January 2019 - Linux-stable-mirror

FAILED: patch "[PATCH] MIPS: c-r4k: Add r4k_blast_scache_node for Loongson-3" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From bb53fdf395eed103f85061bfff3b116cee123895 Mon Sep 17 00:00:00 2001 From: Huacai Chen <chenhc(a)lemote.com> Date: Thu, 15 Nov 2018 15:53:53 +0800 Subject: [PATCH] MIPS: c-r4k: Add r4k_blast_scache_node for Loongson-3 For multi-node Loongson-3 (NUMA configuration), r4k_blast_scache() can only flush Node-0's scache. So we add r4k_blast_scache_node() by using (CAC_BASE | (node_id << NODE_ADDRSPACE_SHIFT)) instead of CKSEG0 as the start address. Signed-off-by: Huacai Chen <chenhc(a)lemote.com> [paul.burton(a)mips.com: Include asm/mmzone.h from asm/r4kcache.h for nid_to_addrbase(). Add asm/mach-generic/mmzone.h to allow inclusion for all platforms.] Signed-off-by: Paul Burton <paul.burton(a)mips.com> Patchwork: https://patchwork.linux-mips.org/patch/21129/ Cc: Ralf Baechle <ralf(a)linux-mips.org> Cc: James Hogan <james.hogan(a)mips.com> Cc: Steven J . Hill <Steven.Hill(a)cavium.com> Cc: linux-mips(a)linux-mips.org Cc: Fuxin Zhang <zhangfx(a)lemote.com> Cc: Zhangjin Wu <wuzhangjin(a)gmail.com> Cc: <stable(a)vger.kernel.org> # 3.15+ diff --git a/arch/mips/include/asm/mach-generic/mmzone.h b/arch/mips/include/asm/mach-generic/mmzone.h new file mode 100644 index 000000000000..826392f2ee32 --- /dev/null +++ b/arch/mips/include/asm/mach-generic/mmzone.h @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Intentionally empty */ diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h index c9f7e231e66b..59c8b11c090e 100644 --- a/arch/mips/include/asm/mach-loongson64/mmzone.h +++ b/arch/mips/include/asm/mach-loongson64/mmzone.h @@ -21,6 +21,7 @@ #define NODE3_ADDRSPACE_OFFSET 0x300000000000UL #define pa_to_nid(addr) (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT) +#define nid_to_addrbase(nid) ((nid) << NODE_ADDRSPACE_SHIFT) #define LEVELS_PER_SLICE 128 diff --git a/arch/mips/include/asm/mmzone.h b/arch/mips/include/asm/mmzone.h index f085fba41da5..2a0fe1d0eac6 100644 --- a/arch/mips/include/asm/mmzone.h +++ b/arch/mips/include/asm/mmzone.h @@ -9,6 +9,14 @@ #include <asm/page.h> #include <mmzone.h> +#ifndef pa_to_nid +#define pa_to_nid(addr) 0 +#endif + +#ifndef nid_to_addrbase +#define nid_to_addrbase(nid) 0 +#endif + #ifdef CONFIG_DISCONTIGMEM #define pfn_to_nid(pfn) pa_to_nid((pfn) << PAGE_SHIFT) diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index d19b2d65336b..7f4a32d3345a 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -20,6 +20,7 @@ #include <asm/cpu-features.h> #include <asm/cpu-type.h> #include <asm/mipsmtregs.h> +#include <asm/mmzone.h> #include <linux/uaccess.h> /* for uaccess_kernel() */ extern void (*r4k_blast_dcache)(void); @@ -674,4 +675,25 @@ __BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, , ) __BUILD_BLAST_CACHE_RANGE(inv_d, dcache, Hit_Invalidate_D, , ) __BUILD_BLAST_CACHE_RANGE(inv_s, scache, Hit_Invalidate_SD, , ) +/* Currently, this is very specific to Loongson-3 */ +#define __BUILD_BLAST_CACHE_NODE(pfx, desc, indexop, hitop, lsize) \ +static inline void blast_##pfx##cache##lsize##_node(long