December 2020 - Linux-stable-mirror

FAILED: patch "[PATCH] powerpc/powernv/memtrace: Fix crashing the kernel when" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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 d6718941a2767fb383e105d257d2105fe4f15f0e Mon Sep 17 00:00:00 2001 From: David Hildenbrand <david(a)redhat.com> Date: Wed, 11 Nov 2020 15:53:16 +0100 Subject: [PATCH] powerpc/powernv/memtrace: Fix crashing the kernel when enabling concurrently It's very easy to crash the kernel right now by simply trying to enable memtrace concurrently, hammering on the "enable" interface loop.sh: #!/bin/bash dmesg --console-off while true; do echo 0x40000000 > /sys/kernel/debug/powerpc/memtrace/enable done [root@localhost ~]# loop.sh & [root@localhost ~]# loop.sh & Resulting quickly in a kernel crash. Let's properly protect using a mutex. Fixes: 9d5171a8f248 ("powerpc/powernv: Enable removal of memory for in memory tracing") Cc: stable(a)vger.kernel.org# v4.14+ Signed-off-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/20201111145322.15793-3-david@redhat.com diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index eea1f94482ff..0e42fe2d7b6a 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -30,6 +30,7 @@ struct memtrace_entry { char name[16]; }; +static DEFINE_MUTEX(memtrace_mutex); static u64 memtrace_size; static struct memtrace_entry *memtrace_array; @@ -279,6 +280,7 @@ static int memtrace_online(void) static int memtrace_enable_set(void *data, u64 val) { + int rc = -EAGAIN; u64 bytes; /* @@ -291,25 +293,31 @@ static int memtrace_enable_set(void *data, u64 val) return -EINVAL; } + mutex_lock(&memtrace_mutex); + /* Re-add/online previously removed/offlined memory */ if (memtrace_size) { if (memtrace_online()) - return -EAGAIN; + goto out_unlock; } - if (!val) - return 0; + if (!val) { + rc = 0; + goto out_unlock; + } /* Offline and remove memory */ if (memtrace_init_regions_runtime(val)) - return -EINVAL; + goto out_unlock; if (memtrace_init_debugfs()) - return -EINVAL; + goto out_unlock; memtrace_size = val; - - return 0; + rc = 0; +out_unlock: + mutex_unlock(&memtrace_mutex); + return rc; } static int memtrace_enable_get(void *data, u64 *val)

3 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] powerpc/bitops: Fix possible undefined behaviour with fls()" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-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 1891ef21d92c4801ea082ee8ed478e304ddc6749 Mon Sep 17 00:00:00 2001 From: Christophe Leroy <christophe.leroy(a)csgroup.eu> Date: Thu, 22 Oct 2020 14:05:46 +0000 Subject: [PATCH] powerpc/bitops: Fix possible undefined behaviour with fls() and fls64() fls() and fls64() are using __builtin_ctz() and _builtin_ctzll(). On powerpc, those builtins trivially use ctlzw and ctlzd power instructions. Allthough those instructions provide the expected result with input argument 0, __builtin_ctz() and __builtin_ctzll() are documented as undefined for value 0. The easiest fix would be to use fls() and fls64() functions defined in include/asm-generic/bitops/builtin-fls.h and include/asm-generic/bitops/fls64.h, but GCC output is not optimal: 00000388 <testfls>: 388: 2c 03 00 00 cmpwi r3,0 38c: 41 82 00 10 beq 39c <testfls+0x14> 390: 7c 63 00 34 cntlzw r3,r3 394: 20 63 00 20 subfic r3,r3,32 398: 4e 80 00 20 blr 39c: 38 60 00 00 li r3,0 3a0: 4e 80 00 20 blr 000003b0 <testfls64>: 3b0: 2c 03 00 00 cmpwi r3,0 3b4: 40 82 00 1c bne 3d0 <testfls64+0x20> 3b8: 2f 84 00 00 cmpwi cr7,r4,0 3bc: 38 60 00 00 li r3,0 3c0: 4d 9e 00 20 beqlr cr7 3c4: 7c 83 00 34 cntlzw r3,r4 3c8: 20 63 00 20 subfic r3,r3,32 3cc: 4e 80 00 20 blr 3d0: 7c 63 00 34 cntlzw r3,r3 3d4: 20 63 00 40 subfic r3,r3,64 3d8: 4e 80 00 20 blr When the input of fls(x) is a constant, just check x for nullity and return either 0 or __builtin_clz(x). Otherwise, use cntlzw instruction directly. For fls64() on PPC64, do the same but with __builtin_clzll() and cntlzd instruction. On PPC32, lets take the generic fls64() which will use our fls(). The result is as expected: 00000388 <testfls>: 388: 7c 63 00 34 cntlzw r3,r3 38c: 20 63 00 20 subfic r3,r3,32 390: 4e 80 00 20 blr 000003a0 <testfls64>: 3a0: 2c 03 00 00 cmpwi r3,0 3a4: 40 82 00 10 bne 3b4 <testfls64+0x14> 3a8: 7c 83 00 34 cntlzw r3,r4 3ac: 20 63 00 20 subfic r3,r3,32 3b0: 4e 80 00 20 blr 3b4: 7c 63 00 34 cntlzw r3,r3 3b8: 20 63 00 40 subfic r3,r3,64 3bc: 4e 80 00 20 blr Fixes: 2fcff790dcb4 ("powerpc: Use builtin functions for fls()/__fls()/fls64()") Cc: stable(a)vger.kernel.org Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Acked-by: Segher Boessenkool <segher(a)kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/348c2d3f19ffcff8abe50d52513f989c4581d000.16033755… diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 4a4d3afd5340..299ab33505a6 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -216,15 +216,34 @@ static inline void arch___clear_bit_unlock(int nr, volatile unsigned long *addr) */ static inline int fls(unsigned int x) { - return 32 - __builtin_clz(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 32 - __builtin_clz(x) : 0; + asm("cntlzw %0,%1" : "=r" (lz) : "r" (x)); + return 32 - lz; } #include <asm-generic/bitops/builtin-__fls.h> +/* + * 64-bit can do this using one cntlzd (count leading zeroes doubleword) + * instruction; for 32-bit we use the generic version, which does two + * 32-bit fls calls. + */ +#ifdef CONFIG_PPC64 static inline int fls64(__u64 x) { - return 64 - __builtin_clzll(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 64 - __builtin_clzll(x) : 0; + asm("cntlzd %0,%1" : "=r" (lz) : "r" (x)); + return 64 - lz; } +#else +#include <asm-generic/bitops/fls64.h> +#endif #ifdef CONFIG_PPC64 unsigned int __arch_hweight8(unsigned int w);

