" \ insn "\n" \ "2: stlxr %w3, %w0, %2\n" \ " cbnz %w3, 1b\n" \ +" dmb ish\n" \ "3:\n" \ " .pushsection .fixup,\"ax\"\n" \ " .align 2\n" \ @@ -111,11 +112,12 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, return -EFAULT; asm volatile("// futex_atomic_cmpxchg_inatomic\n" -"1: ldaxr %w1, %2\n" +"1: ldxr %w1, %2\n" " sub %w3, %w1, %w4\n" " cbnz %w3, 3f\n" "2: stlxr %w3, %w5, %2\n" " cbnz %w3, 1b\n" +" dmb ish\n" "3:\n" " .pushsection .fixup,\"ax\"\n" "4: mov %w0, %w6\n" diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S index 63c48ffdf230..7787208e8cc6 100644 --- a/arch/arm64/kernel/kuser32.S +++ b/arch/arm64/kernel/kuser32.S @@ -38,12 +38,13 @@ __kuser_cmpxchg64: // 0xffff0f60 .inst 0xe92d00f0 // push {r4, r5, r6, r7} .inst 0xe1c040d0 // ldrd r4, r5, [r0] .inst 0xe1c160d0 // ldrd r6, r7, [r1] - .inst 0xe1b20e9f // 1: ldaexd r0, r1, [r2] + .inst 0xe1b20f9f // 1: ldrexd r0, r1, [r2] .inst 0xe0303004 // eors r3, r0, r4 .inst 0x00313005 // eoreqs r3, r1, r5 .inst 0x01a23e96 // stlexdeq r3, r6, [r2] .inst 0x03330001 // teqeq r3, #1 .inst 0x0afffff9 // beq 1b + .inst 0xf57ff05b // dmb ish .inst 0xe2730000 // rsbs r0, r3, #0 .inst 0xe8bd00f0 // pop {r4, r5, r6, r7} .inst 0xe12fff1e // bx lr @@ -55,11 +56,12 @@ __kuser_memory_barrier: // 0xffff0fa0 .align 5 __kuser_cmpxchg: // 0xffff0fc0 - .inst 0xe1923e9f // 1: ldaex r3, [r2] + .inst 0xe1923f9f // 1: ldrex r3, [r2] .inst 0xe0533000 // subs r3, r3, r0 .inst 0x01823e91 // stlexeq r3, r1, [r2] .inst 0x03330001 // teqeq r3, #1 .inst 0x0afffffa // beq 1b + .inst 0xf57ff05b // dmb ish .inst 0xe2730000 // rsbs r0, r3, #0 .inst 0xe12fff1e // bx lr diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S index e5db797790d3..7dac371cc9a2 100644 --- a/arch/arm64/lib/bitops.S +++ b/arch/arm64/lib/bitops.S @@ -46,11 +46,12 @@ ENTRY( \name ) mov x2, #1 add x1, x1, x0, lsr #3 // Get word offset lsl x4, x2, x3 // Create mask -1: ldaxr x2, [x1] +1: ldxr x2, [x1] lsr x0, x2, x3 // Save old value of bit \instr x2, x2, x4 // toggle bit stlxr w5, x2, [x1] cbnz w5, 1b + dmb ish and x0, x0, #1 3: ret ENDPROC(\name ) -- cgit v1.2.3 From 95c4189689f92fba7ecf9097173404d4928c6e9b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 4 Feb 2014 12:29:13 +0000 Subject: arm64: asm: remove redundant "cc" clobbers cbnz/tbnz don't update the condition flags, so remove the "cc" clobbers from inline asm blocks that only use these instructions to implement conditional branches. Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/atomic.h | 24 ++++++++++-------------- arch/arm64/include/asm/cmpxchg.h | 8 ++++---- arch/arm64/include/asm/futex.h | 4 ++-- arch/arm64/include/asm/spinlock.h | 10 +++++----- 4 files changed, 21 insertions(+), 25 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index e32893e005d4..0237f0867e37 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -54,8 +54,7 @@ static inline void atomic_add(int i, atomic_t *v) " stxr %w1, %w0, %2\n" " cbnz %w1, 1b" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i) - : "cc"); + : "Ir" (i)); } static inline int atomic_add_return(int i, atomic_t *v) @@ -70,7 +69,7 @@ static inline int atomic_add_return(int i, atomic_t *v) " cbnz %w1, 1b" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) : "Ir" (i) - : "cc", "memory"); + : "memory"); smp_mb(); return result; @@ -87,8 +86,7 @@ static inline void atomic_sub(int i, atomic_t *v) " stxr %w1, %w0, %2\n" " cbnz %w1, 1b" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i) - : "cc"); + : "Ir" (i)); } static inline int atomic_sub_return(int i, atomic_t *v) @@ -103,7 +101,7 @@ static inline int atomic_sub_return(int i, atomic_t *v) " cbnz %w1, 1b" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) : "Ir" (i) - : "cc", "memory"); + : "memory"); smp_mb(); return result; @@ -125,7 +123,7 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new) "2:" : "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter) : "Ir" (old), "r" (new) - : "cc", "memory"); + : "cc"); smp_mb(); return oldval; @@ -178,8 +176,7 @@ static inline void atomic64_add(u64 i, atomic64_t *v) " stxr %w1, %0, %2\n" " cbnz %w1, 1b" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i) - : "cc"); + : "Ir" (i)); } static inline long atomic64_add_return(long i, atomic64_t *v) @@ -194,7 +191,7 @@ static inline long atomic64_add_return(long i, atomic64_t *v) " cbnz %w1, 1b" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) : "Ir" (i) - : "cc", "memory"); + : "memory"); smp_mb(); return result; @@ -211,8 +208,7 @@ static inline void atomic64_sub(u64 i, atomic64_t *v) " stxr %w1, %0, %2\n" " cbnz %w1, 1b" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : "Ir" (i) - : "cc"); + : "Ir" (i)); } static inline long atomic64_sub_return(long i, atomic64_t *v) @@ -227,7 +223,7 @@ static inline long atomic64_sub_return(long i, atomic64_t *v) " cbnz %w1, 1b" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) : "Ir" (i) - : "cc", "memory"); + : "memory"); smp_mb(); return result; @@ -249,7 +245,7 @@ static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new) "2:" : "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter) : "Ir" (old), "r" (new) - : "cc", "memory"); + : "cc"); smp_mb(); return oldval; diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 189390ce8653..57c0fa7bf711 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -34,7 +34,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size " cbnz %w1, 1b\n" : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) : "r" (x) - : "cc", "memory"); + : "memory"); break; case 2: asm volatile("// __xchg2\n" @@ -43,7 +43,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size " cbnz %w1, 1b\n" : "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr) : "r" (x) - : "cc", "memory"); + : "memory"); break; case 4: asm volatile("// __xchg4\n" @@ -52,7 +52,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size " cbnz %w1, 1b\n" : "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr) : "r" (x) - : "cc", "memory"); + : "memory"); break; case 8: asm volatile("// __xchg8\n" @@ -61,7 +61,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size " cbnz %w1, 1b\n" : "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr) : "r" (x) - : "cc", "memory"); + : "memory"); break; default: BUILD_BUG(); diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 572193d0005d..5f750dc96e0f 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -41,7 +41,7 @@ " .popsection\n" \ : "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp) \ : "r" (oparg), "Ir" (-EFAULT) \ - : "cc", "memory") + : "memory") static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) @@ -129,7 +129,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, " .popsection\n" : "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp) : "r" (oldval), "r" (newval), "Ir" (-EFAULT) - : "cc", "memory"); + : "memory"); *uval = val; return ret; diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index 3d5cf064d7a1..c45b7b1b7197 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -132,7 +132,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw) " cbnz %w0, 2b\n" : "=&r" (tmp), "+Q" (rw->lock) : "r" (0x80000000) - : "cc", "memory"); + : "memory"); } static inline int arch_write_trylock(arch_rwlock_t *rw) @@ -146,7 +146,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) "1:\n" : "=&r" (tmp), "+Q" (rw->lock) : "r" (0x80000000) - : "cc", "memory"); + : "memory"); return !tmp; } @@ -187,7 +187,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw) " cbnz %w1, 2b\n" : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) : - : "cc", "memory"); + : "memory"); } static inline void arch_read_unlock(arch_rwlock_t *rw) @@ -201,7 +201,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) " cbnz %w1, 1b\n" : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) : - : "cc", "memory"); + : "memory"); } static inline int arch_read_trylock(arch_rwlock_t *rw) @@ -216,7 +216,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) "1:\n" : "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock) : - : "cc", "memory"); + : "memory"); return !tmp2; } -- cgit v1.2.3 From 55834a773fe343912b705bef8114ec93fd337188 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 7 Feb 2014 17:12:45 +0000 Subject: arm64: defconfig: Expand default enabled features FPGA implementations of the Cortex-A57 and Cortex-A53 are now available in the form of the SMM-A57 and SMM-A53 Soft Macrocell Models (SMMs) for Versatile Express. As these attach to a Motherboard Express V2M-P1 it would be useful to have support for some V2M-P1 peripherals enabled by default. Additionally a couple of of features have been introduced since the last defconfig update (CMA, jump labels) that would be good to have enabled by default to ensure they are build and boot tested. This patch updates the arm64 defconfig to enable support for these devices and features. The arm64 Kconfig is modified to select HAVE_PATA_PLATFORM, which is required to enable support for the CompactFlash controller on the V2M-P1. A few options which don't need to appear in defconfig are trimmed: * BLK_DEV - selected by default * EXPERIMENTAL - otherwise gone from the kernel * MII - selected by drivers which require it * USB_SUPPORT - selected by default Signed-off-by: Mark Rutland Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 1 + arch/arm64/configs/defconfig | 18 ++++++++++++++---- 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index dd4327f09ba4..27bbcfc7202a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -36,6 +36,7 @@ config ARM64 select HAVE_GENERIC_DMA_COHERENT select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_MEMBLOCK + select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS select IRQ_DOMAIN select MODULES_USE_ELF_RELA diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 84139be62ae6..7959dd0ca5d5 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1,4 +1,3 @@ -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set # CONFIG_SWAP is not set CONFIG_SYSVIPC=y @@ -19,6 +18,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_KALLSYMS_ALL=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set @@ -27,6 +27,7 @@ CONFIG_ARCH_VEXPRESS=y CONFIG_ARCH_XGENE=y CONFIG_SMP=y CONFIG_PREEMPT=y +CONFIG_CMA=y CONFIG_CMDLINE="console=ttyAMA0" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_COMPAT=y @@ -42,14 +43,17 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_WIRELESS is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y -CONFIG_BLK_DEV=y +CONFIG_DMA_CMA=y CONFIG_SCSI=y # CONFIG_SCSI_PROC_FS is not set CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set +CONFIG_ATA=y +CONFIG_PATA_PLATFORM=y +CONFIG_PATA_OF_PLATFORM=y CONFIG_NETDEVICES=y -CONFIG_MII=y CONFIG_SMC91X=y +CONFIG_SMSC911X=y # CONFIG_WLAN is not set CONFIG_INPUT_EVDEV=y # CONFIG_SERIO_I8042 is not set @@ -62,13 +66,19 @@ CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set +CONFIG_REGULATOR=y +CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_FB=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set -# CONFIG_USB_SUPPORT is not set +CONFIG_USB=y +CONFIG_USB_ISP1760_HCD=y +CONFIG_USB_STORAGE=y +CONFIG_MMC=y +CONFIG_MMC_ARMMMCI=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y -- cgit v1.2.3 From 87f9260bf1fb7ec4c3f88c6bb353df17ca1e1c19 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 8 Feb 2014 21:18:24 +0000 Subject: ARM: dts: fix spdif pinmux configuration The spdif pinmux configuration must be connected to the spdif device to take effect, not the spdif-transmitter. Signed-off-by: Russell King --- arch/arm/boot/dts/imx6dl-hummingboard.dts | 10 +++------- arch/arm/boot/dts/imx6qdl-cubox-i.dtsi | 10 +++------- 2 files changed, 6 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/imx6dl-hummingboard.dts b/arch/arm/boot/dts/imx6dl-hummingboard.dts index fd8fc7cd53f3..5bfae54fb780 100644 --- a/arch/arm/boot/dts/imx6dl-hummingboard.dts +++ b/arch/arm/boot/dts/imx6dl-hummingboard.dts @@ -52,12 +52,6 @@ }; }; - codec: spdif-transmitter { - compatible = "linux,spdif-dit"; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_hummingboard_spdif>; - }; - sound-spdif { compatible = "fsl,imx-audio-spdif"; model = "imx-spdif"; @@ -111,7 +105,7 @@ }; pinctrl_hummingboard_spdif: hummingboard-spdif { - fsl,pins = ; + fsl,pins = ; }; pinctrl_hummingboard_usbh1_vbus: hummingboard-usbh1-vbus { @@ -142,6 +136,8 @@ }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_hummingboard_spdif>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi index 64daa3b311f6..c2a24888a276 100644 --- a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi @@ -46,12 +46,6 @@ }; }; - codec: spdif-transmitter { - compatible = "linux,spdif-dit"; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_cubox_i_spdif>; - }; - sound-spdif { compatible = "fsl,imx-audio-spdif"; model = "imx-spdif"; @@ -89,7 +83,7 @@ }; pinctrl_cubox_i_spdif: cubox-i-spdif { - fsl,pins = ; + fsl,pins = ; }; pinctrl_cubox_i_usbh1_vbus: cubox-i-usbh1-vbus { @@ -121,6 +115,8 @@ }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_cubox_i_spdif>; status = "okay"; }; -- cgit v1.2.3 From e97df76377b8b3b1f7dfd5d6f8a1d5a31438b140 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 5 Feb 2014 20:48:51 +0100 Subject: perf/x86/intel/p6: Add userspace RDPMC quirk for PPro PPro machines can die hard when PCE gets enabled due to a CPU erratum. The safe way it so disable it by default and keep it disabled. See erratum 26 in: http://download.intel.com/design/archives/processors/pro/docs/24268935.pdf Reported-and-Tested-by: Mark Davies Cc: Alan Cox Cc: Stephane Eranian Cc: Vince Weaver Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140206170815.GW2936@laptop.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 6 ++++- arch/x86/kernel/cpu/perf_event.h | 1 + arch/x86/kernel/cpu/perf_event_p6.c | 48 +++++++++++++++++++++++++------------ 3 files changed, 39 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index b88645191fe5..1246b853c4e0 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1521,6 +1521,8 @@ static int __init init_hw_perf_events(void) pr_cont("%s PMU driver.\n", x86_pmu.name); + x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ + for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next) quirk->func(); @@ -1534,7 +1536,6 @@ static int __init init_hw_perf_events(void) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, 0, x86_pmu.num_counters, 0, 0); - x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; if (x86_pmu.event_attrs) @@ -1820,6 +1821,9 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (ret) return ret; + if (x86_pmu.attr_rdpmc_broken) + return -ENOTSUPP; + if (!!val != !!x86_pmu.attr_rdpmc) { x86_pmu.attr_rdpmc = !!val; smp_call_function(change_rdpmc, (void *)val, 1); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index c1a861829d81..4972c244d0bc 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -409,6 +409,7 @@ struct x86_pmu { /* * sysfs attrs */ + int attr_rdpmc_broken; int attr_rdpmc; struct attribute **format_attrs; struct attribute **event_attrs; diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index b1e2fe115323..7c1a0c07b607 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -231,31 +231,49 @@ static __initconst const struct x86_pmu p6_pmu = { }; +static __init void p6_pmu_rdpmc_quirk(void) +{ + if (boot_cpu_data.x86_mask < 9) { + /* + * PPro erratum 26; fixed in stepping 9 and above. + */ + pr_warn("Userspace RDPMC support disabled due to a CPU erratum\n"); + x86_pmu.attr_rdpmc_broken = 1; + x86_pmu.attr_rdpmc = 0; + } +} + __init int p6_pmu_init(void) { + x86_pmu = p6_pmu; + switch (boot_cpu_data.x86_model) { - case 1: - case 3: /* Pentium Pro */ - case 5: - case 6: /* Pentium II */ - case 7: - case 8: - case 11: /* Pentium III */ - case 9: - case 13: - /* Pentium M */ + case 1: /* Pentium Pro */ + x86_add_quirk(p6_pmu_rdpmc_quirk); + break; + + case 3: /* Pentium II - Klamath */ + case 5: /* Pentium II - Deschutes */ + case 6: /* Pentium II - Mendocino */ break; + + case 7: /* Pentium III - Katmai */ + case 8: /* Pentium III - Coppermine */ + case 10: /* Pentium III Xeon */ + case 11: /* Pentium III - Tualatin */ + break; + + case 9: /* Pentium M - Banias */ + case 13: /* Pentium M - Dothan */ + break; + default: - pr_cont("unsupported p6 CPU model %d ", - boot_cpu_data.x86_model); + pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model); return -ENODEV; } - x86_pmu = p6_pmu; - memcpy(hw_cache_event_ids, p6_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - return 0; } -- cgit v1.2.3 From 0e9f2204cfa6d79abe3e525ddf7c4ab5792cc751 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 5 Feb 2014 11:19:56 +0100 Subject: perf/x86: Fix Userspace RDPMC switch The current code forgets to change the CR4 state on the current CPU. Use on_each_cpu() instead of smp_call_function(). Reported-by: Mark Davies Suggested-by: Mark Davies Signed-off-by: Peter Zijlstra Cc: fweisbec@gmail.com Link: http://lkml.kernel.org/n/tip-69efsat90ibhnd577zy3z9gh@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1246b853c4e0..895604f2e916 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1826,7 +1826,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (!!val != !!x86_pmu.attr_rdpmc) { x86_pmu.attr_rdpmc = !!val; - smp_call_function(change_rdpmc, (void *)val, 1); + on_each_cpu(change_rdpmc, (void *)val, 1); } return count; -- cgit v1.2.3 From 569d6557ab957d6ae7e97a46ae669174be4189e6 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 4 Feb 2014 14:13:15 -0500 Subject: x86: Use preempt_disable_notrace() in cycles_2_ns() When debug preempt is enabled, preempt_disable() can be traced by function and function graph tracing. There's a place in the function graph tracer that calls trace_clock() which eventually calls cycles_2_ns() outside of the recursion protection. When cycles_2_ns() calls preempt_disable() it gets traced and the graph tracer will go into a recursive loop causing a crash or worse, a triple fault. Simple fix is to use preempt_disable_notrace() in cycles_2_ns, which makes sense because the preempt_disable() tracing may use that code too, and it tracing it, even with recursion protection is rather pointless. Signed-off-by: Steven Rostedt Acked-by: Thomas Gleixner Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20140204141315.2a968a72@gandalf.local.home Signed-off-by: Ingo Molnar --- arch/x86/kernel/tsc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 19e5adb49a27..acb3b606613e 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -209,7 +209,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) * dance when its actually needed. */ - preempt_disable(); + preempt_disable_notrace(); data = this_cpu_read(cyc2ns.head); tail = this_cpu_read(cyc2ns.tail); @@ -229,7 +229,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) if (!--data->__count) this_cpu_write(cyc2ns.tail, data); } - preempt_enable(); + preempt_enable_notrace(); return ns; } -- cgit v1.2.3 From ac1566ece497b2a37667cc5d4258edb0bf3b6836 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Thu, 30 Jan 2014 15:25:37 +0100 Subject: microblaze: Fix missing HZ macro Add missing param.h header because of HZ macro. It is causing compilation failure: In file included from include/linux/delay.h:14:0, from drivers/clk/qcom/reset.c:18: drivers/clk/qcom/reset.c: In function 'qcom_reset': arch/microblaze/include/asm/delay.h:39:35: error: 'HZ' undeclared (first use in this function) Signed-off-by: Michal Simek --- arch/microblaze/include/asm/delay.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/microblaze/include/asm/delay.h b/arch/microblaze/include/asm/delay.h index 05b7d39e4391..66fc24c24238 100644 --- a/arch/microblaze/include/asm/delay.h +++ b/arch/microblaze/include/asm/delay.h @@ -13,6 +13,8 @@ #ifndef _ASM_MICROBLAZE_DELAY_H #define _ASM_MICROBLAZE_DELAY_H +#include + extern inline void __delay(unsigned long loops) { asm volatile ("# __delay \n\t" \ -- cgit v1.2.3 From 4f3cbd79afd99cc5143b2beb126e7425af7f1ff9 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Thu, 30 Jan 2014 15:27:26 +0100 Subject: microblaze: Define readq and writeq IO helper function Some drivers check if readq/writeq functions are defined. If not internal driver functions are used which cause compilation failures. Signed-off-by: Michal Simek --- arch/microblaze/include/asm/io.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch') diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h index a2cea7206077..3fbb7f1db3bc 100644 --- a/arch/microblaze/include/asm/io.h +++ b/arch/microblaze/include/asm/io.h @@ -89,6 +89,11 @@ static inline unsigned int readl(const volatile void __iomem *addr) { return le32_to_cpu(*(volatile unsigned int __force *)addr); } +#define readq readq +static inline u64 readq(const volatile void __iomem *addr) +{ + return le64_to_cpu(__raw_readq(addr)); +} static inline void writeb(unsigned char v, volatile void __iomem *addr) { *(volatile unsigned char __force *)addr = v; @@ -101,6 +106,7 @@ static inline void writel(unsigned int v, volatile void __iomem *addr) { *(volatile unsigned int __force *)addr = cpu_to_le32(v); } +#define writeq(b, addr) __raw_writeq(cpu_to_le64(b), addr) /* ioread and iowrite variants. thease are for now same as __raw_ * variants of accessors. we might check for endianess in the feature -- cgit v1.2.3 From a49f56eec54d864ba0fda838e4c8bf5c72f3eb08 Mon Sep 17 00:00:00 2001 From: "Edgar E. Iglesias" Date: Sat, 8 Feb 2014 02:31:31 +0000 Subject: microblaze: Fix a typo when disabling stack protection Correct a typo causing the stack protector to be left enabled. 0xFFFFFFF -> 0xFFFFFFFF Signed-off-by: Edgar E. Iglesias Tested-by: Guenter Roeck Signed-off-by: Michal Simek --- arch/microblaze/kernel/head.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S index b7fb0438458c..17645b2e2f07 100644 --- a/arch/microblaze/kernel/head.S +++ b/arch/microblaze/kernel/head.S @@ -66,7 +66,7 @@ real_start: mts rmsr, r0 /* Disable stack protection from bootloader */ mts rslr, r0 - addi r8, r0, 0xFFFFFFF + addi r8, r0, 0xFFFFFFFF mts rshr, r8 /* * According to Xilinx, msrclr instruction behaves like 'mfs rX,rpc' -- cgit v1.2.3 From 4d9c5b89cf3605bbc39c6e274351ff25f0d83e6a Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Sun, 2 Feb 2014 22:21:31 +0100 Subject: ARM: 7950/1: mm: Fix stage-2 device memory attributes The stage-2 memory attributes are distinct from the Hyp memory attributes and the Stage-1 memory attributes. We were using the stage-1 memory attributes for stage-2 mappings causing device mappings to be mapped as normal memory. Add the S2 equivalent defines for memory attributes and fix the comments explaining the defines while at it. Add a prot_pte_s2 field to the mem_type struct and fill out the field for device mappings accordingly. Cc: [3.9+] Acked-by: Marc Zyngier Acked-by: Catalin Marinas Signed-off-by: Christoffer Dall Signed-off-by: Russell King --- arch/arm/include/asm/pgtable-3level.h | 15 +++++++++------ arch/arm/mm/mm.h | 1 + arch/arm/mm/mmu.c | 7 ++++++- 3 files changed, 16 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 03243f7eeddf..85c60adc8b60 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -120,13 +120,16 @@ /* * 2nd stage PTE definitions for LPAE. */ -#define L_PTE_S2_MT_UNCACHED (_AT(pteval_t, 0x5) << 2) /* MemAttr[3:0] */ -#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */ -#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */ -#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ -#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ +#define L_PTE_S2_MT_UNCACHED (_AT(pteval_t, 0x0) << 2) /* strongly ordered */ +#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* normal inner write-through */ +#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* normal inner write-back */ +#define L_PTE_S2_MT_DEV_SHARED (_AT(pteval_t, 0x1) << 2) /* device */ +#define L_PTE_S2_MT_MASK (_AT(pteval_t, 0xf) << 2) -#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ +#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ +#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ + +#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ /* * Hyp-mode PL2 PTE definitions for LPAE. diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index d5a982d15a88..7ea641b7aa7d 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -38,6 +38,7 @@ static inline pmd_t *pmd_off_k(unsigned long virt) struct mem_type { pteval_t prot_pte; + pteval_t prot_pte_s2; pmdval_t prot_l1; pmdval_t prot_sect; unsigned int domain; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4f08c133cc25..a623cb3ad012 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -232,12 +232,16 @@ __setup("noalign", noalign_setup); #endif /* ifdef CONFIG_CPU_CP15 / else */ #define PROT_PTE_DEVICE L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN +#define PROT_PTE_S2_DEVICE PROT_PTE_DEVICE #define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE static struct mem_type mem_types[] = { [MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */ .prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED | L_PTE_SHARED, + .prot_pte_s2 = s2_policy(PROT_PTE_S2_DEVICE) | + s2_policy(L_PTE_S2_MT_DEV_SHARED) | + L_PTE_SHARED, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PROT_SECT_DEVICE | PMD_SECT_S, .domain = DOMAIN_IO, @@ -508,7 +512,8 @@ static void __init build_mem_type_table(void) cp = &cache_policies[cachepolicy]; vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; s2_pgprot = cp->pte_s2; - hyp_device_pgprot = s2_device_pgprot = mem_types[MT_DEVICE].prot_pte; + hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte; + s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2; /* * ARMv6 and above have extended page tables. -- cgit v1.2.3 From ca4744084772e1fee999391bee0fcdca5d91a757 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Thu, 6 Feb 2014 19:50:35 +0100 Subject: ARM: 7952/1: mm: Fix the memblock allocation for LPAE machines Commit ad6492b8 added much needed memblock_virt_alloc_low() and further commit 07bacb3 {memblock, bootmem: restore goal for alloc_low} fixed the issue with low memory limit thanks to Yinghai. But even after all these fixes, there is still one case where the limit check done with ARCH_LOW_ADDRESS_LIMIT for low memory fails. Russell pointed out the issue with 32 bit LPAE machines in below thread. https://lkml.org/lkml/2014/1/28/364 Since on some LPAE machines where memory start address is beyond 4GB, the low memory marker in memblock will be set to default ARCH_LOW_ADDRESS_LIMIT which is wrong. We can fix this by letting architectures set the ARCH_LOW_ADDRESS_LIMIT using another export similar to memblock_set_current_limit() but am not sure whether its worth the trouble. Tell me if you think otherwise. Rather am just trying to fix that one broken case using memblock_virt_alloc() in setup code since the memblock.current_limit is updated appropriately makes it work on all ARM 32 bit machines. Cc: Yinghai Lu Cc: Strashko, Grygorii Cc: Andrew Morton Signed-off-by: Santosh Shilimkar Signed-off-by: Russell King --- arch/arm/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index b0df9761de6d..1e8b030dbefd 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -731,7 +731,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) kernel_data.end = virt_to_phys(_end - 1); for_each_memblock(memory, region) { - res = memblock_virt_alloc_low(sizeof(*res), 0); + res = memblock_virt_alloc(sizeof(*res), 0); res->name = "System RAM"; res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; -- cgit v1.2.3 From bae0ca2bc550d1ec6a118fb8f2696f18c4da3d8e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 7 Feb 2014 19:12:20 +0100 Subject: ARM: 7953/1: mm: ensure TLB invalidation is complete before enabling MMU During __v{6,7}_setup, we invalidate the TLBs since we are about to enable the MMU on return to head.S. Unfortunately, without a subsequent dsb instruction, the invalidation is not guaranteed to have completed by the time we write to the sctlr, potentially exposing us to junk/stale translations cached in the TLB. This patch reworks the init functions so that the dsb used to ensure completion of cache/predictor maintenance is also used to ensure completion of the TLB invalidation. Cc: Reported-by: Albin Tonnerre Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/mm/proc-v6.S | 3 ++- arch/arm/mm/proc-v7.S | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 45dc29f85d56..32b3558321c4 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -208,7 +208,6 @@ __v6_setup: mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c15, 0 @ clean+invalidate cache - mcr p15, 0, r0, c7, c10, 4 @ drain write buffer #ifdef CONFIG_MMU mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs mcr p15, 0, r0, c2, c0, 2 @ TTB control register @@ -218,6 +217,8 @@ __v6_setup: ALT_UP(orr r8, r8, #TTB_FLAGS_UP) mcr p15, 0, r8, c2, c0, 1 @ load TTB1 #endif /* CONFIG_MMU */ + mcr p15, 0, r0, c7, c10, 4 @ drain write buffer and + @ complete invalidations adr r5, v6_crval ldmia r5, {r5, r6} ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index bd1781979a39..74f6033e76dd 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -351,7 +351,6 @@ __v7_setup: 4: mov r10, #0 mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate - dsb #ifdef CONFIG_MMU mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs v7_ttb_setup r10, r4, r8, r5 @ TTBCR, TTBRx setup @@ -360,6 +359,7 @@ __v7_setup: mcr p15, 0, r5, c10, c2, 0 @ write PRRR mcr p15, 0, r6, c10, c2, 1 @ write NMRR #endif + dsb @ Complete invalidations #ifndef CONFIG_ARM_THUMBEE mrc p15, 0, r0, c0, c1, 0 @ read ID_PFR0 for ThumbEE and r0, r0, #(0xf << 12) @ ThumbEE enabled field -- cgit v1.2.3 From 7c8746a9eb287642deaad0e7c2cdf482dce5e4be Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 7 Feb 2014 19:12:32 +0100 Subject: ARM: 7955/1: spinlock: ensure we have a compiler barrier before sev When unlocking a spinlock, we require the following, strictly ordered sequence of events: /* dmb */ /* dsb */ Whilst the code does indeed reflect this in terms of the architecture, the final + have been contracted into a single inline asm without a "memory" clobber, therefore the compiler is at liberty to reorder the unlock to the end of the above sequence. In such a case, a waiting CPU may be woken up before the lock has been unlocked, leading to extremely poor performance. This patch reworks the dsb_sev() function to make use of the dsb() macro and ensure ordering against the unlock. Cc: Reported-by: Mark Rutland Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/include/asm/spinlock.