linux/arch/powerpc/include/asm/book3s/64/pgalloc.h

185 lines
4.8 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef _ASM_POWERPC_BOOK3S_64_PGALLOC_H
#define _ASM_POWERPC_BOOK3S_64_PGALLOC_H
/*
*/
#include <linux/slab.h>
#include <linux/cpumask.h>
powerpc/mm: Don't report PUDs as memory leaks when using kmemleak Paul Menzel reported that kmemleak was producing reports such as: unreferenced object 0xc0000000f8b80000 (size 16384): comm "init", pid 1, jiffies 4294937416 (age 312.240s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000d997deb7>] __pud_alloc+0x80/0x190 [<0000000087f2e8a3>] move_page_tables+0xbac/0xdc0 [<00000000091e51c2>] shift_arg_pages+0xc0/0x210 [<00000000ab88670c>] setup_arg_pages+0x22c/0x2a0 [<0000000060871529>] load_elf_binary+0x41c/0x1648 [<00000000ecd9d2d4>] search_binary_handler.part.11+0xbc/0x280 [<0000000034e0cdd7>] __do_execve_file.isra.13+0x73c/0x940 [<000000005f953a6e>] sys_execve+0x58/0x70 [<000000009700a858>] system_call+0x5c/0x70 Indicating that a PUD was being leaked. However what's really happening is that kmemleak is not able to recognise the references from the PGD to the PUD, because they are not fully qualified pointers. We can confirm that in xmon, eg: Find the task struct for pid 1 "init": 0:mon> P task_struct ->thread.ksp PID PPID S P CMD c0000001fe7c0000 c0000001fe803960 1 0 S 13 systemd Dump virtual address 0 to find the PGD: 0:mon> dv 0 c0000001fe7c0000 pgd @ 0xc0000000f8b01000 Dump the memory of the PGD: 0:mon> d c0000000f8b01000 c0000000f8b01000 00000000f8b90000 0000000000000000 |................| c0000000f8b01010 0000000000000000 0000000000000000 |................| c0000000f8b01020 0000000000000000 0000000000000000 |................| c0000000f8b01030 0000000000000000 00000000f8b80000 |................| ^^^^^^^^^^^^^^^^ There we can see the reference to our supposedly leaked PUD. But because it's missing the leading 0xc, kmemleak won't recognise it. We can confirm it's still in use by translating an address that is mapped via it: 0:mon> dv 7fff94000000 c0000001fe7c0000 pgd @ 0xc0000000f8b01000 pgdp @ 0xc0000000f8b01038 = 0x00000000f8b80000 <-- pudp @ 0xc0000000f8b81ff8 = 0x00000000037c4000 pmdp @ 0xc0000000037c5ca0 = 0x00000000fbd89000 ptep @ 0xc0000000fbd89000 = 0xc0800001d5ce0386 Maps physical address = 0x00000001d5ce0000 Flags = Accessed Dirty Read Write The fix is fairly simple. We need to tell kmemleak to ignore PUD allocations and never report them as leaks. We can also tell it not to scan the PGD, because it will never find pointers in there. However it will still notice if we allocate a PGD and then leak it. Reported-by: Paul Menzel <pmenzel@molgen.mpg.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Tested-by: Paul Menzel <pmenzel@molgen.mpg.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-07-19 14:33:16 +00:00
#include <linux/kmemleak.h>
#include <linux/percpu.h>
struct vmemmap_backing {
struct vmemmap_backing *list;
unsigned long phys;
unsigned long virt_addr;
};
extern struct vmemmap_backing *vmemmap_list;
extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long);
extern void pmd_fragment_free(unsigned long *);
extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
#ifdef CONFIG_SMP
extern void __tlb_remove_table(void *_table);
#endif
void pte_frag_destroy(void *pte_frag);
static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
{
#ifdef CONFIG_PPC_64K_PAGES
return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP));
#else
struct page *page;
mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more useful semantic __GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to the page allocator. This has been true but only for allocations requests larger than PAGE_ALLOC_COSTLY_ORDER. It has been always ignored for smaller sizes. This is a bit unfortunate because there is no way to express the same semantic for those requests and they are considered too important to fail so they might end up looping in the page allocator for ever, similarly to GFP_NOFAIL requests. Now that the whole tree has been cleaned up and accidental or misled usage of __GFP_REPEAT flag has been removed for !costly requests we can give the original flag