node) \ +{ \ + unsigned long start = CAC_BASE | nid_to_addrbase(node); \ + unsigned long end = start + current_cpu_data.desc.waysize; \ + unsigned long ws_inc = 1UL << current_cpu_data.desc.waybit; \ + unsigned long ws_end = current_cpu_data.desc.ways << \ + current_cpu_data.desc.waybit; \ + unsigned long ws, addr; \ + \ + for (ws = 0; ws < ws_end; ws += ws_inc) \ + for (addr = start; addr < end; addr += lsize * 32) \ + cache##lsize##_unroll32(addr|ws, indexop); \ +} + +__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16) +__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 32) +__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64) +__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128) + #endif /* _ASM_R4KCACHE_H */ diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 7e430b4d8778..96d666a0f4a0 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -459,11 +459,28 @@ static void r4k_blast_scache_setup(void) r4k_blast_scache = blast_scache128; } +static void (*r4k_blast_scache_node)(long node); + +static void r4k_blast_scache_node_setup(void) +{ + unsigned long sc_lsize = cpu_scache_line_size(); + + if (current_cpu_type() != CPU_LOONGSON3) + r4k_blast_scache_node = (void *)cache_noop; + else if (sc_lsize == 16) + r4k_blast_scache_node = blast_scache16_node; + else if (sc_lsize == 32) + r4k_blast_scache_node = blast_scache32_node; + else if (sc_lsize == 64) + r4k_blast_scache_node = blast_scache64_node; + else if (sc_lsize == 128) + r4k_blast_scache_node = blast_scache128_node; +} + static inline void local_r4k___flush_cache_all(void * args) { switch (current_cpu_type()) { case CPU_LOONGSON2: - case CPU_LOONGSON3: case CPU_R4000SC: case CPU_R4000MC: case CPU_R4400SC: @@ -480,6 +497,11 @@ static inline void local_r4k___flush_cache_all(void * args) r4k_blast_scache(); break; + case CPU_LOONGSON3: + /* Use get_ebase_cpunum() for both NUMA=y/n */ + r4k_blast_scache_node(get_ebase_cpunum() >> 2); + break; + case CPU_BMIPS5000: r4k_blast_scache(); __sync(); @@ -840,10 +862,14 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) preempt_disable(); if (cpu_has_inclusive_pcaches) { - if (size >= scache_size) - r4k_blast_scache(); - else + if (size >= scache_size) { + if (current_cpu_type() != CPU_LOONGSON3) + r4k_blast_scache(); + else + r4k_blast_scache_node(pa_to_nid(addr)); + } else { blast_scache_range(addr, addr + size); + } preempt_enable(); __sync(); return; @@ -877,9 +903,12 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) preempt_disable(); if (cpu_has_inclusive_pcaches) { - if (size >= scache_size) - r4k_blast_scache(); - else { + if (size >= scache_size) { + if (current_cpu_type() != CPU_LOONGSON3) + r4k_blast_scache(); + else + r4k_blast_scache_node(pa_to_nid(addr)); + } else { /* * There is no clearly documented alignment requirement * for the cache instruction on MIPS processors and @@ -1918,6 +1947,7 @@ void r4k_cache_init(void) r4k_blast_scache_page_setup(); r4k_blast_scache_page_indexed_setup(); r4k_blast_scache_setup(); + r4k_blast_scache_node_setup(); #ifdef CONFIG_EVA r4k_blast_dcache_user_page_setup(); r4k_blast_icache_user_page_setup();