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index ef3c6072aa45..ac4bfae26702 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -37,18 +37,9 @@ static inline void dsb_sev(void) { -#if __LINUX_ARM_ARCH__ >= 7 - __asm__ __volatile__ ( - "dsb ishst\n" - SEV - ); -#else - __asm__ __volatile__ ( - "mcr p15, 0, %0, c7, c10, 4\n" - SEV - : : "r" (0) - ); -#endif + + dsb(ishst); + __asm__(SEV); } /* -- cgit v1.2.3 From 29ffa48fa64fcdfc71d80593c8ae79248bc27677 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Feb 2014 13:30:05 +0100 Subject: ARM: pxa: fix compilation problem on AM300EPD board MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This board fails compilation like this: arch/arm/mach-pxa/am300epd.c: In function ‘am300_cleanup’: arch/arm/mach-pxa/am300epd.c:179:2: error: implicit declaration of function ‘PXA_GPIO_TO_IRQ’ [-Werror=implicit-function-declaration] free_irq(PXA_GPIO_TO_IRQ(RDY_GPIO_PIN), par); This was caused by commit 88f718e3fa4d67f3a8dbe79a2f97d722323e4051 "ARM: pxa: delete the custom GPIO header" This is because it was previously getting the macro PXA_GPIO_TO_IRQ implicitly from which in turn implicitly included which in turn included . Add the missing include so that the board compiles again. Reported-by: Arnd Bergmann Signed-off-by: Linus Walleij Signed-off-by: Kevin Hilman --- arch/arm/mach-pxa/am300epd.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/arm/mach-pxa/am300epd.c b/arch/arm/mach-pxa/am300epd.c index c9f309ae88c5..8b90c4f2d430 100644 --- a/arch/arm/mach-pxa/am300epd.c +++ b/arch/arm/mach-pxa/am300epd.c @@ -30,6 +30,7 @@ #include #include +#include #include #include "generic.h" -- cgit v1.2.3 From 9705e74671f0e4f994d86b00cecf441917c64a66 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Feb 2014 13:53:07 +0100 Subject: ARM: pxa: fix various compilation problems MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Due to commit 88f718e3fa4d67f3a8dbe79a2f97d722323e4051 "ARM: pxa: delete the custom GPIO header" some drivers fail compilation, for example like this: In file included from sound/soc/pxa/spitz.c:28:0: sound/soc/pxa/spitz.c: In function ‘spitz_ext_control’: arch/arm/mach-pxa/include/mach/spitz.h:111:30: error: ‘PXA_NR_BUILTIN_GPIO’ undeclared (first use in this function) #define SPITZ_SCP_GPIO_BASE (PXA_NR_BUILTIN_GPIO) (etc.) This is caused by implicit inclusion of from various board-specific headers under in the PXA platform. So we take a sweep over these, and for every such header that uses PXA_NR_BUILTIN_GPIO or PXA_GPIO_TO_IRQ() we explicitly #include "irqs.h" so that we satisfy the dependency in the board include file alone. Reported-by: Arnd Bergmann Signed-off-by: Linus Walleij Cc: stable@vger.kernel.org # v3.13+ Signed-off-by: Kevin Hilman --- arch/arm/mach-pxa/include/mach/balloon3.h | 2 ++ arch/arm/mach-pxa/include/mach/corgi.h | 1 + arch/arm/mach-pxa/include/mach/csb726.h | 2 ++ arch/arm/mach-pxa/include/mach/gumstix.h | 1 + arch/arm/mach-pxa/include/mach/idp.h | 1 + arch/arm/mach-pxa/include/mach/palmld.h | 2 ++ arch/arm/mach-pxa/include/mach/palmt5.h | 2 ++ arch/arm/mach-pxa/include/mach/palmtc.h | 2 ++ arch/arm/mach-pxa/include/mach/palmtx.h | 2 ++ arch/arm/mach-pxa/include/mach/pcm027.h | 2 ++ arch/arm/mach-pxa/include/mach/pcm990_baseboard.h | 1 + arch/arm/mach-pxa/include/mach/poodle.h | 2 ++ arch/arm/mach-pxa/include/mach/spitz.h | 2 +- arch/arm/mach-pxa/include/mach/tosa.h | 2 ++ arch/arm/mach-pxa/include/mach/trizeps4.h | 2 ++ 15 files changed, 25 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/mach-pxa/include/mach/balloon3.h b/arch/arm/mach-pxa/include/mach/balloon3.h index 954641e6c8b1..1b0825911e62 100644 --- a/arch/arm/mach-pxa/include/mach/balloon3.h +++ b/arch/arm/mach-pxa/include/mach/balloon3.h @@ -14,6 +14,8 @@ #ifndef ASM_ARCH_BALLOON3_H #define ASM_ARCH_BALLOON3_H +#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */ + enum balloon3_features { BALLOON3_FEATURE_OHCI, BALLOON3_FEATURE_MMC, diff --git a/arch/arm/mach-pxa/include/mach/corgi.h b/arch/arm/mach-pxa/include/mach/corgi.h index f3c3493b468d..c030d955bbd7 100644 --- a/arch/arm/mach-pxa/include/mach/corgi.h +++ b/arch/arm/mach-pxa/include/mach/corgi.h @@ -13,6 +13,7 @@ #ifndef __ASM_ARCH_CORGI_H #define __ASM_ARCH_CORGI_H 1 +#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */ /* * Corgi (Non Standard) GPIO Definitions diff --git a/arch/arm/mach-pxa/include/mach/csb726.h b/arch/arm/mach-pxa/include/mach/csb726.h index 2628e7b72116..00cfbbbf73f7 100644 --- a/arch/arm/mach-pxa/include/mach/csb726.h +++ b/arch/arm/mach-pxa/include/mach/csb726.h @@ -11,6 +11,8 @@ #ifndef CSB726_H #define CSB726_H +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + #define CSB726_GPIO_IRQ_LAN 52 #define CSB726_GPIO_IRQ_SM501 53 #define CSB726_GPIO_MMC_DETECT 100 diff --git a/arch/arm/mach-pxa/include/mach/gumstix.h b/arch/arm/mach-pxa/include/mach/gumstix.h index dba14b6503ad..f7df27bbb42e 100644 --- a/arch/arm/mach-pxa/include/mach/gumstix.h +++ b/arch/arm/mach-pxa/include/mach/gumstix.h @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ /* BTRESET - Reset line to Bluetooth module, active low signal. */ #define GPIO_GUMSTIX_BTRESET 7 diff --git a/arch/arm/mach-pxa/include/mach/idp.h b/arch/arm/mach-pxa/include/mach/idp.h index 22a96f87232b..7e63f4680271 100644 --- a/arch/arm/mach-pxa/include/mach/idp.h +++ b/arch/arm/mach-pxa/include/mach/idp.h @@ -23,6 +23,7 @@ * IDP hardware. */ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ #define IDP_FLASH_PHYS (PXA_CS0_PHYS) #define IDP_ALT_FLASH_PHYS (PXA_CS1_PHYS) diff --git a/arch/arm/mach-pxa/include/mach/palmld.h b/arch/arm/mach-pxa/include/mach/palmld.h index 2c4471336570..b184f296023b 100644 --- a/arch/arm/mach-pxa/include/mach/palmld.h +++ b/arch/arm/mach-pxa/include/mach/palmld.h @@ -13,6 +13,8 @@ #ifndef _INCLUDE_PALMLD_H_ #define _INCLUDE_PALMLD_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /** HERE ARE GPIOs **/ /* GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/palmt5.h b/arch/arm/mach-pxa/include/mach/palmt5.h index 0bd4f036c72f..e342c5921405 100644 --- a/arch/arm/mach-pxa/include/mach/palmt5.h +++ b/arch/arm/mach-pxa/include/mach/palmt5.h @@ -15,6 +15,8 @@ #ifndef _INCLUDE_PALMT5_H_ #define _INCLUDE_PALMT5_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /** HERE ARE GPIOs **/ /* GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/palmtc.h b/arch/arm/mach-pxa/include/mach/palmtc.h index c383a21680b6..81c727b3cfd2 100644 --- a/arch/arm/mach-pxa/include/mach/palmtc.h +++ b/arch/arm/mach-pxa/include/mach/palmtc.h @@ -16,6 +16,8 @@ #ifndef _INCLUDE_PALMTC_H_ #define _INCLUDE_PALMTC_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /** HERE ARE GPIOs **/ /* GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/palmtx.h b/arch/arm/mach-pxa/include/mach/palmtx.h index f2e530380253..92bc1f05300d 100644 --- a/arch/arm/mach-pxa/include/mach/palmtx.h +++ b/arch/arm/mach-pxa/include/mach/palmtx.h @@ -16,6 +16,8 @@ #ifndef _INCLUDE_PALMTX_H_ #define _INCLUDE_PALMTX_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /** HERE ARE GPIOs **/ /* GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/pcm027.h b/arch/arm/mach-pxa/include/mach/pcm027.h index 6bf28de228bd..86ebd7b6c960 100644 --- a/arch/arm/mach-pxa/include/mach/pcm027.h +++ b/arch/arm/mach-pxa/include/mach/pcm027.h @@ -23,6 +23,8 @@ * Definitions of CPU card resources only */ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /* phyCORE-PXA270 (PCM027) Interrupts */ #define PCM027_IRQ(x) (IRQ_BOARD_START + (x)) #define PCM027_BTDET_IRQ PCM027_IRQ(0) diff --git a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h index 0260aaa2fc17..7e544c14967e 100644 --- a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h +++ b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h @@ -20,6 +20,7 @@ */ #include +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ /* * definitions relevant only when the PCM-990 diff --git a/arch/arm/mach-pxa/include/mach/poodle.h b/arch/arm/mach-pxa/include/mach/poodle.h index f32ff75dcca8..b56b19351a03 100644 --- a/arch/arm/mach-pxa/include/mach/poodle.h +++ b/arch/arm/mach-pxa/include/mach/poodle.h @@ -15,6 +15,8 @@ #ifndef __ASM_ARCH_POODLE_H #define __ASM_ARCH_POODLE_H 1 +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /* * GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/spitz.h b/arch/arm/mach-pxa/include/mach/spitz.h index 0bfe6507c95d..25c9f62e46aa 100644 --- a/arch/arm/mach-pxa/include/mach/spitz.h +++ b/arch/arm/mach-pxa/include/mach/spitz.h @@ -15,8 +15,8 @@ #define __ASM_ARCH_SPITZ_H 1 #endif +#include "irqs.h" /* PXA_NR_BUILTIN_GPIO, PXA_GPIO_TO_IRQ */ #include -#include /* Spitz/Akita GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/tosa.h b/arch/arm/mach-pxa/include/mach/tosa.h index 2bb0e862598c..0497d95cef25 100644 --- a/arch/arm/mach-pxa/include/mach/tosa.h +++ b/arch/arm/mach-pxa/include/mach/tosa.h @@ -13,6 +13,8 @@ #ifndef _ASM_ARCH_TOSA_H_ #define _ASM_ARCH_TOSA_H_ 1 +#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */ + /* TOSA Chip selects */ #define TOSA_LCDC_PHYS PXA_CS4_PHYS /* Internel Scoop */ diff --git a/arch/arm/mach-pxa/include/mach/trizeps4.h b/arch/arm/mach-pxa/include/mach/trizeps4.h index d2ca01053f69..ae3ca013afab 100644 --- a/arch/arm/mach-pxa/include/mach/trizeps4.h +++ b/arch/arm/mach-pxa/include/mach/trizeps4.h @@ -10,6 +10,8 @@ #ifndef _TRIPEPS4_H_ #define _TRIPEPS4_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /* physical memory regions */ #define TRIZEPS4_FLASH_PHYS (PXA_CS0_PHYS) /* Flash region */ #define TRIZEPS4_DISK_PHYS (PXA_CS1_PHYS) /* Disk On Chip region */ -- cgit v1.2.3 From e7c57ecd6019cc6392223605aed18cce257c3eff Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 29 Jan 2014 17:10:04 +0100 Subject: ARM: imx6: Initialize low-power mode early again Since commit 9e8147bb5ec5d1dda2141da70f96b98985a306cb "ARM: imx6q: move low-power code out of clock driver" the kernel fails to boot on i.MX6Q/D if preemption is enabled (CONFIG_PREEMPT=y). The kernel just hangs before the console comes up. The above commit moved the initalization of the low-power mode setting (enabling clocked WAIT states), which was introduced in commit 83ae20981ae924c37d02a42c829155fc3851260c "ARM: imx: correct low-power mode setting", from imx6q_clks_init to imx6q_pm_init. Now it is called much later, after all cores are enabled. This patch moves the low-power mode initialization back to imx6q_clks_init again (and to imx6sl_clks_init). Signed-off-by: Philipp Zabel Signed-off-by: Shawn Guo Signed-off-by: Kevin Hilman --- arch/arm/mach-imx/clk-imx6q.c | 3 +++ arch/arm/mach-imx/clk-imx6sl.c | 3 +++ arch/arm/mach-imx/pm-imx6q.c | 2 -- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index af2e582d2b74..4d677f442539 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -482,6 +482,9 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) if (IS_ENABLED(CONFIG_PCI_IMX6)) clk_set_parent(clk[lvds1_sel], clk[sata_ref]); + /* Set initial power mode */ + imx6q_set_lpm(WAIT_CLOCKED); + np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpt"); base = of_iomap(np, 0); WARN_ON(!base); diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c index 3781a1853998..4c86f3035205 100644 --- a/arch/arm/mach-imx/clk-imx6sl.c +++ b/arch/arm/mach-imx/clk-imx6sl.c @@ -266,6 +266,9 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node) /* Audio-related clocks configuration */ clk_set_parent(clks[IMX6SL_CLK_SPDIF0_SEL], clks[IMX6SL_CLK_PLL3_PFD3]); + /* Set initial power mode */ + imx6q_set_lpm(WAIT_CLOCKED); + np = of_find_compatible_node(NULL, NULL, "fsl,imx6sl-gpt"); base = of_iomap(np, 0); WARN_ON(!base); diff --git a/arch/arm/mach-imx/pm-imx6q.c b/arch/arm/mach-imx/pm-imx6q.c index 9d47adc078aa..7a9b98589db7 100644 --- a/arch/arm/mach-imx/pm-imx6q.c +++ b/arch/arm/mach-imx/pm-imx6q.c @@ -236,8 +236,6 @@ void __init imx6q_pm_init(void) regmap_update_bits(gpr, IOMUXC_GPR1, IMX6Q_GPR1_GINT, IMX6Q_GPR1_GINT); - /* Set initial power mode */ - imx6q_set_lpm(WAIT_CLOCKED); suspend_set_ops(&imx6q_pm_ops); } -- cgit v1.2.3 From 5db1dabc562b27c356376fbb527a746dcf7c9572 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Thu, 6 Feb 2014 09:29:31 -0600 Subject: ARM: multi_v7_defconfig: Select CONFIG_SOC_DRA7XX Select CONFIG_SOC_DRA7XX so that we can boot dra7-evm. DRA7 family are A15 based processors that supports LPAE and an evolutionary update to the OMAP5 generation of processors. Signed-off-by: Nishanth Menon Signed-off-by: Kevin Hilman --- arch/arm/configs/multi_v7_defconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 845bc745706b..ee6982976d66 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -29,6 +29,7 @@ CONFIG_ARCH_OMAP3=y CONFIG_ARCH_OMAP4=y CONFIG_SOC_OMAP5=y CONFIG_SOC_AM33XX=y +CONFIG_SOC_DRA7XX=y CONFIG_SOC_AM43XX=y CONFIG_ARCH_ROCKCHIP=y CONFIG_ARCH_SOCFPGA=y -- cgit v1.2.3 From 46f5b96085b03f9e71a0134de77efc6a1f9d84c3 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Fri, 31 Jan 2014 12:55:06 +0100 Subject: ARM: zynq: Reserve not DMAable space in front of the kernel Reserve space from 0x0 - __pa(swapper_pg_dir), if kernel is loaded from 0, which is not DMAable. It is causing problem with MMC driver and others which want to add dma buffers to this space. Signed-off-by: Michal Simek Signed-off-by: Kevin Hilman --- arch/arm/mach-zynq/common.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'arch') diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c index 1db2a5ca9ab8..8c09a8393fb6 100644 --- a/arch/arm/mach-zynq/common.c +++ b/arch/arm/mach-zynq/common.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -41,6 +42,18 @@ void __iomem *zynq_scu_base; +/** + * zynq_memory_init - Initialize special memory + * + * We need to stop things allocating the low memory as DMA can't work in + * the 1st 512K of memory. + */ +static void __init zynq_memory_init(void) +{ + if (!__pa(PAGE_OFFSET)) + memblock_reserve(__pa(PAGE_OFFSET), __pa(swapper_pg_dir)); +} + static struct platform_device zynq_cpuidle_device = { .name = "cpuidle-zynq", }; @@ -117,5 +130,6 @@ DT_MACHINE_START(XILINX_EP107, "Xilinx Zynq Platform") .init_machine = zynq_init_machine, .init_time = zynq_timer_init, .dt_compat = zynq_dt_match, + .reserve = zynq_memory_init, .restart = zynq_system_reset, MACHINE_END -- cgit v1.2.3 From a18b31dd537f51331b9cd357987a5e807bf3e8d1 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 3 Feb 2014 10:35:35 +0100 Subject: m68k: Sort arch/m68k/include/asm/Kbuild Signed-off-by: Geert Uytterhoeven Acked-by: Greg Ungerer --- arch/m68k/include/asm/Kbuild | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 7cc8c364924d..df4d46fc321b 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,4 +1,3 @@ - generic-y += bitsperlong.h generic-y += clkdev.h generic-y += cputime.h @@ -6,6 +5,7 @@ generic-y += device.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ipcbuf.h @@ -18,6 +18,7 @@ generic-y += local.h generic-y += mman.h generic-y += mutex.h generic-y += percpu.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sections.h @@ -31,5 +32,3 @@ generic-y += trace_clock.h generic-y += types.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h -- cgit v1.2.3 From 3067bab1cb6e45063c602a731b9341651c4f2ddb Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 3 Feb 2014 10:38:39 +0100 Subject: m68k: Switch to asm-generic/barrier.h The generic nop() implementation is fine for m68k. Signed-off-by: Geert Uytterhoeven Acked-by: Greg Ungerer --- arch/m68k/include/asm/Kbuild | 1 + arch/m68k/include/asm/barrier.h | 8 -------- 2 files changed, 1 insertion(+), 8 deletions(-) delete mode 100644 arch/m68k/include/asm/barrier.h (limited to 'arch') diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index df4d46fc321b..6fb9e813a910 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,3 +1,4 @@ +generic-y += barrier.h generic-y += bitsperlong.h generic-y += clkdev.h generic-y += cputime.h diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h deleted file mode 100644 index 15c5f77c1614..000000000000 --- a/arch/m68k/include/asm/barrier.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef _M68K_BARRIER_H -#define _M68K_BARRIER_H - -#define nop() do { asm volatile ("nop"); barrier(); } while (0) - -#include - -#endif /* _M68K_BARRIER_H */ -- cgit v1.2.3 From 7247f55381d54645a1eb47588de51bb26fa7cb7a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 3 Feb 2014 15:07:13 +0100 Subject: m68k: Wire up sched_setattr and sched_getattr Signed-off-by: Geert Uytterhoeven Acked-by: Greg Ungerer --- arch/m68k/include/asm/unistd.h | 2 +- arch/m68k/include/uapi/asm/unistd.h | 2 ++ arch/m68k/kernel/syscalltable.S | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 014f288fc813..9d38b73989eb 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -4,7 +4,7 @@ #include -#define NR_syscalls 349 +#define NR_syscalls 351 #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_OLD_STAT diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h index 625f321001dc..b932dd470041 100644 --- a/arch/m68k/include/uapi/asm/unistd.h +++ b/arch/m68k/include/uapi/asm/unistd.h @@ -354,5 +354,7 @@ #define __NR_process_vm_writev 346 #define __NR_kcmp 347 #define __NR_finit_module 348 +#define __NR_sched_setattr 349 +#define __NR_sched_getattr 350 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */ diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S index 3f04ea0ab802..b6223dc41d82 100644 --- a/arch/m68k/kernel/syscalltable.S +++ b/arch/m68k/kernel/syscalltable.S @@ -369,4 +369,6 @@ ENTRY(sys_call_table) .long sys_process_vm_writev .long sys_kcmp .long sys_finit_module + .long sys_sched_setattr + .long sys_sched_getattr /* 350 */ -- cgit v1.2.3 From a9c8e4beeeb64c22b84c803747487857fe424b68 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 10 Feb 2014 14:25:40 -0800 Subject: xen: properly account for _PAGE_NUMA during xen pte translations Steven Noonan forwarded a users report where they had a problem starting vsftpd on a Xen paravirtualized guest, with this in dmesg: BUG: Bad page map in process vsftpd pte:8000000493b88165 pmd:e9cc01067 page:ffffea00124ee200 count:0 mapcount:-1 mapping: (null) index:0x0 page flags: 0x2ffc0000000014(referenced|dirty) addr:00007f97eea74000 vm_flags:00100071 anon_vma:ffff880e98f80380 mapping: (null) index:7f97eea74 CPU: 4 PID: 587 Comm: vsftpd Not tainted 3.12.7-1-ec2 #1 Call Trace: dump_stack+0x45/0x56 print_bad_pte+0x22e/0x250 unmap_single_vma+0x583/0x890 unmap_vmas+0x65/0x90 exit_mmap+0xc5/0x170 mmput+0x65/0x100 do_exit+0x393/0x9e0 do_group_exit+0xcc/0x140 SyS_exit_group+0x14/0x20 system_call_fastpath+0x1a/0x1f Disabling lock debugging due to kernel taint BUG: Bad rss-counter state mm:ffff880e9ca60580 idx:0 val:-1 BUG: Bad rss-counter state mm:ffff880e9ca60580 idx:1 val:1 The issue could not be reproduced under an HVM instance with the same kernel, so it appears to be exclusive to paravirtual Xen guests. He bisected the problem to commit 1667918b6483 ("mm: numa: clear numa hinting information on mprotect") that was also included in 3.12-stable. The problem was related to how xen translates ptes because it was not accounting for the _PAGE_NUMA bit. This patch splits pte_present to add a pteval_present helper for use by xen so both bare metal and xen use the same code when checking if a PTE is present. [mgorman@suse.de: wrote changelog, proposed minor modifications] [akpm@linux-foundation.org: fix typo in comment] Reported-by: Steven Noonan Tested-by: Steven Noonan Signed-off-by: Elena Ufimtseva Signed-off-by: Mel Gorman Reviewed-by: David Vrabel Acked-by: Konrad Rzeszutek Wilk Cc: [3.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 14 ++++++++++++-- arch/x86/xen/mmu.c | 4 ++-- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index bbc8b12fa443..5ad38ad07890 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -445,10 +445,20 @@ static inline int pte_same(pte_t a, pte_t b) return a.pte == b.pte; } +static inline int pteval_present(pteval_t pteval) +{ + /* + * Yes Linus, _PAGE_PROTNONE == _PAGE_NUMA. Expressing it this + * way clearly states that the intent is that protnone and numa + * hinting ptes are considered present for the purposes of + * pagetable operations like zapping, protection changes, gup etc. + */ + return pteval & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_NUMA); +} + static inline int pte_present(pte_t a) { - return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE | - _PAGE_NUMA); + return pteval_present(pte_flags(a)); } #define pte_accessible pte_accessible diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 2423ef04ffea..256282e7888b 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -365,7 +365,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, /* Assume pteval_t is equivalent to all the other *val_t types. */ static pteval_t pte_mfn_to_pfn(pteval_t val) { - if (val & _PAGE_PRESENT) { + if (pteval_present(val)) { unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; unsigned long pfn = mfn_to_pfn(mfn); @@ -381,7 +381,7 @@ static pteval_t pte_mfn_to_pfn(pteval_t val) static pteval_t pte_pfn_to_mfn(pteval_t val) { - if (val & _PAGE_PRESENT) { + if (pteval_present(val)) { unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; pteval_t flags = val & PTE_FLAGS_MASK; unsigned long mfn; -- cgit v1.2.3 From 0215b4aa069b989c963d594cf0f1c705e21d8ca5 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Fri, 7 Feb 2014 14:50:58 -0500 Subject: powerpc: Fix build failure in sysdev/mpic.c for MPIC_WEIRD=y Commit 446f6d06fab0b49c61887ecbe8286d6aaa796637 ("powerpc/mpic: Properly set default triggers") breaks the mpc7447_hpc_defconfig as follows: CC arch/powerpc/sysdev/mpic.o arch/powerpc/sysdev/mpic.c: In function 'mpic_set_irq_type': arch/powerpc/sysdev/mpic.c:886:9: error: case label does not reduce to an integer constant arch/powerpc/sysdev/mpic.c:890:9: error: case label does not reduce to an integer constant arch/powerpc/sysdev/mpic.c:894:9: error: case label does not reduce to an integer constant arch/powerpc/sysdev/mpic.c:898:9: error: case label does not reduce to an integer constant Looking at the cpp output (gcc 4.7.3), I see: case mpic->hw_set[MPIC_IDX_VECPRI_SENSE_EDGE] | mpic->hw_set[MPIC_IDX_VECPRI_POLARITY_POSITIVE]: The pointer into an array appears because CONFIG_MPIC_WEIRD=y is set for this platform, thus enabling the following: ------------------- #ifdef CONFIG_MPIC_WEIRD static u32 mpic_infos[][MPIC_IDX_END] = { [0] = { /* Original OpenPIC compatible MPIC */ [...] #define MPIC_INFO(name) mpic->hw_set[MPIC_IDX_##name] #else /* CONFIG_MPIC_WEIRD */ #define MPIC_INFO(name) MPIC_##name #endif /* CONFIG_MPIC_WEIRD */ ------------------- Here we convert the case section to if/else if, and also add the equivalent of a default case to warn about unknown types. Boot tested on sbc8548, build tested on all defconfigs. Signed-off-by: Paul Gortmaker Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/sysdev/mpic.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 0e166ed4cd16..8209744b2829 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -886,25 +886,25 @@ int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type) /* Default: read HW settings */ if (flow_type == IRQ_TYPE_DEFAULT) { - switch(vold & (MPIC_INFO(VECPRI_POLARITY_MASK) | - MPIC_INFO(VECPRI_SENSE_MASK))) { - case MPIC_INFO(VECPRI_SENSE_EDGE) | - MPIC_INFO(VECPRI_POLARITY_POSITIVE): - flow_type = IRQ_TYPE_EDGE_RISING; - break; - case MPIC_INFO(VECPRI_SENSE_EDGE) | - MPIC_INFO(VECPRI_POLARITY_NEGATIVE): - flow_type = IRQ_TYPE_EDGE_FALLING; - break; - case MPIC_INFO(VECPRI_SENSE_LEVEL) | - MPIC_INFO(VECPRI_POLARITY_POSITIVE): - flow_type = IRQ_TYPE_LEVEL_HIGH; - break; - case MPIC_INFO(VECPRI_SENSE_LEVEL) | - MPIC_INFO(VECPRI_POLARITY_NEGATIVE): - flow_type = IRQ_TYPE_LEVEL_LOW; - break; - } + int vold_ps; + + vold_ps = vold & (MPIC_INFO(VECPRI_POLARITY_MASK) | + MPIC_INFO(VECPRI_SENSE_MASK)); + + if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) | + MPIC_INFO(VECPRI_POLARITY_POSITIVE))) + flow_type = IRQ_TYPE_EDGE_RISING; + else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) | + MPIC_INFO(VECPRI_POLARITY_NEGATIVE))) + flow_type = IRQ_TYPE_EDGE_FALLING; + else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) | + MPIC_INFO(VECPRI_POLARITY_POSITIVE))) + flow_type = IRQ_TYPE_LEVEL_HIGH; + else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) | + MPIC_INFO(VECPRI_POLARITY_NEGATIVE))) + flow_type = IRQ_TYPE_LEVEL_LOW; + else + WARN_ONCE(1, "mpic: unknown IRQ type %d\n", vold); } /* Apply to irq desc */ -- cgit v1.2.3 From 8cc6b6cd8713457be80202fc4264f05d20bc5e1b Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Wed, 5 Feb 2014 16:20:45 -0200 Subject: powerpc/eeh: Drop taken reference to driver on eeh_rmv_device Commit f5c57710dd62dd06f176934a8b4b8accbf00f9f8 ("powerpc/eeh: Use partial hotplug for EEH unaware drivers") introduces eeh_rmv_device, which may grab a reference to a driver, but not release it. That prevents a driver from being removed after it has gone through EEH recovery. This patch drops the reference if it was taken. Signed-off-by: Thadeu Lima de Souza Cascardo Acked-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh_driver.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 7bb30dca4e19..fdc679d309ec 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -362,9 +362,13 @@ static void *eeh_rmv_device(void *data, void *userdata) */ if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) return NULL; + driver = eeh_pcid_get(dev); - if (driver && driver->err_handler) - return NULL; + if (driver) { + eeh_pcid_put(dev); + if (driver->err_handler) + return NULL; + } /* Remove it from PCI subsystem */ pr_debug("EEH: Removing %s without EEH sensitive driver\n", -- cgit v1.2.3 From 3ec8b78fcc5aa7745026d8d85a4e9ab52c922765 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Fri, 31 Jan 2014 00:30:45 +0530 Subject: powerpc/pseries: Disable relocation on exception while going down during crash. Disable relocation on exception while going down even in kdump case. This is because we are about clear htab mappings while kexec-ing into kdump kernel and we may run into issues if we still have AIL ON. Signed-off-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/setup.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8e639d7cbda7..972df0ffd4dc 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -430,8 +430,7 @@ static void pSeries_machine_kexec(struct kimage *image) { long rc; - if (firmware_has_feature(FW_FEATURE_SET_MODE) && - (image->type != KEXEC_TYPE_CRASH)) { + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { rc = pSeries_disable_reloc_on_exc(); if (rc != H_SUCCESS) pr_warning("Warning: Failed to disable relocation on " -- cgit v1.2.3 From 429d2e8342954d337abe370d957e78291032d867 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Fri, 31 Jan 2014 00:31:04 +0530 Subject: powerpc: Fix kdump hang issue on p8 with relocation on exception enabled. On p8 systems, with relocation on exception feature enabled we are seeing kdump kernel hang at interrupt vector 0xc*4400. The reason is, with this feature enabled, exception are raised with MMU (IR=DR=1) ON with the default offset of 0xc*4000. Since exception is raised in virtual mode it requires the vector region to be executable without which it fails to fetch and execute instruction at 0xc*4xxx. For default kernel since kernel is loaded at real 0, the htab mappings sets the entire kernel text region executable. But for relocatable kernel (e.g. kdump case) we only copy interrupt vectors down to real 0 and never marked that region as executable because in p7 and below we always get exception in real mode. This patch fixes this issue by marking htab mapping range as executable that overlaps with the interrupt vector region for relocatable kernel. Thanks to Ben who helped me to debug this issue and find the root cause. Signed-off-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/sections.h | 12 ++++++++++++ arch/powerpc/mm/hash_utils_64.c | 14 ++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 4ee06fe15de4..d0e784e0ff48 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -8,6 +8,7 @@ #ifdef __powerpc64__ +extern char __start_interrupts[]; extern char __end_interrupts[]; extern char __prom_init_toc_start[]; @@ -21,6 +22,17 @@ static inline int in_kernel_text(unsigned long addr) return 0; } +static inline int overlaps_interrupt_vector_text(unsigned long start, + unsigned long end) +{ + unsigned long real_start, real_end; + real_start = __start_interrupts - _stext; + real_end = __end_interrupts - _stext; + + return start < (unsigned long)__va(real_end) && + (unsigned long)__va(real_start) < end; +} + static inline int overlaps_kernel_text(unsigned long start, unsigned long end) { return start < (unsigned long)__init_end && diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index de6881259aef..d766d6ee33fe 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -207,6 +207,20 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, if (overlaps_kernel_text(vaddr, vaddr + step)) tprot &= ~HPTE_R_N; + /* + * If relocatable, check if it overlaps interrupt vectors that + * are copied down to real 0. For relocatable kernel + * (e.g. kdump case) we copy interrupt vectors down to real + * address 0. Mark that region as executable. This is + * because on p8 system with relocation on exception feature + * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence + * in order to execute the interrupt handlers in virtual + * mode the vector region need to be marked as executable. + */ + if ((PHYSICAL_START > MEMORY_START) && + overlaps_interrupt_vector_text(vaddr, vaddr + step)) + tprot &= ~HPTE_R_N; + hash = hpt_hash(vpn, shift, ssize); hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); -- cgit v1.2.3 From 3b830c824a8b15bf032eafe09c48a09d2441f16d Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Thu, 30 Jan 2014 16:58:42 +0100 Subject: powerpc/relocate fix relocate processing in LE mode Relocation's code is not working in little endian mode because the r_info field, which is a 64 bits value, should be read from the right offset. The current code is optimized to read the r_info field as a 32 bits value starting at the middle of the double word (offset 12). When running in LE mode, the read value is not correct since only the MSB is read. This patch removes this optimization which consist to deal with a 32 bits value instead of a 64 bits one. This way it works in big and little endian mode. Signed-off-by: Laurent Dufour Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/reloc_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index b47a0e1ab001..1482327cfeba 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -69,8 +69,8 @@ _GLOBAL(relocate) * R_PPC64_RELATIVE ones. */ mtctr r8 -5: lwz r0,12(9) /* ELF64_R_TYPE(reloc->r_info) */ - cmpwi r0,R_PPC64_RELATIVE +5: ld r0,8(9) /* ELF64_R_TYPE(reloc->r_info) */ + cmpdi r0,R_PPC64_RELATIVE bne 6f ld r6,0(r9) /* reloc->r_offset */ ld r0,16(r9) /* reloc->r_addend */ -- cgit v1.2.3 From 2fdd313f54eca8221125b7898e6a8393604b6fb6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 24 Jan 2014 15:50:51 +1100 Subject: powerpc/perf: Add Power8 cache & TLB events Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/power8-pmu.c | 144 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 144 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index a3f7abd2f13f..96cee20dcd34 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -25,6 +25,37 @@ #define PM_BRU_FIN 0x10068 #define PM_BR_MPRED_CMPL 0x400f6 +/* All L1 D cache load references counted at finish, gated by reject */ +#define PM_LD_REF_L1 0x100ee +/* Load Missed L1 */ +#define PM_LD_MISS_L1 0x3e054 +/* Store Missed L1 */ +#define PM_ST_MISS_L1 0x300f0 +/* L1 cache data prefetches */ +#define PM_L1_PREF 0x0d8b8 +/* Instruction fetches from L1 */ +#define PM_INST_FROM_L1 0x04080 +/* Demand iCache Miss */ +#define PM_L1_ICACHE_MISS 0x200fd +/* Instruction Demand sectors wriittent into IL1 */ +#define PM_L1_DEMAND_WRITE 0x0408c +/* Instruction prefetch written into IL1 */ +#define PM_IC_PREF_WRITE 0x0408e +/* The data cache was reloaded from local core's L3 due to a demand load */ +#define PM_DATA_FROM_L3 0x4c042 +/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */ +#define PM_DATA_FROM_L3MISS 0x300fe +/* All successful D-side store dispatches for this thread */ +#define PM_L2_ST 0x17080 +/* All successful D-side store dispatches for this thread that were L2 Miss */ +#define PM_L2_ST_MISS 0x17082 +/* Total HW L3 prefetches(Load+store) */ +#define PM_L3_PREF_ALL 0x4e052 +/* Data PTEG reload */ +#define PM_DTLB_MISS 0x300fc +/* ITLB Reloaded */ +#define PM_ITLB_MISS 0x400fc + /* * Raw event encoding for POWER8: @@ -557,6 +588,8 @@ static int power8_generic_events[] = { [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BRU_FIN, [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, + [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, + [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1, }; static u64 power8_bhrb_filter_map(u64 branch_sample_type) @@ -596,6 +629,116 @@ static void power8_config_bhrb(u64 pmu_bhrb_filter) mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter)); } +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_LD_REF_L1, + [ C(RESULT_MISS) ] = PM_LD_MISS_L1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_ST_MISS_L1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_L1_PREF, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_INST_FROM_L1, + [ C(RESULT_MISS) ] = PM_L1_ICACHE_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3, + [ C(RESULT_MISS) ] = PM_DATA_FROM_L3MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = PM_L2_ST, + [ C(RESULT_MISS) ] = PM_L2_ST_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_DTLB_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_ITLB_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_BRU_FIN, + [ C(RESULT_MISS) ] = PM_BR_MPRED_CMPL, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +#undef C + static struct power_pmu power8_pmu = { .name = "POWER8", .n_counter = 6, @@ -611,6 +754,7 @@ static struct power_pmu power8_pmu = { .