From f7a31b5e7874f77464a4eae0a8ba84b9ae0b3a54 Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Wed, 19 Apr 2017 14:07:43 +0200 Subject: MIPS: perf: Remove incorrect odd/even counter handling for I6400 All performance counters on I6400 (odd and even) are capable of counting any of the available events, so drop current logic of using the extra bit to determine which counter to use. Signed-off-by: Marcin Nowakowski Fixes: 4e88a8621301 ("MIPS: Add cases for CPU_I6400") Fixes: fd716fca10fc ("MIPS: perf: Fix I6400 event numbers") Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/15991/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/perf_event_mipsxx.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/mips') diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index 313a88b2973f..f3e301f95aef 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1597,7 +1597,6 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) break; case CPU_P5600: case CPU_P6600: - case CPU_I6400: /* 8-bit event numbers */ raw_id = config & 0x1ff; base_id = raw_id & 0xff; @@ -1610,6 +1609,11 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) raw_event.range = P; #endif break; + case CPU_I6400: + /* 8-bit event numbers */ + base_id = config & 0xff; + raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; + break; case CPU_1004K: if (IS_BOTH_COUNTERS_1004K_EVENT(base_id)) raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; -- cgit v1.2.3 From 71eb989ab5a110df8bcbb9609bacde73feacbedd Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Tue, 11 Apr 2017 09:00:34 +0200 Subject: MIPS: mm: fixed mappings: correct initialisation fixrange_init operates at PMD-granularity and expects the addresses to be PMD-size aligned, but currently that might not be the case for PKMAP_BASE unless it is defined properly, so ensure a correct alignment is used before passing the address to fixrange_init. fixed mappings: only align the start address that is passed to fixrange_init rather than the value before adding the size, as we may end up with uninitialised upper part of the range. Signed-off-by: Marcin Nowakowski Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/15948/ Signed-off-by: Ralf Baechle --- arch/mips/mm/pgtable-32.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/mips') diff --git a/arch/mips/mm/pgtable-32.c b/arch/mips/mm/pgtable-32.c index adc6911ba748..b19a3c506b1e 100644 --- a/arch/mips/mm/pgtable-32.c +++ b/arch/mips/mm/pgtable-32.c @@ -51,15 +51,15 @@ void __init pagetable_init(void) /* * Fixed mappings: */ - vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; - fixrange_init(vaddr, vaddr + FIXADDR_SIZE, pgd_base); + vaddr = __fix_to_virt(__end_of_fixed_addresses - 1); + fixrange_init(vaddr & PMD_MASK, vaddr + FIXADDR_SIZE, pgd_base); #ifdef CONFIG_HIGHMEM /* * Permanent kmaps: */ vaddr = PKMAP_BASE; - fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); + fixrange_init(vaddr & PMD_MASK, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); pgd = swapper_pg_dir + __pgd_offset(vaddr); pud = pud_offset(pgd, vaddr); -- cgit v1.2.3 From 725a269b3dd149f36c206c218253336774ef26f5 Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Tue, 11 Apr 2017 09:00:35 +0200 Subject: MIPS: highmem: ensure that we don't use more than one page for PTEs All PTEs used by PKMAP should be allocated in a contiguous memory area, but we do not currently have a mechanism to enforce that, so ensure that we don't try to allocate more entries than would fit in a single page. Current fixed value of 1024 would not work with XPA enabled when sizeof(pte_t)==8 and we need two pages to store pte tables. Signed-off-by: Marcin Nowakowski Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/15949/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/highmem.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/mips') diff --git a/arch/mips/include/asm/highmem.h b/arch/mips/include/asm/highmem.h index d34536e7653f..279b6d14ffeb 100644 --- a/arch/mips/include/asm/highmem.h +++ b/arch/mips/include/asm/highmem.h @@ -35,7 +35,12 @@ extern pte_t *pkmap_page_table; * easily, subsequent pte tables have to be allocated in one physical * chunk of RAM. */ +#ifdef CONFIG_PHYS_ADDR_T_64BIT +#define LAST_PKMAP 512 +#else #define LAST_PKMAP 1024 +#endif + #define LAST_PKMAP_MASK (LAST_PKMAP-1) #define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT) #define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) -- cgit v1.2.3 From c56e7a4c3e77f6fbd9b55c06c14eda65aae58958 Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Tue, 11 Apr 2017 09:00:36 +0200 Subject: MIPS: mm: adjust PKMAP location Space reserved for PKMap should span from PKMAP_BASE to FIXADDR_START. For large page sizes this is not the case as eg. for 64k pages the range currently defined is from 0xfe000000 to 0x102000000(!!) which obviously isn't right. Remove the hardcoded location and set the BASE address as an offset from FIXADDR_START. Since all PKMAP ptes have to be placed in a contiguous memory, ensure that this is the case by placing them all in a single page. This is achieved by aligning the end address to pkmap pages count pages. Signed-off-by: Marcin Nowakowski Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/15950/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/pgtable-32.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/mips') diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index 6f94bed571c4..74afe8c76bdd 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -19,6 +19,10 @@ #define __ARCH_USE_5LEVEL_HACK #include +#ifdef CONFIG_HIGHMEM +#include +#endif + extern int temp_tlb_entry; /* @@ -62,7 +66,8 @@ extern int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1, #define VMALLOC_START MAP_BASE -#define PKMAP_BASE (0xfe000000UL) +#define PKMAP_END ((FIXADDR_START) & ~((LAST_PKMAP << PAGE_SHIFT)-1)) +#define PKMAP_BASE (PKMAP_END - PAGE_SIZE * LAST_PKMAP) #ifdef CONFIG_HIGHMEM # define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE) -- cgit v1.2.3 From 87051ec120bb9abd9e57aecf2569c00d587b6f33 Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Tue, 23 May 2017 12:56:43 +0200 Subject: MIPS: ftrace: fix init functions tracing Since introduction of tracing for init functions the in_kernel_space() check is no longer correct, as it ignores the init sections. As a result, when probes are inserted (and disabled) in the init functions, a branch instruction is inserted instead of a nop, which is likely to result in random crashes during boot. Remove the MIPS-specific in_kernel_space() method and replace it with a generic core_kernel_text() that also checks for init sections during system boot stage. Fixes: 42c269c88dc1 ("ftrace: Allow for function tracing to record init functions on boot up") Signed-off-by: Marcin Nowakowski Tested-by: Matt Redfearn Cc: Steven Rostedt Cc: Ingo Molnar Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16092/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/ftrace.c | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-) (limited to 'arch/mips') diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 30a3b75e88eb..9d9b8fbae202 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -38,20 +38,6 @@ void arch_ftrace_update_code(int command) #endif -/* - * Check if the address is in kernel space - * - * Clone core_kernel_text() from kernel/extable.c, but doesn't call - * init_kernel_text() for Ftrace doesn't trace functions in init sections. - */ -static inline int in_kernel_space(unsigned long ip) -{ - if (ip >= (unsigned long)_stext && - ip <= (unsigned long)_etext) - return 1; - return 0; -} - #ifdef CONFIG_DYNAMIC_FTRACE #define JAL 0x0c000000 /* jump & link: ip --> ra, jump to target */ @@ -198,7 +184,7 @@ int ftrace_make_nop(struct module *mod, * If ip is in kernel space, no long call, otherwise, long call is * needed. */ - new = in_kernel_space(ip) ? INSN_NOP : INSN_B_1F; + new = core_kernel_text(ip) ? INSN_NOP : INSN_B_1F; #ifdef CONFIG_64BIT return ftrace_modify_code(ip, new); #else @@ -218,12 +204,12 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) unsigned int new; unsigned long ip = rec->ip; - new = in_kernel_space(ip) ? insn_jal_ftrace_caller : insn_la_mcount[0]; + new = core_kernel_text(ip) ? insn_jal_ftrace_caller : insn_la_mcount[0]; #ifdef CONFIG_64BIT return ftrace_modify_code(ip, new); #else - return ftrace_modify_code_2r(ip, new, in_kernel_space(ip) ? + return ftrace_modify_code_2r(ip, new, core_kernel_text(ip) ? INSN_NOP : insn_la_mcount[1]); #endif } @@ -289,7 +275,7 @@ unsigned long ftrace_get_parent_ra_addr(unsigned long self_ra, unsigned long * instruction "lui v1, hi_16bit_of_mcount"(offset is 24), but for * kernel, move after the instruction "move ra, at"(offset is 16) */ - ip = self_ra - (in_kernel_space(self_ra) ? 16 : 24); + ip = self_ra - (core_kernel_text(self_ra) ? 16 : 24); /* * search the text until finding the non-store instruction or "s{d,w} @@ -394,7 +380,7 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, * entries configured through the tracing/set_graph_function interface. */ - insns = in_kernel_space(self_ra) ? 