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] MIPS: c-r4k: Add r4k_blast_scache_node for Loongson-3" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From bb53fdf395eed103f85061bfff3b116cee123895 Mon Sep 17 00:00:00 2001 From: Huacai Chen <chenhc(a)lemote.com> Date: Thu, 15 Nov 2018 15:53:53 +0800 Subject: [PATCH] MIPS: c-r4k: Add r4k_blast_scache_node for Loongson-3 For multi-node Loongson-3 (NUMA configuration), r4k_blast_scache() can only flush Node-0's scache. So we add r4k_blast_scache_node() by using (CAC_BASE | (node_id << NODE_ADDRSPACE_SHIFT)) instead of CKSEG0 as the start address. Signed-off-by: Huacai Chen <chenhc(a)lemote.com> [paul.burton(a)mips.com: Include asm/mmzone.h from asm/r4kcache.h for nid_to_addrbase(). Add asm/mach-generic/mmzone.h to allow inclusion for all platforms.] Signed-off-by: Paul Burton <paul.burton(a)mips.com> Patchwork: https://patchwork.linux-mips.org/patch/21129/ Cc: Ralf Baechle <ralf(a)linux-mips.org> Cc: James Hogan <james.hogan(a)mips.com> Cc: Steven J . Hill <Steven.Hill(a)cavium.com> Cc: linux-mips(a)linux-mips.org Cc: Fuxin Zhang <zhangfx(a)lemote.com> Cc: Zhangjin Wu <wuzhangjin(a)gmail.com> Cc: <stable(a)vger.kernel.org> # 3.15+ diff --git a/arch/mips/include/asm/mach-generic/mmzone.h b/arch/mips/include/asm/mach-generic/mmzone.h new file mode 100644 index 000000000000..826392f2ee32 --- /dev/null +++ b/arch/mips/include/asm/mach-generic/mmzone.h @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Intentionally empty */ diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h index c9f7e231e66b..59c8b11c090e 100644 --- a/arch/mips/include/asm/mach-loongson64/mmzone.h +++ b/arch/mips/include/asm/mach-loongson64/mmzone.h @@ -21,6 +21,7 @@ #define NODE3_ADDRSPACE_OFFSET 0x300000000000UL #define pa_to_nid(addr) (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT) +#define nid_to_addrbase(nid) ((nid) << NODE_ADDRSPACE_SHIFT) #define LEVELS_PER_SLICE 128 diff --git a/arch/mips/include/asm/mmzone.h b/arch/mips/include/asm/mmzone.h index f085fba41da5..2a0fe1d0eac6 100644 --- a/arch/mips/include/asm/mmzone.h +++ b/arch/mips/include/asm/mmzone.h @@ -9,6 +9,14 @@ #include <asm/page.h> #include <mmzone.h> +#ifndef pa_to_nid +#define pa_to_nid(addr) 0 +#endif + +#ifndef nid_to_addrbase +#define nid_to_addrbase(nid) 0 +#endif + #ifdef CONFIG_DISCONTIGMEM #define pfn_to_nid(pfn) pa_to_nid((pfn) << PAGE_SHIFT) diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index d19b2d65336b..7f4a32d3345a 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -20,6 +20,7 @@ #include <asm/cpu-features.h> #include <asm/cpu-type.h> #include <asm/mipsmtregs.h> +#include <asm/mmzone.h> #include <linux/uaccess.h> /* for uaccess_kernel() */ extern void (*r4k_blast_dcache)(void); @@ -674,4 +675,25 @@ __BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, , ) __BUILD_BLAST_CACHE_RANGE(inv_d, dcache, Hit_Invalidate_D, , ) __BUILD_BLAST_CACHE_RANGE(inv_s, scache, Hit_Invalidate_SD, , ) +/* Currently, this is very specific to Loongson-3 */ +#define __BUILD_BLAST_CACHE_NODE(pfx, desc, indexop, hitop, lsize) \ +static inline void blast_##pfx##cache##lsize##_node(long node) \ +{ \ + unsigned long start = CAC_BASE | nid_to_addrbase(node); \ + unsigned long end = start + current_cpu_data.desc.waysize; \ + unsigned long ws_inc = 1UL << current_cpu_data.desc.waybit; \ + unsigned long ws_end = current_cpu_data.desc.ways << \ + current_cpu_data.desc.waybit; \ + unsigned long ws, addr; \ + \ + for (ws = 0; ws < ws_end; ws += ws_inc) \ + for (addr = start; addr < end; addr += lsize * 32) \ + cache##lsize##_unroll32(addr|ws, indexop); \ +} + +__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16) +__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 32) +__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64) +__BUILD_BLAST_CACHE_NODE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128) + #endif /* _ASM_R4KCACHE_H */ diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 7e430b4d8778..96d666a0f4a0 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -459,11 +459,28 @@ static void r4k_blast_scache_setup(void) r4k_blast_scache = blast_scache128; } +static void (*r4k_blast_scache_node)(long node); + +static void r4k_blast_scache_node_setup(void) +{ + unsigned long sc_lsize = cpu_scache_line_size(); + + if (current_cpu_type() != CPU_LOONGSON3) + r4k_blast_scache_node = (void *)cache_noop; + else if (sc_lsize == 16) + r4k_blast_scache_node = blast_scache16_node; + else if (sc_lsize == 32) + r4k_blast_scache_node = blast_scache32_node; + else if (sc_lsize == 64) + r4k_blast_scache_node = blast_scache64_node; + else if (sc_lsize == 128) + r4k_blast_scache_node = blast_scache128_node; +} + static inline void local_r4k___flush_cache_all(void * args) { switch (current_cpu_type()) { case CPU_LOONGSON2: - case CPU_LOONGSON3: case CPU_R4000SC: case CPU_R4000MC: case CPU_R4400SC: @@ -480,6 +497,11 @@ static inline void local_r4k___flush_cache_all(void * args) r4k_blast_scache(); break; + case CPU_LOONGSON3: + /* Use get_ebase_cpunum() for both NUMA=y/n */ + r4k_blast_scache_node(get_ebase_cpunum() >> 2); + break; + case CPU_BMIPS5000: r4k_blast_scache(); __sync(); @@ -840,10 +862,14 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) preempt_disable(); if (cpu_has_inclusive_pcaches) { - if (size >= scache_size) - r4k_blast_scache(); - else + if (size >= scache_size) { + if (current_cpu_type() != CPU_LOONGSON3) + r4k_blast_scache(); + else + r4k_blast_scache_node(pa_to_nid(addr)); + } else { blast_scache_range(addr, addr + size); + } preempt_enable(); __sync(); return; @@ -877,9 +903,12 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) preempt_disable(); if (cpu_has_inclusive_pcaches) { - if (size >= scache_size) - r4k_blast_scache(); - else { + if (size >= scache_size) { + if (current_cpu_type() != CPU_LOONGSON3) + r4k_blast_scache(); + else + r4k_blast_scache_node(pa_to_nid(addr)); + } else { /* * There is no clearly documented alignment requirement * for the cache instruction on MIPS processors and @@ -1918,6 +1947,7 @@ void r4k_cache_init(void) r4k_blast_scache_page_setup(); r4k_blast_scache_page_indexed_setup(); r4k_blast_scache_setup(); + r4k_blast_scache_node_setup(); #ifdef CONFIG_EVA r4k_blast_dcache_user_page_setup(); r4k_blast_icache_user_page_setup();