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB, .n_generic = ARRAY_SIZE(power8_generic_events), .generic_events = power8_generic_events, + .cache_events = &power8_cache_events, .attr_groups = power8_pmu_attr_groups, .bhrb_nr = 32, }; -- cgit v1.2.3 From 8d4887ee30695d6b092e96029ae974505c43bfb6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 10 Dec 2013 14:02:49 +1100 Subject: powerpc/pseries: Select ARCH_RANDOM on pseries We have a driver for the ARCH_RANDOM hook in rng.c, so we should select ARCH_RANDOM on pseries. Without this the build breaks if you turn ARCH_RANDOM off. This hasn't broken the build because pseries_defconfig doesn't specify a value for PPC_POWERNV, which is default y, and selects ARCH_RANDOM. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 37300f6ee244..80b1d57c306a 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -20,6 +20,7 @@ config PPC_PSERIES select PPC_DOORBELL select HAVE_CONTEXT_TRACKING select HOTPLUG_CPU if SMP + select ARCH_RANDOM default y config PPC_SPLPAR -- cgit v1.2.3 From b4d6c06c8de81517320a9964b0c26e096aeadd7b Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 18 Dec 2013 13:14:53 +1100 Subject: powerpc/perf: Configure BHRB filter before enabling PMU interrupts Right now the config_bhrb() PMU specific call happens after write_mmcr0(), which actually enables the PMU for event counting and interrupts. So there is a small window of time where the PMU and BHRB runs without the required HW branch filter (if any) enabled in BHRB. This can cause some of the branch samples to be collected through BHRB without any filter applied and hence affects the correctness of the results. This patch moves the BHRB config function call before enabling interrupts. Here are some data points captured via trace prints which depicts how we could get PMU interrupts with BHRB filter NOT enabled with a standard perf record command line (asking for branch record information as well). $ perf record -j any_call ls Before the patch:- ls-1962 [003] d... 2065.299590: .perf_event_interrupt: MMCRA: 40000000000 ls-1962 [003] d... 2065.299603: .perf_event_interrupt: MMCRA: 40000000000 ... All the PMU interrupts before this point did not have the requested HW branch filter enabled in the MMCRA. ls-1962 [003] d... 2065.299647: .perf_event_interrupt: MMCRA: 40040000000 ls-1962 [003] d... 2065.299662: .perf_event_interrupt: MMCRA: 40040000000 After the patch:- ls-1850 [008] d... 190.311828: .perf_event_interrupt: MMCRA: 40040000000 ls-1850 [008] d... 190.311848: .perf_event_interrupt: MMCRA: 40040000000 All the PMU interrupts have the requested HW BHRB branch filter enabled in MMCRA. Signed-off-by: Anshuman Khandual [mpe: Fixed up whitespace and cleaned up changelog] Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/core-book3s.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 29b89e863d7c..67cf22083f4c 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1147,6 +1147,9 @@ static void power_pmu_enable(struct pmu *pmu) mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]); mb(); + if (cpuhw->bhrb_users) + ppmu->config_bhrb(cpuhw->bhrb_filter); + write_mmcr0(cpuhw, mmcr0); /* @@ -1158,8 +1161,6 @@ static void power_pmu_enable(struct pmu *pmu) } out: - if (cpuhw->bhrb_users) - ppmu->config_bhrb(cpuhw->bhrb_filter); local_irq_restore(flags); } -- cgit v1.2.3 From 730efb6193f8568354fd80849612291afa9fa81e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 23 Dec 2013 23:46:04 +1100 Subject: powerpc/xmon: Don't loop forever in get_output_lock() If we enter with xmon_speaker != 0 we skip the first cmpxchg(), we also skip the while loop because xmon_speaker != last_speaker (0) - meaning we skip the second cmpxchg() also. Following that code path the compiler sees no memory barriers and so is within its rights to never reload xmon_speaker. The end result is we loop forever. This manifests as all cpus being in xmon ('c' command), but they refuse to take control when you switch to them ('c x' for cpu # x). I have seen this deadlock in practice and also checked the generated code to confirm this is what's happening. The simplest fix is just to always try the cmpxchg(). Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/xmon/xmon.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index a90731b3d44a..598cdc7c7adc 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -309,12 +309,12 @@ static void get_output_lock(void) if (xmon_speaker == me) return; + for (;;) { - if (xmon_speaker == 0) { - last_speaker = cmpxchg(&xmon_speaker, 0, me); - if (last_speaker == 0) - return; - } + last_speaker = cmpxchg(&xmon_speaker, 0, me); + if (last_speaker == 0) + return; + timeout = 10000000; while (xmon_speaker == last_speaker) { if (--timeout > 0) -- cgit v1.2.3 From 1507589787529b0d8e2a9e66e0c6f113ecab5181 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 23 Dec 2013 23:46:05 +1100 Subject: powerpc/xmon: Fix timeout loop in get_output_lock() As far as I can tell, our 70s era timeout loop in get_output_lock() is generating no code. This leads to the hostile takeover happening more or less simultaneously on all cpus. The result is "interesting", some example output that is more readable than most: cpu 0x1: Vector: 100 (Scypsut e0mx bR:e setV)e catto xc0p:u[ c 00 c0:0 000t0o0V0erc0td:o5 rfc28050000]0c00 0 0 0 6t(pSrycsV1ppuot uxe 1m 2 0Rx21e3:0s0ce000c00000t00)00 60602oV2SerucSayt0y 0p 1sxs Fix it by using udelay() in the timeout loop. The wait time and check frequency are arbitrary, but seem to work OK. We already rely on udelay() working so this is not a new dependency. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/xmon/xmon.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 598cdc7c7adc..d712b23974ec 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -315,10 +315,17 @@ static void get_output_lock(void) if (last_speaker == 0) return; - timeout = 10000000; + /* + * Wait a full second for the lock, we might be on a slow + * console, but check every 100us. + */ + timeout = 10000; while (xmon_speaker == last_speaker) { - if (--timeout > 0) + if (--timeout > 0) { + udelay(100); continue; + } + /* hostile takeover */ prev = cmpxchg(&xmon_speaker, last_speaker, me); if (prev == last_speaker) -- cgit v1.2.3 From d2b496e5e1fa7a6796534e435440eb9d3ed184dd Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 23 Dec 2013 23:46:06 +1100 Subject: powerpc/xmon: Don't signal we've entered until we're finished printing Currently we set our cpu's bit in cpus_in_xmon, and then we take the output lock and print the exception information. This can race with the master cpu entering the command loop and printing the backtrace. The result is that the backtrace gets garbled with another cpu's exception print out. Fix it by delaying the set of cpus_in_xmon until we are finished printing. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/xmon/xmon.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index d712b23974ec..b07909850f77 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -404,7 +404,6 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } xmon_fault_jmp[cpu] = recurse_jmp; - cpumask_set_cpu(cpu, &cpus_in_xmon); bp = NULL; if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT)) @@ -426,6 +425,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi) release_output_lock(); } + cpumask_set_cpu(cpu, &cpus_in_xmon); + waiting: secondary = 1; while (secondary && !xmon_gate) { -- cgit v1.2.3 From 04a341138da55daf47551308660a5fcc6b5b9077 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Wed, 29 Jan 2014 18:24:54 +0800 Subject: powerpc/ppc32: Fix the bug in the init of non-base exception stack for UP We would allocate one specific exception stack for each kind of non-base exceptions for every CPU. For ppc32 the CPU hard ID is used as the subscript to get the specific exception stack for one CPU. But for an UP kernel, there is only one element in the each kind of exception stack array. We would get stuck if the CPU hard ID is not equal to '0'. So in this case we should use the subscript '0' no matter what the CPU hard ID is. Signed-off-by: Kevin Hao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/irq.c | 5 +++++ arch/powerpc/kernel/setup_32.c | 5 +++++ 2 files changed, 10 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 9729b23bfb0a..1d0848bba049 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -559,8 +559,13 @@ void exc_lvl_ctx_init(void) #ifdef CONFIG_PPC64 cpu_nr = i; #else +#ifdef CONFIG_SMP cpu_nr = get_hard_smp_processor_id(i); +#else + cpu_nr = 0; #endif +#endif + memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE); tp = critirq_ctx[cpu_nr]; tp->cpu = cpu_nr; diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 2b0da27eaee4..04cc4fcca78b 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -247,7 +247,12 @@ static void __init exc_lvl_early_init(void) /* interrupt stacks must be in lowmem, we get that for free on ppc32 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */ for_each_possible_cpu(i) { +#ifdef CONFIG_SMP hw_cpu = get_hard_smp_processor_id(i); +#else + hw_cpu = 0; +#endif + critirq_ctx[hw_cpu] = (struct thread_info *) __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); #ifdef CONFIG_BOOKE -- cgit v1.2.3 From ea961a828fe7250e954f086d74d9323c3d44c3e4 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 22 Jan 2014 08:40:28 +1100 Subject: powerpc: Fix endian issues in kexec and crash dump code We expose a number of OF properties in the kexec and crash dump code and these need to be big endian. Cc: stable@vger.kernel.org # v3.13 Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/machine_kexec.c | 14 ++++++++++---- arch/powerpc/kernel/machine_kexec_64.c | 6 ++++-- 2 files changed, 14 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 75d4f7340da8..015ae55c1868 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -196,7 +196,9 @@ int overlaps_crashkernel(unsigned long start, unsigned long size) /* Values we need to export to the second kernel via the device tree. */ static phys_addr_t kernel_end; +static phys_addr_t crashk_base; static phys_addr_t crashk_size; +static unsigned long long mem_limit; static struct property kernel_end_prop = { .name = "linux,kernel-end", @@ -207,7 +209,7 @@ static struct property kernel_end_prop = { static struct property crashk_base_prop = { .name = "linux,crashkernel-base", .length = sizeof(phys_addr_t), - .value = &crashk_res.start, + .value = &crashk_base }; static struct property crashk_size_prop = { @@ -219,9 +221,11 @@ static struct property crashk_size_prop = { static struct property memory_limit_prop = { .name = "linux,memory-limit", .length = sizeof(unsigned long long), - .value = &memory_limit, + .value = &mem_limit, }; +#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG) + static void __init export_crashk_values(struct device_node *node) { struct property *prop; @@ -237,8 +241,9 @@ static void __init export_crashk_values(struct device_node *node) of_remove_property(node, prop); if (crashk_res.start != 0) { + crashk_base = cpu_to_be_ulong(crashk_res.start), of_add_property(node, &crashk_base_prop); - crashk_size = resource_size(&crashk_res); + crashk_size = cpu_to_be_ulong(resource_size(&crashk_res)); of_add_property(node, &crashk_size_prop); } @@ -246,6 +251,7 @@ static void __init export_crashk_values(struct device_node *node) * memory_limit is required by the kexec-tools to limit the * crash regions to the actual memory used. */ + mem_limit = cpu_to_be_ulong(memory_limit); of_update_property(node, &memory_limit_prop); } @@ -264,7 +270,7 @@ static int __init kexec_setup(void) of_remove_property(node, prop); /* information needed by userspace when using default_machine_kexec */ - kernel_end = __pa(_end); + kernel_end = cpu_to_be_ulong(__pa(_end)); of_add_property(node, &kernel_end_prop); export_crashk_values(node); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index be4e6d648f60..59d229a2a3e0 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -369,6 +369,7 @@ void default_machine_kexec(struct kimage *image) /* Values we need to export to the second kernel via the device tree. */ static unsigned long htab_base; +static unsigned long htab_size; static struct property htab_base_prop = { .name = "linux,htab-base", @@ -379,7 +380,7 @@ static struct property htab_base_prop = { static struct property htab_size_prop = { .name = "linux,htab-size", .length = sizeof(unsigned long), - .value = &htab_size_bytes, + .value = &htab_size, }; static int __init export_htab_values(void) @@ -403,8 +404,9 @@ static int __init export_htab_values(void) if (prop) of_remove_property(node, prop); - htab_base = __pa(htab_address); + htab_base = cpu_to_be64(__pa(htab_address)); of_add_property(node, &htab_base_prop); + htab_size = cpu_to_be64(htab_size_bytes); of_add_property(node, &htab_size_prop); of_node_put(node); -- cgit v1.2.3 From 902e6a0c7eba08ec978cea8304c6cb2ddce7b9dc Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 20 Dec 2013 10:46:52 +0100 Subject: ARM: pxa: Add dummy backlight power supply on Mitac Mio A701 Recent changes to the pwm-backlight driver have made the power supply mandatory. There is code in the regulator core to deal with situations where no regulator is specified and provide a dummy, but that works on DT-based boards only. The situation can be remedied by adding a dummy regulator during board initialization. Tested-by: Robert Jarzmik Signed-off-by: Thierry Reding Signed-off-by: Haojian Zhuang --- arch/arm/mach-pxa/mioa701.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch') diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c index f70583fee59f..29997bde277d 100644 --- a/arch/arm/mach-pxa/mioa701.c +++ b/arch/arm/mach-pxa/mioa701.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include @@ -714,6 +715,10 @@ static struct gpio global_gpios[] = { { GPIO56_MT9M111_nOE, GPIOF_OUT_INIT_LOW, "Camera nOE" }, }; +static struct regulator_consumer_supply fixed_5v0_consumers[] = { + REGULATOR_SUPPLY("power", "pwm-backlight"), +}; + static void __init mioa701_machine_init(void) { int rc; @@ -753,6 +758,10 @@ static void __init mioa701_machine_init(void) pxa_set_i2c_info(&i2c_pdata); pxa27x_set_i2c_power_info(NULL); pxa_set_camera_info(&mioa701_pxacamera_platform_data); + + regulator_register_always_on(0, "fixed-5.0V", fixed_5v0_consumers, + ARRAY_SIZE(fixed_5v0_consumers), + 5000000); } static void mioa701_machine_exit(void) -- cgit v1.2.3 From cd15b048445d0a54f7147c35a86c5a16ef231554 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 11 Feb 2014 11:32:38 +1100 Subject: powerpc/powernv: Add iommu DMA bypass support for IODA2 This patch adds the support for to create a direct iommu "bypass" window on IODA2 bridges (such as Power8) allowing to bypass iommu page translation completely for 64-bit DMA capable devices, thus significantly improving DMA performances. Additionally, this adds a hook to the struct iommu_table so that the IOMMU API / VFIO can disable the bypass when external ownership is requested, since in that case, the device will be used by an environment such as userspace or a KVM guest which must not be allowed to bypass translations. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/dma-mapping.h | 1 + arch/powerpc/include/asm/iommu.h | 1 + arch/powerpc/kernel/dma.c | 10 ++-- arch/powerpc/kernel/iommu.c | 12 +++++ arch/powerpc/platforms/powernv/pci-ioda.c | 84 +++++++++++++++++++++++++++++++ arch/powerpc/platforms/powernv/pci.c | 10 ++++ arch/powerpc/platforms/powernv/pci.h | 6 ++- arch/powerpc/platforms/powernv/powernv.h | 8 +++ arch/powerpc/platforms/powernv/setup.c | 9 ++++ 9 files changed, 137 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index e27e9ad6818e..150866b2a3fe 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -134,6 +134,7 @@ static inline int dma_supported(struct device *dev, u64 mask) } extern int dma_set_mask(struct device *dev, u64 dma_mask); +extern int __dma_set_mask(struct device *dev, u64 dma_mask); #define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index f7a8036579b5..42632c7a2a4e 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -77,6 +77,7 @@ struct iommu_table { #ifdef CONFIG_IOMMU_API struct iommu_group *it_group; #endif + void (*set_bypass)(struct iommu_table *tbl, bool enable); }; /* Pure 2^n version of get_order */ diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 8032b97ccdcb..ee78f6e49d64 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -191,12 +191,10 @@ EXPORT_SYMBOL(dma_direct_ops); #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) -int dma_set_mask(struct device *dev, u64 dma_mask) +int __dma_set_mask(struct device *dev, u64 dma_mask) { struct dma_map_ops *dma_ops = get_dma_ops(dev); - if (ppc_md.dma_set_mask) - return ppc_md.dma_set_mask(dev, dma_mask); if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL)) return dma_ops->set_dma_mask(dev, dma_mask); if (!dev->dma_mask || !dma_supported(dev, dma_mask)) @@ -204,6 +202,12 @@ int dma_set_mask(struct device *dev, u64 dma_mask) *dev->dma_mask = dma_mask; return 0; } +int dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (ppc_md.dma_set_mask) + return ppc_md.dma_set_mask(dev, dma_mask); + return __dma_set_mask(dev, dma_mask); +} EXPORT_SYMBOL(dma_set_mask); u64 dma_get_required_mask(struct device *dev) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index d773dd440a45..88e3ec6e1d96 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1088,6 +1088,14 @@ int iommu_take_ownership(struct iommu_table *tbl) memset(tbl->it_map, 0xff, sz); iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size); + /* + * Disable iommu bypass, otherwise the user can DMA to all of + * our physical memory via the bypass window instead of just + * the pages that has been explicitly mapped into the iommu + */ + if (tbl->set_bypass) + tbl->set_bypass(tbl, false); + return 0; } EXPORT_SYMBOL_GPL(iommu_take_ownership); @@ -1102,6 +1110,10 @@ void iommu_release_ownership(struct iommu_table *tbl) /* Restore bit#0 set by iommu_init_table() */ if (tbl->it_offset == 0) set_bit(0, tbl->it_map); + + /* The kernel owns the device now, we can restore the iommu bypass */ + if (tbl->set_bypass) + tbl->set_bypass(tbl, true); } EXPORT_SYMBOL_GPL(iommu_release_ownership); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 7d6dcc6d5fa9..3b2b4fb3585b 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -460,9 +461,39 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev return; pe = &phb->ioda.pe_array[pdn->pe_number]; + WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops); set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); } +static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, + struct pci_dev *pdev, u64 dma_mask) +{ + struct pci_dn *pdn = pci_get_pdn(pdev); + struct pnv_ioda_pe *pe; + uint64_t top; + bool bypass = false; + + if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) + return -ENODEV;; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + if (pe->tce_bypass_enabled) { + top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1; + bypass = (dma_mask >= top); + } + + if (bypass) { + dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n"); + set_dma_ops(&pdev->dev, &dma_direct_ops); + set_dma_offset(&pdev->dev, pe->tce_bypass_base); + } else { + dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n"); + set_dma_ops(&pdev->dev, &dma_iommu_ops); + set_iommu_table_base(&pdev->dev, &pe->tce32_table); + } + return 0; +} + static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) { struct pci_dev *dev; @@ -657,6 +688,56 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs)); } +static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) +{ + struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, + tce32_table); + uint16_t window_id = (pe->pe_number << 1 ) + 1; + int64_t rc; + + pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis"); + if (enable) { + phys_addr_t top = memblock_end_of_DRAM(); + + top = roundup_pow_of_two(top); + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + window_id, + pe->tce_bypass_base, + top); + } else { + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + window_id, + pe->tce_bypass_base, + 0); + + /* + * We might want to reset the DMA ops of all devices on + * this PE. However in theory, that shouldn't be necessary + * as this is used for VFIO/KVM pass-through and the device + * hasn't yet been returned to its kernel driver + */ + } + if (rc) + pe_err(pe, "OPAL error %lld configuring bypass window\n", rc); + else + pe->tce_bypass_enabled = enable; +} + +static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe) +{ + /* TVE #1 is selected by PCI address bit 59 */ + pe->tce_bypass_base = 1ull << 59; + + /* Install set_bypass callback for VFIO */ + pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass; + + /* Enable bypass by default */ + pnv_pci_ioda2_set_bypass(&pe->tce32_table, true); +} + static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { @@ -727,6 +808,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, else pnv_ioda_setup_bus_dma(pe, pe->pbus); + /* Also create a bypass window */ + pnv_pci_ioda2_setup_bypass_pe(phb, pe); return; fail: if (pe->tce32_seg >= 0) @@ -1286,6 +1369,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, /* Setup TCEs */ phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup; + phb->dma_set_mask = pnv_pci_ioda_dma_set_mask; /* Setup shutdown function for kexec */ phb->shutdown = pnv_pci_ioda_shutdown; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b555ebc57ef5..95633d79ef5d 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -634,6 +634,16 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) pnv_pci_dma_fallback_setup(hose, pdev); } +int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) +{ + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; + + if (phb && phb->dma_set_mask) + return phb->dma_set_mask(phb, pdev, dma_mask); + return __dma_set_mask(&pdev->dev, dma_mask); +} + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 13f1942a9a5f..cde169442775 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -54,7 +54,9 @@ struct pnv_ioda_pe { struct iommu_table tce32_table; phys_addr_t tce_inval_reg_phys; - /* XXX TODO: Add support for additional 64-bit iommus */ + /* 64-bit TCE bypass region */ + bool tce_bypass_enabled; + uint64_t tce_bypass_base; /* MSIs. MVE index is identical for for 32 and 64 bit MSI * and -1 if not supported. (It's actually identical to the @@ -113,6 +115,8 @@ struct pnv_phb { unsigned int hwirq, unsigned int virq, unsigned int is_64, struct msi_msg *msg); void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); + int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev, + u64 dma_mask); void (*fixup_phb)(struct pci_controller *hose); u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); void (*shutdown)(struct pnv_phb *phb); diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index de6819be1f95..0051e108ef0f 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -7,12 +7,20 @@ extern void pnv_smp_init(void); static inline void pnv_smp_init(void) { } #endif +struct pci_dev; + #ifdef CONFIG_PCI extern void pnv_pci_init(void); extern void pnv_pci_shutdown(void); +extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask); #else static inline void pnv_pci_init(void) { } static inline void pnv_pci_shutdown(void) { } + +static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) +{ + return -ENODEV; +} #endif extern void pnv_lpc_init(void); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 21166f65c97c..110f4fbd319f 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -141,6 +142,13 @@ static void pnv_progress(char *s, unsigned short hex) { } +static int pnv_dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (dev_is_pci(dev)) + return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask); + return __dma_set_mask(dev, dma_mask); +} + static void pnv_shutdown(void) { /* Let the PCI code clear up IODA tables */ @@ -238,6 +246,7 @@ define_machine(powernv) { .machine_shutdown = pnv_shutdown, .power_save = powernv_idle, .calibrate_decr = generic_calibrate_decr, + .dma_set_mask = pnv_dma_set_mask, #ifdef CONFIG_KEXEC .kexec_cpu_down = pnv_kexec_cpu_down, #endif -- cgit v1.2.3 From 10c8562f932d89c030083e15f9279971ed637136 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 16 Jan 2014 15:39:17 +0100 Subject: ARM: dma-mapping: fix GFP_ATOMIC macro usage GFP_ATOMIC is not a single gfp flag, but a macro which expands to the other flags and LACK of __GFP_WAIT flag. To check if caller wanted to perform an atomic allocation, the code must test __GFP_WAIT flag presence. This patch fixes the issue introduced in v3.6-rc5 Signed-off-by: Marek Szyprowski CC: stable@vger.kernel.org --- arch/arm/mm/dma-mapping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 1a77450e728a..11b3914660d2 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1358,7 +1358,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - if (gfp & GFP_ATOMIC) + if (!(gfp & __GFP_WAIT)) return __iommu_alloc_atomic(dev, size, handle); /* -- cgit v1.2.3 From c091c71ad2218fc50a07b3d1dab85783f3b77efd Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 24 Jan 2014 14:49:58 +0100 Subject: x86: dma-mapping: fix GFP_ATOMIC macro usage GFP_ATOMIC is not a single gfp flag, but a macro which expands to the other flags, where meaningful is the LACK of __GFP_WAIT flag. To check if caller wants to perform an atomic allocation, the code must test for a lack of the __GFP_WAIT flag. This patch fixes the issue introduced in v3.5-rc1. CC: stable@vger.kernel.org Signed-off-by: Marek Szyprowski --- arch/x86/kernel/pci-dma.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 872079a67e4d..f7d0672481fd 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -100,8 +100,10 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, flag |= __GFP_ZERO; again: page = NULL; - if (!