3 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] powerpc/bitops: Fix possible undefined behaviour with fls()" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-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 1891ef21d92c4801ea082ee8ed478e304ddc6749 Mon Sep 17 00:00:00 2001 From: Christophe Leroy <christophe.leroy(a)csgroup.eu> Date: Thu, 22 Oct 2020 14:05:46 +0000 Subject: [PATCH] powerpc/bitops: Fix possible undefined behaviour with fls() and fls64() fls() and fls64() are using __builtin_ctz() and _builtin_ctzll(). On powerpc, those builtins trivially use ctlzw and ctlzd power instructions. Allthough those instructions provide the expected result with input argument 0, __builtin_ctz() and __builtin_ctzll() are documented as undefined for value 0. The easiest fix would be to use fls() and fls64() functions defined in include/asm-generic/bitops/builtin-fls.h and include/asm-generic/bitops/fls64.h, but GCC output is not optimal: 00000388 <testfls>: 388: 2c 03 00 00 cmpwi r3,0 38c: 41 82 00 10 beq 39c <testfls+0x14> 390: 7c 63 00 34 cntlzw r3,r3 394: 20 63 00 20 subfic r3,r3,32 398: 4e 80 00 20 blr 39c: 38 60 00 00 li r3,0 3a0: 4e 80 00 20 blr 000003b0 <testfls64>: 3b0: 2c 03 00 00 cmpwi r3,0 3b4: 40 82 00 1c bne 3d0 <testfls64+0x20> 3b8: 2f 84 00 00 cmpwi cr7,r4,0 3bc: 38 60 00 00 li r3,0 3c0: 4d 9e 00 20 beqlr cr7 3c4: 7c 83 00 34 cntlzw r3,r4 3c8: 20 63 00 20 subfic r3,r3,32 3cc: 4e 80 00 20 blr 3d0: 7c 63 00 34 cntlzw r3,r3 3d4: 20 63 00 40 subfic r3,r3,64 3d8: 4e 80 00 20 blr When the input of fls(x) is a constant, just check x for nullity and return either 0 or __builtin_clz(x). Otherwise, use cntlzw instruction directly. For fls64() on PPC64, do the same but with __builtin_clzll() and cntlzd instruction. On PPC32, lets take the generic fls64() which will use our fls(). The result is as expected: 00000388 <testfls>: 388: 7c 63 00 34 cntlzw r3,r3 38c: 20 63 00 20 subfic r3,r3,32 390: 4e 80 00 20 blr 000003a0 <testfls64>: 3a0: 2c 03 00 00 cmpwi r3,0 3a4: 40 82 00 10 bne 3b4 <testfls64+0x14> 3a8: 7c 83 00 34 cntlzw r3,r4 3ac: 20 63 00 20 subfic r3,r3,32 3b0: 4e 80 00 20 blr 3b4: 7c 63 00 34 cntlzw r3,r3 3b8: 20 63 00 40 subfic r3,r3,64 3bc: 4e 80 00 20 blr Fixes: 2fcff790dcb4 ("powerpc: Use builtin functions for fls()/__fls()/fls64()") Cc: stable(a)vger.kernel.org Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Acked-by: Segher Boessenkool <segher(a)kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/348c2d3f19ffcff8abe50d52513f989c4581d000.16033755… diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 4a4d3afd5340..299ab33505a6 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -216,15 +216,34 @@ static inline void arch___clear_bit_unlock(int nr, volatile unsigned long *addr) */ static inline int fls(unsigned int x) { - return 32 - __builtin_clz(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 32 - __builtin_clz(x) : 0; + asm("cntlzw %0,%1" : "=r" (lz) : "r" (x)); + return 32 - lz; } #include <asm-generic/bitops/builtin-__fls.h> +/* + * 64-bit can do this using one cntlzd (count leading zeroes doubleword) + * instruction; for 32-bit we use the generic version, which does two + * 32-bit fls calls. + */ +#ifdef CONFIG_PPC64 static inline int fls64(__u64 x) { - return 64 - __builtin_clzll(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 64 - __builtin_clzll(x) : 0; + asm("cntlzd %0,%1" : "=r" (lz) : "r" (x)); + return 64 - lz; } +#else +#include <asm-generic/bitops/fls64.h> +#endif #ifdef CONFIG_PPC64 unsigned int __arch_hweight8(unsigned int w);

3 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] powerpc/bitops: Fix possible undefined behaviour with fls()" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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 1891ef21d92c4801ea082ee8ed478e304ddc6749 Mon Sep 17 00:00:00 2001 From: Christophe Leroy <christophe.leroy(a)csgroup.eu> Date: Thu, 22 Oct 2020 14:05:46 +0000 Subject: [PATCH] powerpc/bitops: Fix possible undefined behaviour with fls() and fls64() fls() and fls64() are using __builtin_ctz() and _builtin_ctzll(). On powerpc, those builtins trivially use ctlzw and ctlzd power instructions. Allthough those instructions provide the expected result with input argument 0, __builtin_ctz() and __builtin_ctzll() are documented as undefined for value 0. The easiest fix would be to use fls() and fls64() functions defined in include/asm-generic/bitops/builtin-fls.h and include/asm-generic/bitops/fls64.h, but GCC output is not optimal: 00000388 <testfls>: 388: 2c 03 00 00 cmpwi r3,0 38c: 41 82 00 10 beq 39c <testfls+0x14> 390: 7c 63 00 34 cntlzw r3,r3 394: 20 63 00 20 subfic r3,r3,32 398: 4e 80 00 20 blr 39c: 38 60 00 00 li r3,0 3a0: 4e 80 00 20 blr 000003b0 <testfls64>: 3b0: 2c 03 00 00 cmpwi r3,0 3b4: 40 82 00 1c bne 3d0 <testfls64+0x20> 3b8: 2f 84 00 00 cmpwi cr7,r4,0 3bc: 38 60 00 00 li r3,0 3c0: 4d 9e 00 20 beqlr cr7 3c4: 7c 83 00 34 cntlzw r3,r4 3c8: 20 63 00 20 subfic r3,r3,32 3cc: 4e 80 00 20 blr 3d0: 7c 63 00 34 cntlzw r3,r3 3d4: 20 63 00 40 subfic r3,r3,64 3d8: 4e 80 00 20 blr When the input of fls(x) is a constant, just check x for nullity and return either 0 or __builtin_clz(x). Otherwise, use cntlzw instruction directly. For fls64() on PPC64, do the same but with __builtin_clzll() and cntlzd instruction. On PPC32, lets take the generic fls64() which will use our fls(). The result is as expected: 00000388 <testfls>: 388: 7c 63 00 34 cntlzw r3,r3 38c: 20 63 00 20 subfic r3,r3,32 390: 4e 80 00 20 blr 000003a0 <testfls64>: 3a0: 2c 03 00 00 cmpwi r3,0 3a4: 40 82 00 10 bne 3b4 <testfls64+0x14> 3a8: 7c 83 00 34 cntlzw r3,r4 3ac: 20 63 00 20 subfic r3,r3,32 3b0: 4e 80 00 20 blr 3b4: 7c 63 00 34 cntlzw r3,r3 3b8: 20 63 00 40 subfic r3,r3,64 3bc: 4e 80 00 20 blr Fixes: 2fcff790dcb4 ("powerpc: Use builtin functions for fls()/__fls()/fls64()") Cc: stable(a)vger.kernel.org Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Acked-by: Segher Boessenkool <segher(a)kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/348c2d3f19ffcff8abe50d52513f989c4581d000.16033755… diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 4a4d3afd5340..299ab33505a6 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -216,15 +216,34 @@ static inline void arch___clear_bit_unlock(int nr, volatile unsigned long *addr) */ static inline int fls(unsigned int x) { - return 32 - __builtin_clz(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 32 - __builtin_clz(x) : 0; + asm("cntlzw %0,%1" : "=r" (lz) : "r" (x)); + return 32 - lz; } #include <asm-generic/bitops/builtin-__fls.h> +/* + * 64-bit can do this using one cntlzd (count leading zeroes doubleword) + * instruction; for 32-bit we use the generic version, which does two + * 32-bit fls calls. + */ +#ifdef CONFIG_PPC64 static inline int fls64(__u64 x) { - return 64 - __builtin_clzll(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 64 - __builtin_clzll(x) : 0; + asm("cntlzd %0,%1" : "=r" (lz) : "r" (x)); + return 64 - lz; } +#else +#include <asm-generic/bitops/fls64.h> +#endif #ifdef CONFIG_PPC64 unsigned int __arch_hweight8(unsigned int w);

3 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] powerpc: Fix incorrect stw{, ux, u, x} instructions in" 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 d85be8a49e733dcd23674aa6202870d54bf5600d Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Date: Thu, 22 Oct 2020 09:29:20 +0000 Subject: [PATCH] powerpc: Fix incorrect stw{, ux, u, x} instructions in __set_pte_at The placeholder for instruction selection should use the second argument's operand, which is %1, not %0. This could generate incorrect assembly code if the memory addressing of operand %0 is a different form from that of operand %1. Also remove the %Un placeholder because having %Un placeholders for two operands which are based on the same local var (ptep) doesn't make much sense. By the way, it doesn't change the current behaviour because "<>" constraint is missing for the associated "=m". [chleroy: revised commit log iaw segher's comments and removed %U0] Fixes: 9bf2b5cdc5fe ("powerpc: Fixes for CONFIG_PTE_64BIT for SMP support") Cc: <stable(a)vger.kernel.org> # v2.6.28+ Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Acked-by: Segher Boessenkool <segher(a)kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/96354bd77977a6a933fe9020da57629007fdb920.16033589… diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 36443cda8dcf..41d8bc6db303 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -522,9 +522,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, if (pte_val(*ptep) & _PAGE_HASHPTE) flush_hash_entry(mm, ptep, addr); __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ + stw%X0 %2,%0\n\ eieio\n\ - stw%U0%X0 %L2,%1" + stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 6277e7596ae5..ac75f4ab0dba 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -192,9 +192,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, */ if (IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_PTE_64BIT) && !percpu) { __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ + stw%X0 %2,%0\n\ eieio\n\ - stw%U0%X0 %L2,%1" + stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); return;

3 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] powerpc: Fix incorrect stw{, ux, u, x} instructions 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 d85be8a49e733dcd23674aa6202870d54bf5600d Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Date: Thu, 22 Oct 2020 09:29:20 +0000 Subject: [PATCH] powerpc: Fix incorrect stw{, ux, u, x} instructions in __set_pte_at The placeholder for instruction selection should use the second argument's operand, which is %1, not %0. This could generate incorrect assembly code if the memory addressing of operand %0 is a different form from that of operand %1. Also remove the %Un placeholder because having %Un placeholders for two operands which are based on the same local var (ptep) doesn't make much sense. By the way, it doesn't change the current behaviour because "<>" constraint is missing for the associated "=m". [chleroy: revised commit log iaw segher's comments and removed %U0] Fixes: 9bf2b5cdc5fe ("powerpc: Fixes for CONFIG_PTE_64BIT for SMP support") Cc: <stable(a)vger.kernel.org> # v2.6.28+ Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Acked-by: Segher Boessenkool <segher(a)kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/96354bd77977a6a933fe9020da57629007fdb920.16033589… diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 36443cda8dcf..41d8bc6db303 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -522,9 +522,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, if (pte_val(*ptep) & _PAGE_HASHPTE) flush_hash_entry(mm, ptep, addr); __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ + stw%X0 %2,%0\n\ eieio\n\ - stw%U0%X0 %L2,%1" + stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 6277e7596ae5..ac75f4ab0dba 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -192,9 +192,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, */ if (IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_PTE_64BIT) && !percpu) { __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ + stw%X0 %2,%0\n\ eieio\n\ - stw%U0%X0 %L2,%1" + stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); return;

