From mboxrd@z Thu Jan 1 00:00:00 1970 Return-path: Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5] helo=mx0a-001b2d01.pphosted.com) by bombadil.infradead.org with esmtps (Exim 4.90_1 #2 (Red Hat Linux)) id 1hFe0m-0003M3-1V for kexec@lists.infradead.org; Sun, 14 Apr 2019 12:13:29 +0000 Received: from pps.filterd (m0098419.ppops.net [127.0.0.1]) by mx0b-001b2d01.pphosted.com (8.16.0.27/8.16.0.27) with SMTP id x3EC9Eqm109725 for ; Sun, 14 Apr 2019 08:13:27 -0400 Received: from e06smtp01.uk.ibm.com (e06smtp01.uk.ibm.com [195.75.94.97]) by mx0b-001b2d01.pphosted.com with ESMTP id 2ruvktmpm4-1 (version=TLSv1.2 cipher=AES256-GCM-SHA384 bits=256 verify=NOT) for ; Sun, 14 Apr 2019 08:13:27 -0400 Received: from localhost by e06smtp01.uk.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Sun, 14 Apr 2019 13:13:25 +0100 Date: Sun, 14 Apr 2019 15:13:15 +0300 From: Mike Rapoport Subject: Re: [PATCH v3 3/4] arm64: kdump: support more than one crash kernel regions References: <20190409102819.121335-1-chenzhou10@huawei.com> <20190409102819.121335-4-chenzhou10@huawei.com> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <20190409102819.121335-4-chenzhou10@huawei.com> Message-Id: <20190414121315.GD20947@rapoport-lnx> List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "kexec" Errors-To: kexec-bounces+dwmw2=infradead.org@lists.infradead.org To: Chen Zhou Cc: wangkefeng.wang@huawei.com, horms@verge.net.au, ard.biesheuvel@linaro.org, catalin.marinas@arm.com, will.deacon@arm.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org, takahiro.akashi@linaro.org, mingo@redhat.com, bp@alien8.de, ebiederm@xmission.com, kexec@lists.infradead.org, tglx@linutronix.de, akpm@linux-foundation.org, linux-arm-kernel@lists.infradead.org Hi, On Tue, Apr 09, 2019 at 06:28:18PM +0800, Chen Zhou wrote: > After commit (arm64: kdump: support reserving crashkernel above 4G), > there may be two crash kernel regions, one is below 4G, the other is > above 4G. > > Crash dump kernel reads more than one crash kernel regions via a dtb > property under node /chosen, > linux,usable-memory-range = Somehow I've missed that previously, but how is this supposed to work on EFI systems? > Signed-off-by: Chen Zhou > --- > arch/arm64/mm/init.c | 66 ++++++++++++++++++++++++++++++++++++++++-------- > include/linux/memblock.h | 6 +++++ > mm/memblock.c | 7 ++--- > 3 files changed, 66 insertions(+), 13 deletions(-) > > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c > index 3bebddf..0f18665 100644 > --- a/arch/arm64/mm/init.c > +++ b/arch/arm64/mm/init.c > @@ -65,6 +65,11 @@ phys_addr_t arm64_dma_phys_limit __ro_after_init; > > #ifdef CONFIG_KEXEC_CORE > > +/* at most two crash kernel regions, low_region and high_region */ > +#define CRASH_MAX_USABLE_RANGES 2 > +#define LOW_REGION_IDX 0 > +#define HIGH_REGION_IDX 1 > + > /* > * reserve_crashkernel() - reserves memory for crash kernel > * > @@ -297,8 +302,8 @@ static int __init early_init_dt_scan_usablemem(unsigned long node, > const char *uname, int depth, void *data) > { > struct memblock_region *usablemem = data; > - const __be32 *reg; > - int len; > + const __be32 *reg, *endp; > + int len, nr = 0; > > if (depth != 1 || strcmp(uname, "chosen") != 0) > return 0; > @@ -307,22 +312,63 @@ static int __init early_init_dt_scan_usablemem(unsigned long node, > if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells))) > return 1; > > - usablemem->base = dt_mem_next_cell(dt_root_addr_cells, ®); > - usablemem->size = dt_mem_next_cell(dt_root_size_cells, ®); > + endp = reg + (len / sizeof(__be32)); > + while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) { > + usablemem[nr].base = dt_mem_next_cell(dt_root_addr_cells, ®); > + usablemem[nr].size = dt_mem_next_cell(dt_root_size_cells, ®); > + > + if (++nr >= CRASH_MAX_USABLE_RANGES) > + break; > + } > > return 1; > } > > static void __init