a better name and more importantly a more useful semantic. Let's rename it to __GFP_RETRY_MAYFAIL which tells the user that the allocator would try really hard but there is no promise of a success. This will work independent of the order and overrides the default allocator behavior. Page allocator users have several levels of guarantee vs. cost options (take GFP_KERNEL as an example) - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_ attempt to free memory at all. The most light weight mode which even doesn't kick the background reclaim. Should be used carefully because it might deplete the memory and the next user might hit the more aggressive reclaim - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic allocation without any attempt to free memory from the current context but can wake kswapd to reclaim memory if the zone is below the low watermark. Can be used from either atomic contexts or when the request is a performance optimization and there is another fallback for a slow path. - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) - non sleeping allocation with an expensive fallback so it can access some portion of memory reserves. Usually used from interrupt/bh context with an expensive slow path fallback. - GFP_KERNEL - both background and direct reclaim are allowed and the _default_ page allocator behavior is used. That means that !costly allocation requests are basically nofail but there is no guarantee of that behavior so failures have to be checked properly by callers (e.g. OOM killer victim is allowed to fail currently). - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior and all allocation requests fail early rather than cause disruptive reclaim (one round of reclaim in this implementation). The OOM killer is not invoked. - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator behavior and all allocation requests try really hard. The request will fail if the reclaim cannot make any progress. The OOM killer won't be triggered. - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior and all allocation requests will loop endlessly until they succeed. This might be really dangerous especially for larger orders. Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL because they already had their semantic. No new users are added. __alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if there is no progress and we have already passed the OOM point. This means that all the reclaim opportunities have been exhausted except the most disruptive one (the OOM killer) and a user defined fallback behavior is more sensible than keep retrying in the page allocator. [akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c] [mhocko@suse.com: semantic fix] Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz [mhocko@kernel.org: address other thing spotted by Vlastimil] Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Alex Belits <alex.belits@cavium.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Darrick J. Wong <darrick.wong@oracle.com> Cc: David Daney <david.daney@cavium.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: NeilBrown <neilb@suse.com> Cc: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-12 21:36:45 +00:00
page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_RETRY_MAYFAIL),
4);
if (!page)
return NULL;
return (pgd_t *) page_address(page);
#endif
}
static inline void radix__pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
#ifdef CONFIG_PPC_64K_PAGES
free_page((unsigned long)pgd);
#else
free_pages((unsigned long)pgd, 4);
#endif
}
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd;
if (radix_enabled())
return radix__pgd_alloc(mm);
pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
pgtable_gfp_flags(mm, GFP_KERNEL));