(flag & GFP_ATOMIC)) + /* CMA can be used only in the context which permits sleeping */ + if (flag & __GFP_WAIT) page = dma_alloc_from_contiguous(dev, count, get_order(size)); + /* fallback */ if (!page) page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); if (!page) -- cgit v1.2.3 From 8858d88a25142544843869f0cd3e6654aa7b4aec Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 11 Feb 2014 14:02:37 +0100 Subject: ARM: ux500: disable msp2 device tree node Commit 70b41abc151f9 "ARM: ux500: move MSP pin control to the device tree" accidentally activated MSP2, giving rise to a boot scroll scream as the kernel attempts to probe a driver for it and fails to obtain DMA channel 14. Fix this up by marking the node disabled again. Acked-by: Lee Jones Signed-off-by: Linus Walleij Signed-off-by: Kevin Hilman --- arch/arm/boot/dts/ste-href.dtsi | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi index 0c1e8d871ed1..6cb9b68e2188 100644 --- a/arch/arm/boot/dts/ste-href.dtsi +++ b/arch/arm/boot/dts/ste-href.dtsi @@ -188,7 +188,6 @@ msp2: msp@80117000 { pinctrl-names = "default"; pinctrl-0 = <&msp2_default_mode>; - status = "okay"; }; msp3: msp@80125000 { -- cgit v1.2.3 From 87fbb2ac6073a7039303517546a76074feb14c84 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 11 Feb 2014 20:19:44 -0500 Subject: ftrace/x86: Use breakpoints for converting function graph caller When the conversion was made to remove stop machine and use the breakpoint logic instead, the modification of the function graph caller is still done directly as though it was being done under stop machine. As it is not converted via stop machine anymore, there is a possibility that the code could be layed across cache lines and if another CPU is accessing that function graph call when it is being updated, it could cause a General Protection Fault. Convert the update of the function graph caller to use the breakpoint method as well. Cc: H. Peter Anvin Cc: stable@vger.kernel.org # 3.5+ Fixes: 08d636b6d4fb "ftrace/x86: Have arch x86_64 use breakpoints instead of stop machine" Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 83 +++++++++++++++++++++++++++--------------------- 1 file changed, 47 insertions(+), 36 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d4bdd253fea7..e6253195a301 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -77,8 +77,7 @@ within(unsigned long addr, unsigned long start, unsigned long end) return addr >= start && addr < end; } -static int -do_ftrace_mod_code(unsigned long ip, const void *new_code) +static unsigned long text_ip_addr(unsigned long ip) { /* * On x86_64, kernel text mappings are mapped read-only with @@ -91,7 +90,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code) if (within(ip, (unsigned long)_text, (unsigned long)_etext)) ip = (unsigned long)__va(__pa_symbol(ip)); - return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE); + return ip; } static const unsigned char *ftrace_nop_replace(void) @@ -123,8 +122,10 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) return -EINVAL; + ip = text_ip_addr(ip); + /* replace the text with the new text */ - if (do_ftrace_mod_code(ip, new_code)) + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) return -EPERM; sync_core(); @@ -221,37 +222,51 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return -EINVAL; } -int ftrace_update_ftrace_func(ftrace_func_t func) +static unsigned long ftrace_update_func; + +static int update_ftrace_func(unsigned long ip, void *new) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char old[MCOUNT_INSN_SIZE], *new; + unsigned char old[MCOUNT_INSN_SIZE]; int ret; - memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, (unsigned long)func); + memcpy(old, (void *)ip, MCOUNT_INSN_SIZE); + + ftrace_update_func = ip; + /* Make sure the breakpoints see the ftrace_update_func update */ + smp_wmb(); /* See comment above by declaration of modifying_ftrace_code */ atomic_inc(&modifying_ftrace_code); ret = ftrace_modify_code(ip, old, new); + atomic_dec(&modifying_ftrace_code); + + return ret; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char *new; + int ret; + + new = ftrace_call_replace(ip, (unsigned long)func); + ret = update_ftrace_func(ip, new); + /* Also update the regs callback function */ if (!ret) { ip = (unsigned long)(&ftrace_regs_call); - memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); new = ftrace_call_replace(ip, (unsigned long)func); - ret = ftrace_modify_code(ip, old, new); + ret = update_ftrace_func(ip, new); } - atomic_dec(&modifying_ftrace_code); - return ret; } static int is_ftrace_caller(unsigned long ip) { - if (ip == (unsigned long)(&ftrace_call) || - ip == (unsigned long)(&ftrace_regs_call)) + if (ip == ftrace_update_func) return 1; return 0; @@ -677,45 +692,41 @@ int __init ftrace_dyn_arch_init(void *data) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); -static int ftrace_mod_jmp(unsigned long ip, - int old_offset, int new_offset) +static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { - unsigned char code[MCOUNT_INSN_SIZE]; + static union ftrace_code_union calc; - if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; + /* Jmp not a call (ignore the .e8) */ + calc.e8 = 0xe9; + calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - if (code[0] != 0xe9 || old_offset != *(int *)(&code[1])) - return -EINVAL; + /* + * ftrace external locks synchronize the access to the static variable. + */ + return calc.code; +} - *(int *)(&code[1]) = new_offset; +static int ftrace_mod_jmp(unsigned long ip, void *func) +{ + unsigned char *new; - if (do_ftrace_mod_code(ip, &code)) - return -EPERM; + new = ftrace_jmp_replace(ip, (unsigned long)func); - return 0; + return update_ftrace_func(ip, new); } int ftrace_enable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_graph_caller); } int ftrace_disable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - - old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_stub); } #endif /* !CONFIG_DYNAMIC_FTRACE */ -- cgit v1.2.3 From 03bbd596ac04fef47ce93a730b8f086d797c3021 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 13 Feb 2014 07:34:30 -0800 Subject: x86, smap: Don't enable SMAP if CONFIG_X86_SMAP is disabled If SMAP support is not compiled into the kernel, don't enable SMAP in CR4 -- in fact, we should clear it, because the kernel doesn't contain the proper STAC/CLAC instructions for SMAP support. Found by Fengguang Wu's test system. Reported-by: Fengguang Wu Link: http://lkml.kernel.org/r/20140213124550.GA30497@localhost Signed-off-by: H. Peter Anvin Cc: # v3.7+ --- arch/x86/kernel/cpu/common.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 24b6fd10625a..8e28bf2fc3ef 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -284,8 +284,13 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); - if (cpu_has(c, X86_FEATURE_SMAP)) + if (cpu_has(c, X86_FEATURE_SMAP)) { +#ifdef CONFIG_X86_SMAP set_in_cr4(X86_CR4_SMAP); +#else + clear_in_cr4(X86_CR4_SMAP); +#endif + } } /* -- cgit v1.2.3 From 4640c7ee9b8953237d05a61ea3ea93981d1bc961 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 13 Feb 2014 07:46:04 -0800 Subject: x86, smap: smap_violation() is bogus if CONFIG_X86_SMAP is off If CONFIG_X86_SMAP is disabled, smap_violation() tests for conditions which are incorrect (as the AC flag doesn't matter), causing spurious faults. The dynamic disabling of SMAP (nosmap on the command line) is fine because it disables X86_FEATURE_SMAP, therefore causing the static_cpu_has() to return false. Found by Fengguang Wu's test system. [ v3: move all predicates into smap_violation() ] [ v2: use IS_ENABLED() instead of #ifdef ] Reported-by: Fengguang Wu Link: http://lkml.kernel.org/r/20140213124550.GA30497@localhost Signed-off-by: H. Peter Anvin Cc: # v3.7+ --- arch/x86/mm/fault.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9d591c895803..6dea040cc3a1 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1001,6 +1001,12 @@ static int fault_in_kernel_space(unsigned long address) static inline bool smap_violation(int error_code, struct pt_regs *regs) { + if (!IS_ENABLED(CONFIG_X86_SMAP)) + return false; + + if (!static_cpu_has(X86_FEATURE_SMAP)) + return false; + if (error_code & PF_USER) return false; @@ -1087,11 +1093,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(error_code & PF_RSVD)) pgtable_bad(regs, error_code, address); - if (static_cpu_has(X86_FEATURE_SMAP)) { - if (unlikely(smap_violation(error_code, regs))) { - bad_area_nosemaphore(regs, error_code, address); - return; - } + if (unlikely(smap_violation(error_code, regs))) { + bad_area_nosemaphore(regs, error_code, address); + return; } /* -- cgit v1.2.3 From d26794c04553901d00c4ca1542e1cbf4ec9580fb Mon Sep 17 00:00:00 2001 From: Marek Belisko Date: Sat, 21 Dec 2013 16:12:23 +0100 Subject: ARM: dts: omap3-gta04: Add EOC irq gpio line handling. BMP085 EOC (End Of Conversion) irq line is connected to gpio113 on gta04. Set irq properties to have driver using irq instead polling for EOC. Signed-off-by: Marek Belisko Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-gta04.dts | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts index b9b55c95a566..7a8e37de51b8 100644 --- a/arch/arm/boot/dts/omap3-gta04.dts +++ b/arch/arm/boot/dts/omap3-gta04.dts @@ -92,6 +92,8 @@ bmp085@77 { compatible = "bosch,bmp085"; reg = <0x77>; + interrupt-parent = <&gpio4>; + interrupts = <17 IRQ_TYPE_EDGE_RISING>; }; /* leds */ -- cgit v1.2.3 From 967d6a0bbfddcc25a7d1debbe8e2e4e7161d0566 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 23 Dec 2013 11:28:34 +0200 Subject: ARM: DTS: am335x-evmsk: Correct audio clock frequency The clock for audio is sourced from virt_24000000_ck, so the correct frequency is 24000000. Signed-off-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am335x-evmsk.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 4718ec4a4dbf..50abe53f6887 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -121,7 +121,7 @@ ti,model = "AM335x-EVMSK"; ti,audio-codec = <&tlv320aic3106>; ti,mcasp-controller = <&mcasp1>; - ti,codec-clock-rate = <24576000>; + ti,codec-clock-rate = <24000000>; ti,audio-routing = "Headphone Jack", "HPLOUT", "Headphone Jack", "HPROUT"; -- cgit v1.2.3 From 29ea5efb0bb612d352aa360de26e2095cb230e4a Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 23 Dec 2013 11:28:35 +0200 Subject: ARM: dts: am335x-evmsk: Fix mmc1 support Add pinctrl section and cd-gpio to mmc1. Without these the SD card is not working on EVM-SK board. Signed-off-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am335x-evmsk.dts | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch') diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 50abe53f6887..486880b74831 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -256,6 +256,12 @@ >; }; + mmc1_pins: pinmux_mmc1_pins { + pinctrl-single,pins = < + 0x160 (PIN_INPUT | MUX_MODE7) /* spi0_cs1.gpio0_6 */ + >; + }; + mcasp1_pins: mcasp1_pins { pinctrl-single,pins = < 0x10c (PIN_INPUT_PULLDOWN | MUX_MODE4) /* mii1_crs.mcasp1_aclkx */ @@ -456,6 +462,9 @@ status = "okay"; vmmc-supply = <&vmmc_reg>; bus-width = <4>; + pinctrl-names = "default"; + pinctrl-0 = <&mmc1_pins>; + cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>; }; &sham { -- cgit v1.2.3 From 22106c11252833419a29c9294411101cb2199a5f Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Wed, 15 Jan 2014 14:00:38 -0600 Subject: ARM: OMAP2+: add missing ARCH_HAS_OPP OMAP5, DRA7, AM43xx all have OPPs. So select the same to allow SoC only configuration boot to work with OPP. Reported-by: Nikhil Devshatwar Signed-off-by: Nishanth Menon Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/Kconfig | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch') diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 653b489479e0..8165a4a3ce20 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -50,6 +50,7 @@ config SOC_OMAP5 bool "TI OMAP5" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS + select ARCH_HAS_OPP select ARM_CPU_SUSPEND if PM select ARM_GIC select CPU_V7 @@ -63,6 +64,7 @@ config SOC_AM33XX bool "TI AM33XX" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS + select ARCH_HAS_OPP select ARM_CPU_SUSPEND if PM select CPU_V7 select MULTI_IRQ_HANDLER @@ -72,6 +74,7 @@ config SOC_AM43XX depends on ARCH_MULTI_V7 select CPU_V7 select ARCH_OMAP2PLUS + select ARCH_HAS_OPP select MULTI_IRQ_HANDLER select ARM_GIC select MACH_OMAP_GENERIC @@ -80,6 +83,7 @@ config SOC_DRA7XX bool "TI DRA7XX" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS + select ARCH_HAS_OPP select ARM_CPU_SUSPEND if PM select ARM_GIC select CPU_V7 -- cgit v1.2.3 From d8bd67317455744039e10fe33d6c76b82262c647 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Sat, 25 Jan 2014 22:28:55 +0100 Subject: ARM: dts: omap3-gta04: Fix 'aux' gpio key flags. It should be ACTIVE_HIGH. Signed-off-by: NeilBrown Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-gta04.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts index 7a8e37de51b8..81e0bb477bcd 100644 --- a/arch/arm/boot/dts/omap3-gta04.dts +++ b/arch/arm/boot/dts/omap3-gta04.dts @@ -32,7 +32,7 @@ aux-button { label = "aux"; linux,code = <169>; - gpios = <&gpio1 7 GPIO_ACTIVE_LOW>; + gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>; gpio-key,wakeup; }; }; -- cgit v1.2.3 From 2d6ac29e6a043c3adc3e82f5200ae1e07617e3ea Mon Sep 17 00:00:00 2001 From: Marek Belisko Date: Sat, 25 Jan 2014 22:28:57 +0100 Subject: ARM: dts: omap3-gta04: Fix mmc1 properties. Does not have an aux supply, and must be non-removable. Otherwise it is removed during suspend and filesystem gets confused. Signed-off-by: NeilBrown Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-gta04.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts index 81e0bb477bcd..c551e4af4d83 100644 --- a/arch/arm/boot/dts/omap3-gta04.dts +++ b/arch/arm/boot/dts/omap3-gta04.dts @@ -143,8 +143,8 @@ pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins>; vmmc-supply = <&vmmc1>; - vmmc_aux-supply = <&vsim>; bus-width = <4>; + ti,non-removable; }; &mmc2 { -- cgit v1.2.3 From 6b187b21c92b6e2c7e8ef0b450181c37a3f31681 Mon Sep 17 00:00:00 2001 From: Pekon Gupta Date: Tue, 28 Jan 2014 11:42:40 +0530 Subject: ARM: OMAP2+: gpmc: fix: DT NAND child nodes not probed when MTD_NAND is built as module Fixes: commit bc6b1e7b86f5d8e4a6fc1c0189e64bba4077efe0 ARM: OMAP: gpmc: add DT bindings for GPMC timings and NAND OMAP SoC(s) depend on GPMC controller driver to parse GPMC DT child nodes and register them platform_device for NAND driver to probe later. However this does not happen if generic MTD_NAND framework is built as module (CONFIG_MTD_NAND=m). Therefore, when MTD/NAND and MTD/NAND/OMAP2 modules are loaded, they are unable to find any matching platform_device and remain un-binded. This causes on board NAND flash to remain un-detected. This patch causes GPMC controller to parse DT nodes when CONFIG_MTD_NAND=y || CONFIG_MTD_NAND=m CC: # 3.9.x+ Signed-off-by: Pekon Gupta Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/gpmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c index d24926e6340f..c77a84b63a59 100644 --- a/arch/arm/mach-omap2/gpmc.c +++ b/arch/arm/mach-omap2/gpmc.c @@ -1339,7 +1339,7 @@ static void __maybe_unused gpmc_read_timings_dt(struct device_node *np, of_property_read_bool(np, "gpmc,time-para-granularity"); } -#ifdef CONFIG_MTD_NAND +#if IS_ENABLED(CONFIG_MTD_NAND) static const char * const nand_xfer_types[] = { [NAND_OMAP_PREFETCH_POLLED] = "prefetch-polled", -- cgit v1.2.3 From 980386d2d6d49e0b42f48550853ef1ad6aa5d79a Mon Sep 17 00:00:00 2001 From: Pekon Gupta Date: Tue, 28 Jan 2014 11:42:41 +0530 Subject: ARM: OMAP2+: gpmc: fix: DT ONENAND child nodes not probed when MTD_ONENAND is built as module Fixes: commit 75d3625e0e86b2d8d77b4e9c6f685fd7ea0d5a96 ARM: OMAP2+: gpmc: add DT bindings for OneNAND OMAP SoC(s) depend on GPMC controller driver to parse GPMC DT child nodes and register them platform_device for ONENAND driver to probe later. However this does not happen if generic MTD_ONENAND framework is built as module (CONFIG_MTD_ONENAND=m). Therefore, when MTD/ONENAND and MTD/ONENAND/OMAP2 modules are loaded, they are unable to find any matching platform_device and remain un-binded. This causes on board ONENAND flash to remain un-detected. This patch causes GPMC controller to parse DT nodes when CONFIG_MTD_ONENAND=y || CONFIG_MTD_ONENAND=m CC: # 3.9.x+ Signed-off-by: Pekon Gupta Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/gpmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c index c77a84b63a59..ab43755364f5 100644 --- a/arch/arm/mach-omap2/gpmc.c +++ b/arch/arm/mach-omap2/gpmc.c @@ -1429,7 +1429,7 @@ static int gpmc_probe_nand_child(struct platform_device *pdev, } #endif -#ifdef CONFIG_MTD_ONENAND +#if IS_ENABLED(CONFIG_MTD_ONENAND) static int gpmc_probe_onenand_child(struct platform_device *pdev, struct device_node *child) { -- cgit v1.2.3 From 8c5cb1a8f81370f60c62450fa5a5cf20aa081050 Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Sat, 8 Feb 2014 15:48:55 +0200 Subject: ARM: OMAP1: nokia770: enable tahvo-usb Add platform data for tahvo-usb. This is the last missing piece to get Tahvo USB working with 3.14. Signed-off-by: Aaro Koskinen Signed-off-by: Tony Lindgren --- arch/arm/mach-omap1/board-nokia770.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c index 91449c5cb70f..85089d821982 100644 --- a/arch/arm/mach-omap1/board-nokia770.c +++ b/arch/arm/mach-omap1/board-nokia770.c @@ -156,6 +156,7 @@ static struct omap_usb_config nokia770_usb_config __initdata = { .register_dev = 1, .hmc_mode = 16, .pins[0] = 6, + .extcon = "tahvo-usb", }; #if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) -- cgit v1.2.3 From 2a074deffd66d5e1893e859dc0737887fea9d46d Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Sun, 9 Feb 2014 14:12:35 +0200 Subject: ARM: dts: N9/N950: fix boot hang with 3.14-rc1 N9/N950 does not boot anymore with 3.14-rc1, because SoC compatible property is missing. Fix that. Signed-off-by: Aaro Koskinen Reviewed-by: Nishanth Menon Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-n9.dts | 2 +- arch/arm/boot/dts/omap3-n950.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/omap3-n9.dts b/arch/arm/boot/dts/omap3-n9.dts index 39828ce464ee..9938b5dc1909 100644 --- a/arch/arm/boot/dts/omap3-n9.dts +++ b/arch/arm/boot/dts/omap3-n9.dts @@ -14,5 +14,5 @@ / { model = "Nokia N9"; - compatible = "nokia,omap3-n9", "ti,omap3"; + compatible = "nokia,omap3-n9", "ti,omap36xx", "ti,omap3"; }; diff --git a/arch/arm/boot/dts/omap3-n950.dts b/arch/arm/boot/dts/omap3-n950.dts index b076a526b999..261c5589bfa3 100644 --- a/arch/arm/boot/dts/omap3-n950.dts +++ b/arch/arm/boot/dts/omap3-n950.dts @@ -14,5 +14,5 @@ / { model = "Nokia N950"; - compatible = "nokia,omap3-n950", "ti,omap3"; + compatible = "nokia,omap3-n950", "ti,omap36xx", "ti,omap3"; }; -- cgit v1.2.3 From c3580bc12569b4c02ab5505b853825d863e6f86e Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Sun, 9 Feb 2014 14:12:36 +0200 Subject: ARM: dts: N900: add missing compatible property Add missing compatible property to avoid problems in the future. Signed-off-by: Aaro Koskinen Reviewed-by: Nishanth Menon Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-n900.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 6fc85f963530..0bf40c90faba 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -1,6 +1,6 @@ /* * Copyright (C) 2013 Pavel Machek - * Copyright 2013 Aaro Koskinen + * Copyright (C) 2013-2014 Aaro Koskinen * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 (or later) as @@ -13,7 +13,7 @@ / { model = "Nokia N900"; - compatible = "nokia,omap3-n900", "ti,omap3"; + compatible = "nokia,omap3-n900", "ti,omap3430", "ti,omap3"; cpus { cpu@0 { -- cgit v1.2.3 From 84b57c84b10de62d832b04da02af9cba60199d0c Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Sun, 9 Feb 2014 16:01:28 +0100 Subject: ARM: OMAP2+: Remove MACH_NOKIA_N800 The last caller of machine_is_nokia_n800() was removed in commit 5a87cde490e1 ("ARM: OMAP2+: Remove legacy booting support for n8x0"). That means that the Kconfig symbol MACH_NOKIA_N800 is now unused. It can safely be removed. Signed-off-by: Paul Bolle Acked-by: Aaro Koskinen Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/Kconfig | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 8165a4a3ce20..9320252ca43a 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -272,9 +272,6 @@ config MACH_OMAP_3430SDP default y select OMAP_PACKAGE_CBB -config MACH_NOKIA_N800 - bool - config MACH_NOKIA_N810 bool @@ -285,7 +282,6 @@ config MACH_NOKIA_N8X0 bool "Nokia N800/N810" depends on SOC_OMAP2420 default y - select MACH_NOKIA_N800 select MACH_NOKIA_N810 select MACH_NOKIA_N810_WIMAX select OMAP_PACKAGE_ZAC -- cgit v1.2.3 From 43e21ef061598024dcb4821b97b9eaebfed0b50d Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Wed, 12 Feb 2014 10:45:52 +0100 Subject: ARM: OMAP2+: Remove legacy macros for zoom platforms Commit 97411608fd5f ("ARM: OMAP2+: Remove legacy support for zoom platforms") removed the Kconfig symbols MACH_OMAP_ZOOM2 and MACH_OMAP_ZOOM3. Remove the last usage of the related macros too. Signed-off-by: Paul Bolle Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/io.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index d408b15b4fbf..af432b191255 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -179,15 +179,6 @@ static struct map_desc omap34xx_io_desc[] __initdata = { .length = L4_EMU_34XX_SIZE, .type = MT_DEVICE }, -#if defined(CONFIG_DEBUG_LL) && \ - (defined(CONFIG_MACH_OMAP_ZOOM2) || defined(CONFIG_MACH_OMAP_ZOOM3)) - { - .virtual = ZOOM_UART_VIRT, - .pfn = __phys_to_pfn(ZOOM_UART_BASE), - .length = SZ_1M, - .type = MT_DEVICE - }, -#endif }; #endif -- cgit v1.2.3 From df1a29f4768a3de4ea793ff0b4c6e79ffa15849d Mon Sep 17 00:00:00 2001 From: Florian Vaussard Date: Thu, 13 Feb 2014 11:25:13 +0100 Subject: ARM: dts: omap3-tobi: Fix boot with OMAP36xx-based Overo Tobi expansion board can be used with both OMAP35xx-based Overo, and OMAP36xx-based Overo. Currently the boot is broken with newer OMAP36xx-based Overo (Storm and alike). Fix include file and compatible string to be able to boot newer models. This will break older models. This will be addressed later. Signed-off-by: Florian Vaussard Tested-by: Kevin Hilman Acked-by: Nishanth Menon Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-overo.dtsi | 3 --- arch/arm/boot/dts/omap3-tobi.dts | 5 ++++- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/omap3-overo.dtsi b/arch/arm/boot/dts/omap3-overo.dtsi index a461d2fd1fb0..597099907f8e 100644 --- a/arch/arm/boot/dts/omap3-overo.dtsi +++ b/arch/arm/boot/dts/omap3-overo.dtsi @@ -9,9 +9,6 @@ /* * The Gumstix Overo must be combined with an expansion board. */ -/dts-v1/; - -#include "omap34xx.dtsi" / { pwmleds { diff --git a/arch/arm/boot/dts/omap3-tobi.dts b/arch/arm/boot/dts/omap3-tobi.dts index 7e4ad2aec37a..0e3b8bf49761 100644 --- a/arch/arm/boot/dts/omap3-tobi.dts +++ b/arch/arm/boot/dts/omap3-tobi.dts @@ -10,11 +10,14 @@ * Tobi expansion board is manufactured by Gumstix Inc. */ +/dts-v1/; + +#include "omap36xx.dtsi" #include "omap3-overo.dtsi" / { model = "TI OMAP3 Gumstix Overo on Tobi"; - compatible = "ti,omap3-tobi", "ti,omap3-overo", "ti,omap3"; + compatible = "ti,omap3-tobi", "ti,omap3-overo", "ti,omap36xx", "ti,omap3"; leds { compatible = "gpio-leds"; -- cgit v1.2.3 From 1ce64826b02032827abb166fc2d8909171d4b296 Mon Sep 17 00:00:00 2001 From: Florian Vaussard Date: Thu, 13 Feb 2014 11:25:14 +0100 Subject: ARM: dts: omap3-tobi: Use the correct vendor prefix Gumstix is the correct vendor for all Overo related products. Reported-by: Javier Martinez Canillas Signed-off-by: Florian Vaussard Acked-by: Nishanth Menon Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-tobi.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/omap3-tobi.dts b/arch/arm/boot/dts/omap3-tobi.dts index 0e3b8bf49761..c742afaa2c26 100644 --- a/arch/arm/boot/dts/omap3-tobi.dts +++ b/arch/arm/boot/dts/omap3-tobi.dts @@ -17,7 +17,7 @@ / { model = "TI OMAP3 Gumstix Overo on Tobi"; - compatible = "ti,omap3-tobi", "ti,omap3-overo", "ti,omap36xx", "ti,omap3"; + compatible = "gumstix,omap3-tobi", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3"; leds { compatible = "gpio-leds"; -- cgit v1.2.3 From f03ef09b6f59c0807d6aeba10f18238be1ea6390 Mon Sep 17 00:00:00 2001 From: Florian Vaussard Date: Thu, 13 Feb 2014 11:25:15 +0100 Subject: ARM: dts: Add support for both OMAP35xx and OMAP36xx Overo/Tobi Unfortunatly the device tree for older OMAP35xx Overo cannot be used with newer OMAP36xx and vice-versa. To address this issue, move most of the Tobi DTS to a common include file, and create model-specific Tobi DTS. Signed-off-by: Florian Vaussard Tested-by: Kevin Hilman Acked-by: Nishanth Menon Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/Makefile | 3 +- arch/arm/boot/dts/omap3-overo-storm-tobi.dts | 22 +++++++ arch/arm/boot/dts/omap3-overo-tobi-common.dtsi | 80 ++++++++++++++++++++++++ arch/arm/boot/dts/omap3-overo-tobi.dts | 22 +++++++ arch/arm/boot/dts/omap3-tobi.dts | 86 -------------------------- 5 files changed, 126 insertions(+), 87 deletions(-) create mode 100644 arch/arm/boot/dts/omap3-overo-storm-tobi.dts create mode 100644 arch/arm/boot/dts/omap3-overo-tobi-common.dtsi create mode 100644 arch/arm/boot/dts/omap3-overo-tobi.dts delete mode 100644 arch/arm/boot/dts/omap3-tobi.dts (limited to 'arch') diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index b9d6a8b485e0..e8355f4d8b0c 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -208,7 +208,8 @@ dtb-$(CONFIG_ARCH_OMAP2PLUS) += omap2420-h4.dtb \ omap3-n900.dtb \ omap3-n9.dtb \ omap3-n950.dtb \ - omap3-tobi.dtb \ + omap3-overo-tobi.dtb \ + omap3-overo-storm-tobi.dtb \ omap3-gta04.dtb \ omap3-igep0020.dtb \ omap3-igep0030.dtb \ diff --git a/arch/arm/boot/dts/omap3-overo-storm-tobi.dts b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts new file mode 100644 index 000000000000..966b5c9cd96a --- /dev/null +++ b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts @@ -0,0 +1,22 @@ +/* + * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * Tobi expansion board is manufactured by Gumstix Inc. + */ + +/dts-v1/; + +#include "omap36xx.dtsi" +#include "omap3-overo-tobi-common.dtsi" + +/ { + model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Tobi"; + compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3"; +}; + diff --git a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi new file mode 100644 index 000000000000..4edc013a91c1 --- /dev/null +++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi @@ -0,0 +1,80 @@ +/* + * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * Tobi expansion board is manufactured by Gumstix Inc. + */ + +#include "omap3-overo.dtsi" + +/ { + leds { + compatible = "gpio-leds"; + heartbeat { + label = "overo:red:gpio21"; + gpios = <&gpio1 21 GPIO_ACTIVE_LOW>; + linux,default-trigger = "heartbeat"; + }; + }; + + vddvario: regulator-vddvario { + compatible = "regulator-fixed"; + regulator-name = "vddvario"; + regulator-always-on; + }; + + vdd33a: regulator-vdd33a { + compatible = "regulator-fixed"; + regulator-name = "vdd33a"; + regulator-always-on; + }; +}; + +&gpmc { + ranges = <5 0 0x2c000000 0x1000000>; /* CS5 */ + + ethernet@5,0 { + compatible = "smsc,lan9221", "smsc,lan9115"; + reg = <5 0 0xff>; + bank-width = <2>; + + gpmc,mux-add-data; + gpmc,cs-on-ns = <0>; + gpmc,cs-rd-off-ns = <42>; + gpmc,cs-wr-off-ns = <36>; + gpmc,adv-on-ns = <6>; + gpmc,adv-rd-off-ns = <12>; + gpmc,adv-wr-off-ns = <12>; + gpmc,oe-on-ns = <0>; + gpmc,oe-off-ns = <42>; + gpmc,we-on-ns = <0>; + gpmc,we-off-ns = <36>; + gpmc,rd-cycle-ns = <60>; + gpmc,wr-cycle-ns = <54>; + gpmc,access-ns = <36>; + gpmc,page-burst-access-ns = <0>; + gpmc,bus-turnaround-ns = <0>; + gpmc,cycle2cycle-delay-ns = <0>; + gpmc,wr-data-mux-bus-ns = <18>; + gpmc,wr-access-ns = <42>; + gpmc,cycle2cycle-samecsen; + gpmc,cycle2cycle-diffcsen; + + interrupt-parent = <&gpio6>; + interrupts = <16 IRQ_TYPE_LEVEL_LOW>; /* GPIO 176 */ + reg-io-width = <4>; + }; +}; + +&i2c3 { + clock-frequency = <100000>; +}; + +&mmc3 { + status = "disabled"; +}; diff --git a/arch/arm/boot/dts/omap3-overo-tobi.dts b/arch/arm/boot/dts/omap3-overo-tobi.dts new file mode 100644 index 000000000000..de5653e1b5ca --- /dev/null +++ b/arch/arm/boot/dts/omap3-overo-tobi.dts @@ -0,0 +1,22 @@ +/* + * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * Tobi expansion board is manufactured by Gumstix Inc. + */ + +/dts-v1/; + +#include "omap34xx.dtsi" +#include "omap3-overo-tobi-common.dtsi" + +/ { + model = "OMAP35xx Gumstix Overo on Tobi"; + compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3430", "ti,omap3"; +}; + diff --git a/arch/arm/boot/dts/omap3-tobi.dts b/arch/arm/boot/dts/omap3-tobi.dts deleted file mode 100644 index c742afaa2c26..000000000000 --- a/arch/arm/boot/dts/omap3-tobi.dts +++ /dev/null @@ -1,86 +0,0 @@ -/* - * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -/* - * Tobi expansion board is manufactured by Gumstix Inc. - */ - -/dts-v1/; - -#include "omap36xx.dtsi" -#include "omap3-overo.dtsi" - -/ { - model = "TI OMAP3 Gumstix Overo on Tobi"; - compatible = "gumstix,omap3-tobi", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3"; - - leds { - compatible = "gpio-leds"; - heartbeat { - label = "overo:red:gpio21"; - gpios = <&gpio1 21 GPIO_ACTIVE_LOW>; - linux,default-trigger = "heartbeat"; - }; - }; - - vddvario: regulator-vddvario { - compatible = "regulator-fixed"; - regulator-name = "vddvario"; - regulator-always-on; - }; - - vdd33a: regulator-vdd33a { - compatible = "regulator-fixed"; - regulator-name = "vdd33a"; - regulator-always-on; - }; -}; - -&gpmc { - ranges = <5 0 0x2c000000 0x1000000>; /* CS5 */ - - ethernet@5,0 { - compatible = "smsc,lan9221", "smsc,lan9115"; - reg = <5 0 0xff>; - bank-width = <2>; - - gpmc,mux-add-data; - gpmc,cs-on-ns = <0>; - gpmc,cs-rd-off-ns = <42>; - gpmc,cs-wr-off-ns = <36>; - gpmc,adv-on-ns = <6>; - gpmc,adv-rd-off-ns = <12>; - gpmc,adv-wr-off-ns = <12>; - gpmc,oe-on-ns = <0>; - gpmc,oe-off-ns = <42>; - gpmc,we-on-ns = <0>; - gpmc,we-off-ns = <36>; - gpmc,rd-cycle-ns = <60>; - gpmc,wr-cycle-ns = <54>; - gpmc,access-ns = <36>; - gpmc,page-burst-access-ns = <0>; - gpmc,bus-turnaround-ns = <0>; - gpmc,cycle2cycle-delay-ns = <0>; - gpmc,wr-data-mux-bus-ns = <18>; - gpmc,wr-access-ns = <42>; - gpmc,cycle2cycle-samecsen; - gpmc,cycle2cycle-diffcsen; - - interrupt-parent = <&gpio6>; - interrupts = <16 IRQ_TYPE_LEVEL_LOW>; /* GPIO 176 */ - reg-io-width = <4>; - }; -}; - -&i2c3 { - clock-frequency = <100000>; -}; - -&mmc3 { - status = "disabled"; -}; -- cgit v1.2.3 From c55d016f7a930dd1c995336017123b469a8c8f5a Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 14 Feb 2014 08:24:24 +0100 Subject: x86/efi: Fix 32-bit fallout We do not enable the new efi memmap on 32-bit and thus we need to run runtime_code_page_mkexec() unconditionally there. Fix that. Reported-and-tested-by: Lejun Zhu Signed-off-by: Borislav Petkov Signed-off-by: Matt Fleming --- arch/x86/include/asm/efi.h | 2 ++ arch/x86/platform/efi/efi.c | 5 ++--- arch/x86/platform/efi/efi_32.c | 6 ++++++ arch/x86/platform/efi/efi_64.c | 9 +++++++++ 4 files changed, 19 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 3b978c472d08..3d6b9f81cc68 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -132,6 +132,8 @@ extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); extern void efi_setup_page_tables(void); extern void __init old_map_region(efi_memory_desc_t *md); +extern void __init runtime_code_page_mkexec(void); +extern void __init efi_runtime_mkexec(void); struct efi_setup_data { u64 fw_vendor; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index d62ec87a2b26..1a201ac7cef8 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -792,7 +792,7 @@ void __init efi_set_executable(efi_memory_desc_t *md, bool executable) set_memory_nx(addr, npages); } -static void __init runtime_code_page_mkexec(void) +void __init runtime_code_page_mkexec(void) { efi_memory_desc_t *md; void *p; @@ -1069,8 +1069,7 @@ void __init efi_enter_virtual_mode(void) efi.update_capsule = virt_efi_update_capsule; efi.query_capsule_caps = virt_efi_query_capsule_caps; - if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) - runtime_code_page_mkexec(); + efi_runtime_mkexec(); kfree(new_memmap); diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 249b183cf417..0b74cdf7f816 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -77,3 +77,9 @@ void efi_call_phys_epilog(void) local_irq_restore(efi_rt_eflags); } + +void __init efi_runtime_mkexec(void) +{ + if (__supported_pte_mask & _PAGE_NX) + runtime_code_page_mkexec(); +} diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 6284f158a47d..0c2a234fef1e 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -233,3 +233,12 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len) { efi_setup = phys_addr + sizeof(struct setup_data); } + +void __init efi_runtime_mkexec(void) +{ + if (!efi_enabled(EFI_OLD_MEMMAP)) + return; + + if (__supported_pte_mask & _PAGE_NX) + runtime_code_page_mkexec(); +} -- cgit v1.2.3 From 09503379dc99535b1bbfa51aa1aeef340f5d82ec Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Thu, 13 Feb 2014 17:17:54 +0000 Subject: x86/efi: Check status field to validate BGRT header Madper reported seeing the following crash, BUG: unable to handle kernel paging request at ffffffffff340003 IP: [] efi_bgrt_init+0x9d/0x133 Call Trace: [] efi_late_init+0x9/0xb [] start_kernel+0x436/0x450 [] ? repair_env_string+0x5c/0x5c [] ? early_idt_handlers+0x120/0x120 [] x86_64_start_reservations+0x2a/0x2c [] x86_64_start_kernel+0x13e/0x14d This is caused because the layout of the ACPI BGRT header on this system doesn't match the definition from the ACPI spec, and so we get a bogus physical address when dereferencing ->image_address in efi_bgrt_init(). Luckily the status field in the BGRT header clearly marks it as invalid, so we can check that field and skip BGRT initialisation. Reported-by: Madper Xie Suggested-by: Toshi Kani Cc: "Rafael J. Wysocki" Cc: Matthew Garrett Cc: Josh Triplett Signed-off-by: Matt Fleming --- arch/x86/platform/efi/efi-bgrt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index 4df9591eadad..f15103dff4b4 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -42,7 +42,7 @@ void __init efi_bgrt_init(void) if (bgrt_tab->header.length < sizeof(*bgrt_tab)) return; - if (bgrt_tab->version != 1) + if (bgrt_tab->version != 1 || bgrt_tab->status != 1) return; if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address) return; -- cgit v1.2.3 From 2a2f3e269c75edf916de5967079069aeb6a601cb Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Sun, 2 Feb 2014 13:41:02 -0800 Subject: arm64: KVM: Add VGIC device control for arm64 This fixes the build breakage introduced by c07a0191ef2de1f9510f12d1f88e3b0b5cd8d66f and adds support for the device control API and save/restore of the VGIC state for ARMv8. The defines were simply missing from the arm64 header files and uaccess.h must be implicitly imported from somewhere else on arm. Signed-off-by: Christoffer Dall Signed-off-by: Paolo Bonzini --- arch/arm64/include/uapi/asm/kvm.h | 9 +++++++++ virt/kvm/arm/vgic.c | 1 + 2 files changed, 10 insertions(+) (limited to 'arch') diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 495ab6f84a61..eaf54a30bedc 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -148,6 +148,15 @@ struct kvm_arch_memory_slot { #define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) #define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2) +/* Device Control API: ARM VGIC */ +#define KVM_DEV_ARM_VGIC_GRP_ADDR 0 +#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 +#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 +#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 +#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) +#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 +#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) + /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_TYPE_SHIFT 24 #define KVM_ARM_IRQ_TYPE_MASK 0xff diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index be456ce264d0..8ca405cd7c1a 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -24,6 +24,7 @@ #include #include #include +#include #include -- cgit v1.2.3 From 1a18a66446f3f289b05b634f18012424d82aa63a Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Fri, 17 Jan 2014 12:25:28 +0800 Subject: powerpc: Set the correct ksp_limit on ppc32 when switching to irq stack Guenter Roeck has got the following call trace on a p2020 board: Kernel stack overflow in process eb3e5a00, r1=eb79df90 CPU: 0 PID: 2838 Comm: ssh Not tainted 3.13.0-rc8-juniper-00146-g19eca00 #4 task: eb3e5a00 ti: c0616000 task.ti: ef440000 NIP: c003a420 LR: c003a410 CTR: c0017518 REGS: eb79dee0 TRAP: 0901 Not tainted (3.13.0-rc8-juniper-00146-g19eca00) MSR: 00029000 CR: 24008444 XER: 00000000 GPR00: c003a410 eb79df90 eb3e5a00 00000000 eb05d900 00000001 65d87646 00000000 GPR08: 00000000 020b8000 00000000 00000000 44008442 NIP [c003a420] __do_softirq+0x94/0x1ec LR [c003a410] __do_softirq+0x84/0x1ec Call Trace: [eb79df90] [c003a410] __do_softirq+0x84/0x1ec (unreliable) [eb79dfe0] [c003a970] irq_exit+0xbc/0xc8 [eb79dff0] [c000cc1c] call_do_irq+0x24/0x3c [ef441f20] [c00046a8] do_IRQ+0x8c/0xf8 [ef441f40] [c000e7f4] ret_from_except+0x0/0x18 --- Exception: 501 at 0xfcda524 LR = 0x10024900 Instruction dump: 7c781b78 3b40000a 3a73b040 543c0024 3a800000 3b3913a0 7ef5bb78 48201bf9 5463103a 7d3b182e 7e89b92e 7c008146 <3ba00000> 7e7e9b78 48000014 57fff87f Kernel panic - not syncing: kernel stack overflow CPU: 0 PID: 2838 Comm: ssh Not tainted 3.13.0-rc8-juniper-00146-g19eca00 #4 Call Trace: The reason is that we have used the wrong register to calculate the ksp_limit in commit cbc9565ee826 (powerpc: Remove ksp_limit on ppc64). Just fix it. As suggested by Benjamin Herrenschmidt, also add the C prototype of the function in the comment in order to avoid such kind of errors in the future. Cc: stable@vger.kernel.org # 3.12 Reported-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Kevin Hao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/misc_32.S | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 879f09620f83..7c6bb4b17b49 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -57,11 +57,14 @@ _GLOBAL(call_do_softirq) mtlr r0 blr +/* + * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); + */ _GLOBAL(call_do_irq) mflr r0 stw r0,4(r1) lwz r10,THREAD+KSP_LIMIT(r2) - addi r11,r3,THREAD_INFO_GAP + addi r11,r4,THREAD_INFO_GAP stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4) mr r1,r4 stw r10,8(r1) -- cgit v1.2.3 From b020cc6c03a37c3526fcb1dff274f649257949e0 Mon Sep 17 00:00:00 2001 From: Kleber Sacilotto de Souza Date: Fri, 17 Jan 2014 11:56:51 -0200 Subject: powerpc/pseries: Fix regression on PCI link speed Commit 5091f0c (powerpc/pseries: Fix PCIE link speed endian issue) introduced a regression on the PCI link speed detection using the device-tree property. The ibm,pcie-link-speed-stats property is composed of two 32-bit integers, the first one being the maxinum link speed and the second the current link speed. The changes introduced by the aforementioned commit are considering just the first integer. Fix this issue by changing how the property is accessed, using the helper functions to properly access the array of values. The explicit byte swapping is not needed anymore here, since it's done by the helper functions. Signed-off-by: Kleber Sacilotto de Souza Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/pci.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 70670a2d9cf2..a6f7a1460e2f 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -113,7 +113,8 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) { struct device_node *dn, *pdn; struct pci_bus *bus; - const __be32 *pcie_link_speed_stats; + u32 pcie_link_speed_stats[2]; + int rc; bus = bridge->bus; @@ -122,20 +123,21 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) return 0; for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) { - pcie_link_speed_stats = of_get_property(pdn, - "ibm,pcie-link-speed-stats", NULL); - if (pcie_link_speed_stats) + rc = of_property_read_u32_array(pdn, + "ibm,pcie-link-speed-stats", + &pcie_link_speed_stats[0], 2); + if (!rc) break; } of_node_put(pdn); - if (!pcie_link_speed_stats) { + if (rc) { pr_err("no ibm,pcie-link-speed-stats property\n"); return 0; } - switch (be32_to_cpup(pcie_link_speed_stats)) { + switch (pcie_link_speed_stats[0]) { case 0x01: bus->max_bus_speed = PCIE_SPEED_2_5GT; break; @@ -147,7 +149,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) break; } - switch (be32_to_cpup(pcie_link_speed_stats)) { + switch (pcie_link_speed_stats[1]) { case 0x01: bus->cur_bus_speed = PCIE_SPEED_2_5GT; break; -- cgit v1.2.3 From 49d9684a54d21930372b7fb0d3d7b5617f621706 Mon Sep 17 00:00:00 2001 From: Kleber Sacilotto de Souza Date: Fri, 17 Jan 2014 11:56:52 -0200 Subject: powerpc/pseries: Add Gen3 definitions for PCIE link speed Rev3 of the PCI Express Base Specification defines a Supported Link Speeds Vector where the bit definitions within this field are: Bit 0 - 2.5 GT/s Bit 1 - 5.0 GT/s Bit 2 - 8.0 GT/s This vector definition is used by the platform firmware to export the maximum and current link speeds of the PCI bus via the "ibm,pcie-link-speed-stats" device-tree property. This patch updates pseries_root_bridge_prepare() to detect Gen3 speed buses (defined by 0x04). Signed-off-by: Kleber Sacilotto de Souza Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/pci.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index a6f7a1460e2f..c413ec158ff5 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -144,6 +144,9 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) case 0x02: bus->max_bus_speed = PCIE_SPEED_5_0GT; break; + case 0x04: + bus->max_bus_speed = PCIE_SPEED_8_0GT; + break; default: bus->max_bus_speed = PCI_SPEED_UNKNOWN; break; @@ -156,6 +159,9 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) case 0x02: bus->cur_bus_speed = PCIE_SPEED_5_0GT; break; + case 0x04: + bus->cur_bus_speed = PCIE_SPEED_8_0GT; + break; default: bus->cur_bus_speed = PCI_SPEED_UNKNOWN; break; -- cgit v1.2.3 From 88247e8d7ba6639f2c199e147ebbc91f7673150c Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Feb 2014 09:13:36 +0530 Subject: powerpc/mm: Add new "set" flag argument to pte/pmd update function pte_update() is a powerpc-ism used to change the bits of a PTE when the access permission is being restricted (a flush is potentially needed). It uses atomic operations on when needed and handles the hash synchronization on hash based processors. It is currently only used to clear PTE bits and so the current implementation doesn't provide a way to also set PTE bits. The new _PAGE_NUMA bit, when set, is actually restricting access so it must use that function too, so this change adds the ability for pte_update() to also set bits. We will use this later to set the _PAGE_NUMA bit. Acked-by: Mel Gorman Acked-by: Rik van Riel Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hugetlb.h | 2 +- arch/powerpc/include/asm/pgtable-ppc64.h | 26 +++++++++++++++----------- arch/powerpc/mm/pgtable_64.c | 12 +++++++----- arch/powerpc/mm/subpage-prot.c | 2 +- 4 files changed, 24 insertions(+), 18 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index d750336b171d..623f2971ce0e 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -127,7 +127,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_PPC64 - return __pte(pte_update(mm, addr, ptep, ~0UL, 1)); + return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1)); #else return __pte(pte_update(ptep, ~0UL, 0)); #endif diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index bc141c950b1e..eb9261024f51 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -195,6 +195,7 @@ extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long clr, + unsigned long set, int huge) { #ifdef PTE_ATOMIC_UPDATES @@ -205,14 +206,15 @@ static inline unsigned long pte_update(struct mm_struct *mm, andi. %1,%0,%6\n\ bne- 1b \n\ andc %1,%0,%4 \n\ + or %1,%1,%7\n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*ptep) - : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY) + : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set) : "cc" ); #else unsigned long old = pte_val(*ptep); - *ptep = __pte(old & ~clr); + *ptep = __pte((old & ~clr) | set); #endif /* huge pages use the old page table lock */ if (!huge) @@ -231,9 +233,9 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, { unsigned long old; - if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) + if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) return 0; - old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0); + old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); return (old & _PAGE_ACCESSED) != 0; } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG @@ -252,7 +254,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - pte_update(mm, addr, ptep, _PAGE_RW, 0); + pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); } static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, @@ -261,7 +263,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - pte_update(mm, addr, ptep, _PAGE_RW, 1); + pte_update(mm, addr, ptep, _PAGE_RW, 0, 1); } /* @@ -284,14 +286,14 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0); + unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); return __pte(old); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t * ptep) { - pte_update(mm, addr, ptep, ~0UL, 0); + pte_update(mm, addr, ptep, ~0UL, 0, 0); } @@ -506,7 +508,9 @@ extern int pmdp_set_access_flags(struct vm_area_struct *vma, extern unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, unsigned long clr); + pmd_t *pmdp, + unsigned long clr, + unsigned long set); static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) @@ -515,7 +519,7 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) return 0; - old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED); + old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0); return ((old & _PAGE_ACCESSED) != 0); } @@ -542,7 +546,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, if ((pmd_val(*pmdp) & _PAGE_RW) == 0) return; - pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW); + pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0); } #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 65b7b65e8708..62bf5e8e78da 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -510,7 +510,8 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, } unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, unsigned long clr) + pmd_t *pmdp, unsigned long clr, + unsigned long set) { unsigned long old, tmp; @@ -526,14 +527,15 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, andi. %1,%0,%6\n\ bne- 1b \n\ andc %1,%0,%4 \n\ + or %1,%1,%7\n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*pmdp) - : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY) + : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set) : "cc" ); #else old = pmd_val(*pmdp); - *pmdp = __pmd(old & ~clr); + *pmdp = __pmd((old & ~clr) | set); #endif if (old & _PAGE_HASHPTE) hpte_do_hugepage_flush(mm, addr, pmdp); @@ -708,7 +710,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT); + pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0); } /* @@ -835,7 +837,7 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long old; pgtable_t *pgtable_slot; - old = pmd_hugepage_update(mm, addr, pmdp, ~0UL); + old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0); old_pmd = __pmd(old); /* * We have pmd == none and we are holding page_table_lock. diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index a770df2dae70..6c0b1f5f8d2c 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -78,7 +78,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr, pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); for (; npages > 0; --npages) { - pte_update(mm, addr, pte, 0, 0); + pte_update(mm, addr, pte, 0, 0, 0); addr += PAGE_SIZE; ++pte; } -- cgit v1.2.3 From 56eecdb912b536a4fa97fb5bfe5a940a54d79be6 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Feb 2014 09:13:38 +0530 Subject: mm: Use ptep/pmdp_set_numa() for updating _PAGE_NUMA bit Archs like ppc64 doesn't do tlb flush in set_pte/pmd functions when using a hash table MMU for various reasons (the flush is handled as part of the PTE modification when necessary). ppc64 thus doesn't implement flush_tlb_range for hash based MMUs. Additionally ppc64 require the tlb flushing to be batched within ptl locks. The reason to do that is to ensure that the hash page table is in sync with linux page table. We track the hpte index in linux pte and if we clear them without flushing hash and drop the ptl lock, we can have another cpu update the pte and can end up with duplicate entry in the hash table, which is fatal. We also want to keep set_pte_at simpler by not requiring them to do hash flush for performance reason. We do that by assuming that set_pte_at() is never *ever* called on a PTE that is already valid. This was the case until the NUMA code went in which broke that assumption. Fix that by introducing a new pair of helpers to set _PAGE_NUMA in a way similar to ptep/pmdp_set_wrprotect(), with a generic implementation using set_pte_at() and a powerpc specific one using the appropriate mechanism needed to keep the hash table in sync. Acked-by: Mel Gorman Reviewed-by: Rik van Riel Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pgtable.h | 22 +++++++++++++++++++++ include/asm-generic/pgtable.h | 39 ++++++++++++++++++++++++++++++++++++++ mm/huge_memory.c | 9 ++------- mm/mprotect.c | 4 +--- 4 files changed, 64 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index f83b6f3e1b39..3ebb188c3ff5 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -75,12 +75,34 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +#define ptep_set_numa ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + if ((pte_val(*ptep) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0); + return; +} + #define pmd_numa pmd_numa static inline int pmd_numa(pmd_t pmd) { return pte_numa(pmd_pte(pmd)); } +#define pmdp_set_numa pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA); + return; +} + #define pmd_mknonnuma pmd_mknonnuma static inline pmd_t pmd_mknonnuma(pmd_t pmd) { diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 8e4f41d9af4d..34c7bdc06014 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -701,6 +701,18 @@ static inline pte_t pte_mknuma(pte_t pte) } #endif +#ifndef ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t ptent = *ptep; + + ptent = pte_mknuma(ptent); + set_pte_at(mm, addr, ptep, ptent); + return; +} +#endif + #ifndef pmd_mknuma static inline pmd_t pmd_mknuma(pmd_t pmd) { @@ -708,6 +720,18 @@ static inline pmd_t pmd_mknuma(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } #endif + +#ifndef pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + + pmd = pmd_mknuma(pmd); + set_pmd_at(mm, addr, pmdp, pmd); + return; +} +#endif #else extern int pte_numa(pte_t pte); extern int pmd_numa(pmd_t pmd); @@ -715,6 +739,8 @@ extern pte_t pte_mknonnuma(pte_t pte); extern pmd_t pmd_mknonnuma(pmd_t pmd); extern pte_t pte_mknuma(pte_t pte); extern pmd_t pmd_mknuma(pmd_t pmd); +extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); #endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ #else static inline int pmd_numa(pmd_t pmd) @@ -742,10 +768,23 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return; +} + + static inline pmd_t pmd_mknuma(pmd_t pmd) { return pmd; } + +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + return ; +} #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 82166bf974e1..da23eb96779f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1545,6 +1545,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); BUG_ON(pmd_write(entry)); } else { struct page *page = pmd_page(*pmd); @@ -1557,16 +1558,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { - entry = *pmd; - entry = pmd_mknuma(entry); + pmdp_set_numa(mm, addr, pmd); ret = HPAGE_PMD_NR; } } - - /* Set PMD if cleared earlier */ - if (ret == HPAGE_PMD_NR) - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(ptl); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 33eab902f10e..769a67a15803 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -69,12 +69,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } else { struct page *page; - ptent = *pte; page = vm_normal_page(vma, addr, oldpte); if (page && !PageKsm(page)) { if (!pte_numa(oldpte)) { - ptent = pte_mknuma(ptent); - set_pte_at(mm, addr, pte, ptent); + ptep_set_numa(mm, addr, pte); updated = true; } } -- cgit v1.2.3 From a0a4419e302fedb548d56129e02130347810f892 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 12 Feb 2014 17:17:05 +1100 Subject: powerpc: Link VDSOs at 0x0 perf is failing to resolve symbols in the VDSO. A while (1) gettimeofday() loop shows: 93.99% [vdso] [.] 0x00000000000005e0 3.12% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18 2.81% test [.] main The reason for this is that we are linking our VDSO shared libraries at 1MB, which is a little weird. Even though this is uncommon, Alan points out that it is valid and we should probably fix perf userspace. Regardless, I can't see a reason why we are doing this. The code is all position independent and we never rely on the VDSO ending up at 1M (and we never place it there on 64bit tasks). Changing our link address to 0x0 fixes perf VDSO symbol resolution: 73.18% [vdso] [.] 0x000000000000060c 12.39% [vdso] [.] __kernel_gettimeofday 3.58% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18 2.94% [vdso] [.] __kernel_datapage_offset 2.90% test [.] main We still have some local symbol resolution issues that will be fixed in a subsequent patch. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/vdso.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h index 0d9cecddf8a4..c53f5f6d1761 100644 --- a/arch/powerpc/include/asm/vdso.h +++ b/arch/powerpc/include/asm/vdso.h @@ -4,11 +4,11 @@ #ifdef __KERNEL__ /* Default link addresses for the vDSOs */ -#define VDSO32_LBASE 0x100000 -#define VDSO64_LBASE 0x100000 +#define VDSO32_LBASE 0x0 +#define VDSO64_LBASE 0x0 /* Default map addresses for 32bit vDSO */ -#define VDSO32_MBASE VDSO32_LBASE +#define VDSO32_MBASE 0x100000 #define VDSO_VERSION_STRING LINUX_2.6.15 -- cgit v1.2.3 From 24b659a13866b935eca72748ce725279bd3c4466 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 12 Feb 2014 17:18:50 +1100 Subject: powerpc: Use unstripped VDSO image for more accurate profiling data We are seeing a lot of hits in the VDSO that are not resolved by perf. A while(1) gettimeofday() loop shows the issue: 27.64% [vdso] [.] 0x000000000000060c 22.57% [vdso] [.] 0x0000000000000628 16.88% [vdso] [.] 0x0000000000000610 12.39% [vdso] [.] __kernel_gettimeofday 6.09% [vdso] [.] 0x00000000000005f8 3.58% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18 2.94% [vdso] [.] __kernel_datapage_offset 2.90% test [.] main We are using a stripped VDSO image which means only symbols with relocation info can be resolved. There isn't a lot of point to stripping the VDSO, the debug info is only about 1kB: 4680 arch/powerpc/kernel/vdso64/vdso64.so 5815 arch/powerpc/kernel/vdso64/vdso64.so.dbg By using the unstripped image, we can resolve all the symbols in the VDSO and the perf profile data looks much better: 76.53% [vdso] [.] __do_get_tspec 12.20% [vdso] [.] __kernel_gettimeofday 5.05% [vdso] [.] __get_datapage 3.20% test [.] main 2.92% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18 Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/vdso32/vdso32_wrapper.S | 2 +- arch/powerpc/kernel/vdso64/vdso64_wrapper.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S index 79683d0393f5..6ac107ac402a 100644 --- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S @@ -6,7 +6,7 @@ .globl vdso32_start, vdso32_end .balign PAGE_SIZE vdso32_start: - .incbin "arch/powerpc/kernel/vdso32/vdso32.so" + .incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg" .balign PAGE_SIZE vdso32_end: diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S index 8df9e2463007..df60fca6a13d 100644 --- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S @@ -6,7 +6,7 @@ .globl vdso64_start, vdso64_end .balign PAGE_SIZE vdso64_start: - .incbin "arch/powerpc/kernel/vdso64/vdso64.so" + .incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg" .balign PAGE_SIZE vdso64_end: -- cgit v1.2.3 From 5b2e198e50f6ba57081586b853163ea1bb95f1a8 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 12 Feb 2014 15:24:54 +0800 Subject: powerpc/powernv: Rework EEH reset When doing reset in order to recover the affected PE, we issue hot reset on PE primary bus if it's not root bus. Otherwise, we issue hot or fundamental reset on root port or PHB accordingly. For the later case, we didn't cover the situation where PE only includes root port and it potentially causes kernel crash upon EEH error to the PE. The patch reworks the logic of EEH reset to improve the code readability and also avoid the kernel crash. Cc: stable@vger.kernel.org Reported-by: Thadeu Lima de Souza Cascardo Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/eeh-ioda.c | 29 ++++------------------------- 1 file changed, 4 insertions(+), 25 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index e1e71618b70c..fcb79cffdb66 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -489,8 +489,7 @@ static int ioda_eeh_bridge_reset(struct pci_controller *hose, static int ioda_eeh_reset(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; - struct eeh_dev *edev; - struct pci_dev *dev; + struct pci_bus *bus; int ret; /* @@ -519,31 +518,11 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) if (pe->type & EEH_PE_PHB) { ret = ioda_eeh_phb_reset(hose, option); } else { - if (pe->type & EEH_PE_DEVICE) { - /* - * If it's device PE, we didn't refer to the parent - * PCI bus yet. So we have to figure it out indirectly. - */ - edev = list_first_entry(&pe->edevs, - struct eeh_dev, list); - dev = eeh_dev_to_pci_dev(edev); - dev = dev->bus->self; - } else { - /* - * If it's bus PE, the parent PCI bus is already there - * and just pick it up. - */ - dev = pe->bus->self; - } - - /* - * Do reset based on the fact that the direct upstream bridge - * is root bridge (port) or not. - */ - if (dev->bus->number == 0) + bus = eeh_pe_bus_get(pe); + if (pci_is_root_bus(bus)) ret = ioda_eeh_root_reset(hose, option); else - ret = ioda_eeh_bridge_reset(hose, dev, option); + ret = ioda_eeh_bridge_reset(hose, bus->self, option); } return ret; -- cgit v1.2.3 From 2ec5a0adf60c23bb6b0a95d3b96a8c1ff1e1aa5a Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 12 Feb 2014 15:24:55 +0800 Subject: powerpc/eeh: Cleanup on eeh_subsystem_enabled The patch cleans up variable eeh_subsystem_enabled so that we needn't refer the variable directly from external. Instead, we will use function eeh_enabled() and eeh_set_enable() to operate the variable. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 21 +++++++++++++++++++-- arch/powerpc/kernel/eeh.c | 12 ++++++------ arch/powerpc/platforms/powernv/eeh-powernv.c | 2 +- arch/powerpc/platforms/pseries/eeh_pseries.c | 2 +- 4 files changed, 27 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 9e39ceb1d19f..d4dd41fb951b 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -172,10 +172,20 @@ struct eeh_ops { }; extern struct eeh_ops *eeh_ops; -extern int eeh_subsystem_enabled; +extern bool eeh_subsystem_enabled; extern raw_spinlock_t confirm_error_lock; extern int eeh_probe_mode; +static inline bool eeh_enabled(void) +{ + return eeh_subsystem_enabled; +} + +static inline void eeh_set_enable(bool mode) +{ + eeh_subsystem_enabled = mode; +} + #define EEH_PROBE_MODE_DEV (1<<0) /* From PCI device */ #define EEH_PROBE_MODE_DEVTREE (1<<1) /* From device tree */ @@ -246,7 +256,7 @@ void eeh_remove_device(struct pci_dev *); * If this macro yields TRUE, the caller relays to eeh_check_failure() * which does further tests out of line. */ -#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_subsystem_enabled) +#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_enabled()) /* * Reads from a device which has been isolated by EEH will return @@ -257,6 +267,13 @@ void eeh_remove_device(struct pci_dev *); #else /* !CONFIG_EEH */ +static inline bool eeh_enabled(void) +{ + return false; +} + +static inline void eeh_set_enable(bool mode) { } + static inline int eeh_init(void) { return 0; diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 148db72a8c43..f22f7b6f6b01 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -89,7 +89,7 @@ /* Platform dependent EEH operations */ struct eeh_ops *eeh_ops = NULL; -int eeh_subsystem_enabled; +bool eeh_subsystem_enabled = false; EXPORT_SYMBOL(eeh_subsystem_enabled); /* @@ -364,7 +364,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) eeh_stats.total_mmio_ffs++; - if (!eeh_subsystem_enabled) + if (!eeh_enabled()) return 0; if (!edev) { @@ -822,7 +822,7 @@ int eeh_init(void) return ret; } - if (eeh_subsystem_enabled) + if (eeh_enabled()) pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); else pr_warning("EEH: No capable adapters found\n"); @@ -897,7 +897,7 @@ void eeh_add_device_late(struct pci_dev *dev) struct device_node *dn; struct eeh_dev *edev; - if (!dev || !eeh_subsystem_enabled) + if (!dev || !eeh_enabled()) return; pr_debug("EEH: Adding device %s\n", pci_name(dev)); @@ -1005,7 +1005,7 @@ void eeh_remove_device(struct pci_dev *dev) { struct eeh_dev *edev; - if (!dev || !eeh_subsystem_enabled) + if (!dev || !eeh_enabled()) return; edev = pci_dev_to_eeh_dev(dev); @@ -1045,7 +1045,7 @@ void eeh_remove_device(struct pci_dev *dev) static int proc_eeh_show(struct seq_file *m, void *v) { - if (0 == eeh_subsystem_enabled) { + if (!eeh_enabled()) { seq_printf(m, "EEH Subsystem is globally disabled\n"); seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs); } else { diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index a79fddc5e74e..a59788e83b8b 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -145,7 +145,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * Enable EEH explicitly so that we will do EEH check * while accessing I/O stuff */ - eeh_subsystem_enabled = 1; + eeh_set_enable(true); /* Save memory bars */ eeh_save_bars(edev); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 9ef3cc8ebc11..8a8f0472d98f 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -265,7 +265,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) enable = 1; if (enable) { - eeh_subsystem_enabled = 1; + eeh_set_enable(true); eeh_add_to_parent_pe(edev); pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n", -- cgit v1.2.3 From 66f9af83e56bfa12964d251df9d60fb571579913 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 12 Feb 2014 15:24:56 +0800 Subject: powerpc/eeh: Disable EEH on reboot We possiblly detect EEH errors during reboot, particularly in kexec path, but it's impossible for device drivers and EEH core to handle or recover them properly. The patch registers one reboot notifier for EEH and disable EEH subsystem during reboot. That means the EEH errors is going to be cleared by hardware reset or second kernel during early stage of PCI probe. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh.c | 20 ++++++++++++++++++++ arch/powerpc/platforms/powernv/eeh-ioda.c | 3 ++- 2 files changed, 22 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index f22f7b6f6b01..e7b76a6bf150 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -747,6 +748,17 @@ int __exit eeh_ops_unregister(const char *name) return -EEXIST; } +static int eeh_reboot_notifier(struct notifier_block *nb, + unsigned long action, void *unused) +{ + eeh_set_enable(false); + return NOTIFY_DONE; +} + +static struct notifier_block eeh_reboot_nb = { + .notifier_call = eeh_reboot_notifier, +}; + /** * eeh_init - EEH initialization * @@ -778,6 +790,14 @@ int eeh_init(void) if (machine_is(powernv) && cnt++ <= 0) return ret; + /* Register reboot notifier */ + ret = register_reboot_notifier(&eeh_reboot_nb); + if (ret) { + pr_warn("%s: Failed to register notifier (%d)\n", + __func__, ret); + return ret; + } + /* call platform initialization function */ if (!eeh_ops) { pr_warning("%s: Platform EEH operation not found\n", diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index fcb79cffdb66..f51474336460 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -44,7 +44,8 @@ static int ioda_eeh_event(struct notifier_block *nb, /* We simply send special EEH event */ if ((changed_evts & OPAL_EVENT_PCI_ERROR) && - (events & OPAL_EVENT_PCI_ERROR)) + (events & OPAL_EVENT_PCI_ERROR) && + eeh_enabled()) eeh_send_failure_event(NULL); return 0; -- cgit v1.2.3 From e306dfd06fcb44d21c80acb8e5a88d55f3d1cf63 Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Fri, 14 Feb 2014 19:35:15 +0000 Subject: ARM64: unwind: Fix PC calculation The frame PC value in the unwind code used to just take the saved LR value and use that. That's incorrect as a stack trace, since it shows the return path stack, not the call path stack. In particular, it shows faulty information in case the bl is done as the very last instruction of one label, since the return point will be in the next label. That can easily be seen with tail calls to panic(), which is marked __noreturn and thus doesn't have anything useful after it. Easiest here is to just correct the unwind code and do a -4, to get the actual call site for the backtrace instead of the return site. Signed-off-by: Olof Johansson Cc: stable@vger.kernel.org Signed-off-by: Catalin Marinas --- arch/arm64/kernel/stacktrace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index c3b6c63ea5fb..38f0558f0c0a 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -48,7 +48,11 @@ int unwind_frame(struct stackframe *frame) frame->sp = fp + 0x10; frame->fp = *(unsigned long *)(fp); - frame->pc = *(unsigned long *)(fp + 8); + /* + * -4 here because we care about the PC at time of bl, + * not where the return will go. + */ + frame->pc = *(unsigned long *)(fp + 8) - 4; return 0; } -- cgit v1.2.3 From 5745d6a41a4f4aec29e2ccd591c6fb09ed73a955 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Fri, 10 Jan 2014 09:29:39 -0500 Subject: avr32: fix missing module.h causing build failure in mimc200/fram.c Causing this: In file included from arch/avr32/boards/mimc200/fram.c:13: include/linux/miscdevice.h:51: error: field 'list' has incomplete type include/linux/miscdevice.h:55: error: expected specifier-qualifier-list before 'mode_t' arch/avr32/boards/mimc200/fram.c:42: error: 'THIS_MODULE' undeclared here (not in a function) Reported-by: Fengguang Wu Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Signed-off-by: Paul Gortmaker Signed-off-by: Sergei Trofimovich Acked-by: Hans-Christian Egtvedt Cc: stable@vger.kernel.org --- arch/avr32/boards/mimc200/fram.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/avr32/boards/mimc200/fram.c b/arch/avr32/boards/mimc200/fram.c index 9764a1a1073e..c1466a872b9c 100644 --- a/arch/avr32/boards/mimc200/fram.c +++ b/arch/avr32/boards/mimc200/fram.c @@ -11,6 +11,7 @@ #define FRAM_VERSION "1.0" #include +#include #include #include #include -- cgit v1.2.3 From 8d80390cfc9434d5aa4fb9e5f9768a66b30cb8a6 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Sat, 1 Feb 2014 20:35:54 +0800 Subject: avr32: Makefile: add '-D__linux__' flag for gcc-4.4.7 use For avr32 cross compiler, do not define '__linux__' internally, so it will cause issue with allmodconfig. The related error: CC [M] fs/coda/psdev.o In file included from include/linux/coda.h:64, from fs/coda/psdev.c:45: include/uapi/linux/coda.h:221: error: expected specifier-qualifier-list before 'u_quad_t' The related toolchain version (which only download, not re-compile): [root@gchen linux-next]# /upstream/toolchain/download/avr32-gnu-toolchain-linux_x86/bin/avr32-gcc -v Using built-in specs. Target: avr32 Configured with: /data2/home/toolsbuild/jenkins-knuth/workspace/avr32-gnu-toolchain/src/gcc/configure --target=avr32 --host=i686-pc-linux-gnu --build=x86_64-pc-linux-gnu --prefix=/home/toolsbuild/jenkins-knuth/workspace/avr32-gnu-toolchain/avr32-gnu-toolchain-linux_x86 --enable-languages=c,c++ --disable-nls --disable-libssp --disable-libstdcxx-pch --with-dwarf2 --enable-version-specific-runtime-libs --disable-shared --enable-doc --with-mpfr-lib=/home/toolsbuild/jenkins-knuth/workspace/avr32-gnu-toolchain/avr32-gnu-toolchain-linux_x86/lib --with-mpfr-include=/home/toolsbuild/jenkins-knuth/workspace/avr32-gnu-toolchain/avr32-gnu-toolchain-linux_x86/include --with-gmp=/home/toolsbuild/jenkins-knuth/workspace/avr32-gnu-toolchain/avr32-gnu-toolchain-linux_x86 --with-mpc=/home/toolsbuild/jenkins-knuth/workspace/avr32-gnu-toolchain/avr32-gnu-toolchain-linux_x86 --enable-__cxa_atexit --disable-shared --with-newlib --with-pkgversion=AVR_32_bit_GNU_Toolchain_3.4.2_435 --with-bugurl=http://www .atmel.com/avr Thread model: single gcc version 4.4.7 (AVR_32_bit_GNU_Toolchain_3.4.2_435) Signed-off-by: Chen Gang Acked-by: Hans-Christian Egtvedt Cc: stable@vger.kernel.org --- arch/avr32/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/avr32/Makefile b/arch/avr32/Makefile index 22fb66590dcd..dba48a5d5bb9 100644 --- a/arch/avr32/Makefile +++ b/arch/avr32/Makefile @@ -11,7 +11,7 @@ all: uImage vmlinux.elf KBUILD_DEFCONFIG := atstk1002_defconfig -KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic +KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic -D__linux__ KBUILD_AFLAGS += -mrelax -mno-pic KBUILD_CFLAGS_MODULE += -mno-relax LDFLAGS_vmlinux += --relax -- cgit v1.2.3 From 1bbce4f3d11a6bfac0c51800f6337766f82b42da Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Sun, 16 Feb 2014 19:39:30 +0800 Subject: avr32: add generic ioremap_wc() definition in io.h Need generic ioremap_wc(), or can not pass compiling with allmodconfig, the related error: CC [M] drivers/gpu/drm/drm_bufs.o drivers/gpu/drm/drm_bufs.c: In function 'drm_addmap_core': drivers/gpu/drm/drm_bufs.c:217: error: implicit declaration of function 'ioremap_wc' drivers/gpu/drm/drm_bufs.c:218: warning: assignment makes pointer from integer without a cast Signed-off-by: Chen Gang Acked-by: Hans-Christian Egtvedt --- arch/avr32/include/asm/io.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h index fc6483f83ccc..4f5ec2bb7172 100644 --- a/arch/avr32/include/asm/io.h +++ b/arch/avr32/include/asm/io.h @@ -295,6 +295,8 @@ extern void __iounmap(void __iomem *addr); #define iounmap(addr) \ __iounmap(addr) +#define ioremap_wc ioremap_nocache + #define cached(addr) P1SEGADDR(addr) #define uncached(addr) P2SEGADDR(addr) -- cgit v1.2.3 From d7668f9d448aa757971ec3e68ecedb5ebecbddcc Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Sun, 16 Feb 2014 19:36:06 +0800 Subject: avr32: add generic vga.h to Kbuild Need add generic "vga.h", or can not pass building for allmodconfig, the related error: CC [M] drivers/gpu/drm/drm_irq.o In file included from include/linux/vgaarb.h:34, from drivers/gpu/drm/drm_irq.c:42: include/video/vga.h:22:21: error: asm/vga.h: No such file or directory Signed-off-by: Chen Gang Acked-by: Hans-Christian Egtvedt --- arch/avr32/include/asm/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index cfb9fe1b8df9..c7c64a63c29f 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -17,5 +17,6 @@ generic-y += scatterlist.h generic-y += sections.h generic-y += topology.h generic-y += trace_clock.h +generic-y += vga.h generic-y += xor.h generic-y += hash.h -- cgit v1.2.3 From 39544ac9df20f73e49fc6b9ac19ff533388c82c0 Mon Sep 17 00:00:00 2001 From: Vinayak Kale Date: Wed, 12 Feb 2014 07:30:01 +0100 Subject: ARM: 7957/1: add DSB after icache flush in __flush_icache_all() Add DSB after icache flush to complete the cache maintenance operation. Signed-off-by: Vinayak Kale Acked-by: Catalin Marinas Cc: Signed-off-by: Russell King --- arch/arm/include/asm/cacheflush.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index e9a49fe0284e..8b8b61685a34 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -212,6 +212,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, static inline void __flush_icache_all(void) { __flush_icache_preferred(); + dsb(); } /* -- cgit v1.2.3 From ae10f8329f9b22d650aa12307b260eba2bc0c571 Mon Sep 17 00:00:00 2001 From: Jason Cooper Date: Mon, 17 Feb 2014 19:09:58 +0000 Subject: ARM: dove: dt: revert PMU interrupt controller node The corresponding driver didn't make it into v3.14, so we need to remove the node. Dove systems fail to boot with the node present and no driver. This node will be re-added when the driver makes it to mainline. Reported-by: Jean-Francois Moine Tested-by: Jean-Francois Moine Signed-off-by: Jason Cooper --- arch/arm/boot/dts/dove.dtsi | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi index 2b76524f4aa7..187fd46b7b5e 100644 --- a/arch/arm/boot/dts/dove.dtsi +++ b/arch/arm/boot/dts/dove.dtsi @@ -379,15 +379,6 @@ #clock-cells = <1>; }; - pmu_intc: pmu-interrupt-ctrl@d0050 { - compatible = "marvell,dove-pmu-intc"; - interrupt-controller; - #interrupt-cells = <1>; - reg = <0xd0050 0x8>; - interrupts = <33>; - marvell,#interrupts = <7>; - }; - pinctrl: pin-ctrl@d0200 { compatible = "marvell,dove-pinctrl"; reg = <0xd0200 0x10>; @@ -610,8 +601,6 @@ rtc: real-time-clock@d8500 { compatible = "marvell,orion-rtc"; reg = <0xd8500 0x20>; - interrupt-parent = <&pmu_intc>; - interrupts = <5>; }; gpio2: gpio-ctrl@e8400 { -- cgit v1.2.3 From 763fbff2bef5d5db5a993b54c29c841432e056ec Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Thu, 13 Feb 2014 17:18:26 -0700 Subject: ARM: tegra: fix RTC0 alias for Cardhu This alias entry was evidently cut/paste from a different board, and not correctly updated to match Cardhu. Fix this. Fixes: 553c0a200e20 ("ARM: tegra: set up /aliases entries for RTCs") Signed-off-by: Stephen Warren Signed-off-by: Olof Johansson --- arch/arm/boot/dts/tegra30-cardhu.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/tegra30-cardhu.dtsi b/arch/arm/boot/dts/tegra30-cardhu.dtsi index 9104224124ee..1e156d9d0506 100644 --- a/arch/arm/boot/dts/tegra30-cardhu.dtsi +++ b/arch/arm/boot/dts/tegra30-cardhu.dtsi @@ -28,7 +28,7 @@ compatible = "nvidia,cardhu", "nvidia,tegra30"; aliases { - rtc0 = "/i2c@7000d000/tps6586x@34"; + rtc0 = "/i2c@7000d000/tps65911@2d"; rtc1 = "/rtc@7000e000"; }; -- cgit v1.2.3 From 28a9f3b078c545064dcf4b46d2c6917554d1642e Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Tue, 18 Feb 2014 10:35:05 +0800 Subject: ARM: imx6: build pm-imx6q.c independently of CONFIG_PM When building a kernel image with only CONFIG_CPU_IDLE but no CONFIG_PM, we will get the following link error. LD init/built-in.o arch/arm/mach-imx/built-in.o: In function `imx6q_enter_wait': platform-spi_imx.c:(.text+0x25c0): undefined reference to `imx6q_set_lpm' platform-spi_imx.c:(.text+0x25d4): undefined reference to `imx6q_set_lpm' arch/arm/mach-imx/built-in.o: In function `imx6q_cpuidle_init': platform-spi_imx.c:(.init.text+0x75d4): undefined reference to `imx6q_set_chicken_bit' make[1]: *** [vmlinux] Error 1 Since pm-imx6q.c has been a collection of library functions that access CCM low-power registers used by not only suspend but also cpuidle and other drivers, let's build pm-imx6q.c independently of CONFIG_PM to fix above error. Reported-by: Lucas Stach Signed-off-by: Shawn Guo Cc: stable@vger.kernel.org Acked-by: Christian Gmeiner Signed-off-by: Olof Johansson --- arch/arm/mach-imx/Makefile | 2 -- arch/arm/mach-imx/common.h | 4 +--- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index befcaf5d0574..ec419649320f 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -101,11 +101,9 @@ obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o obj-$(CONFIG_SOC_IMX6Q) += clk-imx6q.o mach-imx6q.o obj-$(CONFIG_SOC_IMX6SL) += clk-imx6sl.o mach-imx6sl.o -ifeq ($(CONFIG_PM),y) obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o headsmp.o # i.MX6SL reuses i.MX6Q code obj-$(CONFIG_SOC_IMX6SL) += pm-imx6q.o headsmp.o -endif # i.MX5 based machines obj-$(CONFIG_MACH_MX51_BABBAGE) += mach-mx51_babbage.o diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 59c3b9b26bb4..baf439dc22d8 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -144,13 +144,11 @@ void imx6q_set_chicken_bit(void); void imx_cpu_die(unsigned int cpu); int imx_cpu_kill(unsigned int cpu); -#ifdef CONFIG_PM void imx6q_pm_init(void); void imx6q_pm_set_ccm_base(void __iomem *base); +#ifdef CONFIG_PM void imx5_pm_init(void); #else -static inline void imx6q_pm_init(void) {} -static inline void imx6q_pm_set_ccm_base(void __iomem *base) {} static inline void imx5_pm_init(void) {} #endif -- cgit v1.2.3 From 688b56b485578465f6619b9529d08c2b95641915 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Tue, 18 Feb 2014 23:03:31 +0100 Subject: ARM: tegra: Add head numbers to display controllers The number of the head specifies the index of the display controller unit and is required to properly configure outputs so that they receive video data from the correct source. Signed-off-by: Thierry Reding Acked-by: Stephen Warren Signed-off-by: Olof Johansson --- arch/arm/boot/dts/tegra114.dtsi | 4 ++++ arch/arm/boot/dts/tegra20.dtsi | 4 ++++ arch/arm/boot/dts/tegra30.dtsi | 4 ++++ 3 files changed, 12 insertions(+) (limited to 'arch') diff --git a/arch/arm/boot/dts/tegra114.dtsi b/arch/arm/boot/dts/tegra114.dtsi index 389e987ec281..44ec401ec366 100644 --- a/arch/arm/boot/dts/tegra114.dtsi +++ b/arch/arm/boot/dts/tegra114.dtsi @@ -57,6 +57,8 @@ resets = <&tegra_car 27>; reset-names = "dc"; + nvidia,head = <0>; + rgb { status = "disabled"; }; @@ -72,6 +74,8 @@ resets = <&tegra_car 26>; reset-names = "dc"; + nvidia,head = <1>; + rgb { status = "disabled"; }; diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi index 480ecda3416b..48d2a7f4d0c0 100644 --- a/arch/arm/boot/dts/tegra20.dtsi +++ b/arch/arm/boot/dts/tegra20.dtsi @@ -94,6 +94,8 @@ resets = <&tegra_car 27>; reset-names = "dc"; + nvidia,head = <0>; + rgb { status = "disabled"; }; @@ -109,6 +111,8 @@ resets = <&tegra_car 26>; reset-names = "dc"; + nvidia,head = <1>; + rgb { status = "disabled"; }; diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi index ed8e7700b46d..19a84e933f4e 100644 --- a/arch/arm/boot/dts/tegra30.dtsi +++ b/arch/arm/boot/dts/tegra30.dtsi @@ -170,6 +170,8 @@ resets = <&tegra_car 27>; reset-names = "dc"; + nvidia,head = <0>; + rgb { status = "disabled"; }; @@ -185,6 +187,8 @@ resets = <&tegra_car 26>; reset-names = "dc"; + nvidia,head = <1>; + rgb { status = "disabled"; }; -- cgit v1.2.3 From 8859685785bfafadf9bc922dd3a2278e59886947 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Tue, 18 Feb 2014 16:51:58 -0700 Subject: ARM: tegra: only run PL310 init on systems with one Fix tegra_init_cache() to check whether the system has a PL310 cache before touching the PL310 registers. This prevents access to non-existent registers on Tegra114 and later. Note for stable kernels: In <= v3.12, the file to patch is arch/arm/mach-tegra/common.c. Cc: # v3.9+ Signed-off-by: Stephen Warren Signed-off-by: Olof Johansson --- arch/arm/mach-tegra/tegra.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'arch') diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c index 303a285d80fd..6191603379e1 100644 --- a/arch/arm/mach-tegra/tegra.c +++ b/arch/arm/mach-tegra/tegra.c @@ -73,10 +73,20 @@ u32 tegra_uart_config[3] = { static void __init tegra_init_cache(void) { #ifdef CONFIG_CACHE_L2X0 + static const struct of_device_id pl310_ids[] __initconst = { + { .compatible = "arm,pl310-cache", }, + {} + }; + + struct device_node *np; int ret; void __iomem *p = IO_ADDRESS(TEGRA_ARM_PERIF_BASE) + 0x3000; u32 aux_ctrl, cache_type; + np = of_find_matching_node(NULL, pl310_ids); + if (!np) + return; + cache_type = readl(p + L2X0_CACHE_TYPE); aux_ctrl = (cache_type & 0x700) << (17-8); aux_ctrl |= 0x7C400001; -- cgit v1.2.3 From 5f0e030930d715920be4de638084aaf8653867e8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 19 Feb 2014 13:52:29 +0200 Subject: x86, tsc: Fallback to normal calibration if fast MSR calibration fails If we cannot calibrate TSC via MSR based calibration try_msr_calibrate_tsc() stores zero to fast_calibrate and returns that to the caller. This value gets then propagated further to clockevents code resulting division by zero oops like the one below: divide error: 0000 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 3.13.0+ #47 task: ffff880075508000 ti: ffff880075506000 task.ti: ffff880075506000 RIP: 0010:[] [] clockevents_config.part.3+0x24/0xa0 RSP: 0000:ffff880075507e58 EFLAGS: 00010246 RAX: ffffffffffffffff RBX: ffff880079c0cd80 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffffffffffff RBP: ffff880075507e70 R08: 0000000000000001 R09: 00000000000000be R10: 00000000000000bd R11: 0000000000000003 R12: 000000000000b008 R13: 0000000000000008 R14: 000000000000b010 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff880079c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff880079fff000 CR3: 0000000001c0b000 CR4: 00000000001006f0 Stack: ffff880079c0cd80 000000000000b008 0000000000000008 ffff880075507e88 ffffffff810aecb0 ffff880079c0cd80 ffff880075507e98 ffffffff81030168 ffff880075507ed8 ffffffff81d1104f 00000000000000c3 0000000000000000 Call Trace: [] clockevents_config_and_register+0x20/0x30 [] setup_APIC_timer+0xc8/0xd0 [] setup_boot_APIC_clock+0x4cc/0x4d8 [] native_smp_prepare_cpus+0x3dd/0x3f0 [] kernel_init_freeable+0xc3/0x205 [] ? rest_init+0x90/0x90 [] kernel_init+0xe/0x120 [] ret_from_fork+0x7c/0xb0 [] ? rest_init+0x90/0x90 Prevent this from happening by: 1) Modifying try_msr_calibrate_tsc() to return calibration value or zero if it fails. 2) Check this return value in native_calibrate_tsc() and in case of zero fallback to use normal non-MSR based calibration. [mw: Added subject and changelog] Reported-and-tested-by: Mika Westerberg Signed-off-by: Thomas Gleixner Cc: Bin Gao Cc: One Thousand Gnomes Cc: Ingo Molnar Cc: H. Peter Anvin Link: http://lkml.kernel.org/r/1392810750-18660-1-git-send-email-mika.westerberg@linux.intel.com Signed-off-by: Mika Westerberg Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/tsc.h | 2 +- arch/x86/kernel/tsc.c | 7 ++----- arch/x86/kernel/tsc_msr.c | 28 ++++++++++++++-------------- 3 files changed, 17 insertions(+), 20 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 57ae63cd6ee2..94605c0e9cee 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -66,6 +66,6 @@ extern void tsc_save_sched_clock_state(void); extern void tsc_restore_sched_clock_state(void); /* MSR based TSC calibration for Intel Atom SoC platforms */ -int try_msr_calibrate_tsc(unsigned long *fast_calibrate); +unsigned long try_msr_calibrate_tsc(void); #endif /* _ASM_X86_TSC_H */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index acb3b606613e..cfbe99f88830 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -653,13 +653,10 @@ unsigned long native_calibrate_tsc(void) /* Calibrate TSC using MSR for Intel Atom SoCs */ local_irq_save(flags); - i = try_msr_calibrate_tsc(&fast_calibrate); + fast_calibrate = try_msr_calibrate_tsc(); local_irq_restore(flags); - if (i >= 0) { - if (i == 0) - pr_warn("Fast TSC calibration using MSR failed\n"); + if (fast_calibrate) return fast_calibrate; - } local_irq_save(flags); fast_calibrate = quick_pit_calibrate(); diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 8b5434f4389f..5dfff5809e74 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -77,21 +77,18 @@ static int match_cpu(u8 family, u8 model) /* * Do MSR calibration only for known/supported CPUs. - * Return values: - * -1: CPU is unknown/unsupported for MSR based calibration - * 0: CPU is known/supported, but calibration failed - * 1: CPU is known/supported, and calibration succeeded + * + * Returns the calibration value or 0 if MSR calibration failed. */ -int try_msr_calibrate_tsc(unsigned long *fast_calibrate) +unsigned long try_msr_calibrate_tsc(void) { - int cpu_index; u32 lo, hi, ratio, freq_id, freq; + unsigned long res; + int cpu_index; cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model); if (cpu_index < 0) - return -1; - - *fast_calibrate = 0; + return 0; if (freq_desc_tables[cpu_index].msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); @@ -103,7 +100,7 @@ int try_msr_calibrate_tsc(unsigned long *fast_calibrate) pr_info("Maximum core-clock to bus-clock ratio: 0x%x\n", ratio); if (!ratio) - return 0; + goto fail; /* Get FSB FREQ ID */ rdmsr(MSR_FSB_FREQ, lo, hi); @@ -112,16 +109,19 @@ int try_msr_calibrate_tsc(unsigned long *fast_calibrate) pr_info("Resolved frequency ID: %u, frequency: %u KHz\n", freq_id, freq); if (!freq) - return 0; + goto fail; /* TSC frequency = maximum resolved freq * maximum resolved bus ratio */ - *fast_calibrate = freq * ratio; - pr_info("TSC runs at %lu KHz\n", *fast_calibrate); + res = freq * ratio; + pr_info("TSC runs at %lu KHz\n", res); #ifdef CONFIG_X86_LOCAL_APIC lapic_timer_frequency = (freq * 1000) / HZ; pr_info("lapic_timer_frequency = %d\n", lapic_timer_frequency); #endif + return res; - return 1; +fail: + pr_warn("Fast TSC calibration using MSR failed\n"); + return 0; } -- cgit v1.2.3 From 3e11e818bfd7bd4a8e1214970337bab73ffed32d Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 19 Feb 2014 13:52:30 +0200 Subject: x86: tsc: Add missing Baytrail frequency to the table Intel Baytrail is based on Silvermont core so MSR_FSB_FREQ[2:0] == 0 means that the CPU reference clock runs at 83.3MHz. Add this missing frequency to the table. Signed-off-by: Mika Westerberg Cc: Bin Gao Cc: One Thousand Gnomes Cc: Ingo Molnar Cc: H. Peter Anvin Link: http://lkml.kernel.org/r/1392810750-18660-2-git-send-email-mika.westerberg@linux.intel.com Signed-off-by: Thomas Gleixner --- arch/x86/kernel/tsc_msr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 5dfff5809e74..92ae6acac8a7 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -53,7 +53,7 @@ static struct freq_desc freq_desc_tables[] = { /* TNG */ { 6, 0x4a, 1, { 0, FREQ_100, FREQ_133, 0, 0, 0, 0, 0 } }, /* VLV2 */ - { 6, 0x37, 1, { 0, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } }, + { 6, 0x37, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } }, /* ANN */ { 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } }, }; -- cgit v1.2.3 From 4f6500fff5f7644a03c46728fd7ef0f62fa6940b Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 13 Feb 2014 13:57:44 -0500 Subject: sparc32: fix build failure for arch_jump_label_transform In arch/sparc/Kernel/Makefile, we see: obj-$(CONFIG_SPARC64) += jump_label.o However, the Kconfig selects HAVE_ARCH_JUMP_LABEL unconditionally for all SPARC. This in turn leads to the following failure when doing allmodconfig coverage builds: kernel/built-in.o: In function `__jump_label_update': jump_label.c:(.text+0x8560c): undefined reference to `arch_jump_label_transform' kernel/built-in.o: In function `arch_jump_label_transform_static': (.text+0x85cf4): undefined reference to `arch_jump_label_transform' make: *** [vmlinux] Error 1 Change HAVE_ARCH_JUMP_LABEL to be conditional on SPARC64 so that it matches the Makefile. Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- arch/sparc/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c51efdcd07a2..7d8b7e94b93b 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -27,7 +27,7 @@ config SPARC select RTC_DRV_M48T59 select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG - select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_JUMP_LABEL if SPARC64 select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_PCI_IOMAP -- cgit v1.2.3 From a56b072fa357ab076cb6c9b52e58fbe3c709da10 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 13 Feb 2014 16:15:01 -0500 Subject: sparc32: make copy_to/from_user_page() usable from modular code While copy_to/from_user_page() users are uncommon, there is one in drivers/staging/lustre/lustre/libcfs/linux/linux-curproc.c which leads to the following: ERROR: "sparc32_cachetlb_ops" [drivers/staging/lustre/lustre/libcfs/libcfs.ko] undefined! during routine allmodconfig build coverage. The reason this happens is as follows: In arch/sparc/include/asm/cacheflush_32.h we have: #define flush_cache_page(vma,addr,pfn) \ sparc32_cachetlb_ops->cache_page(vma, addr) #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ flush_cache_page(vma, vaddr, page_to_pfn(page));\ memcpy(dst, src, len); \ } while (0) #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ do { \ flush_cache_page(vma, vaddr, page_to_pfn(page));\ memcpy(dst, src, len); \ } while (0) However, sparc32_cachetlb_ops isn't exported and hence the error. Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- arch/sparc/mm/srmmu.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index 869023abe5a4..cfbe53c17b0d 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -62,6 +63,7 @@ extern unsigned long last_valid_pfn; static pgd_t *srmmu_swapper_pg_dir; const struct sparc32_cachetlb_ops *sparc32_cachetlb_ops; +EXPORT_SYMBOL(sparc32_cachetlb_ops); #ifdef CONFIG_SMP const struct sparc32_cachetlb_ops *local_ops; -- cgit v1.2.3 From b5190516b282bee6f10569c3387d16f83447d280 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 18 Feb 2014 21:46:16 +0000 Subject: of: Move testcase FDT data into drivers/of The testcase data is usable by any platform. This patch moves it into the drivers/of directory so it can be included by any architecture. Using the test cases requires manually adding #include to the end of the boards .dtsi file and enabling CONFIG_OF_SELFTEST. Not pretty though. A useful project would be to make the testcase code easier to execute. Signed-off-by: Grant Likely --- arch/arm/boot/dts/testcases/tests-interrupts.dtsi | 58 ----------------------- arch/arm/boot/dts/testcases/tests-phandle.dtsi | 39 --------------- arch/arm/boot/dts/testcases/tests.dtsi | 2 - arch/arm/boot/dts/versatile-pb.dts | 4 +- drivers/of/testcase-data/testcases.dtsi | 2 + drivers/of/testcase-data/tests-interrupts.dtsi | 58 +++++++++++++++++++++++ drivers/of/testcase-data/tests-phandle.dtsi | 39 +++++++++++++++ scripts/Makefile.lib | 1 + 8 files changed, 102 insertions(+), 101 deletions(-) delete mode 100644 arch/arm/boot/dts/testcases/tests-interrupts.dtsi delete mode 100644 arch/arm/boot/dts/testcases/tests-phandle.dtsi delete mode 100644 arch/arm/boot/dts/testcases/tests.dtsi create mode 100644 drivers/of/testcase-data/testcases.dtsi create mode 100644 drivers/of/testcase-data/tests-interrupts.dtsi create mode 100644 drivers/of/testcase-data/tests-phandle.dtsi (limited to 'arch') diff --git a/arch/arm/boot/dts/testcases/tests-interrupts.dtsi b/arch/arm/boot/dts/testcases/tests-interrupts.dtsi deleted file mode 100644 index c843720bd3e5..000000000000 --- a/arch/arm/boot/dts/testcases/tests-interrupts.dtsi +++ /dev/null @@ -1,58 +0,0 @@ - -/ { - testcase-data { - interrupts { - #address-cells = <1>; - #size-cells = <1>; - test_intc0: intc0 { - interrupt-controller; - #interrupt-cells = <1>; - }; - - test_intc1: intc1 { - interrupt-controller; - #interrupt-cells = <3>; - }; - - test_intc2: intc2 { - interrupt-controller; - #interrupt-cells = <2>; - }; - - test_intmap0: intmap0 { - #interrupt-cells = <1>; - #address-cells = <0>; - interrupt-map = <1 &test_intc0 9>, - <2 &test_intc1 10 11 12>, - <3 &test_intc2 13 14>, - <4 &test_intc2 15 16>; - }; - - test_intmap1: intmap1 { - #interrupt-cells = <2>; - interrupt-map = <0x5000 1 2 &test_intc0 15>; - }; - - interrupts0 { - interrupt-parent = <&test_intc0>; - interrupts = <1>, <2>, <3>, <4>; - }; - - interrupts1 { - interrupt-parent = <&test_intmap0>; - interrupts = <1>, <2>, <3>, <4>; - }; - - interrupts-extended0 { - reg = <0x5000 0x100>; - interrupts-extended = <&test_intc0 1>, - <&test_intc1 2 3 4>, - <&test_intc2 5 6>, - <&test_intmap0 1>, - <&test_intmap0 2>, - <&test_intmap0 3>, - <&test_intmap1 1 2>; - }; - }; - }; -}; diff --git a/arch/arm/boot/dts/testcases/tests-phandle.dtsi b/arch/arm/boot/dts/testcases/tests-phandle.dtsi deleted file mode 100644 index 0007d3cd7dc2..000000000000 --- a/arch/arm/boot/dts/testcases/tests-phandle.dtsi +++ /dev/null @@ -1,39 +0,0 @@ - -/ { - testcase-data { - phandle-tests { - provider0: provider0 { - #phandle-cells = <0>; - }; - - provider1: provider1 { - #phandle-cells = <1>; - }; - - provider2: provider2 { - #phandle-cells = <2>; - }; - - provider3: provider3 { - #phandle-cells = <3>; - }; - - consumer-a { - phandle-list = <&provider1 1>, - <&provider2 2 0>, - <0>, - <&provider3 4 4 3>, - <&provider2 5 100>, - <&provider0>, - <&provider1 7>; - phandle-list-names = "first", "second", "third"; - - phandle-list-bad-phandle = <12345678 0 0>; - phandle-list-bad-args = <&provider2 1 0>, - <&provider3 0>; - empty-property; - unterminated-string = [40 41 42 43]; - }; - }; - }; -}; diff --git a/arch/arm/boot/dts/testcases/tests.dtsi b/arch/arm/boot/dts/testcases/tests.dtsi deleted file mode 100644 index 3f123ecc9dd7..000000000000 --- a/arch/arm/boot/dts/testcases/tests.dtsi +++ /dev/null @@ -1,2 +0,0 @@ -/include/ "tests-phandle.dtsi" -/include/ "tests-interrupts.dtsi" diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index f43907c40c93..65f657711323 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -1,4 +1,4 @@ -/include/ "versatile-ab.dts" +#include / { model = "ARM Versatile PB"; @@ -47,4 +47,4 @@ }; }; -/include/ "testcases/tests.dtsi" +#include diff --git a/drivers/of/testcase-data/testcases.dtsi b/drivers/of/testcase-data/testcases.dtsi new file mode 100644 index 000000000000..3cc2f55534ac --- /dev/null +++ b/drivers/of/testcase-data/testcases.dtsi @@ -0,0 +1,2 @@ +#include "tests-phandle.dtsi" +#include "tests-interrupts.dtsi" diff --git a/drivers/of/testcase-data/tests-interrupts.dtsi b/drivers/of/testcase-data/tests-interrupts.dtsi new file mode 100644 index 000000000000..c843720bd3e5 --- /dev/null +++ b/drivers/of/testcase-data/tests-interrupts.dtsi @@ -0,0 +1,58 @@ + +/ { + testcase-data { + interrupts { + #address-cells = <1>; + #size-cells = <1>; + test_intc0: intc0 { + interrupt-controller; + #interrupt-cells = <1>; + }; + + test_intc1: intc1 { + interrupt-controller; + #interrupt-cells = <3>; + }; + + test_intc2: intc2 { + interrupt-controller; + #interrupt-cells = <2>; + }; + + test_intmap0: intmap0 { + #interrupt-cells = <1>; + #address-cells = <0>; + interrupt-map = <1 &test_intc0 9>, + <2 &test_intc1 10 11 12>, + <3 &test_intc2 13 14>, + <4 &test_intc2 15 16>; + }; + + test_intmap1: intmap1 { + #interrupt-cells = <2>; + interrupt-map = <0x5000 1 2 &test_intc0 15>; + }; + + interrupts0 { + interrupt-parent = <&test_intc0>; + interrupts = <1>, <2>, <3>, <4>; + }; + + interrupts1 { + interrupt-parent = <&test_intmap0>; + interrupts = <1>, <2>, <3>, <4>; + }; + + interrupts-extended0 { + reg = <0x5000 0x100>; + interrupts-extended = <&test_intc0 1>, + <&test_intc1 2 3 4>, + <&test_intc2 5 6>, + <&test_intmap0 1>, + <&test_intmap0 2>, + <&test_intmap0 3>, + <&test_intmap1 1 2>; + }; + }; + }; +}; diff --git a/drivers/of/testcase-data/tests-phandle.dtsi b/drivers/of/testcase-data/tests-phandle.dtsi new file mode 100644 index 000000000000..0007d3cd7dc2 --- /dev/null +++ b/drivers/of/testcase-data/tests-phandle.dtsi @@ -0,0 +1,39 @@ + +/ { + testcase-data { + phandle-tests { + provider0: provider0 { + #phandle-cells = <0>; + }; + + provider1: provider1 { + #phandle-cells = <1>; + }; + + provider2: provider2 { + #phandle-cells = <2>; + }; + + provider3: provider3 { + #phandle-cells = <3>; + }; + + consumer-a { + phandle-list = <&provider1 1>, + <&provider2 2 0>, + <0>, + <&provider3 4 4 3>, + <&provider2 5 100>, + <&provider0>, + <&provider1 7>; + phandle-list-names = "first", "second", "third"; + + phandle-list-bad-phandle = <12345678 0 0>; + phandle-list-bad-args = <&provider2 1 0>, + <&provider3 0>; + empty-property; + unterminated-string = [40 41 42 43]; + }; + }; + }; +}; diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 49392ecbef17..79c059e70860 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -152,6 +152,7 @@ ld_flags = $(LDFLAGS) $(ldflags-y) dtc_cpp_flags = -Wp,-MD,$(depfile).pre.tmp -nostdinc \ -I$(srctree)/arch/$(SRCARCH)/boot/dts \ -I$(srctree)/arch/$(SRCARCH)/boot/dts/include \ + -I$(srctree)/drivers/of/testcase-data \ -undef -D__DTS__ # Finds the multi-part object the current object will be linked into -- cgit v1.2.3 From 423edb6fce67133d4524513954af943a75bb6ef5 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 10 Feb 2014 13:15:28 +0100 Subject: s390/compat: fix sys_sched_getattr compat wrapper Fix stupid typo. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/compat_wrapper.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 59c8efce1b99..0248949a756d 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1421,5 +1421,5 @@ ENTRY(sys_sched_setattr_wrapper) ENTRY(sys_sched_getattr_wrapper) lgfr %r2,%r2 # pid_t llgtr %r3,%r3 # const char __user * - llgfr %r3,%r3 # unsigned int + llgfr %r4,%r4 # unsigned int jg sys_sched_getattr -- cgit v1.2.3 From 5ec6d4918a45952e99b1b36c93372d79d6927c57 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Tue, 18 Feb 2014 19:47:17 +0100 Subject: s390/pci/dma: use correct segment boundary size The boundary size for iommu_area_alloc() is currently set to a constant value. This is wrong, we shouldn't use a constant value but rather the return value of dma_get_seg_boundary(), since a device driver can override the default. Reviewed-by: Sebastian Ott Signed-off-by: Gerald Schaefer Signed-off-by: Martin Schwidefsky --- arch/s390/pci/pci_dma.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 60c11a629d96..f91c03119804 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -206,11 +206,13 @@ static void dma_cleanup_tables(struct zpci_dev *zdev) zdev->dma_table = NULL; } -static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, unsigned long start, - int size) +static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, + unsigned long start, int size) { - unsigned long boundary_size = 0x1000000; + unsigned long boundary_size; + boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1, + PAGE_SIZE) >> PAGE_SHIFT; return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages, start, size, 0, boundary_size, 0); } -- cgit v1.2.3 From e9d6dca51823b94e1ca28cb5e9180701d4375d61 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Fri, 31 Jan 2014 05:38:21 +0400 Subject: xtensa: don't pass high memory to bootmem allocator This fixes panic when booting on machine with more than 128M memory passed from the bootloader. Signed-off-by: Max Filippov --- arch/xtensa/mm/init.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 479d7537a32a..aff108df92d3 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -90,7 +90,7 @@ int __init mem_reserve(unsigned long start, unsigned long end, int must_exist) /* - * Initialize the bootmem system and give it all the memory we have available. + * Initialize the bootmem system and give it all low memory we have available. */ void __init bootmem_init(void) @@ -142,9 +142,14 @@ void __init bootmem_init(void) /* Add all remaining memory pieces into the bootmem map */ - for (i=0; i> PAGE_SHIFT < max_low_pfn) { + unsigned long end = min(max_low_pfn << PAGE_SHIFT, + sysmem.bank[i].end); + free_bootmem(sysmem.bank[i].start, + end - sysmem.bank[i].start); + } + } } -- cgit v1.2.3 From 8e9356c6146d0bb81a6ffb02eae522e57ff29662 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Fri, 7 Feb 2014 11:09:52 +0400 Subject: xtensa: fsf: drop nonexistent GPIO32 support The toolchain for xtensa FSF core never supported GPIO32, drop it on the linux side too. Reported-by: Fengguang Wu Signed-off-by: Max Filippov Acked-by: Baruch Siach --- arch/xtensa/Kconfig | 1 - arch/xtensa/variants/fsf/include/variant/tie.h | 9 ++------- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index ba56e11cbf77..1cfb3d50602e 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -80,7 +80,6 @@ choice config XTENSA_VARIANT_FSF bool "fsf - default (not generic) configuration" select MMU - select HAVE_XTENSA_GPIO32 config XTENSA_VARIANT_DC232B bool "dc232b - Diamond 232L Standard Core Rev.B (LE)" diff --git a/arch/xtensa/variants/fsf/include/variant/tie.h b/arch/xtensa/variants/fsf/include/variant/tie.h index bf4020116df5..244cdea4dee5 100644 --- a/arch/xtensa/variants/fsf/include/variant/tie.h +++ b/arch/xtensa/variants/fsf/include/variant/tie.h @@ -18,13 +18,6 @@ #define XCHAL_CP_MASK 0x00 /* bitmask of all CPs by ID */ #define XCHAL_CP_PORT_MASK 0x00 /* bitmask of only port CPs */ -/* Basic parameters of each coprocessor: */ -#define XCHAL_CP7_NAME "XTIOP" -#define XCHAL_CP7_IDENT XTIOP -#define XCHAL_CP7_SA_SIZE 0 /* size of state save area */ -#define XCHAL_CP7_SA_ALIGN 1 /* min alignment of save area */ -#define XCHAL_CP_ID_XTIOP 7 /* coprocessor ID (0..7) */ - /* Filler info for unassigned coprocessors, to simplify arrays etc: */ #define XCHAL_NCP_SA_SIZE 0 #define XCHAL_NCP_SA_ALIGN 1 @@ -42,6 +35,8 @@ #define XCHAL_CP5_SA_ALIGN 1 #define XCHAL_CP6_SA_SIZE 0 #define XCHAL_CP6_SA_ALIGN 1 +#define XCHAL_CP7_SA_SIZE 0 +#define XCHAL_CP7_SA_ALIGN 1 /* Save area for non-coprocessor optional and custom (TIE) state: */ #define XCHAL_NCP_SA_SIZE 0 -- cgit v1.2.3 From 4e3b4df839b550aec463945b10141c65c69f5135 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Sun, 9 Feb 2014 15:45:06 +0100 Subject: xtensa: no need to select USE_GENERIC_SMP_HELPERS Commit f615136c06a7 ("xtensa: add SMP support") added "select USE_GENERIC_SMP_HELPERS". But the Kconfig symbol USE_GENERIC_SMP_HELPERS was already removed in v3.13, so that select is a nop. Drop it. Signed-off-by: Paul Bolle Signed-off-by: Max Filippov --- arch/xtensa/Kconfig | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 1cfb3d50602e..44f1152efa2f 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -134,7 +134,6 @@ config HAVE_SMP config SMP bool "Enable Symmetric multi-processing support" depends on HAVE_SMP - select USE_GENERIC_SMP_HELPERS select GENERIC_SMP_IDLE_THREAD help Enabled SMP Software; allows more than one CPU/CORE -- cgit v1.2.3 From bda8932d234aeaee870ac666e776a5ba03bb13a4 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 29 Jan 2014 06:20:46 +0400 Subject: xtensa: support common clock framework Signed-off-by: Max Filippov --- arch/xtensa/Kconfig | 1 + arch/xtensa/kernel/setup.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 44f1152efa2f..c87ae7c6e5f9 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -20,6 +20,7 @@ config XTENSA select HAVE_FUNCTION_TRACER select HAVE_IRQ_TIME_ACCOUNTING select HAVE_PERF_EVENTS + select COMMON_CLK help Xtensa processors are 32-bit RISC machines designed by Tensilica primarily for embedded systems. These processors are both diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 7d12af1317f1..84fe931bb60e 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -276,6 +277,7 @@ void __init early_init_devtree(void *params) static int __init xtensa_device_probe(void) { + of_clk_init(NULL); of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); return 0; } -- cgit v1.2.3 From cdc9af7ccfc26d35ff8a29dded2cc2c096c0fc1e Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 29 Jan 2014 07:42:46 +0400 Subject: xtensa: xtfpga: use common clock framework With this change the board needs to set up single clock object, users of this clock will get correct frequency automatically. Signed-off-by: Max Filippov --- arch/xtensa/boot/dts/xtfpga.dtsi | 11 ++++++++--- arch/xtensa/platforms/xtfpga/setup.c | 6 +++--- 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi index 46b4f5eab421..d5ccbbb7eec1 100644 --- a/arch/xtensa/boot/dts/xtfpga.dtsi +++ b/arch/xtensa/boot/dts/xtfpga.dtsi @@ -35,6 +35,13 @@ interrupt-controller; }; + clocks { + osc: main-oscillator { + #clock-cells = <0>; + compatible = "fixed-clock"; + }; + }; + serial0: serial@fd050020 { device_type = "serial"; compatible = "ns16550a"; @@ -42,9 +49,7 @@ reg = <0xfd050020 0x20>; reg-shift = <2>; interrupts = <0 1>; /* external irq 0 */ - /* Filled in by platform_setup from FPGA register - * clock-frequency = <100000000>; - */ + clocks = <&osc>; }; enet0: ethoc@fd030000 { diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c index 800227862fe8..03729132ae44 100644 --- a/arch/xtensa/platforms/xtfpga/setup.c +++ b/arch/xtensa/platforms/xtfpga/setup.c @@ -135,11 +135,11 @@ static void __init update_local_mac(struct device_node *node) static int __init machine_setup(void) { - struct device_node *serial; + struct device_node *clock; struct device_node *eth = NULL; - for_each_compatible_node(serial, NULL, "ns16550a") - update_clock_frequency(serial); + for_each_node_by_name(clock, "main-oscillator") + update_clock_frequency(clock); if ((eth = of_find_compatible_node(eth, NULL, "opencores,ethoc"))) update_local_mac(eth); -- cgit v1.2.3 From 2bc2fde63858322a942864bf6cb2d54f5aa33186 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 29 Jan 2014 07:53:44 +0400 Subject: xtensa: xtfpga: set ethoc clock frequency Connect xtfpga board ethernet MAC to the clock in the DTS. Set up MAC base frequency in the platform data in case of build w/o CONFIG_OF. Signed-off-by: Max Filippov --- arch/xtensa/boot/dts/xtfpga.dtsi | 1 + arch/xtensa/platforms/xtfpga/setup.c | 1 + 2 files changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi index d5ccbbb7eec1..e7370b11348e 100644 --- a/arch/xtensa/boot/dts/xtfpga.dtsi +++ b/arch/xtensa/boot/dts/xtfpga.dtsi @@ -57,5 +57,6 @@ reg = <0xfd030000 0x4000 0xfd800000 0x4000>; interrupts = <1 1>; /* external irq 1 */ local-mac-address = [00 50 c2 13 6f 00]; + clocks = <&osc>; }; }; diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c index 03729132ae44..57fd08b36f51 100644 --- a/arch/xtensa/platforms/xtfpga/setup.c +++ b/arch/xtensa/platforms/xtfpga/setup.c @@ -290,6 +290,7 @@ static int __init xtavnet_init(void) * knows whether they set it correctly on the DIP switches. */ pr_info("XTFPGA: Ethernet MAC %pM\n", ethoc_pdata.hwaddr); + ethoc_pdata.eth_clkfreq = *(long *)XTFPGA_CLKFRQ_VADDR; return 0; } -- cgit v1.2.3 From f63b6d7555cd4064554b39da4d44c4cbbc9d6a4a Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Tue, 18 Feb 2014 16:00:05 +0400 Subject: xtensa: wire up sched_setattr and sched_getattr syscalls Signed-off-by: Max Filippov --- arch/xtensa/include/uapi/asm/unistd.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h index 51940fec6990..b9395529f02d 100644 --- a/arch/xtensa/include/uapi/asm/unistd.h +++ b/arch/xtensa/include/uapi/asm/unistd.h @@ -734,7 +734,12 @@ __SYSCALL(332, sys_finit_module, 3) #define __NR_accept4 333 __SYSCALL(333, sys_accept4, 4) -#define __NR_syscall_count 334 +#define __NR_sched_setattr 334 +__SYSCALL(334, sys_sched_setattr, 2) +#define __NR_sched_getattr 335 +__SYSCALL(335, sys_sched_getattr, 3) + +#define __NR_syscall_count 336 /* * sysxtensa syscall handler -- cgit v1.2.3 From a3ef2229c94ff70998724cb64b9cb4c77db9e950 Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Fri, 14 Feb 2014 16:44:08 -0800 Subject: perf, nmi: Fix unknown NMI warning When using BTS on Core i7-4*, I get the below kernel warning. $ perf record -c 1 -e branches:u ls Message from syslogd@labpc1501 at Nov 11 15:49:25 ... kernel:[ 438.317893] Uhhuh. NMI received for unknown reason 31 on CPU 2. Message from syslogd@labpc1501 at Nov 11 15:49:25 ... kernel:[ 438.317920] Do you have a strange power saving mode enabled? Message from syslogd@labpc1501 at Nov 11 15:49:25 ... kernel:[ 438.317945] Dazed and confused, but trying to continue Make intel_pmu_handle_irq() take the full exit path when returning early. Cc: eranian@google.com Cc: peterz@infradead.org Cc: mingo@kernel.org Signed-off-by: Markus Metzger Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1392425048-5309-1-git-send-email-andi@firstfloor.org Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/perf_event_intel.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 0fa4f242f050..698ae77d6f18 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1361,10 +1361,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); - if (!status) { - intel_pmu_enable_all(0); - return handled; - } + if (!status) + goto done; loops = 0; again: -- cgit v1.2.3 From c9b08884c9c98929ec2d8abafd78e89062d01ee7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 3 Feb 2014 14:29:03 +0100 Subject: perf/x86: Correctly use FEATURE_PDCM The current code simply assumes Intel Arch PerfMon v2+ to have the IA32_PERF_CAPABILITIES MSR; the SDM specifies that we should check CPUID[1].ECX[15] (aka, FEATURE_PDCM) instead. This was found by KVM which implements v2+ but didn't provide the capabilities MSR. Change the code to DTRT; KVM will also implement the MSR and return 0. Cc: pbonzini@redhat.com Reported-by: "Michael S. Tsirkin" Suggested-by: Eduardo Habkost Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140203132903.GI8874@twins.programming.kicks-ass.net Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/perf_event_intel.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 698ae77d6f18..aa333d966886 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2308,10 +2308,7 @@ __init int intel_pmu_init(void) if (version > 1) x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); - /* - * v2 and above have a perf capabilities MSR - */ - if (version > 1) { + if (boot_cpu_has(X86_FEATURE_PDCM)) { u64 capabilities; rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities); -- cgit v1.2.3 From 337397f3afc911d94d1d71371a36a53ce218b41f Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 19 Feb 2014 14:10:18 +0100 Subject: perf/x86/uncore: Fix IVT/SNB-EP uncore CBOX NID filter table This patch updates the CBOX PMU filters mapping tables for SNB-EP and IVT (model 45 and 62 respectively). The NID umask always comes in addition to another umask. When set, the NID filter is applied. The current mapping tables were missing some code/umask combinations to account for the NID umask. This patch fixes that. Cc: mingo@elte.hu Cc: ak@linux.intel.com Reviewed-by: Yan, Zheng Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140219131018.GA24475@quad Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/perf_event_intel_uncore.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 29c248799ced..c88f7f4b03ee 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -501,8 +501,11 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, SNBEP_CBO_PMON_CTL_TID_EN, 0x1), SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), @@ -1178,10 +1181,15 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, SNBEP_CBO_PMON_CTL_TID_EN, 0x1), SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), -- cgit v1.2.3 From b6085a865762236bb84934161273cdac6dd11c2d Mon Sep 17 00:00:00 2001 From: Eugene Surovegin Date: Thu, 23 Jan 2014 09:31:20 -0800 Subject: x86, kaslr: export offset in VMCOREINFO ELF notes Include kASLR offset in VMCOREINFO ELF notes to assist in debugging. [ hpa: pushing this for v3.14 to avoid having a kernel version with kASLR where we can't debug output. ] Signed-off-by: Eugene Surovegin Link: http://lkml.kernel.org/r/20140123173120.GA25474@www.outflux.net Signed-off-by: Kees Cook Signed-off-by: H. Peter Anvin --- arch/x86/kernel/machine_kexec_64.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 4eabc160696f..679cef0791cd 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -279,5 +279,7 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_SYMBOL(node_data); VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); #endif + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", + (unsigned long)&_text - __START_KERNEL); } -- cgit v1.2.3 From e290e8c59dbc2a15088d868170d799f763202fef Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sun, 9 Feb 2014 13:56:44 -0800 Subject: x86, kaslr: add missed "static" declarations This silences build warnings about unexported variables and functions. Signed-off-by: Kees Cook Link: http://lkml.kernel.org/r/20140209215644.GA30339@www.outflux.net Signed-off-by: H. Peter Anvin --- arch/x86/boot/compressed/aslr.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index 90a21f430117..4dbf967da50d 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -111,7 +111,7 @@ struct mem_vector { }; #define MEM_AVOID_MAX 5 -struct mem_vector mem_avoid[MEM_AVOID_MAX]; +static struct mem_vector mem_avoid[MEM_AVOID_MAX]; static bool mem_contains(struct mem_vector *region, struct mem_vector *item) { @@ -180,7 +180,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, } /* Does this memory vector overlap a known avoided area? */ -bool mem_avoid_overlap(struct mem_vector *img) +static bool mem_avoid_overlap(struct mem_vector *img) { int i; @@ -192,8 +192,9 @@ bool mem_avoid_overlap(struct mem_vector *img) return false; } -unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN]; -unsigned long slot_max = 0; +static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / + CONFIG_PHYSICAL_ALIGN]; +static unsigned long slot_max; static void slots_append(unsigned long addr) { -- cgit v1.2.3 From 404381c5839d67aa0c275ad1da96ef3d3928ca2c Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Mon, 24 Feb 2014 13:59:32 -0300 Subject: KVM: MMU: drop read-only large sptes when creating lower level sptes Read-only large sptes can be created due to read-only faults as follows: - QEMU pagetable entry that maps guest memory is read-only due to COW. - Guest read faults such memory, COW is not broken, because it is a read-only fault. - Enable dirty logging, large spte not nuked because it is read-only. - Write-fault on such memory causes guest to loop endlessly (which must go down to level 1 because dirty logging is enabled). Fix by dropping large spte when necessary. Signed-off-by: Marcelo Tosatti Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e50425d0f5f7..9b531351a587 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2672,6 +2672,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, break; } + drop_large_spte(vcpu, iterator.sptep); if (!is_shadow_present_pte(*iterator.sptep)) { u64 base_addr = iterator.addr; -- cgit v1.2.3 From 26e61e8939b1fe8729572dabe9a9e97d930dd4f6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 21 Feb 2014 16:03:12 +0100 Subject: perf/x86: Fix event scheduling Vince "Super Tester" Weaver reported a new round of syscall fuzzing (Trinity) failures, with perf WARN_ON()s triggering. He also provided traces of the failures. This is I think the relevant bit: > pec_1076_warn-2804 [000] d... 147.926153: x86_pmu_disable: x86_pmu_disable > pec_1076_warn-2804 [000] d... 147.926153: x86_pmu_state: Events: { > pec_1076_warn-2804 [000] d... 147.926156: x86_pmu_state: 0: state: .R config: ffffffffffffffff ( (null)) > pec_1076_warn-2804 [000] d... 147.926158: x86_pmu_state: 33: state: AR config: 0 (ffff88011ac99800) > pec_1076_warn-2804 [000] d... 147.926159: x86_pmu_state: } > pec_1076_warn-2804 [000] d... 147.926160: x86_pmu_state: n_events: 1, n_added: 0, n_txn: 1 > pec_1076_warn-2804 [000] d... 147.926161: x86_pmu_state: Assignment: { > pec_1076_warn-2804 [000] d... 147.926162: x86_pmu_state: 0->33 tag: 1 config: 0 (ffff88011ac99800) > pec_1076_warn-2804 [000] d... 147.926163: x86_pmu_state: } > pec_1076_warn-2804 [000] d... 147.926166: collect_events: Adding event: 1 (ffff880119ec8800) So we add the insn:p event (fd[23]). At this point we should have: n_events = 2, n_added = 1, n_txn = 1 > pec_1076_warn-2804 [000] d... 147.926170: collect_events: Adding event: 0 (ffff8800c9e01800) > pec_1076_warn-2804 [000] d... 147.926172: collect_events: Adding event: 4 (ffff8800cbab2c00) We try and add the {BP,cycles,br_insn} group (fd[3], fd[4], fd[15]). These events are 0:cycles and 4:br_insn, the BP event isn't x86_pmu so that's not visible. group_sched_in() pmu->start_txn() /* nop - BP pmu */ event_sched_in() event->pmu->add() So here we should end up with: 0: n_events = 3, n_added = 2, n_txn = 2 4: n_events = 4, n_added = 3, n_txn = 3 But seeing the below state on x86_pmu_enable(), the must have failed, because the 0 and 4 events aren't there anymore. Looking at group_sched_in(), since the BP is the leader, its event_sched_in() must have succeeded, for otherwise we would not have seen the sibling adds. But since neither 0 or 4 are in the below state; their event_sched_in() must have failed; but I don't see why, the complete state: 0,0,1:p,4 fits perfectly fine on a core2. However, since we try and schedule 4 it means the 0 event must have succeeded! Therefore the 4 event must have failed, its failure will have put group_sched_in() into the fail path, which will call: event_sched_out() event->pmu->del() on 0 and the BP event. Now x86_pmu_del() will reduce n_events; but it will not reduce n_added; giving what we see below: n_event = 2, n_added = 2, n_txn = 2 > pec_1076_warn-2804 [000] d... 147.926177: x86_pmu_enable: x86_pmu_enable > pec_1076_warn-2804 [000] d... 147.926177: x86_pmu_state: Events: { > pec_1076_warn-2804 [000] d... 147.926179: x86_pmu_state: 0: state: .R config: ffffffffffffffff ( (null)) > pec_1076_warn-2804 [000] d... 147.926181: x86_pmu_state: 33: state: AR config: 0 (ffff88011ac99800) > pec_1076_warn-2804 [000] d... 147.926182: x86_pmu_state: } > pec_1076_warn-2804 [000] d... 147.926184: x86_pmu_state: n_events: 2, n_added: 2, n_txn: 2 > pec_1076_warn-2804 [000] d... 147.926184: x86_pmu_state: Assignment: { > pec_1076_warn-2804 [000] d... 147.926186: x86_pmu_state: 0->33 tag: 1 config: 0 (ffff88011ac99800) > pec_1076_warn-2804 [000] d... 147.926188: x86_pmu_state: 1->0 tag: 1 config: 1 (ffff880119ec8800) > pec_1076_warn-2804 [000] d... 147.926188: x86_pmu_state: } > pec_1076_warn-2804 [000] d... 147.926190: x86_pmu_enable: S0: hwc->idx: 33, hwc->last_cpu: 0, hwc->last_tag: 1 hwc->state: 0 So the problem is that x86_pmu_del(), when called from a group_sched_in() that fails (for whatever reason), and without x86_pmu TXN support (because the leader is !x86_pmu), will corrupt the n_added state. Reported-and-Tested-by: Vince Weaver Signed-off-by: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Stephane Eranian Cc: Dave Jones Cc: Link: http://lkml.kernel.org/r/20140221150312.GF3104@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 895604f2e916..79f9f848bee4 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1192,6 +1192,9 @@ static void x86_pmu_del(struct perf_event *event, int flags) for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) { + if (i >= cpuc->n_events - cpuc->n_added) + --cpuc->n_added; + if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, event); -- cgit v1.2.3 From b20c9f29c5c25921c6ad18b50d4b61e6d181c3cc Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 26 Feb 2014 18:47:36 +0000 Subject: arm/arm64: KVM: detect CPU reset on CPU_PM_EXIT Commit 1fcf7ce0c602 (arm: kvm: implement CPU PM notifier) added support for CPU power-management, using a cpu_notifier to re-init KVM on a CPU that entered CPU idle. The code assumed that a CPU entering idle would actually be powered off, loosing its state entierely, and would then need to be reinitialized. It turns out that this is not always the case, and some HW performs CPU PM without actually killing the core. In this case, we try to reinitialize KVM while it is still live. It ends up badly, as reported by Andre Przywara (using a Calxeda Midway): [ 3.663897] Kernel panic - not syncing: unexpected prefetch abort in Hyp mode at: 0x685760 [ 3.663897] unexpected data abort in Hyp mode at: 0xc067d150 [ 3.663897] unexpected HVC/SVC trap in Hyp mode at: 0xc0901dd0 The trick here is to detect if we've been through a full re-init or not by looking at HVBAR (VBAR_EL2 on arm64). This involves implementing the backend for __hyp_get_vectors in the main KVM HYP code (rather small), and checking the return value against the default one when the CPU notifier is called on CPU_PM_EXIT. Reported-by: Andre Przywara Tested-by: Andre Przywara Cc: Lorenzo Pieralisi Cc: Rob Herring Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier Signed-off-by: Paolo Bonzini --- arch/arm/kvm/arm.c | 3 ++- arch/arm/kvm/interrupts.S | 11 ++++++++++- arch/arm64/kvm/hyp.S | 27 +++++++++++++++++++++++++-- 3 files changed, 37 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 1d8248ea5669..bd18bb8b2770 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -878,7 +878,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { - if (cmd == CPU_PM_EXIT) { + if (cmd == CPU_PM_EXIT && + __hyp_get_vectors() == hyp_default_vectors) { cpu_init_hyp_mode(NULL); return NOTIFY_OK; } diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index ddc15539bad2..0d68d4073068 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -220,6 +220,10 @@ after_vfp_restore: * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are * passed in r0 and r1. * + * A function pointer with a value of 0xffffffff has a special meaning, + * and is used to implement __hyp_get_vectors in the same way as in + * arch/arm/kernel/hyp_stub.S. + * * The calling convention follows the standard AAPCS: * r0 - r3: caller save * r12: caller save @@ -363,6 +367,11 @@ hyp_hvc: host_switch_to_hyp: pop {r0, r1, r2} + /* Check for __hyp_get_vectors */ + cmp r0, #-1 + mrceq p15, 4, r0, c12, c0, 0 @ get HVBAR + beq 1f + push {lr} mrs lr, SPSR push {lr} @@ -378,7 +387,7 @@ THUMB( orr lr, #1) pop {lr} msr SPSR_csxf, lr pop {lr} - eret +1: eret guest_trap: load_vcpu @ Load VCPU pointer to r0 diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 3b47c36e10ff..2c56012cb2d2 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -694,6 +694,24 @@ __hyp_panic_str: .align 2 +/* + * u64 kvm_call_hyp(void *hypfn, ...); + * + * This is not really a variadic function in the classic C-way and care must + * be taken when calling this to ensure parameters are passed in registers + * only, since the stack will change between the caller and the callee. + * + * Call the function with the first argument containing a pointer to the + * function you wish to call in Hyp mode, and subsequent arguments will be + * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the + * function pointer can be passed). The function being called must be mapped + * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are + * passed in r0 and r1. + * + * A function pointer with a value of 0 has a special meaning, and is + * used to implement __hyp_get_vectors in the same way as in + * arch/arm64/kernel/hyp_stub.S. + */ ENTRY(kvm_call_hyp) hvc #0 ret @@ -737,7 +755,12 @@ el1_sync: // Guest trapped into EL2 pop x2, x3 pop x0, x1 - push lr, xzr + /* Check for __hyp_get_vectors */ + cbnz x0, 1f + mrs x0, vbar_el2 + b 2f + +1: push lr, xzr /* * Compute the function address in EL2, and shuffle the parameters. @@ -750,7 +773,7 @@ el1_sync: // Guest trapped into EL2 blr lr pop lr, xzr - eret +2: eret el1_trap: /* -- cgit v1.2.3 From a08d3b3b99efd509133946056531cdf8f3a0c09b Mon Sep 17 00:00:00 2001 From: Andrew Honig Date: Thu, 27 Feb 2014 19:35:14 +0100 Subject: kvm: x86: fix emulator buffer overflow (CVE-2014-0049) The problem occurs when the guest performs a pusha with the stack address pointing to an mmio address (or an invalid guest physical address) to start with, but then extending into an ordinary guest physical address. When doing repeated emulated pushes emulator_read_write sets mmio_needed to 1 on the first one. On a later push when the stack points to regular memory, mmio_nr_fragments is set to 0, but mmio_is_needed is not set to 0. As a result, KVM exits to userspace, and then returns to complete_emulated_mmio. In complete_emulated_mmio vcpu->mmio_cur_fragment is incremented. The termination condition of vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments is never achieved. The code bounces back and fourth to userspace incrementing mmio_cur_fragment past it's buffer. If the guest does nothing else it eventually leads to a a crash on a memcpy from invalid memory address. However if a guest code can cause the vm to be destroyed in another vcpu with excellent timing, then kvm_clear_async_pf_completion_queue can be used by the guest to control the data that's pointed to by the call to cancel_work_item, which can be used to gain execution. Fixes: f78146b0f9230765c6315b2e14f56112513389ad Signed-off-by: Andrew Honig Cc: stable@vger.kernel.org (3.5+) Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 39c28f09dfd5..2b8578432d5b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6186,7 +6186,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) frag->len -= len; } - if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) { + if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { vcpu->mmio_needed = 0; /* FIXME: return into emulator if single-stepping. */ -- cgit v1.2.3 From 1b385cbdd74aa803e966e01e5fe49490d6044e30 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 27 Feb 2014 22:54:11 +0100 Subject: kvm, vmx: Really fix lazy FPU on nested guest Commit e504c9098ed6 (kvm, vmx: Fix lazy FPU on nested guest, 2013-11-13) highlighted a real problem, but the fix was subtly wrong. nested_read_cr0 is the CR0 as read by L2, but here we want to look at the CR0 value reflecting L1's setup. In other words, L2 might think that TS=0 (so nested_read_cr0 has the bit clear); but if L1 is actually running it with TS=1, we should inject the fault into L1. The effective value of CR0 in L2 is contained in vmcs12->guest_cr0, use it. Fixes: e504c9098ed6acd9e1079c5e10e4910724ad429f Reported-by: Kashyap Chamarty Reported-by: Stefan Bader Tested-by: Kashyap Chamarty Tested-by: Anthoine Bourgeois Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a06f101ef64b..392752834751 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6688,7 +6688,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) else if (is_page_fault(intr_info)) return enable_ept; else if (is_no_device(intr_info) && - !(nested_read_cr0(vmcs12) & X86_CR0_TS)) + !(vmcs12->guest_cr0 & X86_CR0_TS)) return 0; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); -- cgit v1.2.3 From 41dd03a94c7d408d2ef32530545097f7d1befe5c Mon Sep 17 00:00:00 2001 From: Tony Breeds Date: Thu, 20 Feb 2014 21:13:52 +1100 Subject: powerpc/le: Ensure that the 'stop-self' RTAS token is handled correctly Currently we're storing a host endian RTAS token in rtas_stop_self_args.token. We then pass that directly to rtas. This is fine on big endian however on little endian the token is not what we expect. This will typically result in hitting: panic("Alas, I survived.\n"); To fix this we always use the stop-self token in host order and always convert it to be32 before passing this to rtas. Signed-off-by: Tony Breeds Cc: stable@vger.kernel.org Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/hotplug-cpu.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 82789e79e539..0ea99e3d4815 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -35,12 +35,7 @@ #include "offline_states.h" /* This version can't take the spinlock, because it never returns */ -static struct rtas_args rtas_stop_self_args = { - .token = RTAS_UNKNOWN_SERVICE, - .nargs = 0, - .nret = 1, - .rets = &rtas_stop_self_args.args[0], -}; +static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) = CPU_STATE_OFFLINE; @@ -93,15 +88,20 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args *args = &rtas_stop_self_args; + struct rtas_args args = { + .token = cpu_to_be32(rtas_stop_self_token), + .nargs = 0, + .nret = 1, + .rets = &args.args[0], + }; local_irq_disable(); - BUG_ON(args->token == RTAS_UNKNOWN_SERVICE); + BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); printk("cpu %u (hwid %u) Ready to die...\n", smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(args)); + enter_rtas(__pa(&args)); panic("Alas, I survived.\n"); } @@ -392,10 +392,10 @@ static int __init pseries_cpu_hotplug_init(void) } } - rtas_stop_self_args.token = rtas_token("stop-self"); + rtas_stop_self_token = rtas_token("stop-self"); qcss_tok = rtas_token("query-cpu-stopped-state"); - if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE || + if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE || qcss_tok == RTAS_UNKNOWN_SERVICE) { printk(KERN_INFO "CPU Hotplug not supported by firmware " "- disabling.\n"); -- cgit v1.2.3 From f5295bd8ea8a65dc5eac608b151386314cb978f1 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Mon, 24 Feb 2014 17:30:55 +0100 Subject: powerpc/crashdump : Fix page frame number check in copy_oldmem_page In copy_oldmem_page, the current check using max_pfn and min_low_pfn to decide if the page is backed or not, is not valid when the memory layout is not continuous. This happens when running as a QEMU/KVM guest, where RTAS is mapped higher in the memory. In that case max_pfn points to the end of RTAS, and a hole between the end of the kdump kernel and RTAS is not backed by PTEs. As a consequence, the kdump kernel is crashing in copy_oldmem_page when accessing in a direct way the pages in that hole. This fix relies on the memblock's service memblock_is_region_memory to check if the read page is part or not of the directly accessible memory. Signed-off-by: Laurent Dufour Tested-by: Mahesh Salgaonkar CC: Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/crash_dump.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 11c1d069d920..7a13f378ca2c 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -98,17 +98,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf) { void *vaddr; + phys_addr_t paddr; if (!csize) return 0; csize = min_t(size_t, csize, PAGE_SIZE); + paddr = pfn << PAGE_SHIFT; - if ((min_low_pfn < pfn) && (pfn < max_pfn)) { - vaddr = __va(pfn << PAGE_SHIFT); + if (memblock_is_region_memory(paddr, csize)) { + vaddr = __va(paddr); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); } else { - vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0); + vaddr = __ioremap(paddr, PAGE_SIZE, 0); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); iounmap(vaddr); } -- cgit v1.2.3 From a95fc58549e8f462e560868a16b1fa97b12d5db6 Mon Sep 17 00:00:00 2001 From: Liu Ping Fan Date: Wed, 26 Feb 2014 10:23:01 +0800 Subject: powerpc/ftrace: bugfix for test_24bit_addr The branch target should be the func addr, not the addr of func_descr_t. So using ppc_function_entry() to generate the right target addr. Signed-off-by: Liu Ping Fan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/ftrace.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 9b27b293a922..b0ded97ee4e1 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -74,6 +74,7 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new) */ static int test_24bit_addr(unsigned long ip, unsigned long addr) { + addr = ppc_function_entry((void *)addr); /* use the create_branch to verify that this offset can be branched */ return create_branch((unsigned int *)ip, addr, 0); -- cgit v1.2.3 From 573ebfa6601fa58b439e7f15828762839ccd306a Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 26 Feb 2014 17:07:38 +1100 Subject: powerpc: Increase stack redzone for 64-bit userspace to 512 bytes The new ELFv2 little-endian ABI increases the stack redzone -- the area below the stack pointer that can be used for storing data -- from 288 bytes to 512 bytes. This means that we need to allow more space on the user stack when delivering a signal to a 64-bit process. To make the code a bit clearer, we define new USER_REDZONE_SIZE and KERNEL_REDZONE_SIZE symbols in ptrace.h. For now, we leave the kernel redzone size at 288 bytes, since increasing it to 512 bytes would increase the size of interrupt stack frames correspondingly. Gcc currently only makes use of 288 bytes of redzone even when compiling for the new little-endian ABI, and the kernel cannot currently be compiled with the new ABI anyway. In the future, hopefully gcc will provide an option to control the amount of redzone used, and then we could reduce it even more. This also changes the code in arch_compat_alloc_user_space() to preserve the expanded redzone. It is not clear why this function would ever be used on a 64-bit process, though. Signed-off-by: Paul Mackerras CC: [v3.13] Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/compat.h | 5 +++-- arch/powerpc/include/asm/ptrace.h | 16 +++++++++++++++- arch/powerpc/kernel/signal_64.c | 4 ++-- 3 files changed, 20 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 84fdf6857c31..a613d2c82fd9 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -200,10 +200,11 @@ static inline void __user *arch_compat_alloc_user_space(long len) /* * We can't access below the stack pointer in the 32bit ABI and - * can access 288 bytes in the 64bit ABI + * can access 288 bytes in the 64bit big-endian ABI, + * or 512 bytes with the new ELFv2 little-endian ABI. */ if (!is_32bit_task()) - usp -= 288; + usp -= USER_REDZONE_SIZE; return (void __user *) (usp - len); } diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index becc08e6a65c..279b80f3bb29 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -28,11 +28,23 @@ #ifdef __powerpc64__ +/* + * Size of redzone that userspace is allowed to use below the stack + * pointer. This is 288 in the 64-bit big-endian ELF ABI, and 512 in + * the new ELFv2 little-endian ABI, so we allow the larger amount. + * + * For kernel code we allow a 288-byte redzone, in order to conserve + * kernel stack space; gcc currently only uses 288 bytes, and will + * hopefully allow explicit control of the redzone size in future. + */ +#define USER_REDZONE_SIZE 512 +#define KERNEL_REDZONE_SIZE 288 + #define STACK_FRAME_OVERHEAD 112 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 2 /* Location of LR in stack frame */ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265) #define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + \ - STACK_FRAME_OVERHEAD + 288) + STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE) #define STACK_FRAME_MARKER 12 /* Size of dummy stack frame allocated when calling signal handler. */ @@ -41,6 +53,8 @@ #else /* __powerpc64__ */ +#define USER_REDZONE_SIZE 0 +#define KERNEL_REDZONE_SIZE 0 #define STACK_FRAME_OVERHEAD 16 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 1 /* Location of LR in stack frame */ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773) diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index e35bf773df7a..8d253c29649b 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -65,8 +65,8 @@ struct rt_sigframe { struct siginfo __user *pinfo; void __user *puc; struct siginfo info; - /* 64 bit ABI allows for 288 bytes below sp before decrementing it. */ - char abigap[288]; + /* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */ + char abigap[USER_REDZONE_SIZE]; } __attribute__ ((aligned (16))); static const char fmt32[] = KERN_INFO \ -- cgit v1.2.3 From 947166043732b69878123bf31f51933ad0316080 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 25 Feb 2014 15:28:37 +0800 Subject: powerpc/powernv: Dump PHB diag-data immediately The PHB diag-data is important to help locating the root cause for EEH errors such as frozen PE or fenced PHB. However, the EEH core enables IO path by clearing part of HW registers before collecting this data causing it to be corrupted. This patch fixes this by dumping the PHB diag-data immediately when frozen/fenced state on PE or PHB is detected for the first time in eeh_ops::get_state() or next_error() backend. Signed-off-by: Gavin Shan CC: Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/eeh-ioda.c | 96 ++++++++++++++----------------- 1 file changed, 43 insertions(+), 53 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index f51474336460..253fefe3d1a0 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -114,6 +114,7 @@ DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get, ioda_eeh_inbB_dbgfs_set, "0x%llx\n"); #endif /* CONFIG_DEBUG_FS */ + /** * ioda_eeh_post_init - Chip dependent post initialization * @hose: PCI controller @@ -221,6 +222,22 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option) return ret; } +static void ioda_eeh_phb_diag(struct pci_controller *hose) +{ + struct pnv_phb *phb = hose->private_data; + long rc; + + rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, + PNV_PCI_DIAG_BUF_SIZE); + if (rc != OPAL_SUCCESS) { + pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n", + __func__, hose->global_number, rc); + return; + } + + pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); +} + /** * ioda_eeh_get_state - Retrieve the state of PE * @pe: EEH PE @@ -272,6 +289,9 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) result |= EEH_STATE_DMA_ACTIVE; result |= EEH_STATE_MMIO_ENABLED; result |= EEH_STATE_DMA_ENABLED; + } else if (!(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); } return result; @@ -315,6 +335,15 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) __func__, fstate, hose->global_number, pe_no); } + /* Dump PHB diag-data for frozen PE */ + if (result != EEH_STATE_NOT_SUPPORT && + (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) != + (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) && + !(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); + } + return result; } @@ -529,42 +558,6 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) return ret; } -/** - * ioda_eeh_get_log - Retrieve error log - * @pe: EEH PE - * @severity: Severity level of the log - * @drv_log: buffer to store the log - * @len: space of the log buffer - * - * The function is used to retrieve error log from P7IOC. - */ -static int ioda_eeh_get_log(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len) -{ - s64 ret; - unsigned long flags; - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - - spin_lock_irqsave(&phb->lock, flags); - - ret = opal_pci_get_phb_diag_data2(phb->opal_id, - phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE); - if (ret) { - spin_unlock_irqrestore(&phb->lock, flags); - pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n", - __func__, hose->global_number, pe->addr, ret); - return -EIO; - } - - /* The PHB diag-data is always indicative */ - pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); - - spin_unlock_irqrestore(&phb->lock, flags); - - return 0; -} - /** * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE * @pe: EEH PE @@ -646,22 +639,6 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose) } } -static void ioda_eeh_phb_diag(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - long rc; - - rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, - PNV_PCI_DIAG_BUF_SIZE); - if (rc != OPAL_SUCCESS) { - pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n", - __func__, hose->global_number, rc); - return; - } - - pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); -} - static int ioda_eeh_get_phb_pe(struct pci_controller *hose, struct eeh_pe **pe) { @@ -834,6 +811,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) __func__, err_type); } + /* + * EEH core will try recover from fenced PHB or + * frozen PE. In the time for frozen PE, EEH core + * enable IO path for that before collecting logs, + * but it ruins the site. So we have to dump the + * log in advance here. + */ + if ((ret == EEH_NEXT_ERR_FROZEN_PE || + ret == EEH_NEXT_ERR_FENCED_PHB) && + !((*pe)->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); + } + /* * If we have no errors on the specific PHB or only * informative error there, we continue poking it. @@ -852,7 +843,6 @@ struct pnv_eeh_ops ioda_eeh_ops = { .set_option = ioda_eeh_set_option, .get_state = ioda_eeh_get_state, .reset = ioda_eeh_reset, - .get_log = ioda_eeh_get_log, .configure_bridge = ioda_eeh_configure_bridge, .next_error = ioda_eeh_next_error }; -- cgit v1.2.3 From af87d2fe95444d107e0c0cf0ba7e20e6716a7bfd Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 25 Feb 2014 15:28:38 +0800 Subject: powerpc/powernv: Refactor PHB diag-data dump As Ben suggested, the patch prints PHB diag-data with multiple fields in one line and omits the line if the fields of that line are all zero. With the patch applied, the PHB3 diag-data dump looks like: PHB3 PHB#3 Diag-data (Version: 1) brdgCtl: 00000002 RootSts: 0000000f 00400000 b0830008 00100147 00002000 nFir: 0000000000000000 0030006e00000000 0000000000000000 PhbSts: 0000001c00000000 0000000000000000 Lem: 0000000000100000 42498e327f502eae 0000000000000000 InAErr: 8000000000000000 8000000000000000 0402030000000000 0000000000000000 PE[ 8] A/B: 8480002b00000000 8000000000000000 [ The current diag data is so big that it overflows the printk buffer pretty quickly in cases when we get a handful of errors at once which can happen. --BenH ] Signed-off-by: Gavin Shan CC: Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/pci.c | 220 ++++++++++++++++++++--------------- 1 file changed, 125 insertions(+), 95 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 95633d79ef5d..8518817dcdfd 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -134,57 +134,72 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose, pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n", hose->global_number, common->version); - pr_info(" brdgCtl: %08x\n", data->brdgCtl); - - pr_info(" portStatusReg: %08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); - - pr_info(" deviceStatus: %08x\n", data->deviceStatus); - pr_info(" slotStatus: %08x\n", data->slotStatus); - pr_info(" linkStatus: %08x\n", data->linkStatus); - pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); - pr_info(" devSecStatus: %08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); - pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); - pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); - pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); - pr_info(" sourceId: %08x\n", data->sourceId); - pr_info(" errorClass: %016llx\n", data->errorClass); - pr_info(" correlator: %016llx\n", data->correlator); - pr_info(" p7iocPlssr: %016llx\n", data->p7iocPlssr); - pr_info(" p7iocCsr: %016llx\n", data->p7iocCsr); - pr_info(" lemFir: %016llx\n", data->lemFir); - pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); - pr_info(" lemWOF: %016llx\n", data->lemWOF); - pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); + if (data->brdgCtl) + pr_info(" brdgCtl: %08x\n", + data->brdgCtl); + if (data->portStatusReg || data->rootCmplxStatus || + data->busAgentStatus) + pr_info(" UtlSts: %08x %08x %08x\n", + data->portStatusReg, data->rootCmplxStatus, + data->busAgentStatus); + if (data->deviceStatus || data->slotStatus || + data->linkStatus || data->devCmdStatus || + data->devSecStatus) + pr_info(" RootSts: %08x %08x %08x %08x %08x\n", + data->deviceStatus, data->slotStatus, + data->linkStatus, data->devCmdStatus, + data->devSecStatus); + if (data->rootErrorStatus || data->uncorrErrorStatus || + data->corrErrorStatus) + pr_info(" RootErrSts: %08x %08x %08x\n", + data->rootErrorStatus, data->uncorrErrorStatus, + data->corrErrorStatus); + if (data->tlpHdr1 || data->tlpHdr2 || + data->tlpHdr3 || data->tlpHdr4) + pr_info(" RootErrLog: %08x %08x %08x %08x\n", + data->tlpHdr1, data->tlpHdr2, + data->tlpHdr3, data->tlpHdr4); + if (data->sourceId || data->errorClass || + data->correlator) + pr_info(" RootErrLog1: %08x %016llx %016llx\n", + data->sourceId, data->errorClass, + data->correlator); + if (data->p7iocPlssr || data->p7iocCsr) + pr_info(" PhbSts: %016llx %016llx\n", + data->p7iocPlssr, data->p7iocCsr); + if (data->lemFir || data->lemErrorMask || + data->lemWOF) + pr_info(" Lem: %016llx %016llx %016llx\n", + data->lemFir, data->lemErrorMask, + data->lemWOF); + if (data->phbErrorStatus || data->phbFirstErrorStatus || + data->phbErrorLog0 || data->phbErrorLog1) + pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n", + data->phbErrorStatus, data->phbFirstErrorStatus, + data->phbErrorLog0, data->phbErrorLog1); + if (data->mmioErrorStatus || data->mmioFirstErrorStatus || + data->mmioErrorLog0 || data->mmioErrorLog1) + pr_info(" OutErr: %016llx %016llx %016llx %016llx\n", + data->mmioErrorStatus, data->mmioFirstErrorStatus, + data->mmioErrorLog0, data->mmioErrorLog1); + if (data->dma0ErrorStatus || data->dma0FirstErrorStatus || + data->dma0ErrorLog0 || data->dma0ErrorLog1) + pr_info(" InAErr: %016llx %016llx %016llx %016llx\n", + data->dma0ErrorStatus, data->dma0FirstErrorStatus, + data->dma0ErrorLog0, data->dma0ErrorLog1); + if (data->dma1ErrorStatus || data->dma1FirstErrorStatus || + data->dma1ErrorLog0 || data->dma1ErrorLog1) + pr_info(" InBErr: %016llx %016llx %016llx %016llx\n", + data->dma1ErrorStatus, data->dma1FirstErrorStatus, + data->dma1ErrorLog0, data->dma1ErrorLog1); for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) { if ((data->pestA[i] >> 63) == 0 && (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); - pr_info(" PESTB: %016llx\n", data->pestB[i]); + pr_info(" PE[%3d] A/B: %016llx %016llx\n", + i, data->pestA[i], data->pestB[i]); } } @@ -197,62 +212,77 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose, data = (struct OpalIoPhb3ErrorData*)common; pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n", hose->global_number, common->version); - - pr_info(" brdgCtl: %08x\n", data->brdgCtl); - - pr_info(" portStatusReg: %08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); - - pr_info(" deviceStatus: %08x\n", data->deviceStatus); - pr_info(" slotStatus: %08x\n", data->slotStatus); - pr_info(" linkStatus: %08x\n", data->linkStatus); - pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); - pr_info(" devSecStatus: %08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); - pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); - pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); - pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); - pr_info(" sourceId: %08x\n", data->sourceId); - pr_info(" errorClass: %016llx\n", data->errorClass); - pr_info(" correlator: %016llx\n", data->correlator); - - pr_info(" nFir: %016llx\n", data->nFir); - pr_info(" nFirMask: %016llx\n", data->nFirMask); - pr_info(" nFirWOF: %016llx\n", data->nFirWOF); - pr_info(" PhbPlssr: %016llx\n", data->phbPlssr); - pr_info(" PhbCsr: %016llx\n", data->phbCsr); - pr_info(" lemFir: %016llx\n", data->lemFir); - pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); - pr_info(" lemWOF: %016llx\n", data->lemWOF); - pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); + if (data->brdgCtl) + pr_info(" brdgCtl: %08x\n", + data->brdgCtl); + if (data->portStatusReg || data->rootCmplxStatus || + data->busAgentStatus) + pr_info(" UtlSts: %08x %08x %08x\n", + data->portStatusReg, data->rootCmplxStatus, + data->busAgentStatus); + if (data->deviceStatus || data->slotStatus || + data->linkStatus || data->devCmdStatus || + data->devSecStatus) + pr_info(" RootSts: %08x %08x %08x %08x %08x\n", + data->deviceStatus, data->slotStatus, + data->linkStatus, data->devCmdStatus, + data->devSecStatus); + if (data->rootErrorStatus || data->uncorrErrorStatus || + data->corrErrorStatus) + pr_info(" RootErrSts: %08x %08x %08x\n", + data->rootErrorStatus, data->uncorrErrorStatus, + data->corrErrorStatus); + if (data->tlpHdr1 || data->tlpHdr2 || + data->tlpHdr3 || data->tlpHdr4) + pr_info(" RootErrLog: %08x %08x %08x %08x\n", + data->tlpHdr1, data->tlpHdr2, + data->tlpHdr3, data->tlpHdr4); + if (data->sourceId || data->errorClass || + data->correlator) + pr_info(" RootErrLog1: %08x %016llx %016llx\n", + data->sourceId, data->errorClass, + data->correlator); + if (data->nFir || data->nFirMask || + data->nFirWOF) + pr_info(" nFir: %016llx %016llx %016llx\n", + data->nFir, data->nFirMask, + data->nFirWOF); + if (data->phbPlssr || data->phbCsr) + pr_info(" PhbSts: %016llx %016llx\n", + data->phbPlssr, data->phbCsr); + if (data->lemFir || data->lemErrorMask || + data->lemWOF) + pr_info(" Lem: %016llx %016llx %016llx\n", + data->lemFir, data->lemErrorMask, + data->lemWOF); + if (data->phbErrorStatus || data->phbFirstErrorStatus || + data->phbErrorLog0 || data->phbErrorLog1) + pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n", + data->phbErrorStatus, data->phbFirstErrorStatus, + data->phbErrorLog0, data->phbErrorLog1); + if (data->mmioErrorStatus || data->mmioFirstErrorStatus || + data->mmioErrorLog0 || data->mmioErrorLog1) + pr_info(" OutErr: %016llx %016llx %016llx %016llx\n", + data->mmioErrorStatus, data->mmioFirstErrorStatus, + data->mmioErrorLog0, data->mmioErrorLog1); + if (data->dma0ErrorStatus || data->dma0FirstErrorStatus || + data->dma0ErrorLog0 || data->dma0ErrorLog1) + pr_info(" InAErr: %016llx %016llx %016llx %016llx\n", + data->dma0ErrorStatus, data->dma0FirstErrorStatus, + data->dma0ErrorLog0, data->dma0ErrorLog1); + if (data->dma1ErrorStatus || data->dma1FirstErrorStatus || + data->dma1ErrorLog0 || data->dma1ErrorLog1) + pr_info(" InBErr: %016llx %016llx %016llx %016llx\n", + data->dma1ErrorStatus, data->dma1FirstErrorStatus, + data->dma1ErrorLog0, data->dma1ErrorLog1); for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) { if ((data->pestA[i] >> 63) == 0 && (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); - pr_info(" PESTB: %016llx\n", data->pestB[i]); + pr_info(" PE[%3d] A/B: %016llx %016llx\n", + i, data->pestA[i], data->pestB[i]); } } -- cgit v1.2.3 From 2f3f38e4d3d03dd4125cc9a1f49ab3cc91d8d670 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 28 Feb 2014 16:20:29 +1100 Subject: powerpc/powernv: Fix opal_xscom_{read,write} prototype The OPAL firmware functions opal_xscom_read and opal_xscom_write take a 64-bit argument for the XSCOM (PCB) address in order to support the indirect mode on P8. Signed-off-by: Benjamin Herrenschmidt CC: [v3.13] --- arch/powerpc/include/asm/opal.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 40157e2ca691..ed82142a3251 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -816,8 +816,8 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe, int64_t opal_pci_poll(uint64_t phb_id); int64_t opal_return_cpu(void); -int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val); -int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val); +int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val); +int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val); int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type, uint32_t addr, uint32_t data, uint32_t sz); -- cgit v1.2.3 From e0cf957614976896111e676e5134ac98ee227d3d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 28 Feb 2014 16:20:38 +1100 Subject: powerpc/powernv: Fix indirect XSCOM unmangling We need to unmangle the full address, not just the register number, and we also need to support the real indirect bit being set for in-kernel uses. Signed-off-by: Benjamin Herrenschmidt CC: [v3.13] --- arch/powerpc/platforms/powernv/opal-xscom.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 4fbf276ac99e..4cd2ea6c0dbe 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -71,11 +71,11 @@ static int opal_xscom_err_xlate(int64_t rc) } } -static u64 opal_scom_unmangle(u64 reg) +static u64 opal_scom_unmangle(u64 addr) { /* * XSCOM indirect addresses have the top bit set. Additionally - * the reset of the top 3 nibbles is always 0. + * the rest of the top 3 nibbles is always 0. * * Because the debugfs interface uses signed offsets and shifts * the address left by 3, we basically cannot use the top 4 bits @@ -86,10 +86,13 @@ static u64 opal_scom_unmangle(u64 reg) * conversion here. To leave room for further xscom address * expansion, we only clear out the top byte * + * For in-kernel use, we also support the real indirect bit, so + * we test for any of the top 5 bits + * */ - if (reg & (1ull << 59)) - reg = (reg & ~(0xffull << 56)) | (1ull << 63); - return reg; + if (addr & (0x1full << 59)) + addr = (addr & ~(0xffull << 56)) | (1ull << 63); + return addr; } static int opal_scom_read(scom_map_t map, u64 reg, u64 *value) @@ -98,8 +101,8 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value) int64_t rc; __be64 v; - reg = opal_scom_unmangle(reg); - rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v)); + reg = opal_scom_unmangle(m->addr + reg); + rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v)); *value = be64_to_cpu(v); return opal_xscom_err_xlate(rc); } @@ -109,8 +112,8 @@ static int opal_scom_write(scom_map_t map, u64 reg, u64 value) struct opal_scom_map *m = map; int64_t rc; - reg = opal_scom_unmangle(reg); - rc = opal_xscom_write(m->chip, m->addr + reg, value); + reg = opal_scom_unmangle(m->addr + reg); + rc = opal_xscom_write(m->chip, reg, value); return opal_xscom_err_xlate(rc); } -- cgit v1.2.3 From 84fe6826c28f69d8708bd575faed7f75e6b6f57f Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Tue, 25 Feb 2014 11:38:53 +0000 Subject: arm64: mm: Add double logical invert to pte accessors Page table entries on ARM64 are 64 bits, and some pte functions such as pte_dirty return a bitwise-and of a flag with the pte value. If the flag to be tested resides in the upper 32 bits of the pte, then we run into the danger of the result being dropped if downcast. For example: gather_stats(page, md, pte_dirty(*pte), 1); where pte_dirty(*pte) is downcast to an int. This patch adds a double logical invert to all the pte_ accessors to ensure predictable downcasting. Signed-off-by: Steve Capper Cc: Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgtable.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b524dcd17243..aa3917c8b623 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -136,11 +136,11 @@ extern struct page *empty_zero_page; /* * The following only work if pte_present(). Undefined behaviour otherwise. */ -#define pte_present(pte) (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) -#define pte_dirty(pte) (pte_val(pte) & PTE_DIRTY) -#define pte_young(pte) (pte_val(pte) & PTE_AF) -#define pte_special(pte) (pte_val(pte) & PTE_SPECIAL) -#define pte_write(pte) (pte_val(pte) & PTE_WRITE) +#define pte_present(pte) (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))) +#define pte_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) +#define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) +#define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) +#define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_valid_user(pte) \ -- cgit v1.2.3 From b57fc9e80692043e2a3a74e1d2c047eb700dcd0c Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Fri, 28 Feb 2014 16:12:25 +0000 Subject: arm64: Fix !CONFIG_SMP kernel build Commit fb4a96029c8a (arm64: kernel: fix per-cpu offset restore on resume) uses per_cpu_offset() unconditionally during CPU wakeup, however, this is only defined for the SMP case. Signed-off-by: Catalin Marinas Reported-by: Dave P Martin --- arch/arm64/include/asm/percpu.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch') diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 13fb0b3efc5f..453a179469a3 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -16,6 +16,8 @@ #ifndef __ASM_PERCPU_H #define __ASM_PERCPU_H +#ifdef CONFIG_SMP + static inline void set_my_cpu_offset(unsigned long off) { asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory"); @@ -36,6 +38,12 @@ static inline unsigned long __my_cpu_offset(void) } #define __my_cpu_offset __my_cpu_offset() +#else /* !CONFIG_SMP */ + +#define set_my_cpu_offset(x) do { } while (0) + +#endif /* CONFIG_SMP */ + #include #endif /* __ASM_PERCPU_H */ -- cgit v1.2.3