Re: [PATCH v4 1/6] powerpc: prefer memblock APIs returning virtual address

From: Mike Rapoport
Date: Tue Jan 08 2019 - 09:24:00 EST

Next message: Halil Pasic: "Re: [PATCH v5 10/15] KVM: s390: add functions to (un)register GISC with GISA"
Previous message: Greg KH: "Re: [PATCH v2] kobject: add kernel/uevent_features sysfs file"
In reply to: Christophe Leroy: "Re: [PATCH v4 1/6] powerpc: prefer memblock APIs returning virtual address"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Hi,

On Tue, Jan 08, 2019 at 11:02:24AM +0100, Christophe Leroy wrote:
>
> Le 31/12/2018 à 10:29, Mike Rapoport a écrit :
> >There are a several places that allocate memory using memblock APIs that
> >return a physical address, convert the returned address to the virtual
> >address and frequently also memset(0) the allocated range.
> >
> >Update these places to use memblock allocators already returning a virtual
> >address. Use memblock functions that clear the allocated memory instead of
> >calling memset(0) where appropriate.
> >
> >The calls to memblock_alloc_base() that were not followed by memset(0) are
> >replaced with memblock_alloc_try_nid_raw(). Since the latter does not
> >panic() when the allocation fails, the appropriate panic() calls are added
> >to the call sites.
> >
> >Signed-off-by: Mike Rapoport <rppt@xxxxxxxxxxxxx>
> >---
> > arch/powerpc/kernel/paca.c | 16 ++++++----------
> > arch/powerpc/kernel/setup_64.c | 24 ++++++++++--------------
> > arch/powerpc/mm/hash_utils_64.c | 6 +++---
> > arch/powerpc/mm/pgtable-book3e.c | 8 ++------
> > arch/powerpc/mm/pgtable-book3s64.c | 5 +----
> > arch/powerpc/mm/pgtable-radix.c | 25 +++++++------------------
> > arch/powerpc/platforms/pasemi/iommu.c | 5 +++--
> > arch/powerpc/platforms/pseries/setup.c | 18 ++++++++++++++----
> > arch/powerpc/sysdev/dart_iommu.c | 7 +++++--
> > 9 files changed, 51 insertions(+), 63 deletions(-)
> >
> >diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
> >index 913bfca..276d36d4 100644
> >--- a/arch/powerpc/kernel/paca.c
> >+++ b/arch/powerpc/kernel/paca.c
> >@@ -27,7 +27,7 @@
> > static void *__init alloc_paca_data(unsigned long size, unsigned long align,
> > unsigned long limit, int cpu)
> > {
> >- unsigned long pa;
> >+ void *ptr;
> > int nid;
> > /*
> >@@ -42,17 +42,15 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align,
> > nid = early_cpu_to_node(cpu);
> > }
> >- pa = memblock_alloc_base_nid(size, align, limit, nid, MEMBLOCK_NONE);
> >- if (!pa) {
> >- pa = memblock_alloc_base(size, align, limit);
> >- if (!pa)
> >- panic("cannot allocate paca data");
> >- }
> >+ ptr = memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
> >+ limit, nid);
> >+ if (!ptr)
> >+ panic("cannot allocate paca data");
>
> AFAIKS, memblock_alloc_try_nid() panics if memblock_alloc_internal() returns
> NULL, so the above panic is useless, isn't it ?

My plan is to make all memblock_alloc() APIs to return NULL rather then
panic and then get rid of _nopanic variants. It's currently WIP and
hopefully I'll have the patches ready next week.