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] f2fs: read page index before freeing" failed to apply to 3.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 3.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 0ea295dd853e0879a9a30ab61f923c26be35b902 Mon Sep 17 00:00:00 2001 From: Pan Bian <bianpan2016(a)163.com> Date: Thu, 22 Nov 2018 18:58:46 +0800 Subject: [PATCH] f2fs: read page index before freeing The function truncate_node frees the page with f2fs_put_page. However, the page index is read after that. So, the patch reads the index before freeing the page. Fixes: bf39c00a9a7f ("f2fs: drop obsolete node page when it is truncated") Cc: <stable(a)vger.kernel.org> Signed-off-by: Pan Bian <bianpan2016(a)163.com> Reviewed-by: Chao Yu <yuchao0(a)huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index e60c7779e114..a2273340991f 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -826,6 +826,7 @@ static int truncate_node(struct dnode_of_data *dn) struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info ni; int err; + pgoff_t index; err = f2fs_get_node_info(sbi, dn->nid, &ni); if (err) @@ -845,10 +846,11 @@ static int truncate_node(struct dnode_of_data *dn) clear_node_page_dirty(dn->node_page); set_sbi_flag(sbi, SBI_IS_DIRTY); + index = dn->node_page->index; f2fs_put_page(dn->node_page, 1); invalidate_mapping_pages(NODE_MAPPING(sbi), - dn->node_page->index, dn->node_page->index); + index, index); dn->node_page = NULL; trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] f2fs: read page index before freeing" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 0ea295dd853e0879a9a30ab61f923c26be35b902 Mon Sep 17 00:00:00 2001 From: Pan Bian <bianpan2016(a)163.com> Date: Thu, 22 Nov 2018 18:58:46 +0800 Subject: [PATCH] f2fs: read page index before freeing The function truncate_node frees the page with f2fs_put_page. However, the page index is read after that. So, the patch reads the index before freeing the page. Fixes: bf39c00a9a7f ("f2fs: drop obsolete node page when it is truncated") Cc: <stable(a)vger.kernel.org> Signed-off-by: Pan Bian <bianpan2016(a)163.com> Reviewed-by: Chao Yu <yuchao0(a)huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index e60c7779e114..a2273340991f 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -826,6 +826,7 @@ static int truncate_node(struct dnode_of_data *dn) struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info ni; int err; + pgoff_t index; err = f2fs_get_node_info(sbi, dn->nid, &ni); if (err) @@ -845,10 +846,11 @@ static int truncate_node(struct dnode_of_data *dn) clear_node_page_dirty(dn->node_page); set_sbi_flag(sbi, SBI_IS_DIRTY); + index = dn->node_page->index; f2fs_put_page(dn->node_page, 1); invalidate_mapping_pages(NODE_MAPPING(sbi), - dn->node_page->index, dn->node_page->index); + index, index); dn->node_page = NULL; trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);

5 years, 11 months

1
0
0 0

FAILED: patch "[PATCH] f2fs: read page index before freeing" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 0ea295dd853e0879a9a30ab61f923c26be35b902 Mon Sep 17 00:00:00 2001 From: Pan Bian <bianpan2016(a)163.com> Date: Thu, 22 Nov 2018 18:58:46 +0800 Subject: [PATCH] f2fs: read page index before freeing The function truncate_node frees the page with f2fs_put_page. However, the page index is read after that. So, the patch reads the index before freeing the page. Fixes: bf39c00a9a7f ("f2fs: drop obsolete node page when it is truncated") Cc: <stable(a)vger.kernel.org> Signed-off-by: Pan Bian <bianpan2016(a)163.com> Reviewed-by: Chao Yu <yuchao0(a)huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index e60c7779e114..a2273340991f 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -826,6 +826,7 @@ static int truncate_node(struct dnode_of_data *dn) struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info ni; int err; + pgoff_t index; err = f2fs_get_node_info(sbi, dn->nid, &ni); if (err) @@ -845,10 +846,11 @@ static int truncate_node(struct dnode_of_data *dn) clear_node_page_dirty(dn->node_page); set_sbi_flag(sbi, SBI_IS_DIRTY); + index = dn->node_page->index; f2fs_put_page(dn->node_page, 1); invalidate_mapping_pages(NODE_MAPPING(sbi), - dn->node_page->index, dn->node_page->index); + index, index); dn->node_page = NULL; trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);

5 years, 11 months

1
0
0 0

[PATCH v2 4.14 0/5] netfilter: xt_connlimit: backport upstream fixes for race in connection counting

by Mauricio Faria de Oliveira

From: Ubuntu <ubuntu(a)petilil.segmaas.1ss> [changelog] - v2: include patch 5/5 (a very recent fix to patch 4/5) which is not yet in Linus's tree but it's in nf.git + linux-next.git, thus should make it shortly. Test results still consistent. Thanks Florian Westphal for reviewing and pointing that out. Recently, Alakesh Haloi reported the following issue [1] with stable/4.14: """ An iptable rule like the following on a multicore systems will result in accepting more connections than set in the rule. iptables -A INPUT -p tcp -m tcp --syn --dport 7777 -m connlimit \ --connlimit-above 2000 --connlimit-mask 0 -j DROP """ And proposed a fix that is not in Linus's tree. The discussion went on to confirm whether the issue was still reproducible with mainline/nf.git tip, and to either identify the upstream fix or re-submit the non-upstream fix. Alakesh eventually was able to test with upstream, and reported that issue was still reproducible [2]. On that, our findinds diverge, at least in my test environment: First, I verified that the suggested mainline fix for the issue [3] indeed fixes it, by testing with it applied and reverted on v4.18, a clean revert. (The issue is reproducible with the commit reverted). Then, with a consistent reproducer, I moved to nf.git, with HEAD on commit a007232 ("netfilter: nf_conncount: fix argument order to find_next_bit"), and the issues was not reproducible (even with 20+ threads on client side, the number Alakesh reported to achieve 2150+ connections [4], and I tried spreading the network interface IRQ affinity over more and more CPUs too.) Either way, the suggested mainline fix does actually fix the issue in 4.14 for at least one environment. So, it might well be the case that Alakesh's test environment has differences/subtleties that leads to more connections accepted, and more commits are needed for that particular environment type. (v2 update: see Florian's reply to v1 thread [1]; these different results are probably explained by very recent fixes still missing back then.) But for now, with one bare-metal environment (24-core server, 4-core client) verified, I thought of submitting the patches for review/comments/testing, then looking for additional fixes for that environment separately. The fix is PATCH 4 (needs fix in PATCH 5), and PATCHes 1-3 are helpers for a cleaner backport. All backports are simple, and essentially consist of refresh context lines and use older struct/file names. Reviews from netfilter maintainers are very appreciated, as I've no previous experience in this area, and although the backports look simple and build/run correctly, there's usually stuff that only more experienced people may notice. Thanks, Mauricio Links: ===== [1] https://www.spinics.net/lists/stable/msg270040.html [2] https://www.spinics.net/lists/stable/msg273669.html [3] https://www.spinics.net/lists/stable/msg271300.html [4] https://www.spinics.net/lists/stable/msg273669.html [5] https://www.spinics.net/lists/stable/msg276883.html Test-case: ========= - v4.14.91 (original): client achieves 2000+ connections (6000 target) with 3 threads. server # iptables -F server # iptables -A INPUT -p tcp -m tcp --syn --dport 7777 -m connlimit --connlimit-above 2000 --connlimit-mask 0 -j DROP server # iptables -L Chain INPUT (policy ACCEPT) target prot opt source destination DROP tcp -- anywhere anywhere tcp dpt:7777 flags:FIN,SYN,RST,ACK/SYN #conn src/0 > 2000 Chain FORWARD (policy ACCEPT) target prot opt source destination Chain OUTPUT (policy ACCEPT) target prot opt source destination server # ulimit -SHn 65000 server # ruby server.rb <... listening ...> client # ulimit -SHn 65000 client # ruby client.rb 10.230.56.100 7777 6000 3 Connecting to ["10.230.56.100"]:7777 6000 times with 3 1 2 3 <...> 2000 <...> 6000 Target reached. Thread finishing 6001 Target reached. Thread finishing 6002 Target reached. Thread finishing Threads done. 6002 connections press enter to exit - v4.14.91 + patches: client only achieved 2000 connections. server # (same procedure) client # (same procedure) Connecting to ["10.230.56.100"]:7777 6000 times with 3 1 2 3 <...> 2000 <... blocked for a while...> failed to create connection: Connection timed out - connect(2) for "10.230.56.100" port 7777 failed to create connection: Connection timed out - connect(2) for "10.230.56.100" port 7777 failed to create connection: Connection timed out - connect(2) for "10.230.56.100" port 7777 Threads done. 2000 connections press enter to exit Florian Westphal (3): netfilter: xt_connlimit: don't store address in the conn nodes netfilter: nf_conncount: fix garbage collection confirm race netfilter: nf_conncount: don't skip eviction when age is negative Pablo Neira Ayuso (1): netfilter: nf_conncount: expose connection list interface Yi-Hung Wei (1): netfilter: nf_conncount: Fix garbage collection with zones include/net/netfilter/nf_conntrack_count.h | 15 +++++ net/netfilter/xt_connlimit.c | 99 +++++++++++++++++++++++------- 2 files changed, 91 insertions(+), 23 deletions(-) create mode 100644 include/net/netfilter/nf_conntrack_count.h -- 2.7.4

