mirror of
				https://github.com/torvalds/linux.git
				synced 2025-11-04 10:40:15 +02:00 
			
		
		
		
	This has been a slightly more active cycle than normal with ongoing core
 changes and quite a lot of collected driver updates.
 
 - Various driver fixes for bnxt_re, cxgb4, hns, mlx5, pvrdma, rxe
 
 - A new data transfer mode for HFI1 giving higher performance
 
 - Significant functional and bug fix update to the mlx5 On-Demand-Paging MR
   feature
 
 - A chip hang reset recovery system for hns
 
 - Change mm->pinned_vm to an atomic64
 
 - Update bnxt_re to support a new 57500 chip
 
 - A sane netlink 'rdma link add' method for creating rxe devices and fixing
   the various unregistration race conditions in rxe's unregister flow
 
 - Allow lookup up objects by an ID over netlink
 
 - Various reworking of the core to driver interface:
   * Drivers should not assume umem SGLs are in PAGE_SIZE chunks
   * ucontext is accessed via udata not other means
   * Start to make the core code responsible for object memory
     allocation
   * Drivers should convert struct device to struct ib_device
     via a helper
   * Drivers have more tools to avoid use after unregister problems
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEfB7FMLh+8QxL+6i3OG33FX4gmxoFAlyAJYYACgkQOG33FX4g
 mxrWwQ/+OyAx4Moru7Aix0C6GWxTJp/wKgw21CS3reZxgLai6x81xNYG/s2wCNjo
 IccObVd7mvzyqPdxOeyHBsJBbQDqWvoD6O2duH8cqGMgBRgh3CSdUep2zLvPpSAx
 2W1SvWYCLDnCuarboFrCA8c4AN3eCZiqD7z9lHyFQGjy3nTUWzk1uBaOP46uaiMv
 w89N8EMdXJ/iY6ONzihvE05NEYbMA8fuvosKLLNdghRiHIjbMQU8SneY23pvyPDd
 ZziPu9NcO3Hw9OVbkwtJp47U3KCBgvKHmnixyZKkikjiD+HVoABw2IMwcYwyBZwP
 Bic/ddONJUvAxMHpKRnQaW7znAiHARk21nDG28UAI7FWXH/wMXgicMp6LRcNKqKF
 vqXdxHTKJb0QUR4xrYI+eA8ihstss7UUpgSgByuANJ0X729xHiJtlEvPb1DPo1Dz
 9CB4OHOVRl5O8sA5Jc6PSusZiKEpvWoyWbdmw0IiwDF5pe922VLl5Nv88ta+sJ38
 v2Ll5AgYcluk7F3599Uh9D7gwp5hxW2Ph3bNYyg2j3HP4/dKsL9XvIJPXqEthgCr
 3KQS9rOZfI/7URieT+H+Mlf+OWZhXsZilJG7No0fYgIVjgJ00h3SF1/299YIq6Qp
 9W7ZXBfVSwLYA2AEVSvGFeZPUxgBwHrSZ62wya4uFeB1jyoodPk=
 =p12E
 -----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull rdma updates from Jason Gunthorpe:
 "This has been a slightly more active cycle than normal with ongoing
  core changes and quite a lot of collected driver updates.
   - Various driver fixes for bnxt_re, cxgb4, hns, mlx5, pvrdma, rxe
   - A new data transfer mode for HFI1 giving higher performance
   - Significant functional and bug fix update to the mlx5
     On-Demand-Paging MR feature
   - A chip hang reset recovery system for hns
   - Change mm->pinned_vm to an atomic64
   - Update bnxt_re to support a new 57500 chip
   - A sane netlink 'rdma link add' method for creating rxe devices and
     fixing the various unregistration race conditions in rxe's
     unregister flow
   - Allow lookup up objects by an ID over netlink
   - Various reworking of the core to driver interface:
       - drivers should not assume umem SGLs are in PAGE_SIZE chunks
       - ucontext is accessed via udata not other means
       - start to make the core code responsible for object memory
         allocation
       - drivers should convert struct device to struct ib_device via a
         helper
       - drivers have more tools to avoid use after unregister problems"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (280 commits)
  net/mlx5: ODP support for XRC transport is not enabled by default in FW
  IB/hfi1: Close race condition on user context disable and close
  RDMA/umem: Revert broken 'off by one' fix
  RDMA/umem: minor bug fix in error handling path
  RDMA/hns: Use GFP_ATOMIC in hns_roce_v2_modify_qp
  cxgb4: kfree mhp after the debug print
  IB/rdmavt: Fix concurrency panics in QP post_send and modify to error
  IB/rdmavt: Fix loopback send with invalidate ordering
  IB/iser: Fix dma_nents type definition
  IB/mlx5: Set correct write permissions for implicit ODP MR
  bnxt_re: Clean cq for kernel consumers only
  RDMA/uverbs: Don't do double free of allocated PD
  RDMA: Handle ucontext allocations by IB/core
  RDMA/core: Fix a WARN() message
  bnxt_re: fix the regression due to changes in alloc_pbl
  IB/mlx4: Increase the timeout for CM cache
  IB/core: Abort page fault handler silently during owning process exit
  IB/mlx5: Validate correct PD before prefetch MR
  IB/mlx5: Protect against prefetch of invalid MR
  RDMA/uverbs: Store PR pointer before it is overwritten
  ...
		
	
			
		
			
				
	
	
		
			240 lines
		
	
	
	
		
			5.9 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			240 lines
		
	
	
	
		
			5.9 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
// SPDX-License-Identifier: GPL-2.0
 | 
						|
/*
 | 
						|
 * mm/debug.c
 | 
						|
 *
 | 
						|
 * mm/ specific debug routines.
 | 
						|
 *
 | 
						|
 */
 | 
						|
 | 
						|
#include <linux/kernel.h>
 | 
						|
#include <linux/mm.h>
 | 
						|
#include <linux/trace_events.h>
 | 
						|
#include <linux/memcontrol.h>
 | 
						|
#include <trace/events/mmflags.h>
 | 
						|
#include <linux/migrate.h>
 | 
						|
#include <linux/page_owner.h>
 | 
						|
#include <linux/ctype.h>
 | 
						|
 | 
						|
#include "internal.h"
 | 
						|
 | 
						|
const char *migrate_reason_names[MR_TYPES] = {
 | 
						|
	"compaction",
 | 
						|
	"memory_failure",
 | 
						|
	"memory_hotplug",
 | 
						|
	"syscall_or_cpuset",
 | 
						|
	"mempolicy_mbind",
 | 
						|
	"numa_misplaced",
 | 
						|
	"cma",
 | 
						|
};
 | 
						|
 | 
						|
const struct trace_print_flags pageflag_names[] = {
 | 
						|
	__def_pageflag_names,
 | 
						|
	{0, NULL}
 | 
						|
};
 | 
						|
 | 
						|
const struct trace_print_flags gfpflag_names[] = {
 | 
						|
	__def_gfpflag_names,
 | 
						|
	{0, NULL}
 | 
						|
};
 | 
						|
 | 
						|
const struct trace_print_flags vmaflag_names[] = {
 | 
						|
	__def_vmaflag_names,
 | 
						|
	{0, NULL}
 | 
						|
};
 | 
						|
 | 
						|
void __dump_page(struct page *page, const char *reason)
 | 
						|
{
 | 
						|
	struct address_space *mapping;
 | 
						|
	bool page_poisoned = PagePoisoned(page);
 | 
						|
	int mapcount;
 | 
						|
 | 
						|
	/*
 | 
						|
	 * If struct page is poisoned don't access Page*() functions as that
 | 
						|
	 * leads to recursive loop. Page*() check for poisoned pages, and calls
 | 
						|
	 * dump_page() when detected.
 | 
						|
	 */
 | 
						|
	if (page_poisoned) {
 | 
						|
		pr_warn("page:%px is uninitialized and poisoned", page);
 | 
						|
		goto hex_only;
 | 
						|
	}
 | 
						|
 | 
						|
	mapping = page_mapping(page);
 | 
						|
 | 
						|
	/*
 | 
						|
	 * Avoid VM_BUG_ON() in page_mapcount().
 | 
						|
	 * page->_mapcount space in struct page is used by sl[aou]b pages to
 | 
						|
	 * encode own info.
 | 
						|
	 */
 | 
						|
	mapcount = PageSlab(page) ? 0 : page_mapcount(page);
 | 
						|
 | 
						|
	pr_warn("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
 | 
						|
		  page, page_ref_count(page), mapcount,
 | 
						|
		  page->mapping, page_to_pgoff(page));
 | 
						|
	if (PageCompound(page))
 | 
						|
		pr_cont(" compound_mapcount: %d", compound_mapcount(page));
 | 
						|
	pr_cont("\n");
 | 
						|
	if (PageAnon(page))
 | 
						|
		pr_warn("anon ");
 | 
						|
	else if (PageKsm(page))
 | 
						|
		pr_warn("ksm ");
 | 
						|
	else if (mapping) {
 | 
						|
		pr_warn("%ps ", mapping->a_ops);
 | 
						|