> > if (cpu == boot_cpuid)
> > memblock_set_bottom_up(false);
> >- return __va(pa);
> >+ return ptr;
> > }
> > #ifdef CONFIG_PPC_PSERIES
> >@@ -118,7 +116,6 @@ static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit)
> > }
> > s = alloc_paca_data(sizeof(*s), L1_CACHE_BYTES, limit, cpu);
> >- memset(s, 0, sizeof(*s));
> > s->persistent = cpu_to_be32(SLB_NUM_BOLTED);
> > s->buffer_length = cpu_to_be32(sizeof(*s));
> >@@ -222,7 +219,6 @@ void __init allocate_paca(int cpu)
> > paca = alloc_paca_data(sizeof(struct paca_struct), L1_CACHE_BYTES,
> > limit, cpu);
> > paca_ptrs[cpu] = paca;
> >- memset(paca, 0, sizeof(struct paca_struct));
> > initialise_paca(paca, cpu);
> > #ifdef CONFIG_PPC_PSERIES
> >diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
> >index 236c115..3dcd779 100644
> >--- a/arch/powerpc/kernel/setup_64.c
> >+++ b/arch/powerpc/kernel/setup_64.c
> >@@ -634,19 +634,17 @@ __init u64 ppc64_bolted_size(void)
> > static void *__init alloc_stack(unsigned long limit, int cpu)
> > {
> >- unsigned long pa;
> >+ void *ptr;
> > BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16);
> >- pa = memblock_alloc_base_nid(THREAD_SIZE, THREAD_SIZE, limit,
> >- early_cpu_to_node(cpu), MEMBLOCK_NONE);
> >- if (!pa) {
> >- pa = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
> >- if (!pa)
> >- panic("cannot allocate stacks");
> >- }
> >+ ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_SIZE,
> >+ MEMBLOCK_LOW_LIMIT, limit,
> >+ early_cpu_to_node(cpu));
> >+ if (!ptr)
> >+ panic("cannot allocate stacks");
>
> Same ?
>
> Christophe
>
> >- return __va(pa);
> >+ return ptr;
> > }
> > void __init irqstack_early_init(void)
> >@@ -739,20 +737,17 @@ void __init emergency_stack_init(void)
> > struct thread_info *ti;
> > ti = alloc_stack(limit, i);
> >- memset(ti, 0, THREAD_SIZE);
> > emerg_stack_init_thread_info(ti, i);
> > paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
> > #ifdef CONFIG_PPC_BOOK3S_64
> > /* emergency stack for NMI exception handling. */
> > ti = alloc_stack(limit, i);
> >- memset(ti, 0, THREAD_SIZE);
> > emerg_stack_init_thread_info(ti, i);
> > paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
> > /* emergency stack for machine check exception handling. */
> > ti = alloc_stack(limit, i);
> >- memset(ti, 0, THREAD_SIZE);
> > emerg_stack_init_thread_info(ti, i);
> > paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
> > #endif
> >@@ -933,8 +928,9 @@ static void __ref init_fallback_flush(void)
> > * hardware prefetch runoff. We don't have a recipe for load patterns to
> > * reliably avoid the prefetcher.
> > */
> >- l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit));
> >- memset(l1d_flush_fallback_area, 0, l1d_size * 2);
> >+ l1d_flush_fallback_area = memblock_alloc_try_nid(l1d_size * 2,
> >+ l1d_size, MEMBLOCK_LOW_LIMIT,
> >+ limit, NUMA_NO_NODE);
> > for_each_possible_cpu(cpu) {
> > struct paca_struct *paca = paca_ptrs[cpu];
> >diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
> >index 0cc7fbc..bc6be44 100644
> >--- a/arch/powerpc/mm/hash_utils_64.c
> >+++ b/arch/powerpc/mm/hash_utils_64.c
> >@@ -908,9 +908,9 @@ static void __init htab_initialize(void)
> > #ifdef CONFIG_DEBUG_PAGEALLOC
> > if (debug_pagealloc_enabled()) {
> > linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
> >- linear_map_hash_slots = __va(memblock_alloc_base(
> >- linear_map_hash_count, 1, ppc64_rma_size));
> >- memset(linear_map_hash_slots, 0, linear_map_hash_count);
> >+ linear_map_hash_slots = memblock_alloc_try_nid(
> >+ linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT,
> >+ ppc64_rma_size, NUMA_NO_NODE);
> > }
> > #endif /* CONFIG_DEBUG_PAGEALLOC */
> >diff --git a/arch/powerpc/mm/pgtable-book3e.c b/arch/powerpc/mm/pgtable-book3e.c
> >index e0ccf36..53cbc7d 100644
> >--- a/arch/powerpc/mm/pgtable-book3e.c
> >+++ b/arch/powerpc/mm/pgtable-book3e.c
> >@@ -57,12 +57,8 @@ void vmemmap_remove_mapping(unsigned long start,
> > static __ref void *early_alloc_pgtable(unsigned long size)
> > {
> >- void *pt;
> >-
> >- pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS)));
> >- memset(pt, 0, size);
> >-
> >- return pt;
> >+ return memblock_alloc_try_nid(size, size, MEMBLOCK_LOW_LIMIT,
> >+ __pa(MAX_DMA_ADDRESS), NUMA_NO_NODE);
> > }
> > /*
> >diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
> >index f3c31f5..55876b7 100644
> >--- a/arch/powerpc/mm/pgtable-book3s64.c
> >+++ b/arch/powerpc/mm/pgtable-book3s64.c
> >@@ -195,11 +195,8 @@ void __init mmu_partition_table_init(void)
> > unsigned long ptcr;
> > BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large.");
> >- partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
> >- MEMBLOCK_ALLOC_ANYWHERE));
> >-
> > /* Initialize the Partition Table with no entries */
> >- memset((void *)partition_tb, 0, patb_size);
> >+ partition_tb = memblock_alloc(patb_size, patb_size);
> > /*
> > * update partition table control register,
> >diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
> >index 9311560..29bcea5 100644
> >--- a/arch/powerpc/mm/pgtable-radix.c
> >+++ b/arch/powerpc/mm/pgtable-radix.c
> >@@ -51,26 +51,15 @@ static int native_register_process_table(unsigned long base, unsigned long pg_sz
> > static __ref void *early_alloc_pgtable(unsigned long size, int nid,
> > unsigned long region_start, unsigned long region_end)
> > {
> >- unsigned long pa = 0;
> >- void *pt;
> >+ phys_addr_t min_addr = MEMBLOCK_LOW_LIMIT;
> >+ phys_addr_t max_addr = MEMBLOCK_ALLOC_ANYWHERE;
> >- if (region_start || region_end) /* has region hint */
> >- pa = memblock_alloc_range(size, size, region_start, region_end,
> >- MEMBLOCK_NONE);
> >- else if (nid != -1) /* has node hint */
> >- pa = memblock_alloc_base_nid(size, size,
> >- MEMBLOCK_ALLOC_ANYWHERE,
> >- nid, MEMBLOCK_NONE);
> >+ if (region_start)
> >+ min_addr = region_start;
> >+ if (region_end)
> >+ max_addr = region_end;
> >- if (!pa)
> >- pa = memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE);
> >-
> >- BUG_ON(!pa);
> >-
> >- pt = __va(pa);
> >- memset(pt, 0, size);
> >-
> >- return pt;
> >+ return memblock_alloc_try_nid(size, size, min_addr, max_addr, nid);
> > }
> > static int early_map_kernel_page(unsigned long ea, unsigned long pa,
> >diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
> >index f297152..f62930f 100644
> >--- a/arch/powerpc/platforms/pasemi/iommu.c
> >+++ b/arch/powerpc/platforms/pasemi/iommu.c
> >@@ -208,7 +208,9 @@ static int __init iob_init(struct device_node *dn)
> > pr_debug(" -> %s\n", __func__);