5 years, 11 months

2
6
0 0

[4.19-stable PATCH 0/2] dax: Don't access a freed inode

by Dan Williams

The original upstream fix, commit 55e56f06ed71 "dax: Don't access a freed inode", prompted an immediate cleanup request. Now that the cleanup has landed, commit d8a706414af4 "dax: Use non-exclusive wait in wait_entry_unlocked()", backport them both to -stable. --- Dan Williams (1): dax: Use non-exclusive wait in wait_entry_unlocked() Matthew Wilcox (1): dax: Don't access a freed inode fs/dax.c | 69 ++++++++++++++++++++++++++++---------------------------------- 1 file changed, 31 insertions(+), 38 deletions(-)

5 years, 11 months

2
3
0 0

Re: [PATCH] smb3: fix large reads on encrypted connections

by Steve French

On Sun, Jan 6, 2019 at 4:58 AM Sebastian Kemper <sebastian_ml(a)gmx.net> wrote: > Sorry for probably breaking the thread. This is really in reply to Paul > Aubrich's patch titled "smb3: fix large reads on encrypted connections". > I browsed linux-cifs and found Paul's patch. With the patch applied the > problem is gone, kernel 4.19 works like 4.9 did without encryption. > > The patch title suggests that only large reads are not working. Well, > considering the cutoff is between 13K and 17K I'd say that encryption on > 4.19 for cifs can be considered broken without this patch. It'd be cool > if this could make it to stable kernels pronto. Yes - it is a a very important patch, and is merged in and marked for stable (for 4.19 and 4.20 kernels). Hopefully can be included soon. The good news though is that with the improved test automation that Paulo/Aurelien/Ronnie have been doing, we have added more to the automated xfstests run before checkin and more importantly added various different mount configrations that are much broader (used to be only a very small set that ran) and so would have caught this (and also other regressions that had made it through over the past couple years). Now our next challenge is figuring out how to get automated tests for smb3 to run reasonably regularly against some of the stable kernels and also against the full backports of cifs.ko to earlier kernels etc. which some need to get the many security, performance and functional improvements over the past year. -- Thanks, Steve