fdt_enforce_memory_region(void) > { > - struct memblock_region reg = { > - .size = 0, > - }; > + int i, cnt = 0; > + struct memblock_region regs[CRASH_MAX_USABLE_RANGES]; > + > + memset(regs, 0, sizeof(regs)); > + of_scan_flat_dt(early_init_dt_scan_usablemem, regs); > + > + for (i = 0; i < CRASH_MAX_USABLE_RANGES; i++) > + if (regs[i].size) > + cnt++; > + else > + break; > + > + if (cnt - 1 == LOW_REGION_IDX) > + memblock_cap_memory_range(regs[LOW_REGION_IDX].base, > + regs[LOW_REGION_IDX].size); > + else if (cnt - 1 == HIGH_REGION_IDX) { > + /* > + * Two crash kernel regions, cap the memory range > + * [regs[LOW_REGION_IDX].base, regs[HIGH_REGION_IDX].end] > + * and then remove the memory range in the middle. > + */ > + int start_rgn, end_rgn, i, ret; > + phys_addr_t mid_base, mid_size; > + > + mid_base = regs[LOW_REGION_IDX].base + regs[LOW_REGION_IDX].size; > + mid_size = regs[HIGH_REGION_IDX].base - mid_base; > + ret = memblock_isolate_range(&memblock.memory, mid_base, > + mid_size, &start_rgn, &end_rgn); > > - of_scan_flat_dt(early_init_dt_scan_usablemem, ®); > + if (ret) > + return; > > - if (reg.size) > - memblock_cap_memory_range(reg.base, reg.size); > + memblock_cap_memory_range(regs[LOW_REGION_IDX].base, > + regs[HIGH_REGION_IDX].base - > + regs[LOW_REGION_IDX].base + > + regs[HIGH_REGION_IDX].size); > + for (i = end_rgn - 1; i >= start_rgn; i--) { > + if (!memblock_is_nomap(&memblock.memory.regions[i])) > + memblock_remove_region(&memblock.memory, i); > + } > + memblock_remove_range(&memblock.reserved, mid_base, > + mid_base + mid_size); > + } > } > > void __init arm64_memblock_init(void) > diff --git a/include/linux/memblock.h b/include/linux/memblock.h > index 294d5d8..787d252 100644 > --- a/include/linux/memblock.h > +++ b/include/linux/memblock.h > @@ -110,9 +110,15 @@ void memblock_discard(void); > > phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, > phys_addr_t size, phys_addr_t align); > +void memblock_remove_region(struct memblock_type *type, unsigned long r); > void memblock_allow_resize(void); > int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); > int memblock_add(phys_addr_t base, phys_addr_t size); > +int memblock_isolate_range(struct memblock_type *type, > + phys_addr_t base, phys_addr_t size, > + int *start_rgn, int *end_rgn); > +int memblock_remove_range(struct memblock_type *type, > + phys_addr_t base, phys_addr_t size); > int memblock_remove(phys_addr_t base, phys_addr_t size); > int memblock_free(phys_addr_t base, phys_addr_t size); > int memblock_reserve(phys_addr_t base, phys_addr_t size); > diff --git a/mm/memblock.c b/mm/memblock.c > index e7665cf..1846e2d 100644 > --- a/mm/memblock.c > +++ b/mm/memblock.c > @@ -357,7 +357,8 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, > return ret; > } > > -static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) > +void __init_memblock memblock_remove_region(struct memblock_type *type, > + unsigned long r) > { > type->total_size -= type->regions[r].size; > memmove(&type->regions[r], &type->regions[r + 1], > @@ -724,7 +725,7 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) > * Return: > * 0 on success, -errno on failure. > */ > -static int __init_memblock memblock_isolate_range(struct memblock_type *type, > +int __init_memblock memblock_isolate_range(struct memblock_type *type, > phys_addr_t base, phys_addr_t size, > int *start_rgn, int *end_rgn) > { > @@ -784,7 +785,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, > return 0; > } > > -static int __init_memblock memblock_remove_range(struct memblock_type *type, > +int __init_memblock memblock_remove_range(struct memblock_type *type, > phys_addr_t base, phys_addr_t size) > { > int start_rgn, end_rgn; > -- > 2.7.4 > -- Sincerely yours, Mike. _______________________________________________ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec