From 965278dcb8ab0b1f666cc47937933c4be4aea48d Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 13 May 2015 15:07:54 +0100 Subject: ARM: 8356/1: mm: handle non-pmd-aligned end of RAM At boot time we round the memblock limit down to section size in an attempt to ensure that we will have mapped this RAM with section mappings prior to allocating from it. When mapping RAM we iterate over PMD-sized chunks, creating these section mappings. Section mappings are only created when the end of a chunk is aligned to section size. Unfortunately, with classic page tables (where PMD_SIZE is 2 * SECTION_SIZE) this means that if a chunk is between 1M and 2M in size the first 1M will not be mapped despite having been accounted for in the memblock limit. This has been observed to result in page tables being allocated from unmapped memory, causing boot-time hangs. This patch modifies the memblock limit rounding to always round down to PMD_SIZE instead of SECTION_SIZE. For classic MMU this means that we will round the memblock limit down to a 2M boundary, matching the limits on section mappings, and preventing allocations from unmapped memory. For LPAE there should be no change as PMD_SIZE == SECTION_SIZE. Signed-off-by: Mark Rutland Reported-by: Stefan Agner Tested-by: Stefan Agner Acked-by: Laura Abbott Tested-by: Hans de Goede Cc: Catalin Marinas Cc: Steve Capper Cc: stable@vger.kernel.org Signed-off-by: Russell King --- arch/arm/mm/mmu.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4e6ef896c619..7186382672b5 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1112,22 +1112,22 @@ void __init sanity_check_meminfo(void) } /* - * Find the first non-section-aligned page, and point + * Find the first non-pmd-aligned page, and point * memblock_limit at it. This relies on rounding the - * limit down to be section-aligned, which happens at - * the end of this function. + * limit down to be pmd-aligned, which happens at the + * end of this function. * * With this algorithm, the start or end of almost any - * bank can be non-section-aligned. The only exception - * is that the start of the bank 0 must be section- + * bank can be non-pmd-aligned. The only exception is + * that the start of the bank 0 must be section- * aligned, since otherwise memory would need to be * allocated when mapping the start of bank 0, which * occurs before any free memory is mapped. */ if (!memblock_limit) { - if (!IS_ALIGNED(block_start, SECTION_SIZE)) + if (!IS_ALIGNED(block_start, PMD_SIZE)) memblock_limit = block_start; - else if (!IS_ALIGNED(block_end, SECTION_SIZE)) + else if (!IS_ALIGNED(block_end, PMD_SIZE)) memblock_limit = arm_lowmem_limit; } @@ -1137,12 +1137,12 @@ void __init sanity_check_meminfo(void) high_memory = __va(arm_lowmem_limit - 1) + 1; /* - * Round the memblock limit down to a section size. This + * Round the memblock limit down to a pmd size. This * helps to ensure that we will allocate memory from the - * last full section, which should be mapped. + * last full pmd, which should be mapped. */ if (memblock_limit) - memblock_limit = round_down(memblock_limit, SECTION_SIZE); + memblock_limit = round_down(memblock_limit, PMD_SIZE); if (!memblock_limit) memblock_limit = arm_lowmem_limit; -- cgit v1.2.3 From 1b97937246d8b97c0760d16d8992c7937bdf5e6a Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 15 May 2015 11:02:23 +0100 Subject: ARM: fix missing syscall trace exit Josh Stone reports: I've discovered a case where both arm and arm64 will miss a ptrace syscall-exit that they should report. If the syscall is entered without TIF_SYSCALL_TRACE set, then it goes on the fast path. It's then possible to have TIF_SYSCALL_TRACE added in the middle of the syscall, but ret_fast_syscall doesn't check this flag again. Fix this by always checking for a syscall trace in the fast exit path. Reported-by: Josh Stone Signed-off-by: Russell King --- arch/arm/kernel/entry-common.S | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index f8ccc21fa032..4e7f40c577e6 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -33,7 +33,9 @@ ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq @ disable interrupts - ldr r1, [tsk, #TI_FLAGS] + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing + tst r1, #_TIF_SYSCALL_WORK + bne __sys_trace_return tst r1, #_TIF_WORK_MASK bne fast_work_pending asm_trace_hardirqs_on -- cgit v1.2.3 From 8d2812849acbc13c07bdad8a0a55a342ec1ce3a4 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 14 May 2015 18:07:44 +0100 Subject: ARM: 8357/1: perf: fix memory leak when probing PMU PPIs Commit 338d9dd3e2ae ("ARM: 8351/1: perf: don't warn about missing interrupt-affinity property for PPIs") added a check for PPIs so that we avoid parsing the interrupt-affinity property for these naturally affine interrupts. Unfortunately, this check can trigger an early (successful) return and we will leak the irqs array. This patch fixes the issue by reordering the code so that the check is performed before any independent allocation. Reported-by: David Binderman Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/kernel/perf_event_cpu.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 213919ba326f..3b8c2833c537 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -304,16 +304,17 @@ static int probe_current_pmu(struct arm_pmu *pmu) static int of_pmu_irq_cfg(struct platform_device *pdev) { int i, irq; - int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); - - if (!irqs) - return -ENOMEM; + int *irqs; /* Don't bother with PPIs; they're already affine */ irq = platform_get_irq(pdev, 0); if (irq >= 0 && irq_is_percpu(irq)) return 0; + irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); + if (!irqs) + return -ENOMEM; + for (i = 0; i < pdev->num_resources; ++i) { struct device_node *dn; int cpu; -- cgit v1.2.3