5 years, 11 months

2
1
0 0

FAILED: patch "[PATCH] ext4: check for shutdown and r/o file system in" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 18f2c4fcebf2582f96cbd5f2238f4f354a0e4847 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o <tytso(a)mit.edu> Date: Wed, 19 Dec 2018 14:36:58 -0500 Subject: [PATCH] ext4: check for shutdown and r/o file system in ext4_write_inode() If the file system has been shut down or is read-only, then ext4_write_inode() needs to bail out early. Also use jbd2_complete_transaction() instead of ext4_force_commit() so we only force a commit if it is needed. Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 664b434ba836..9affabd07682 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5400,9 +5400,13 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; - if (WARN_ON_ONCE(current->flags & PF_MEMALLOC)) + if (WARN_ON_ONCE(current->flags & PF_MEMALLOC) || + sb_rdonly(inode->i_sb)) return 0; + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + return -EIO; + if (EXT4_SB(inode->i_sb)->s_journal) { if (ext4_journal_current_handle()) { jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); @@ -5418,7 +5422,8 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync) return 0; - err = ext4_force_commit(inode->i_sb); + err = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal, + EXT4_I(inode)->i_sync_tid); } else { struct ext4_iloc iloc;

5 years, 11 months

1
0
0 0

[PATCH 03/16] crypto: ofb - fix handling partial blocks and make thread-safe

by Eric Biggers

From: Eric Biggers <ebiggers(a)google.com> Fix multiple bugs in the OFB implementation: 1. It stored the per-request state 'cnt' in the tfm context, which can be used by multiple threads concurrently (e.g. via AF_ALG). 2. It didn't support messages not a multiple of the block cipher size, despite being a stream cipher. 3. It didn't set cra_blocksize to 1 to indicate it is a stream cipher. To fix these, set the 'chunksize' property to the cipher block size to guarantee that when walking through the scatterlist, a partial block can only occur at the end. Then change the implementation to XOR a block at a time at first, then XOR the partial block at the end if needed. This is the same way CTR and CFB are implemented. As a bonus, this also improves performance in most cases over the current approach. Fixes: e497c51896b3 ("crypto: ofb - add output feedback mode") Cc: <stable(a)vger.kernel.org> # v4.20+ Cc: Gilad Ben-Yossef <gilad(a)benyossef.com> Signed-off-by: Eric Biggers <ebiggers(a)google.com> --- crypto/ofb.c | 91 ++++++++++++++++++++---------------------------- crypto/testmgr.h | 28 +++++++++++++-- 2 files changed, 63 insertions(+), 56 deletions(-) diff --git a/crypto/ofb.c b/crypto/ofb.c index 886631708c5e9..cab0b80953fed 100644 --- a/crypto/ofb.c +++ b/crypto/ofb.c @@ -5,9 +5,6 @@ * * Copyright (C) 2018 ARM Limited or its affiliates. * All rights reserved. - * - * Based loosely on public domain code gleaned from libtomcrypt - * (https://github.com/libtom/libtomcrypt). */ #include <crypto/algapi.h> @@ -21,7 +18,6 @@ struct crypto_ofb_ctx { struct crypto_cipher *child; - int cnt; }; @@ -41,58 +37,40 @@ static int crypto_ofb_setkey(struct crypto_skcipher *parent, const u8 *key, return err; } -static int crypto_ofb_encrypt_segment(struct crypto_ofb_ctx *ctx, - struct skcipher_walk *walk, - struct crypto_cipher *tfm) +static int crypto_ofb_crypt(struct skcipher_request *req) { - int bsize = crypto_cipher_blocksize(tfm); - int nbytes = walk->nbytes; - - u8 *src = walk->src.virt.addr; - u8 *dst = walk->dst.virt.addr; - u8 *iv = walk->iv; - - do { - if (ctx->cnt == bsize) { - if (nbytes < bsize) - break; - crypto_cipher_encrypt_one(tfm, iv, iv); - ctx->cnt = 0; - } - *dst = *src ^ iv[ctx->cnt]; - src++; - dst++; - ctx->cnt++; - } while (--nbytes); - return nbytes; -} - -static int crypto_ofb_encrypt(struct skcipher_request *req) -{ - struct skcipher_walk walk; struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - unsigned int bsize; struct crypto_ofb_ctx *ctx = crypto_skcipher_ctx(tfm); - struct