3 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] powerpc: Fix incorrect stw{, ux, u, x} instructions in" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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 d85be8a49e733dcd23674aa6202870d54bf5600d Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Date: Thu, 22 Oct 2020 09:29:20 +0000 Subject: [PATCH] powerpc: Fix incorrect stw{, ux, u, x} instructions in __set_pte_at The placeholder for instruction selection should use the second argument's operand, which is %1, not %0. This could generate incorrect assembly code if the memory addressing of operand %0 is a different form from that of operand %1. Also remove the %Un placeholder because having %Un placeholders for two operands which are based on the same local var (ptep) doesn't make much sense. By the way, it doesn't change the current behaviour because "<>" constraint is missing for the associated "=m". [chleroy: revised commit log iaw segher's comments and removed %U0] Fixes: 9bf2b5cdc5fe ("powerpc: Fixes for CONFIG_PTE_64BIT for SMP support") Cc: <stable(a)vger.kernel.org> # v2.6.28+ Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Acked-by: Segher Boessenkool <segher(a)kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/96354bd77977a6a933fe9020da57629007fdb920.16033589… diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 36443cda8dcf..41d8bc6db303 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -522,9 +522,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, if (pte_val(*ptep) & _PAGE_HASHPTE) flush_hash_entry(mm, ptep, addr); __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ + stw%X0 %2,%0\n\ eieio\n\ - stw%U0%X0 %L2,%1" + stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 6277e7596ae5..ac75f4ab0dba 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -192,9 +192,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, */ if (IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_PTE_64BIT) && !percpu) { __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ + stw%X0 %2,%0\n\ eieio\n\ - stw%U0%X0 %L2,%1" + stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); return;

3 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Assign dev to DM MR" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-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 ca991a7d14d4835b302bcd182fdbf54470f45520 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb <maorg(a)nvidia.com> Date: Thu, 3 Dec 2020 21:08:07 +0200 Subject: [PATCH] RDMA/mlx5: Assign dev to DM MR Currently, DM MR registration flow doesn't set the mlx5_ib_dev pointer and can cause a NULL pointer dereference if userspace dumps the MR via rdma tool. Assign the IB device together with the other fields and remove the redundant reference of mlx5_ib_dev from mlx5_ib_mr. Cc: stable(a)vger.kernel.org Fixes: 6c29f57ea475 ("IB/mlx5: Device memory mr registration support") Link: https://lore.kernel.org/r/20201203190807.127189-1-leon@kernel.org Signed-off-by: Maor Gottlieb <maorg(a)nvidia.com> Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index fac495e7834e..c33d6fd64fb6 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -669,7 +669,6 @@ struct mlx5_ib_mr { struct mlx5_shared_mr_info *smr_info; struct list_head list; struct mlx5_cache_ent *cache_ent; - struct mlx5_ib_dev *dev; u32 out[MLX5_ST_SZ_DW(create_mkey_out)]; struct mlx5_core_sig_ctx *sig; void *descs_alloc; @@ -1107,6 +1106,11 @@ static inline struct mlx5_ib_dev *to_mdev(struct ib_device *ibdev) return container_of(ibdev, struct mlx5_ib_dev, ib_dev); } +static inline struct mlx5_ib_dev *mr_to_mdev(struct mlx5_ib_mr *mr) +{ + return to_mdev(mr->ibmr.device); +} + static inline struct mlx5_ib_dev *mlx5_udata_to_mdev(struct ib_udata *udata) { struct mlx5_ib_ucontext *context = rdma_udata_to_drv_context( diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 281032d2827f..6fa869c30e3f 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -137,8 +137,8 @@ static void create_mkey_callback(int status, struct mlx5_async_work *context) { struct mlx5_ib_mr *mr = container_of(context, struct mlx5_ib_mr, cb_work); - struct mlx5_ib_dev *dev = mr->dev; struct mlx5_cache_ent *ent = mr->cache_ent; + struct mlx5_ib_dev *dev = ent->dev; unsigned long flags; if (status) { @@ -176,7 +176,6 @@ static struct mlx5_ib_mr *alloc_cache_mr(struct mlx5_cache_ent *ent, void *mkc) if (!mr) return NULL; mr->cache_ent = ent; - mr->dev = ent->dev; set_mkc_access_pd_addr_fields(mkc, 0, 0, ent->dev->umrc.pd); MLX5_SET(mkc, mkc, free, 1); @@ -931,6 +930,7 @@ static void set_mr_fields(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, mr->ibmr.lkey = mr->mmkey.key; mr->ibmr.rkey = mr->mmkey.key; mr->ibmr.length = length; + mr->ibmr.device = &dev->ib_dev; mr->access_flags = access_flags; } @@ -1062,7 +1062,7 @@ static void *mlx5_ib_create_xlt_wr(struct mlx5_ib_mr *mr, size_t nents, size_t ent_size, unsigned int flags) { - struct mlx5_ib_dev *dev = mr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; dma_addr_t dma; void *xlt; @@ -1124,7 +1124,7 @@ static unsigned int xlt_wr_final_send_flags(unsigned int flags) int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, int page_shift, int flags) { - struct mlx5_ib_dev *dev = mr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; void *xlt; struct mlx5_umr_wr wr; @@ -1203,7 +1203,7 @@ int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, */ static int mlx5_ib_update_mr_pas(struct mlx5_ib_mr *mr, unsigned int flags) { - struct mlx5_ib_dev *dev = mr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; struct ib_block_iter biter; struct mlx5_mtt *cur_mtt; @@ -1335,7 +1335,6 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem, } mr->mmkey.type = MLX5_MKEY_MR; mr->desc_size = sizeof(struct mlx5_mtt); - mr->dev = dev; mr->umem = umem; set_mr_fields(dev, mr, umem->length, access_flags); kvfree(in); @@ -1579,17 +1578,17 @@ int mlx5_mr_cache_invalidate(struct mlx5_ib_mr *mr) { struct mlx5_umr_wr umrwr = {}; - if (mr->dev->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + if (mr_to_mdev(mr)->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) return 0; umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR | MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS; umrwr.wr.opcode = MLX5_IB_WR_UMR; - umrwr.pd = mr->dev->umrc.pd; + umrwr.pd = mr_to_mdev(mr)->umrc.pd; umrwr.mkey = mr->mmkey.key; umrwr.ignore_free_state = 1; - return mlx5_ib_post_send_wait(mr->dev, &umrwr); + return mlx5_ib_post_send_wait(mr_to_mdev(mr), &umrwr); } /* diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index f4a28a012187..aa2413b50adc 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -102,7 +102,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, if (flags & MLX5_IB_UPD_XLT_ZAP) { for (; pklm != end; pklm++, idx++) { pklm->bcount = cpu_to_be32(MLX5_IMR_MTT_SIZE); - pklm->key = cpu_to_be32(imr->dev->null_mkey); + pklm->key = cpu_to_be32(mr_to_mdev(imr)->null_mkey); pklm->va = 0; } return; @@ -129,7 +129,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, * locking around the xarray. */ lockdep_assert_held(&to_ib_umem_odp(imr->umem)->umem_mutex); - lockdep_assert_held(&imr->dev->odp_srcu); + lockdep_assert_held(&mr_to_mdev(imr)->odp_srcu); for (; pklm != end; pklm++, idx++) { struct mlx5_ib_mr *mtt = xa_load(&imr->implicit_children, idx); @@ -139,7 +139,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, pklm->key = cpu_to_be32(mtt->ibmr.lkey); pklm->va = cpu_to_be64(idx * MLX5_IMR_MTT_SIZE); } else { - pklm->key = cpu_to_be32(imr->dev->null_mkey); + pklm->key = cpu_to_be32(mr_to_mdev(imr)->null_mkey); pklm->va = 0; } } @@ -199,7 +199,7 @@ static void dma_fence_odp_mr(struct mlx5_ib_mr *mr) mutex_unlock(&odp->umem_mutex); if (!mr->cache_ent) { - mlx5_core_destroy_mkey(mr->dev->mdev, &mr->mmkey); + mlx5_core_destroy_mkey(mr_to_mdev(mr)->mdev, &mr->mmkey); WARN_ON(mr->descs); } } @@ -222,19 +222,19 @@ static void free_implicit_child_mr(struct mlx5_ib_mr *mr, bool need_imr_xlt) WARN_ON(atomic_read(&mr->num_deferred_work)); if (need_imr_xlt) { - srcu_key = srcu_read_lock(&mr->dev->odp_srcu); + srcu_key = srcu_read_lock(&mr_to_mdev(mr)->odp_srcu); mutex_lock(&odp_imr->umem_mutex); mlx5_ib_update_xlt(mr->parent, idx, 1, 0, MLX5_IB_UPD_XLT_INDIRECT | MLX5_IB_UPD_XLT_ATOMIC); mutex_unlock(&odp_imr->umem_mutex); - srcu_read_unlock(&mr->dev->odp_srcu, srcu_key); + srcu_read_unlock(&mr_to_mdev(mr)->odp_srcu, srcu_key); } dma_fence_odp_mr(mr); mr->parent = NULL; - mlx5_mr_cache_free(mr->dev, mr); + mlx5_mr_cache_free(mr_to_mdev(mr), mr); ib_umem_odp_release(odp); if (atomic_dec_and_test(&imr->num_deferred_work)) wake_up(&imr->q_deferred_work); @@ -274,7 +274,7 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr) goto out_unlock; atomic_inc(&imr->num_deferred_work); - call_srcu(&mr->dev->odp_srcu, &mr->odp_destroy.rcu, + call_srcu(&mr_to_mdev(mr)->odp_srcu, &mr->odp_destroy.rcu, free_implicit_child_mr_rcu); out_unlock: @@ -476,12 +476,13 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, if (IS_ERR(odp)) return ERR_CAST(odp); - ret = mr = mlx5_mr_cache_alloc(imr->dev, MLX5_IMR_MTT_CACHE_ENTRY, - imr->access_flags); + ret = mr = mlx5_mr_cache_alloc( + mr_to_mdev(imr), MLX5_IMR_MTT_CACHE_ENTRY, imr->access_flags); if (IS_ERR(mr)) goto out_umem; mr->ibmr.pd = imr->ibmr.pd; + mr->ibmr.device = &mr_to_mdev(imr)->ib_dev; mr->umem = &odp->umem; mr->ibmr.lkey = mr->mmkey.key; mr->ibmr.rkey = mr->mmkey.key; @@ -517,11 +518,11 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, goto out_mr; } - mlx5_ib_dbg(imr->dev, "key %x mr %p\n", mr->mmkey.key, mr); + mlx5_ib_dbg(mr_to_mdev(imr), "key %x mr %p\n", mr->mmkey.key, mr); return mr; out_mr: - mlx5_mr_cache_free(imr->dev, mr); + mlx5_mr_cache_free(mr_to_mdev(imr), mr); out_umem: ib_umem_odp_release(odp); return ret; @@ -555,6 +556,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, imr->umem = &umem_odp->umem; imr->ibmr.lkey = imr->mmkey.key; imr->ibmr.rkey = imr->mmkey.key; + imr->ibmr.device = &dev->ib_dev; imr->umem = &umem_odp->umem; imr->is_odp_implicit = true; atomic_set(&imr->num_deferred_work, 0); @@ -588,7 +590,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) { struct ib_umem_odp *odp_imr = to_ib_umem_odp(imr->umem); - struct mlx5_ib_dev *dev = imr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(imr); struct list_head destroy_list; struct mlx5_ib_mr *mtt; struct mlx5_ib_mr *tmp; @@ -658,10 +660,10 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) void mlx5_ib_fence_odp_mr(struct mlx5_ib_mr *mr) { /* Prevent new page faults and prefetch requests from succeeding */ - xa_erase(&mr->dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key)); + xa_erase(&mr_to_mdev(mr)->odp_mkeys, mlx5_base_mkey(mr->mmkey.key)); /* Wait for all running page-fault handlers to finish. */ - synchronize_srcu(&mr->dev->odp_srcu); + synchronize_srcu(&mr_to_mdev(mr)->odp_srcu); wait_event(mr->q_deferred_work, !atomic_read(&mr->num_deferred_work)); @@ -705,7 +707,7 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp, if (ret < 0) { if (ret != -EAGAIN) - mlx5_ib_err(mr->dev, + mlx5_ib_err(mr_to_mdev(mr), "Failed to update mkey page tables\n"); goto out; } @@ -795,7 +797,7 @@ static int pagefault_implicit_mr(struct mlx5_ib_mr *imr, MLX5_IB_UPD_XLT_ATOMIC); mutex_unlock(&odp_imr->umem_mutex); if (err) { - mlx5_ib_err(imr->dev, "Failed to update PAS\n"); + mlx5_ib_err(mr_to_mdev(imr), "Failed to update PAS\n"); return err; } return ret; @@ -815,7 +817,7 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt, { struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem); - lockdep_assert_held(&mr->dev->odp_srcu); + lockdep_assert_held(&mr_to_mdev(mr)->odp_srcu); if (unlikely(io_virt < mr->mmkey.iova)) return -EFAULT; @@ -1783,7 +1785,7 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *w) /* We rely on IB/core that work is executed if we have num_sge != 0 only. */ WARN_ON(!work->num_sge); - dev = work->frags[0].mr->dev; + dev = mr_to_mdev(work->frags[0].mr); /* SRCU should be held when calling to mlx5_odp_populate_xlt() */ srcu_key = srcu_read_lock(&dev->odp_srcu); for (i = 0; i < work->num_sge; ++i) { diff --git a/drivers/infiniband/hw/mlx5/restrack.c b/drivers/infiniband/hw/mlx5/restrack.c index 887270dd3ce2..4ac429e72004 100644 --- a/drivers/infiniband/hw/mlx5/restrack.c +++ b/drivers/infiniband/hw/mlx5/restrack.c @@ -116,7 +116,7 @@ static int fill_res_mr_entry_raw(struct sk_buff *msg, struct ib_mr *ibmr) { struct mlx5_ib_mr *mr = to_mmr(ibmr); - return fill_res_raw(msg, mr->dev, MLX5_SGMT_TYPE_PRM_QUERY_MKEY, + return fill_res_raw(msg, mr_to_mdev(mr), MLX5_SGMT_TYPE_PRM_QUERY_MKEY, mlx5_mkey_to_idx(mr->mmkey.key)); }