		if (mapping->host->i_dentry.first) {
 | 
						|
			struct dentry *dentry;
 | 
						|
			dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias);
 | 
						|
			pr_warn("name:\"%pd\" ", dentry);
 | 
						|
		}
 | 
						|
	}
 | 
						|
	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
 | 
						|
 | 
						|
	pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags);
 | 
						|
 | 
						|
hex_only:
 | 
						|
	print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32,
 | 
						|
			sizeof(unsigned long), page,
 | 
						|
			sizeof(struct page), false);
 | 
						|
 | 
						|
	if (reason)
 | 
						|
		pr_warn("page dumped because: %s\n", reason);
 | 
						|
 | 
						|
#ifdef CONFIG_MEMCG
 | 
						|
	if (!page_poisoned && page->mem_cgroup)
 | 
						|
		pr_warn("page->mem_cgroup:%px\n", page->mem_cgroup);
 | 
						|
#endif
 | 
						|
}
 | 
						|
 | 
						|
void dump_page(struct page *page, const char *reason)
 | 
						|
{
 | 
						|
	__dump_page(page, reason);
 | 
						|
	dump_page_owner(page);
 | 
						|
}
 | 
						|
EXPORT_SYMBOL(dump_page);
 | 
						|
 | 
						|
#ifdef CONFIG_DEBUG_VM
 | 
						|
 | 
						|
void dump_vma(const struct vm_area_struct *vma)
 | 
						|
{
 | 
						|
	pr_emerg("vma %px start %px end %px\n"
 | 
						|
		"next %px prev %px mm %px\n"
 | 
						|
		"prot %lx anon_vma %px vm_ops %px\n"
 | 
						|
		"pgoff %lx file %px private_data %px\n"
 | 
						|
		"flags: %#lx(%pGv)\n",
 | 
						|
		vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
 | 
						|
		vma->vm_prev, vma->vm_mm,
 | 
						|
		(unsigned long)pgprot_val(vma->vm_page_prot),
 | 
						|
		vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
 | 
						|
		vma->vm_file, vma->vm_private_data,
 | 
						|
		vma->vm_flags, &vma->vm_flags);
 | 
						|
}
 | 
						|
EXPORT_SYMBOL(dump_vma);
 | 
						|
 | 
						|
void dump_mm(const struct mm_struct *mm)
 | 
						|
{
 | 
						|
	pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n"
 | 
						|
#ifdef CONFIG_MMU
 | 
						|
		"get_unmapped_area %px\n"
 | 
						|
#endif
 | 
						|
		"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
 | 
						|
		"pgd %px mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n"
 | 
						|
		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
 | 
						|
		"pinned_vm %llx data_vm %lx exec_vm %lx stack_vm %lx\n"
 | 
						|
		"start_code %lx end_code %lx start_data %lx end_data %lx\n"
 | 
						|
		"start_brk %lx brk %lx start_stack %lx\n"
 | 
						|
		"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
 | 
						|
		"binfmt %px flags %lx core_state %px\n"
 | 
						|
#ifdef CONFIG_AIO
 | 
						|
		"ioctx_table %px\n"
 | 
						|
#endif
 | 
						|
#ifdef CONFIG_MEMCG
 | 
						|
		"owner %px "
 | 
						|
#endif
 | 
						|
		"exe_file %px\n"
 | 
						|
#ifdef CONFIG_MMU_NOTIFIER
 | 
						|
		"mmu_notifier_mm %px\n"
 | 
						|
#endif
 | 
						|
#ifdef CONFIG_NUMA_BALANCING
 | 
						|
		"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
 | 
						|
#endif
 | 
						|
		"tlb_flush_pending %d\n"
 | 
						|
		"def_flags: %#lx(%pGv)\n",
 | 
						|
 | 
						|
		mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size,
 | 
						|
#ifdef CONFIG_MMU
 | 
						|
		mm->get_unmapped_area,
 | 
						|
#endif
 | 
						|
		mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
 | 
						|
		mm->pgd, atomic_read(&mm->mm_users),
 | 
						|
		atomic_read(&mm->mm_count),
 | 
						|
		mm_pgtables_bytes(mm),
 | 
						|
		mm->map_count,
 | 
						|
		mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
 | 
						|
		atomic64_read(&mm->pinned_vm),
 | 
						|
		mm->data_vm, mm->exec_vm, mm->stack_vm,
 | 
						|
		mm->start_code, mm->end_code, mm->start_data, mm->end_data,
 | 
						|
		mm->start_brk, mm->brk, mm->start_stack,
 | 
						|
		mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
 | 
						|
		mm->binfmt, mm->flags, mm->core_state,
 | 
						|
#ifdef CONFIG_AIO
 | 
						|
		mm->ioctx_table,
 | 
						|
#endif
 | 
						|
#ifdef CONFIG_MEMCG
 | 
						|
		mm->owner,
 | 
						|
#endif
 | 
						|
		mm->exe_file,
 | 
						|
#ifdef CONFIG_MMU_NOTIFIER
 | 
						|
		mm->mmu_notifier_mm,
 | 
						|
#endif
 | 
						|
#ifdef CONFIG_NUMA_BALANCING
 | 
						|
		mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
 | 
						|
#endif
 | 
						|
		atomic_read(&mm->tlb_flush_pending),
 | 
						|
		mm->def_flags, &mm->def_flags
 | 
						|
	);
 | 
						|
}
 | 
						|
 | 
						|
static bool page_init_poisoning __read_mostly = true;
 | 
						|
 | 
						|
static int __init setup_vm_debug(char *str)
 | 
						|
{
 | 
						|
	bool __page_init_poisoning = true;
 | 
						|
 | 
						|
	/*
 | 
						|
	 * Calling vm_debug with no arguments is equivalent to requesting
 | 
						|
	 * to enable all debugging options we can control.
 | 
						|
	 */
 | 
						|
	if (*str++ != '=' || !*str)
 | 
						|
		goto out;
 | 
						|
 | 
						|
	__page_init_poisoning = false;
 | 
						|
	if (*str == '-')
 | 
						|
		goto out;
 | 
						|
 | 
						|
	while (*str) {
 | 
						|
		switch (tolower(*str)) {
 | 
						|
		case'p':
 | 
						|
			__page_init_poisoning = true;
 | 
						|
			break;
 | 
						|
		default:
 | 
						|
			pr_err("vm_debug option '%c' unknown. skipped\n",
 | 
						|
			       *str);
 | 
						|
		}
 | 
						|
 | 
						|
		str++;
 | 
						|
	}
 | 
						|
out:
 | 
						|
	if (page_init_poisoning && !__page_init_poisoning)
 | 
						|
		pr_warn("Page struct poisoning disabled by kernel command line option 'vm_debug'\n");
 | 
						|
 | 
						|
	page_init_poisoning = __page_init_poisoning;
 | 
						|
 | 
						|
	return 1;
 | 
						|
}
 | 
						|
__setup("vm_debug", setup_vm_debug);
 | 
						|
 | 
						|
void page_init_poison(struct page *page, size_t size)
 | 
						|
{
 | 
						|
	if (page_init_poisoning)
 | 
						|
		memset(page, PAGE_POISON_PATTERN, size);
 | 
						|
}
 | 
						|
EXPORT_SYMBOL_GPL(page_init_poison);
 | 
						|
#endif		/* CONFIG_DEBUG_VM */
 |