powerpc/book3s/64: check for NULL pointer in pgd_alloc() When the memset code was added to pgd_alloc(), it failed to consider that kmem_cache_alloc() can return NULL. It's uncommon, but not impossible under heavy memory contention. Example oops: Unable to handle kernel paging request for data at address 0x00000000 Faulting instruction address: 0xc0000000000a4000 Oops: Kernel access of bad area, sig: 11 [#1] LE SMP NR_CPUS=2048 NUMA pSeries CPU: 70 PID: 48471 Comm: entrypoint.sh Kdump: loaded Not tainted 4.14.0-115.6.1.el7a.ppc64le #1 task: c000000334a00000 task.stack: c000000331c00000 NIP: c0000000000a4000 LR: c00000000012f43c CTR: 0000000000000020 REGS: c000000331c039c0 TRAP: 0300 Not tainted (4.14.0-115.6.1.el7a.ppc64le) MSR: 800000010280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE,TM[E]> CR: 44022840 XER: 20040000 CFAR: c000000000008874 DAR: 0000000000000000 DSISR: 42000000 SOFTE: 1 ... NIP [c0000000000a4000] memset+0x68/0x104 LR [c00000000012f43c] mm_init+0x27c/0x2f0 Call Trace: mm_init+0x260/0x2f0 (unreliable) copy_mm+0x11c/0x638 copy_process.isra.28.part.29+0x6fc/0x1080 _do_fork+0xdc/0x4c0 ppc_clone+0x8/0xc Instruction dump: 409e000c b0860000 38c60002 409d000c 90860000 38c60004 78a0d183 78a506a0 7c0903a6 41820034 60000000 60420000 <f8860000> f8860008 f8860010 f8860018 Fixes: fc5c2f4a55a2 ("powerpc/mm/hash64: Zero PGD pages on allocation") Cc: stable@vger.kernel.org # v4.16+ Signed-off-by: Rick Lindsley <ricklind@vnet.linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-05-06 00:20:43 +00:00
if (unlikely(!pgd))
return pgd;
powerpc/mm: Don't report PUDs as memory leaks when using kmemleak Paul Menzel reported that kmemleak was producing reports such as: unreferenced object 0xc0000000f8b80000 (size 16384): comm "init", pid 1, jiffies 4294937416 (age 312.240s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000d997deb7>] __pud_alloc+0x80/0x190 [<0000000087f2e8a3>] move_page_tables+0xbac/0xdc0 [<00000000091e51c2>] shift_arg_pages+0xc0/0x210 [<00000000ab88670c>] setup_arg_pages+0x22c/0x2a0 [<0000000060871529>] load_elf_binary+0x41c/0x1648 [<00000000ecd9d2d4>] search_binary_handler.part.11+0xbc/0x280 [<0000000034e0cdd7>] __do_execve_file.isra.13+0x73c/0x940 [<000000005f953a6e>] sys_execve+0x58/0x70 [<000000009700a858>] system_call+0x5c/0x70 Indicating that a PUD was being leaked. However what's really happening is that kmemleak is not able to recognise the references from the PGD to the PUD, because they are not fully qualified pointers. We can confirm that in xmon, eg: Find the task struct for pid 1 "init": 0:mon> P task_struct ->thread.ksp PID PPID S P CMD c0000001fe7c0000 c0000001fe803960 1 0 S 13 systemd Dump virtual address 0 to find the PGD: 0:mon> dv 0 c0000001fe7c0000 pgd @ 0xc0000000f8b01000 Dump the memory of the PGD: 0:mon> d c0000000f8b01000 c0000000f8b01000 00000000f8b90000 0000000000000000 |................| c0000000f8b01010 0000000000000000 0000000000000000 |................| c0000000f8b01020 0000000000000000 0000000000000000 |................| c0000000f8b01030 0000000000000000 00000000f8b80000 |................| ^^^^^^^^^^^^^^^^ There we can see the reference to our supposedly leaked PUD. But because it's missing the leading 0xc, kmemleak won't recognise it. We can confirm it's still in use by translating an address that is mapped via it: 0:mon> dv 7fff94000000 c0000001fe7c0000 pgd @ 0xc0000000f8b01000 pgdp @ 0xc0000000f8b01038 = 0x00000000f8b80000 <-- pudp @ 0xc0000000f8b81ff8 = 0x00000000037c4000 pmdp @ 0xc0000000037c5ca0 = 0x00000000fbd89000 ptep @ 0xc0000000fbd89000 = 0xc0800001d5ce0386 Maps physical address = 0x00000001d5ce0000 Flags = Accessed Dirty Read Write The fix is fairly simple. We need to tell kmemleak to ignore PUD allocations and never report them as leaks. We can also tell it not to scan the PGD, because it will never find pointers in there. However it will still notice if we allocate a PGD and then leak it. Reported-by: Paul Menzel <pmenzel@molgen.mpg.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Tested-by: Paul Menzel <pmenzel@molgen.mpg.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-07-19 14:33:16 +00:00
/*
* Don't scan the PGD for pointers, it contains references to PUDs but
* those references are not full pointers and so can't be recognised by
* kmemleak.
*/
kmemleak_no_scan(pgd);
/*
* With hugetlb, we don't clear the second half of the page table.
* If we share the same slab cache with the pmd or pud level table,
* we need to make sure we zero out the full table on alloc.
* With 4K we don't store slot in the second half. Hence we don't
* need to do this for 4k.
*/
#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) && \
(H_PGD_INDEX_SIZE == H_PUD_CACHE_INDEX)
memset(pgd, 0, PGD_TABLE_SIZE);
#endif
return pgd;
}
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
if (radix_enabled())
return radix__pgd_free(mm, pgd);
kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
}
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
{
*pgd = __pgd(__pgtable_ptr_val(pud) | PGD_VAL_BITS);
}
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
powerpc/mm: Don't report PUDs as memory leaks when using kmemleak Paul Menzel reported that kmemleak was producing reports such as: unreferenced object 0xc0000000f8b80000 (size 16384): comm "init", pid 1, jiffies 4294937416 (age 312.240s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000d997deb7>] __pud_alloc+0x80/0x190 [<0000000087f2e8a3>] move_page_tables+0xbac/0xdc0 [<00000000091e51c2>] shift_arg_pages+0xc0/0x210 [<00000000ab88670c>] setup_arg_pages+0x22c/0x2a0 [<0000000060871529>] load_elf_binary+0x41c/0x1648 [<00000000ecd9d2d4>] search_binary_handler.part.11+0xbc/0x280 [<0000000034e0cdd7>] __do_execve_file.isra.13+0x73c/0x940 [<000000005f953a6e>] sys_execve+0x58/0x70 [<000000009700a858>] system_call+0x5c/0x70 Indicating that a PUD was being leaked. However what's really happening is that kmemleak is not able to recognise the references from the PGD to the PUD, because they are not fully qualified pointers. We can confirm that in xmon, eg: Find the task struct for pid 1 "init": 0:mon> P task_struct ->thread.ksp PID PPID S P CMD c0000001fe7c0000 c0000001fe803960 1 0 S 13 systemd Dump virtual address 0 to find the PGD: 0:mon> dv 0 c0000001fe7c0000 pgd @ 0xc0000000f8b01000 Dump the memory of the PGD: 0:mon> d c0000000f8b01000 c0000000f8b01000 00000000f8b90000 0000000000000000 |................| c0000000f8b01010 0000000000000000 0000000000000000 |................| c0000000f8b01020 0000000000000000 0000000000000000 |................| c0000000f8b01030 0000000000000000 00000000f8b80000 |................| ^^^^^^^^^^^^^^^^ There we can see the reference to our supposedly leaked PUD. But because it's missing the leading 0xc, kmemleak won't recognise it. We can confirm it's still in use by translating an address that is mapped via it: 0:mon> dv 7fff94000000 c0000001fe7c0000 pgd @ 0xc0000000f8b01000 pgdp @ 0xc0000000f8b01038 = 0x00000000f8b80000 <-- pudp @ 0xc0000000f8b81ff8 = 0x00000000037c4000 pmdp @ 0xc0000000037c5ca0 = 0x00000000fbd89000 ptep @ 0xc0000000fbd89000 = 0xc0800001d5ce0386 Maps physical address = 0x00000001d5ce0000 Flags = Accessed Dirty Read Write The fix is fairly simple. We need to tell kmemleak to ignore PUD allocations and never report them as leaks. We can also tell it not to scan the PGD, because it will never find pointers in there. However it will still notice if we allocate a PGD and then leak it. Reported-by: Paul Menzel <pmenzel@molgen.mpg.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Tested-by: Paul Menzel <pmenzel@molgen.mpg.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-07-19 14:33:16 +00:00
pud_t *pud;
pud = kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX),
pgtable_gfp_flags(mm, GFP_KERNEL));
/*
* Tell kmemleak to ignore the PUD, that means don't scan it for
* pointers and don't consider it a leak. PUDs are typically only
* referred to by their PGD, but kmemleak is not able to recognise those
* as pointers, leading to false leak reports.
*/
kmemleak_ignore(pud);
return pud;
}
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
{
kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud);
}
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
{
*pud = __pud(__pgtable_ptr_val(pmd) | PUD_VAL_BITS);
}
static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
unsigned long address)
{
/*
* By now all the pud entries should be none entries. So go
* ahead and flush the page walk cache
*/
flush_tlb_pgtable(tlb, address);
pgtable_free_tlb(tlb, pud, PUD_INDEX);
}
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
return pmd_fragment_alloc(mm, addr);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
pmd_fragment_free((unsigned long *)pmd);
}
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
unsigned long address)
{
/*
* By now all the pud entries should be none entries. So go
* ahead and flush the page walk cache
*/
flush_tlb_pgtable(tlb, address);
return pgtable_free_tlb(tlb, pmd, PMD_INDEX);
}
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
pte_t *pte)
{
*pmd = __pmd(__pgtable_ptr_val(pte) | PMD_VAL_BITS);
}
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
pgtable_t pte_page)
{
*pmd = __pmd(__pgtable_ptr_val(pte_page) | PMD_VAL_BITS);
}
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
/*
* By now all the pud entries should be none entries. So go
* ahead and flush the page walk cache
*/
flush_tlb_pgtable(tlb, address);
pgtable_free_tlb(tlb, table, PTE_INDEX);
}
extern atomic_long_t direct_pages_count[MMU_PAGE_COUNT];
static inline void update_page_count(int psize, long count)
{
if (IS_ENABLED(CONFIG_PROC_FS))
atomic_long_add(count, &direct_pages_count[psize]);
}
#endif /* _ASM_POWERPC_BOOK3S_64_PGALLOC_H */