3 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Assign dev to DM MR" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-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 ca991a7d14d4835b302bcd182fdbf54470f45520 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb <maorg(a)nvidia.com> Date: Thu, 3 Dec 2020 21:08:07 +0200 Subject: [PATCH] RDMA/mlx5: Assign dev to DM MR Currently, DM MR registration flow doesn't set the mlx5_ib_dev pointer and can cause a NULL pointer dereference if userspace dumps the MR via rdma tool. Assign the IB device together with the other fields and remove the redundant reference of mlx5_ib_dev from mlx5_ib_mr. Cc: stable(a)vger.kernel.org Fixes: 6c29f57ea475 ("IB/mlx5: Device memory mr registration support") Link: https://lore.kernel.org/r/20201203190807.127189-1-leon@kernel.org Signed-off-by: Maor Gottlieb <maorg(a)nvidia.com> Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index fac495e7834e..c33d6fd64fb6 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -669,7 +669,6 @@ struct mlx5_ib_mr { struct mlx5_shared_mr_info *smr_info; struct list_head list; struct mlx5_cache_ent *cache_ent; - struct mlx5_ib_dev *dev; u32 out[MLX5_ST_SZ_DW(create_mkey_out)]; struct mlx5_core_sig_ctx *sig; void *descs_alloc; @@ -1107,6 +1106,11 @@ static inline struct mlx5_ib_dev *to_mdev(struct ib_device *ibdev) return container_of(ibdev, struct mlx5_ib_dev, ib_dev); } +static inline struct mlx5_ib_dev *mr_to_mdev(struct mlx5_ib_mr *mr) +{ + return to_mdev(mr->ibmr.device); +} + static inline struct mlx5_ib_dev *mlx5_udata_to_mdev(struct ib_udata *udata) { struct mlx5_ib_ucontext *context = rdma_udata_to_drv_context( diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 281032d2827f..6fa869c30e3f 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -137,8 +137,8 @@ static void create_mkey_callback(int status, struct mlx5_async_work *context) { struct mlx5_ib_mr *mr = container_of(context, struct mlx5_ib_mr, cb_work); - struct mlx5_ib_dev *dev = mr->dev; struct mlx5_cache_ent *ent = mr->cache_ent; + struct mlx5_ib_dev *dev = ent->dev; unsigned long flags; if (status) { @@ -176,7 +176,6 @@ static struct mlx5_ib_mr *alloc_cache_mr(struct mlx5_cache_ent *ent, void *mkc) if (!mr) return NULL; mr->cache_ent = ent; - mr->dev = ent->dev; set_mkc_access_pd_addr_fields(mkc, 0, 0, ent->dev->umrc.pd); MLX5_SET(mkc, mkc, free, 1); @@ -931,6 +930,7 @@ static void set_mr_fields(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, mr->ibmr.lkey = mr->mmkey.key; mr->ibmr.rkey = mr->mmkey.key; mr->ibmr.length = length; + mr->ibmr.device = &dev->ib_dev; mr->access_flags = access_flags; } @@ -1062,7 +1062,7 @@ static void *mlx5_ib_create_xlt_wr(struct mlx5_ib_mr *mr, size_t nents, size_t ent_size, unsigned int flags) { - struct mlx5_ib_dev *dev = mr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; dma_addr_t dma; void *xlt; @@ -1124,7 +1124,7 @@ static unsigned int xlt_wr_final_send_flags(unsigned int flags) int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, int page_shift, int flags) { - struct mlx5_ib_dev *dev = mr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; void *xlt; struct mlx5_umr_wr wr; @@ -1203,7 +1203,7 @@ int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, */ static int mlx5_ib_update_mr_pas(struct mlx5_ib_mr *mr, unsigned int flags) { - struct mlx5_ib_dev *dev = mr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; struct ib_block_iter biter; struct mlx5_mtt *cur_mtt; @@ -1335,7 +1335,6 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem, } mr->mmkey.type = MLX5_MKEY_MR; mr->desc_size = sizeof(struct mlx5_mtt); - mr->dev = dev; mr->umem = umem; set_mr_fields(dev, mr, umem->length, access_flags); kvfree(in); @@ -1579,17 +1578,17 @@ int mlx5_mr_cache_invalidate(struct mlx5_ib_mr *mr) { struct mlx5_umr_wr umrwr = {}; - if (mr->dev->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + if (mr_to_mdev(mr)->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) return 0; umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR | MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS; umrwr.wr.opcode = MLX5_IB_WR_UMR; - umrwr.pd = mr->dev->umrc.pd; + umrwr.pd = mr_to_mdev(mr)->umrc.pd; umrwr.mkey = mr->mmkey.key; umrwr.ignore_free_state = 1; - return mlx5_ib_post_send_wait(mr->dev, &umrwr); + return mlx5_ib_post_send_wait(mr_to_mdev(mr), &umrwr); } /* diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index f4a28a012187..aa2413b50adc 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -102,7 +102,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, if (flags & MLX5_IB_UPD_XLT_ZAP) { for (; pklm != end; pklm++, idx++) { pklm->bcount = cpu_to_be32(MLX5_IMR_MTT_SIZE); - pklm->key = cpu_to_be32(imr->dev->null_mkey); + pklm->key = cpu_to_be32(mr_to_mdev(imr)->null_mkey); pklm->va = 0; } return; @@ -129,7 +129,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, * locking around the xarray. */ lockdep_assert_held(&to_ib_umem_odp(imr->umem)->umem_mutex); - lockdep_assert_held(&imr->dev->odp_srcu); + lockdep_assert_held(&mr_to_mdev(imr)->odp_srcu); for (; pklm != end; pklm++, idx++) { struct mlx5_ib_mr *mtt = xa_load(&imr->implicit_children, idx); @@ -139,7 +139,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, pklm->key = cpu_to_be32(mtt->ibmr.lkey); pklm->va = cpu_to_be64(idx * MLX5_IMR_MTT_SIZE); } else { - pklm->key = cpu_to_be32(imr->dev->null_mkey); + pklm->key = cpu_to_be32(mr_to_mdev(imr)->null_mkey); pklm->va = 0; } } @@ -199,7 +199,7 @@ static void dma_fence_odp_mr(struct mlx5_ib_mr *mr) mutex_unlock(&odp->umem_mutex); if (!mr->cache_ent) { - mlx5_core_destroy_mkey(mr->dev->mdev, &mr->mmkey); + mlx5_core_destroy_mkey(mr_to_mdev(mr)->mdev, &mr->mmkey); WARN_ON(mr->descs); } } @@ -222,19 +222,19 @@ static void free_implicit_child_mr(struct mlx5_ib_mr *mr, bool need_imr_xlt) WARN_ON(atomic_read(&mr->num_deferred_work)); if (need_imr_xlt) { - srcu_key = srcu_read_lock(&mr->dev->odp_srcu); + srcu_key = srcu_read_lock(&mr_to_mdev(mr)->odp_srcu); mutex_lock(&odp_imr->umem_mutex); mlx5_ib_update_xlt(mr->parent, idx, 1, 0, MLX5_IB_UPD_XLT_INDIRECT | MLX5_IB_UPD_XLT_ATOMIC); mutex_unlock(&odp_imr->umem_mutex); - srcu_read_unlock(&mr->dev->odp_srcu, srcu_key); + srcu_read_unlock(&mr_to_mdev(mr)->odp_srcu, srcu_key); } dma_fence_odp_mr(mr); mr->parent = NULL; - mlx5_mr_cache_free(mr->dev, mr); + mlx5_mr_cache_free(mr_to_mdev(mr), mr); ib_umem_odp_release(odp); if (atomic_dec_and_test(&imr->num_deferred_work)) wake_up(&imr->q_deferred_work); @@ -274,7 +274,7 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr) goto out_unlock; atomic_inc(&imr->num_deferred_work); - call_srcu(&mr->dev->odp_srcu, &mr->odp_destroy.rcu, + call_srcu(&mr_to_mdev(mr)->odp_srcu, &mr->odp_destroy.rcu, free_implicit_child_mr_rcu); out_unlock: @@ -476,12 +476,13 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, if (IS_ERR(odp)) return ERR_CAST(odp); - ret = mr = mlx5_mr_cache_alloc(imr->dev, MLX5_IMR_MTT_CACHE_ENTRY, - imr->access_flags); + ret = mr = mlx5_mr_cache_alloc( + mr_to_mdev(imr), MLX5_IMR_MTT_CACHE_ENTRY, imr->access_flags); if (IS_ERR(mr)) goto out_umem; mr->ibmr.pd = imr->ibmr.pd; + mr->ibmr.device = &mr_to_mdev(imr)->ib_dev; mr->umem = &odp->umem; mr->ibmr.lkey = mr->mmkey.key; mr->ibmr.rkey = mr->mmkey.key; @@ -517,11 +518,11 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, goto out_mr; } - mlx5_ib_dbg(imr->dev, "key %x mr %p\n", mr->mmkey.key, mr); + mlx5_ib_dbg(mr_to_mdev(imr), "key %x mr %p\n", mr->mmkey.key, mr); return mr; out_mr: - mlx5_mr_cache_free(imr->dev, mr); + mlx5_mr_cache_free(mr_to_mdev(imr), mr); out_umem: ib_umem_odp_release(odp); return ret; @@ -555,6 +556,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, imr->umem = &umem_odp->umem; imr->ibmr.lkey = imr->mmkey.key; imr->ibmr.rkey = imr->mmkey.key; + imr->ibmr.device = &dev->ib_dev; imr->umem = &umem_odp->umem; imr->is_odp_implicit = true; atomic_set(&imr->num_deferred_work, 0); @@ -588,7 +590,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) { struct ib_umem_odp *odp_imr = to_ib_umem_odp(imr->umem); - struct mlx5_ib_dev *dev = imr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(imr); struct list_head destroy_list; struct mlx5_ib_mr *mtt; struct mlx5_ib_mr *tmp; @@ -658,10 +660,10 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) void mlx5_ib_fence_odp_mr(struct mlx5_ib_mr *mr) { /* Prevent new page faults and prefetch requests from succeeding */ - xa_erase(&mr->dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key)); + xa_erase(&mr_to_mdev(mr)->odp_mkeys, mlx5_base_mkey(mr->mmkey.key)); /* Wait for all running page-fault handlers to finish. */ - synchronize_srcu(&mr->dev->odp_srcu); + synchronize_srcu(&mr_to_mdev(mr)->odp_srcu); wait_event(mr->q_deferred_work, !atomic_read(&mr->num_deferred_work)); @@ -705,7 +707,7 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp, if (ret < 0) { if (ret != -EAGAIN) - mlx5_ib_err(mr->dev, + mlx5_ib_err(mr_to_mdev(mr), "Failed to update mkey page tables\n"); goto out; } @@ -795,7 +797,7 @@ static int pagefault_implicit_mr(struct mlx5_ib_mr *imr, MLX5_IB_UPD_XLT_ATOMIC); mutex_unlock(&odp_imr->umem_mutex); if (err) { - mlx5_ib_err(imr->dev, "Failed to update PAS\n"); + mlx5_ib_err(mr_to_mdev(imr), "Failed to update PAS\n"); return err; } return ret; @@ -815,7 +817,7 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt, { struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem); - lockdep_assert_held(&mr->dev->odp_srcu); + lockdep_assert_held(&mr_to_mdev(mr)->odp_srcu); if (unlikely(io_virt < mr->mmkey.iova)) return -EFAULT; @@ -1783,7 +1785,7 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *w) /* We rely on IB/core that work is executed if we have num_sge != 0 only. */ WARN_ON(!work->num_sge); - dev = work->frags[0].mr->dev; + dev = mr_to_mdev(work->frags[0].mr); /* SRCU should be held when calling to mlx5_odp_populate_xlt() */ srcu_key = srcu_read_lock(&dev->odp_srcu); for (i = 0; i < work->num_sge; ++i) { diff --git a/drivers/infiniband/hw/mlx5/restrack.c b/drivers/infiniband/hw/mlx5/restrack.c index 887270dd3ce2..4ac429e72004 100644 --- a/drivers/infiniband/hw/mlx5/restrack.c +++ b/drivers/infiniband/hw/mlx5/restrack.c @@ -116,7 +116,7 @@ static int fill_res_mr_entry_raw(struct sk_buff *msg, struct ib_mr *ibmr) { struct mlx5_ib_mr *mr = to_mmr(ibmr); - return fill_res_raw(msg, mr->dev, MLX5_SGMT_TYPE_PRM_QUERY_MKEY, + return fill_res_raw(msg, mr_to_mdev(mr), MLX5_SGMT_TYPE_PRM_QUERY_MKEY, mlx5_mkey_to_idx(mr->mmkey.key)); }