2 : MCOUNT_OFFSET_INSNS + 1; + insns = core_kernel_text(self_ra) ? 2 : MCOUNT_OFFSET_INSNS + 1; trace.func = self_ra - (MCOUNT_INSN_SIZE * insns); /* Only trace if the calling function expects to */ -- cgit v1.2.3 From 698b851073ddf5a894910d63ca04605e0473414e Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Thu, 8 Jun 2017 15:20:32 +0200 Subject: MIPS: kprobes: flush_insn_slot should flush only if probe initialised When ftrace is used with kprobes, it is possible for a kprobe to contain an invalid location (ie. only initialised to 0 and not to a specific location in the code). Trying to perform a cache flush on such location leads to a crash r4k_flush_icache_range(). Fixes: c1bf207d6ee1 ("MIPS: kprobe: Add support.") Signed-off-by: Marcin Nowakowski Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16296/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/kprobes.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/mips') diff --git a/arch/mips/include/asm/kprobes.h b/arch/mips/include/asm/kprobes.h index 291846d9ba83..ad1a99948f27 100644 --- a/arch/mips/include/asm/kprobes.h +++ b/arch/mips/include/asm/kprobes.h @@ -43,7 +43,8 @@ typedef union mips_instruction kprobe_opcode_t; #define flush_insn_slot(p) \ do { \ - flush_icache_range((unsigned long)p->addr, \ + if (p->addr) \ + flush_icache_range((unsigned long)p->addr, \ (unsigned long)p->addr + \ (MAX_INSN_SIZE * sizeof(kprobe_opcode_t))); \ } while (0) -- cgit v1.2.3 From 1a73d9310e093fc3adffba4d0a67b9fab2ee3f63 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 11:35:01 -0700 Subject: MIPS: Fix bnezc/jialc return address calculation The code handling the pop76 opcode (ie. bnezc & jialc instructions) in __compute_return_epc_for_insn() needs to set the value of $31 in the jialc case, which is encoded with rs = 0. However its check to differentiate bnezc (rs != 0) from jialc (rs = 0) was unfortunately backwards, meaning that if we emulate a bnezc instruction we clobber $31 & if we emulate a jialc instruction it actually behaves like a jic instruction. Fix this by inverting the check of rs to match the way the instructions are actually encoded. Signed-off-by: Paul Burton Fixes: 28d6f93d201d ("MIPS: Emulate the new MIPS R6 BNEZC and JIALC instructions") Cc: stable # v4.0+ Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16178/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/branch.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/mips') diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index b11facd11c9d..f702a459a830 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -804,8 +804,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, break; } /* Compact branch: BNEZC || JIALC */ - if (insn.i_format.rs) + if (!insn.i_format.rs) { + /* JIALC: set $31/ra */ regs->regs[31] = epc + 4; + } regs->cp0_epc += 8; break; #endif -- cgit v1.2.3 From bcd7c45e0d5a82be9a64b90050f0e09d41a50758 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:02:08 -0700 Subject: MIPS: .its targets depend on vmlinux The .its targets require information about the kernel binary, such as its entry point, which is extracted from the vmlinux ELF. We therefore require that the ELF is built before the .its files are generated. Declare this requirement in the Makefile such that make will ensure this is always the case, otherwise in corner cases we can hit issues as the .its is generated with an incorrect (either invalid or stale) entry point. Signed-off-by: Paul Burton Fixes: cf2a5e0bb4c6 ("MIPS: Support generating Flattened Image Trees (.itb)") Cc: linux-mips@linux-mips.org Cc: stable # v4.9+ Patchwork: https://patchwork.linux-mips.org/patch/16179/ Signed-off-by: Ralf Baechle --- arch/mips/boot/Makefile | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/mips') diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile index 2728a9a9c7c5..145b5ce8eb7e 100644 --- a/arch/mips/boot/Makefile +++ b/arch/mips/boot/Makefile @@ -128,19 +128,19 @@ quiet_cmd_cpp_its_S = ITS $@ -DADDR_BITS=$(ADDR_BITS) \ -DADDR_CELLS=$(itb_addr_cells) -$(obj)/vmlinux.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE +$(obj)/vmlinux.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S $(VMLINUX) FORCE $(call if_changed_dep,cpp_its_S,none,vmlinux.bin) -$(obj)/vmlinux.gz.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE +$(obj)/vmlinux.gz.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S $(VMLINUX) FORCE $(call if_changed_dep,cpp_its_S,gzip,vmlinux.bin.gz) -$(obj)/vmlinux.bz2.