crypto_cipher *child = ctx->child; - int ret = 0; + struct crypto_cipher *cipher = ctx->child; + const unsigned int bsize = crypto_cipher_blocksize(cipher); + struct skcipher_walk walk; + int err; - bsize = crypto_cipher_blocksize(child); - ctx->cnt = bsize; + err = skcipher_walk_virt(&walk, req, false); - ret = skcipher_walk_virt(&walk, req, false); + while (walk.nbytes >= bsize) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + u8 * const iv = walk.iv; + unsigned int nbytes = walk.nbytes; - while (walk.nbytes) { - ret = crypto_ofb_encrypt_segment(ctx, &walk, child); - ret = skcipher_walk_done(&walk, ret); - } + do { + crypto_cipher_encrypt_one(cipher, iv, iv); + crypto_xor_cpy(dst, src, iv, bsize); + dst += bsize; + src += bsize; + } while ((nbytes -= bsize) >= bsize); - return ret; -} + err = skcipher_walk_done(&walk, nbytes); + } -/* OFB encrypt and decrypt are identical */ -static int crypto_ofb_decrypt(struct skcipher_request *req) -{ - return crypto_ofb_encrypt(req); + if (walk.nbytes) { + crypto_cipher_encrypt_one(cipher, walk.iv, walk.iv); + crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, walk.iv, + walk.nbytes); + err = skcipher_walk_done(&walk, 0); + } + return err; } static int crypto_ofb_init_tfm(struct crypto_skcipher *tfm) @@ -165,13 +143,18 @@ static int crypto_ofb_create(struct crypto_template *tmpl, struct rtattr **tb) if (err) goto err_drop_spawn; + /* OFB mode is a stream cipher. */ + inst->alg.base.cra_blocksize = 1; + + /* + * To simplify the implementation, configure the skcipher walk to only + * give a partial block at the very end, never earlier. + */ + inst->alg.chunksize = alg->cra_blocksize; + inst->alg.base.cra_priority = alg->cra_priority; - inst->alg.base.cra_blocksize = alg->cra_blocksize; inst->alg.base.cra_alignmask = alg->cra_alignmask; - /* We access the data as u32s when xoring. */ - inst->alg.base.cra_alignmask |= __alignof__(u32) - 1; - inst->alg.ivsize = alg->cra_blocksize; inst->alg.min_keysize = alg->cra_cipher.cia_min_keysize; inst->alg.max_keysize = alg->cra_cipher.cia_max_keysize; @@ -182,8 +165,8 @@ static int crypto_ofb_create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.exit = crypto_ofb_exit_tfm; inst->alg.setkey = crypto_ofb_setkey; - inst->alg.encrypt = crypto_ofb_encrypt; - inst->alg.decrypt = crypto_ofb_decrypt; + inst->alg.encrypt = crypto_ofb_crypt; + inst->alg.decrypt = crypto_ofb_crypt; inst->free = crypto_ofb_free; diff --git a/crypto/testmgr.h b/crypto/testmgr.h index 7f4dae7a57a1c..ca8e8ebef309d 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -16681,8 +16681,7 @@ static const struct cipher_testvec aes_ctr_rfc3686_tv_template[] = { }; static const struct cipher_testvec aes_ofb_tv_template[] = { - /* From NIST Special Publication 800-38A, Appendix F.5 */ - { + { /* From NIST Special Publication 800-38A, Appendix F.5 */ .key = "\x2b\x7e\x15\x16\x28\xae\xd2\xa6" "\xab\xf7\x15\x88\x09\xcf\x4f\x3c", .klen = 16, @@ -16705,6 +16704,31 @@ static const struct cipher_testvec aes_ofb_tv_template[] = { "\x30\x4c\x65\x28\xf6\x59\xc7\x78" "\x66\xa5\x10\xd9\xc1\xd6\xae\x5e", .len = 64, + .also_non_np = 1, + .np = 2, + .tap = { 31, 33 }, + }, { /* > 16 bytes, not a multiple of 16 bytes */ + .key = "\x2b\x7e\x15\x16\x28\xae\xd2\xa6" + "\xab\xf7\x15\x88\x09\xcf\x4f\x3c", + .klen = 16, + .iv = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", + .ptext = "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96" + "\xe9\x3d\x7e\x11\x73\x93\x17\x2a" + "\xae", + .ctext = "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20" + "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a" + "\x77", + .len = 17, + }, { /* < 16 bytes */ + .key = "\x2b\x7e\x15\x16\x28\xae\xd2\xa6" + "\xab\xf7\x15\x88\x09\xcf\x4f\x3c", + .klen = 16, + .iv = "\x00\x01\x02\x03\x04\x05\x06\x07" + "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f", + .ptext = "\x6b\xc1\xbe\xe2\x2e\x40\x9f", + .ctext = "\x3b\x3f\xd9\x2e\xb7\x2d\xad", + .len = 7, } }; -- 2.20.1

5 years, 11 months

2
1
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2019