From bc2dc4406c463174613047d8b7946e12c8808cda Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Sat, 21 Nov 2020 22:17:01 -0800 Subject: compiler-clang: remove version check for BPF Tracing bpftrace parses the kernel headers and uses Clang under the hood. Remove the version check when __BPF_TRACING__ is defined (as bpftrace does) so that this tool can continue to parse kernel headers, even with older clang sources. Fixes: commit 1f7a44f63e6c ("compiler-clang: add build check for clang 10.0.1") Reported-by: Chen Yu Reported-by: Jarkko Sakkinen Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton Tested-by: Jarkko Sakkinen Acked-by: Jarkko Sakkinen Acked-by: Song Liu Acked-by: Nathan Chancellor Acked-by: Miguel Ojeda Link: https://lkml.kernel.org/r/20201104191052.390657-1-ndesaulniers@google.com Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index dd7233c48bf3..98cff1b4b088 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -8,8 +8,10 @@ + __clang_patchlevel__) #if CLANG_VERSION < 100001 +#ifndef __BPF_TRACING__ # error Sorry, your version of Clang is too old - please use 10.0.1 or newer. #endif +#endif /* Compiler specific definitions for Clang compiler */ -- cgit v1.2.3-58-ga151 From a927bd6ba952d13c52b8b385030943032f659a3e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 21 Nov 2020 22:17:05 -0800 Subject: mm: fix phys_to_target_node() and memory_add_physaddr_to_nid() exports The core-mm has a default __weak implementation of phys_to_target_node() to mirror the weak definition of memory_add_physaddr_to_nid(). That symbol is exported for modules. However, while the export in mm/memory_hotplug.c exported the symbol in the configuration cases of: CONFIG_NUMA_KEEP_MEMINFO=y CONFIG_MEMORY_HOTPLUG=y ...and: CONFIG_NUMA_KEEP_MEMINFO=n CONFIG_MEMORY_HOTPLUG=y ...it failed to export the symbol in the case of: CONFIG_NUMA_KEEP_MEMINFO=y CONFIG_MEMORY_HOTPLUG=n Not only is that broken, but Christoph points out that the kernel should not be exporting any __weak symbol, which means that memory_add_physaddr_to_nid() example that phys_to_target_node() copied is broken too. Rework the definition of phys_to_target_node() and memory_add_physaddr_to_nid() to not require weak symbols. Move to the common arch override design-pattern of an asm header defining a symbol to replace the default implementation. The only common header that all memory_add_physaddr_to_nid() producing architectures implement is asm/sparsemem.h. In fact, powerpc already defines its memory_add_physaddr_to_nid() helper in sparsemem.h. Double-down on that observation and define phys_to_target_node() where necessary in asm/sparsemem.h. An alternate consideration that was discarded was to put this override in asm/numa.h, but that entangles with the definition of MAX_NUMNODES relative to the inclusion of linux/nodemask.h, and requires powerpc to grow a new header. The dependency on NUMA_KEEP_MEMINFO for DEV_DAX_HMEM_DEVICES is invalid now that the symbol is properly exported / stubbed in all combinations of CONFIG_NUMA_KEEP_MEMINFO and CONFIG_MEMORY_HOTPLUG. [dan.j.williams@intel.com: v4] Link: https://lkml.kernel.org/r/160461461867.1505359.5301571728749534585.stgit@dwillia2-desk3.amr.corp.intel.com [dan.j.williams@intel.com: powerpc: fix create_section_mapping compile warning] Link: https://lkml.kernel.org/r/160558386174.2948926.2740149041249041764.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: a035b6bf863e ("mm/memory_hotplug: introduce default phys_to_target_node() implementation") Reported-by: Randy Dunlap Reported-by: Thomas Gleixner Reported-by: kernel test robot Reported-by: Christoph Hellwig Signed-off-by: Dan Williams Signed-off-by: Andrew Morton Tested-by: Randy Dunlap Tested-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Christoph Hellwig Cc: Joao Martins Cc: Tony Luck Cc: Fenghua Yu Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Vishal Verma Cc: Stephen Rothwell Link: https://lkml.kernel.org/r/160447639846.1133764.7044090803980177548.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/sparsemem.h | 6 ++++++ arch/powerpc/include/asm/mmzone.h | 5 +++++ arch/powerpc/include/asm/sparsemem.h | 5 ++--- arch/powerpc/mm/mem.c | 1 + arch/x86/include/asm/sparsemem.h | 10 ++++++++++ arch/x86/mm/numa.c | 2 ++ drivers/dax/Kconfig | 1 - include/linux/memory_hotplug.h | 14 -------------- include/linux/numa.h | 30 +++++++++++++++++++++++++++++- mm/memory_hotplug.c | 18 ------------------ 10 files changed, 55 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index 336d0570e1fa..dd8c166ffd7b 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -18,4 +18,10 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifdef CONFIG_MEMORY_HOTPLUG +int memory_add_physaddr_to_nid(u64 addr); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif + #endif /* _ASM_IA64_SPARSEMEM_H */ diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 91c69ff53a8a..6cda76b57c5d 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -46,5 +46,10 @@ u64 memory_hotplug_max(void); #define __HAVE_ARCH_RESERVED_KERNEL_PAGES #endif +#ifdef CONFIG_MEMORY_HOTPLUG +extern int create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 1e6fa371cc38..d072866842e4 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -13,9 +13,9 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG -extern int create_section_mapping(unsigned long start, unsigned long end, - int nid, pgprot_t prot); extern int remove_section_mapping(unsigned long start, unsigned long end); +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); @@ -26,6 +26,5 @@ static inline int hot_add_scn_to_nid(unsigned long scn_addr) } #endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_SPARSEMEM_H */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 01ec2a252f09..3fc325bebe4d 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -50,6 +50,7 @@ #include #include #include +#include #include diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 6bfc878f6771..6a9ccc1b2be5 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -28,4 +28,14 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_NUMA_KEEP_MEMINFO +extern int phys_to_target_node(phys_addr_t start); +#define phys_to_target_node phys_to_target_node +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_SPARSEMEM_H */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 44148691d78b..5eb4dc2b97da 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -938,6 +938,7 @@ int phys_to_target_node(phys_addr_t start) return meminfo_to_nid(&numa_reserved_meminfo, start); } +EXPORT_SYMBOL_GPL(phys_to_target_node); int memory_add_physaddr_to_nid(u64 start) { @@ -947,4 +948,5 @@ int memory_add_physaddr_to_nid(u64 start) nid = numa_meminfo.blk[0].nid; return nid; } +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index 567428e10b7b..d2834c2cfa10 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -50,7 +50,6 @@ config DEV_DAX_HMEM Say M if unsure. config DEV_DAX_HMEM_DEVICES - depends on NUMA_KEEP_MEMINFO # for phys_to_target_node() depends on DEV_DAX_HMEM && DAX=y def_bool y diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index d65c6fdc5cfc..551093b74596 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -281,20 +281,6 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ -#ifdef CONFIG_NUMA -extern int memory_add_physaddr_to_nid(u64 start); -extern int phys_to_target_node(u64 start); -#else -static inline int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -static inline int phys_to_target_node(u64 start) -{ - return 0; -} -#endif - #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions diff --git a/include/linux/numa.h b/include/linux/numa.h index 8cb33ccfb671..cb44cfe2b725 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -21,13 +21,41 @@ #endif #ifdef CONFIG_NUMA +#include +#include + /* Generic implementation available */ int numa_map_to_online_node(int node); -#else + +#ifndef memory_add_physaddr_to_nid +static inline int memory_add_physaddr_to_nid(u64 start) +{ + pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#ifndef phys_to_target_node +static inline int phys_to_target_node(u64 start) +{ + pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#else /* !CONFIG_NUMA */ static inline int numa_map_to_online_node(int node) { return NUMA_NO_NODE; } +static inline int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +static inline int phys_to_target_node(u64 start) +{ + return 0; +} #endif #endif /* _LINUX_NUMA_H */ diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b44d4c7ba73b..63b2e46b6555 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -350,24 +350,6 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, return err; } -#ifdef CONFIG_NUMA -int __weak memory_add_physaddr_to_nid(u64 start) -{ - pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); - -int __weak phys_to_target_node(u64 start) -{ - pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(phys_to_target_node); -#endif - /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, -- cgit v1.2.3-58-ga151 From 4349a83a3190c1d4414371161b0f4a4c3ccd3f9d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 21 Nov 2020 22:17:08 -0800 Subject: mm: fix readahead_page_batch for retry entries Both btrfs and fuse have reported faults caused by seeing a retry entry instead of the page they were looking for. This was caused by a missing check in the iterator. As can be seen in the below panic log, the accessing 0x402 causes a panic. In the xarray.h, 0x402 means RETRY_ENTRY. BUG: kernel NULL pointer dereference, address: 0000000000000402 CPU: 14 PID: 306003 Comm: as Not tainted 5.9.0-1-amd64 #1 Debian 5.9.1-1 Hardware name: Lenovo ThinkSystem SR665/7D2VCTO1WW, BIOS D8E106Q-1.01 05/30/2020 RIP: 0010:fuse_readahead+0x152/0x470 [fuse] Code: 41 8b 57 18 4c 8d 54 10 ff 4c 89 d6 48 8d 7c 24 10 e8 d2 e3 28 f9 48 85 c0 0f 84 fe 00 00 00 44 89 f2 49 89 04 d4 44 8d 72 01 <48> 8b 10 41 8b 4f 1c 48 c1 ea 10 83 e2 01 80 fa 01 19 d2 81 e2 01 RSP: 0018:ffffad99ceaebc50 EFLAGS: 00010246 RAX: 0000000000000402 RBX: 0000000000000001 RCX: 0000000000000002 RDX: 0000000000000000 RSI: ffff94c5af90bd98 RDI: ffffad99ceaebc60 RBP: ffff94ddc1749a00 R08: 0000000000000402 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000100 R12: ffff94de6c429ce0 R13: ffff94de6c4d3700 R14: 0000000000000001 R15: ffffad99ceaebd68 FS: 00007f228c5c7040(0000) GS:ffff94de8ed80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000402 CR3: 0000001dbd9b4000 CR4: 0000000000350ee0 Call Trace: read_pages+0x83/0x270 page_cache_readahead_unbounded+0x197/0x230 generic_file_buffered_read+0x57a/0xa20 new_sync_read+0x112/0x1a0 vfs_read+0xf8/0x180 ksys_read+0x5f/0xe0 do_syscall_64+0x33/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 042124cc64c3 ("mm: add new readahead_control API") Reported-by: David Sterba Reported-by: Wonhyuk Yang Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: Link: https://lkml.kernel.org/r/20201103142852.8543-1-willy@infradead.org Link: https://lkml.kernel.org/r/20201103124349.16722-1-vvghjk1234@gmail.com Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e1e19c1f9ec9..d5570deff400 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -906,6 +906,8 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { + if (xas_retry(&xas, page)) + continue; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; -- cgit v1.2.3-58-ga151