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE +$(obj)/vmlinux.bz2.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S $(VMLINUX) FORCE $(call if_changed_dep,cpp_its_S,bzip2,vmlinux.bin.bz2) -$(obj)/vmlinux.lzma.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE +$(obj)/vmlinux.lzma.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S $(VMLINUX) FORCE $(call if_changed_dep,cpp_its_S,lzma,vmlinux.bin.lzma) -$(obj)/vmlinux.lzo.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE +$(obj)/vmlinux.lzo.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S $(VMLINUX) FORCE $(call if_changed_dep,cpp_its_S,lzo,vmlinux.bin.lzo) quiet_cmd_itb-image = ITB $@ -- cgit v1.2.3 From 1be7107fbe18eed3e319a6c3e83c78254b693acb Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 19 Jun 2017 04:03:24 -0700 Subject: mm: larger stack guard gap, between vmas Stack guard page is a useful feature to reduce a risk of stack smashing into a different mapping. We have been using a single page gap which is sufficient to prevent having stack adjacent to a different mapping. But this seems to be insufficient in the light of the stack usage in userspace. E.g. glibc uses as large as 64kB alloca() in many commonly used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX] which is 256kB or stack strings with MAX_ARG_STRLEN. This will become especially dangerous for suid binaries and the default no limit for the stack size limit because those applications can be tricked to consume a large portion of the stack and a single glibc call could jump over the guard page. These attacks are not theoretical, unfortunatelly. Make those attacks less probable by increasing the stack guard gap to 1MB (on systems with 4k pages; but make it depend on the page size because systems with larger base pages might cap stack allocations in the PAGE_SIZE units) which should cover larger alloca() and VLA stack allocations. It is obviously not a full fix because the problem is somehow inherent, but it should reduce attack space a lot. One could argue that the gap size should be configurable from userspace, but that can be done later when somebody finds that the new 1MB is wrong for some special case applications. For now, add a kernel command line option (stack_guard_gap) to specify the stack gap size (in page units). Implementation wise, first delete all the old code for stack guard page: because although we could get away with accounting one extra page in a stack vma, accounting a larger gap can break userspace - case in point, a program run with "ulimit -S -v 20000" failed when the 1MB gap was counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK and strict non-overcommit mode. Instead of keeping gap inside the stack vma, maintain the stack guard gap as a gap between vmas: using vm_start_gap() in place of vm_start (or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few places which need to respect the gap - mainly arch_get_unmapped_area(), and and the vma tree's subtree_gap support for that. Original-patch-by: Oleg Nesterov Original-patch-by: Michal Hocko Signed-off-by: Hugh Dickins Acked-by: Michal Hocko Tested-by: Helge Deller # parisc Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 7 ++ arch/arc/mm/mmap.c | 2 +- arch/arm/mm/mmap.c | 4 +- arch/frv/mm/elf-fdpic.c | 2 +- arch/mips/mm/mmap.c | 2 +- arch/parisc/kernel/sys_parisc.c | 15 ++- arch/powerpc/mm/hugetlbpage-radix.c | 2 +- arch/powerpc/mm/mmap.c | 4 +- arch/powerpc/mm/slice.c | 2 +- arch/s390/mm/mmap.c | 4 +- arch/sh/mm/mmap.c | 4 +- arch/sparc/kernel/sys_sparc_64.c | 4 +- arch/sparc/mm/hugetlbpage.c | 2 +- arch/tile/mm/hugetlbpage.c | 2 +- arch/x86/kernel/sys_x86_64.c | 4 +- arch/x86/mm/hugetlbpage.c | 2 +- arch/xtensa/kernel/syscall.c | 2 +- fs/hugetlbfs/inode.c | 2 +- fs/proc/task_mmu.c | 4 - include/linux/mm.h | 53 ++++----- mm/gup.c | 5 - mm/memory.c | 38 ------ mm/mmap.c | 149 ++++++++++++++---------- 23 files changed, 152 insertions(+), 163 deletions(-) (limited to 'arch/mips') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 0f5c3b4347c6..7737ab5d04b2 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3811,6 +3811,13 @@ expediting. Set to zero to disable automatic expediting. + stack_guard_gap= [MM] + override the default stack gap protection. The value + is in page units and it defines how many pages prior + to (for stacks growing down) resp. after (for stacks + growing up) the main stack are reserved for no other + mapping. Default value is 256 pages. + stacktrace [FTRACE] Enabled the stack tracer on boot up. diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c index 3e25e8d6486b..2e13683dfb24 100644 --- a/arch/arc/mm/mmap.c +++ b/arch/arc/mm/mmap.c @@ -65,7 +65,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 2239fde10b80..f0701d8d24df 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -90,7 +90,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -141,7 +141,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/frv/mm/elf-fdpic.c b/arch/frv/mm/elf-fdpic.c index da82c25301e7..46aa289c5102 100644 --- a/arch/frv/mm/elf-fdpic.c +++ b/arch/frv/mm/elf-fdpic.c @@ -75,7 +75,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi addr = PAGE_ALIGN(addr); vma = find_vma(current->mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) goto success; } diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 64dd8bdd92c3..28adeabe851f 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -93,7 +93,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index e5288638a1d9..378a754ca186 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -90,7 +90,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; unsigned long task_size = TASK_SIZE; int do_color_align, last_mmap; struct vm_unmapped_area_info info; @@ -117,9 +117,10 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, else addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + vma = find_vma_prev(mm, addr, &prev); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) goto found_addr; } @@ -143,7 +144,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, const unsigned long flags) { - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; unsigned long addr = addr0; int do_color_align, last_mmap; @@ -177,9 +178,11 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = COLOR_ALIGN(addr, last_mmap, pgoff); else addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + + vma = find_vma_prev(mm, addr, &prev); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) goto found_addr; } diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c index 6575b9aabef4..a12e86395025 100644 --- a/arch/powerpc/mm/hugetlbpage-radix.c +++ b/arch/powerpc/mm/hugetlbpage-radix.c @@ -68,7 +68,7 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (mm->task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } /* diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 9dbd2a733d6b..0ee6be4f1ba4 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -112,7 +112,7 @@ radix__arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (mm->task_size - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -157,7 +157,7 @@ radix__arch_get_unmapped_area_topdown(struct file *filp, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (mm->task_size - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 966b9fccfa66..45f6740dd407 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -99,7 +99,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr, if ((mm->task_size - len) < addr) return 0; vma = find_vma(mm, addr); - return (!vma || (addr + len) <= vma->vm_start); + return (!vma || (addr + len) <= vm_start_gap(vma)); } static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice) diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index b017daed6887..b854b1da281a 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -101,7 +101,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) goto check_asce_limit; } @@ -151,7 +151,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) goto check_asce_limit; } diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c index 08e7af0be4a7..6a1a1297baae 100644 --- a/arch/sh/mm/mmap.c +++ b/arch/sh/mm/mmap.c @@ -64,7 +64,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -114,7 +114,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index ef4520efc813..043544d0cda3 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -120,7 +120,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -183,7 +183,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 7c29d38e6b99..88855e383b34 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -120,7 +120,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c index cb10153b5c9f..03e5cc4e76e4 100644 --- a/arch/tile/mm/hugetlbpage.c +++ b/arch/tile/mm/hugetlbpage.c @@ -233,7 +233,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (current->mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 207b8f2582c7..213ddf3e937d 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (end - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -187,7 +187,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 302f43fd9c28..adad702b39cd 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -148,7 +148,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c index 06937928cb72..74afbf02d07e 100644 --- a/arch/xtensa/kernel/syscall.c +++ b/arch/xtensa/kernel/syscall.c @@ -88,7 +88,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, /* At this point: (!vmm || addr < vmm->vm_end). */ if (TASK_SIZE - len < addr) return -ENOMEM; - if (!vmm || addr + len <= vmm->vm_start) + if (!vmm || addr + len <= vm_start_gap(vmm)) return addr; addr = vmm->vm_end; if (flags & MAP_SHARED) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index dde861387a40..d44f5456eb9b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -200,7 +200,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f0c8b33d99b1..520802da059c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -300,11 +300,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) /* We don't show the stack guard page in /proc/maps */ start = vma->vm_start; - if (stack_guard_page_start(vma, start)) - start += PAGE_SIZE; end = vma->vm_end; - if (stack_guard_page_end(vma, end)) - end -= PAGE_SIZE; seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", diff --git a/include/linux/mm.h b/include/linux/mm.h index b892e95d4929..6f543a47fc92 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1393,12 +1393,6 @@ int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); -/* Is the vma a continuation of the stack vma above it? */ -static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr) -{ - return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); -} - static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; @@ -1414,28 +1408,6 @@ bool vma_is_shmem(struct vm_area_struct *vma); static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } #endif -static inline int stack_guard_page_start(struct vm_area_struct *vma, - unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSDOWN) && - (vma->vm_start == addr) && - !vma_growsdown(vma->vm_prev, addr); -} - -/* Is the vma a continuation of the stack vma below it? */ -static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr) -{ - return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP); -} - -static inline int stack_guard_page_end(struct vm_area_struct *vma, - unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSUP) && - (vma->vm_end == addr) && - !vma_growsup(vma->vm_next, addr); -} - int vma_is_stack_for_current(struct vm_area_struct *vma); extern unsigned long move_page_tables(struct vm_area_struct *vma, @@ -2222,6 +2194,7 @@ void page_cache_async_readahead(struct address_space *mapping, pgoff_t offset, unsigned long size); +extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); @@ -2250,6 +2223,30 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m return vma; } +static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +{ + unsigned long vm_start = vma->vm_start; + + if (vma->vm_flags & VM_GROWSDOWN) { + vm_start -= stack_guard_gap; + if (vm_start > vma->vm_start) + vm_start = 0; + } + return vm_start; +} + +static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +{ + unsigned long vm_end = vma->vm_end; + + if (vma->vm_flags & VM_GROWSUP) { + vm_end += stack_guard_gap; + if (vm_end < vma->vm_end) + vm_end = -PAGE_SIZE; + } + return vm_end; +} + static inline unsigned long vma_pages(struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; diff --git a/mm/gup.c b/mm/gup.c index b3c7214d710d..576c4df58882 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -387,11 +387,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, /* mlock all present pages, but do not fault in new pages */ if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK) return -ENOENT; - /* For mm_populate(), just skip the stack guard page. */ - if ((*flags & FOLL_POPULATE) && - (stack_guard_page_start(vma, address) || - stack_guard_page_end(vma, address + PAGE_SIZE))) - return -ENOENT; if (*flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (*flags & FOLL_REMOTE) diff --git a/mm/memory.c b/mm/memory.c index 2e65df1831d9..bb11c474857e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2854,40 +2854,6 @@ out_release: return ret; } -/* - * This is like a special single-page "expand_{down|up}wards()", - * except we must first make sure that 'address{-|+}PAGE_SIZE' - * doesn't hit another vma. - */ -static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address) -{ - address &= PAGE_MASK; - if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) { - struct vm_area_struct *prev = vma->vm_prev; - - /* - * Is there a mapping abutting this one below? - * - * That's only ok if it's the same stack mapping - * that has gotten split.. - */ - if (prev && prev->vm_end == address) - return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; - - return expand_downwards(vma, address - PAGE_SIZE); - } - if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { - struct vm_area_struct *next = vma->vm_next; - - /* As VM_GROWSDOWN but s/below/above/ */ - if (next && next->vm_start == address + PAGE_SIZE) - return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; - - return expand_upwards(vma, address + PAGE_SIZE); - } - return 0; -} - /* * We enter with non-exclusive mmap_sem (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. @@ -2904,10 +2870,6 @@ static int do_anonymous_page(struct vm_fault *vmf) if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; - /* Check if we need to add a guard page to the stack */ - if (check_stack_guard_page(vma, vmf->address) < 0) - return VM_FAULT_SIGSEGV; - /* * Use pte_alloc() instead of pte_alloc_map(). We can't run * pte_offset_map() on pmds where a huge pmd might be created diff --git a/mm/mmap.c b/mm/mmap.c index f82741e199c0..8e07976d5e47 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -183,6 +183,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) unsigned long retval; unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; + struct vm_area_struct *next; unsigned long min_brk; bool populate; LIST_HEAD(uf); @@ -229,7 +230,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) } /* Check against existing mmap mappings. */ - if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE)) + next = find_vma(mm, oldbrk); + if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; /* Ok, looks good - let it rip. */ @@ -253,10 +255,22 @@ out: static long vma_compute_subtree_gap(struct vm_area_struct *vma) { - unsigned long max, subtree_gap; - max = vma->vm_start; - if (vma->vm_prev) - max -= vma->vm_prev->vm_end; + unsigned long max, prev_end, subtree_gap; + + /* + * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we + * allow two stack_guard_gaps between them here, and when choosing + * an unmapped area; whereas when expanding we only require one. + * That's a little inconsistent, but keeps the code here simpler. + */ + max = vm_start_gap(vma); + if (vma->vm_prev) { + prev_end = vm_end_gap(vma->vm_prev); + if (max > prev_end) + max -= prev_end; + else + max = 0; + } if (vma->vm_rb.rb_left) { subtree_gap = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb)->rb_subtree_gap; @@ -352,7 +366,7 @@ static void validate_mm(struct mm_struct *mm) anon_vma_unlock_read(anon_vma); } - highest_address = vma->vm_end; + highest_address = vm_end_gap(vma); vma = vma->vm_next; i++; } @@ -541,7 +555,7 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, if (vma->vm_next) vma_gap_update(vma->vm_next); else - mm->highest_vm_end = vma->vm_end; + mm->highest_vm_end = vm_end_gap(vma); /* * vma->vm_prev wasn't known when we followed the rbtree to find the @@ -856,7 +870,7 @@ again: vma_gap_update(vma); if (end_changed) { if (!next) - mm->highest_vm_end = end; + mm->highest_vm_end = vm_end_gap(vma); else if (!adjust_next) vma_gap_update(next); } @@ -941,7 +955,7 @@ again: * mm->highest_vm_end doesn't need any update * in remove_next == 1 case. */ - VM_WARN_ON(mm->highest_vm_end != end); + VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma)); } } if (insert && file) @@ -1787,7 +1801,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info) while (true) { /* Visit left subtree if it looks promising */ - gap_end = vma->vm_start; + gap_end = vm_start_gap(vma); if (gap_end >= low_limit && vma->vm_rb.rb_left) { struct vm_area_struct *left = rb_entry(vma->vm_rb.rb_left, @@ -1798,7 +1812,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info) } } - gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0; + gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; check_current: /* Check if current node has a suitable gap */ if (gap_start > high_limit) @@ -1825,8 +1839,8 @@ check_current: vma = rb_entry(rb_parent(prev), struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_left) { - gap_start = vma->vm_prev->vm_end; - gap_end = vma->vm_start; + gap_start = vm_end_gap(vma->vm_prev); + gap_end = vm_start_gap(vma); goto check_current; } } @@ -1890,7 +1904,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) while (true) { /* Visit right subtree if it looks promising */ - gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0; + gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; if (gap_start <= high_limit && vma->vm_rb.rb_right) { struct vm_area_struct *right = rb_entry(vma->vm_rb.rb_right, @@ -1903,7 +1917,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) check_current: /* Check if current node has a suitable gap */ - gap_end = vma->vm_start; + gap_end = vm_start_gap(vma); if (gap_end < low_limit) return -ENOMEM; if (gap_start <= high_limit && gap_end - gap_start >= length) @@ -1929,7 +1943,7 @@ check_current: struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_right) { gap_start = vma->vm_prev ? - vma->vm_prev->vm_end : 0; + vm_end_gap(vma->vm_prev) : 0; goto check_current; } } @@ -1967,7 +1981,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info; if (len > TASK_SIZE - mmap_min_addr) @@ -1978,9 +1992,10 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, if (addr) { addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + vma = find_vma_prev(mm, addr, &prev); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) return addr; } @@ -2003,7 +2018,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, const unsigned long flags) { - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; unsigned long addr = addr0; struct vm_unmapped_area_info info; @@ -2018,9 +2033,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + vma = find_vma_prev(mm, addr, &prev); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) return addr; } @@ -2155,21 +2171,19 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr, * update accounting. This is shared with both the * grow-up and grow-down cases. */ -static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) +static int acct_stack_growth(struct vm_area_struct *vma, + unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; - unsigned long new_start, actual_size; + unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ - actual_size = size; - if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN))) - actual_size -= PAGE_SIZE; - if (actual_size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur)) + if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -2207,17 +2221,30 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *next; + unsigned long gap_addr; int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; /* Guard against wrapping around to address 0. */ - if (address < PAGE_ALIGN(address+4)) - address = PAGE_ALIGN(address+4); - else + address &= PAGE_MASK; + address += PAGE_SIZE; + if (!address) return -ENOMEM; + /* Enforce stack_guard_gap */ + gap_addr = address + stack_guard_gap; + if (gap_addr < address) + return -ENOMEM; + next = vma->vm_next; + if (next && next->vm_start < gap_addr) { + if (!(next->vm_flags & VM_GROWSUP)) + return -ENOMEM; + /* Check that both stack segments have the same anon_vma? */ + } + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; @@ -2261,7 +2288,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) if (vma->vm_next) vma_gap_update(vma->vm_next); else - mm->highest_vm_end = address; + mm->highest_vm_end = vm_end_gap(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); @@ -2282,6 +2309,8 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *prev; + unsigned long gap_addr; int error; address &= PAGE_MASK; @@ -2289,6 +2318,17 @@ int expand_downwards(struct vm_area_struct *vma, if (error) return error; + /* Enforce stack_guard_gap */ + gap_addr = address - stack_guard_gap; + if (gap_addr > address) + return -ENOMEM; + prev = vma->vm_prev; + if (prev && prev->vm_end > gap_addr) { + if (!(prev->vm_flags & VM_GROWSDOWN)) + return -ENOMEM; + /* Check that both stack segments have the same anon_vma? */ + } + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; @@ -2343,28 +2383,25 @@ int expand_downwards(struct vm_area_struct *vma, return error; } -/* - * Note how expand_stack() refuses to expand the stack all the way to - * abut the next virtual mapping, *unless* that mapping itself is also - * a stack mapping. We want to leave room for a guard page, after all - * (the guard page itself is not added here, that is done by the - * actual page faulting logic) - * - * This matches the behavior of the guard page logic (see mm/memory.c: - * check_stack_guard_page()), which only allows the guard page to be - * removed under these circumstances. - */ +/* enforced gap between the expanding stack and other mappings. */ +unsigned long stack_guard_gap = 256UL<