> > /* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */
> >- iob_l2_base = (u32 *)__va(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000));
> >+ iob_l2_base = memblock_alloc_try_nid_raw(1UL << 21, 1UL << 21,
> >+ MEMBLOCK_LOW_LIMIT, 0x80000000,
> >+ NUMA_NO_NODE);
> > pr_info("IOBMAP L2 allocated at: %p\n", iob_l2_base);
> >@@ -269,4 +271,3 @@ void __init iommu_init_early_pasemi(void)
> > pasemi_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pasemi;
> > set_pci_dma_ops(&dma_iommu_ops);
> > }
> >-
> >diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
> >index 41f62ca2..e4f0dfd 100644
> >--- a/arch/powerpc/platforms/pseries/setup.c
> >+++ b/arch/powerpc/platforms/pseries/setup.c
> >@@ -130,8 +130,13 @@ static void __init fwnmi_init(void)
> > * It will be used in real mode mce handler, hence it needs to be
> > * below RMA.
> > */
> >- mce_data_buf = __va(memblock_alloc_base(RTAS_ERROR_LOG_MAX * nr_cpus,
> >- RTAS_ERROR_LOG_MAX, ppc64_rma_size));
> >+ mce_data_buf = memblock_alloc_try_nid_raw(RTAS_ERROR_LOG_MAX * nr_cpus,
> >+ RTAS_ERROR_LOG_MAX, MEMBLOCK_LOW_LIMIT,
> >+ ppc64_rma_size, NUMA_NO_NODE);
> >+ if (!mce_data_buf)
> >+ panic("Failed to allocate %d bytes below %pa for MCE buffer\n",
> >+ RTAS_ERROR_LOG_MAX * nr_cpus, &ppc64_rma_size);
> >+
> > for_each_possible_cpu(i) {
> > paca_ptrs[i]->mce_data_buf = mce_data_buf +
> > (RTAS_ERROR_LOG_MAX * i);
> >@@ -140,8 +145,13 @@ static void __init fwnmi_init(void)
> > #ifdef CONFIG_PPC_BOOK3S_64
> > /* Allocate per cpu slb area to save old slb contents during MCE */
> > size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus;
> >- slb_ptr = __va(memblock_alloc_base(size, sizeof(struct slb_entry),
> >- ppc64_rma_size));
> >+ slb_ptr = memblock_alloc_try_nid_raw(size, sizeof(struct slb_entry),
> >+ MEMBLOCK_LOW_LIMIT, ppc64_rma_size,
> >+ NUMA_NO_NODE);
> >+ if (!slb_ptr)
> >+ panic("Failed to allocate %zu bytes below %pa for slb area\n",
> >+ size, &ppc64_rma_size);
> >+
> > for_each_possible_cpu(i)
> > paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i);
> > #endif
> >diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
> >index a5b40d1..25bc25f 100644
> >--- a/arch/powerpc/sysdev/dart_iommu.c
> >+++ b/arch/powerpc/sysdev/dart_iommu.c
> >@@ -251,8 +251,11 @@ static void allocate_dart(void)
> > * 16MB (1 << 24) alignment. We allocate a full 16Mb chuck since we
> > * will blow up an entire large page anyway in the kernel mapping.
> > */
> >- dart_tablebase = __va(memblock_alloc_base(1UL<<24,
> >- 1UL<<24, 0x80000000L));
> >+ dart_tablebase = memblock_alloc_try_nid_raw(SZ_16M, SZ_16M,
> >+ MEMBLOCK_LOW_LIMIT, SZ_2G,
> >+ NUMA_NO_NODE);
> >+ if (!dart_tablebase)
> >+ panic("Failed to allocate 16MB below 2GB for DART table\n");
> > /* There is no point scanning the DART space for leaks*/
> > kmemleak_no_scan((void *)dart_tablebase);
> >
>

--
Sincerely yours,
Mike.

Next message: Halil Pasic: "Re: [PATCH v5 10/15] KVM: s390: add functions to (un)register GISC with GISA"
Previous message: Greg KH: "Re: [PATCH v2] kobject: add kernel/uevent_features sysfs file"
In reply to: Christophe Leroy: "Re: [PATCH v4 1/6] powerpc: prefer memblock APIs returning virtual address"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]