3 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Assign dev to DM MR" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-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 ca991a7d14d4835b302bcd182fdbf54470f45520 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb <maorg(a)nvidia.com> Date: Thu, 3 Dec 2020 21:08:07 +0200 Subject: [PATCH] RDMA/mlx5: Assign dev to DM MR Currently, DM MR registration flow doesn't set the mlx5_ib_dev pointer and can cause a NULL pointer dereference if userspace dumps the MR via rdma tool. Assign the IB device together with the other fields and remove the redundant reference of mlx5_ib_dev from mlx5_ib_mr. Cc: stable(a)vger.kernel.org Fixes: 6c29f57ea475 ("IB/mlx5: Device memory mr registration support") Link: https://lore.kernel.org/r/20201203190807.127189-1-leon@kernel.org Signed-off-by: Maor Gottlieb <maorg(a)nvidia.com> Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index fac495e7834e..c33d6fd64fb6 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -669,7 +669,6 @@ struct mlx5_ib_mr { struct mlx5_shared_mr_info *smr_info; struct list_head list; struct mlx5_cache_ent *cache_ent; - struct mlx5_ib_dev *dev; u32 out[MLX5_ST_SZ_DW(create_mkey_out)]; struct mlx5_core_sig_ctx *sig; void *descs_alloc; @@ -1107,6 +1106,11 @@ static inline struct mlx5_ib_dev *to_mdev(struct ib_device *ibdev) return container_of(ibdev, struct mlx5_ib_dev, ib_dev); } +static inline struct mlx5_ib_dev *mr_to_mdev(struct mlx5_ib_mr *mr) +{ + return to_mdev(mr->ibmr.device); +} + static inline struct mlx5_ib_dev *mlx5_udata_to_mdev(struct ib_udata *udata) { struct mlx5_ib_ucontext *context = rdma_udata_to_drv_context( diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 281032d2827f..6fa869c30e3f 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -137,8 +137,8 @@ static void create_mkey_callback(int status, struct mlx5_async_work *context) { struct mlx5_ib_mr *mr = container_of(context, struct mlx5_ib_mr, cb_work); - struct mlx5_ib_dev *dev = mr->dev; struct mlx5_cache_ent *ent = mr->cache_ent; + struct mlx5_ib_dev *dev = ent->dev; unsigned long flags; if (status) { @@ -176,7 +176,6 @@ static struct mlx5_ib_mr *alloc_cache_mr(struct mlx5_cache_ent *ent, void *mkc) if (!mr) return NULL; mr->cache_ent = ent; - mr->dev = ent->dev; set_mkc_access_pd_addr_fields(mkc, 0, 0, ent->dev->umrc.pd); MLX5_SET(mkc, mkc, free, 1); @@ -931,6 +930,7 @@ static void set_mr_fields(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, mr->ibmr.lkey = mr->mmkey.key; mr->ibmr.rkey = mr->mmkey.key; mr->ibmr.length = length; + mr->ibmr.device = &dev->ib_dev; mr->access_flags = access_flags; } @@ -1062,7 +1062,7 @@ static void *mlx5_ib_create_xlt_wr(struct mlx5_ib_mr *mr, size_t nents, size_t ent_size, unsigned int flags) { - struct mlx5_ib_dev *dev = mr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; dma_addr_t dma; void *xlt; @@ -1124,7 +1124,7 @@ static unsigned int xlt_wr_final_send_flags(unsigned int flags) int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, int page_shift, int flags) { - struct mlx5_ib_dev *dev = mr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; void *xlt; struct mlx5_umr_wr wr; @@ -1203,7 +1203,7 @@ int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, */ static int mlx5_ib_update_mr_pas(struct mlx5_ib_mr *mr, unsigned int flags) { - struct mlx5_ib_dev *dev = mr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; struct ib_block_iter biter; struct mlx5_mtt *cur_mtt; @@ -1335,7 +1335,6 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem, } mr->mmkey.type = MLX5_MKEY_MR; mr->desc_size = sizeof(struct mlx5_mtt); - mr->dev = dev; mr->umem = umem; set_mr_fields(dev, mr, umem->length, access_flags); kvfree(in); @@ -1579,17 +1578,17 @@ int mlx5_mr_cache_invalidate(struct mlx5_ib_mr *mr) { struct mlx5_umr_wr umrwr = {}; - if (mr->dev->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + if (mr_to_mdev(mr)->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) return 0; umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR | MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS; umrwr.wr.opcode = MLX5_IB_WR_UMR; - umrwr.pd = mr->dev->umrc.pd; + umrwr.pd = mr_to_mdev(mr)->umrc.pd; umrwr.mkey = mr->mmkey.key; umrwr.ignore_free_state = 1; - return mlx5_ib_post_send_wait(mr->dev, &umrwr); + return mlx5_ib_post_send_wait(mr_to_mdev(mr), &umrwr); } /* diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index f4a28a012187..aa2413b50adc 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -102,7 +102,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, if (flags & MLX5_IB_UPD_XLT_ZAP) { for (; pklm != end; pklm++, idx++) { pklm->bcount = cpu_to_be32(MLX5_IMR_MTT_SIZE); - pklm->key = cpu_to_be32(imr->dev->null_mkey); + pklm->key = cpu_to_be32(mr_to_mdev(imr)->null_mkey); pklm->va = 0; } return; @@ -129,7 +129,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, * locking around the xarray. */ lockdep_assert_held(&to_ib_umem_odp(imr->umem)->umem_mutex); - lockdep_assert_held(&imr->dev->odp_srcu); + lockdep_assert_held(&mr_to_mdev(imr)->odp_srcu); for (; pklm != end; pklm++, idx++) { struct mlx5_ib_mr *mtt = xa_load(&imr->implicit_children, idx); @@ -139,7 +139,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, pklm->key = cpu_to_be32(mtt->ibmr.lkey); pklm->va = cpu_to_be64(idx * MLX5_IMR_MTT_SIZE); } else { - pklm->key = cpu_to_be32(imr->dev->null_mkey); + pklm->key = cpu_to_be32(mr_to_mdev(imr)->null_mkey); pklm->va = 0; } } @@ -199,7 +199,7 @@ static void dma_fence_odp_mr(struct mlx5_ib_mr *mr) mutex_unlock(&odp->umem_mutex); if (!mr->cache_ent) { - mlx5_core_destroy_mkey(mr->dev->mdev, &mr->mmkey); + mlx5_core_destroy_mkey(mr_to_mdev(mr)->mdev, &mr->mmkey); WARN_ON(mr->descs); } } @@ -222,19 +222,19 @@ static void free_implicit_child_mr(struct mlx5_ib_mr *mr, bool need_imr_xlt) WARN_ON(atomic_read(&mr->num_deferred_work)); if (need_imr_xlt) { - srcu_key = srcu_read_lock(&mr->dev->odp_srcu); + srcu_key = srcu_read_lock(&mr_to_mdev(mr)->odp_srcu); mutex_lock(&odp_imr->umem_mutex); mlx5_ib_update_xlt(mr->parent, idx, 1, 0, MLX5_IB_UPD_XLT_INDIRECT | MLX5_IB_UPD_XLT_ATOMIC); mutex_unlock(&odp_imr->umem_mutex); - srcu_read_unlock(&mr->dev->odp_srcu, srcu_key); + srcu_read_unlock(&mr_to_mdev(mr)->odp_srcu, srcu_key); } dma_fence_odp_mr(mr); mr->parent = NULL; - mlx5_mr_cache_free(mr->dev, mr); + mlx5_mr_cache_free(mr_to_mdev(mr), mr); ib_umem_odp_release(odp); if (atomic_dec_and_test(&imr->num_deferred_work)) wake_up(&imr->q_deferred_work); @@ -274,7 +274,7 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr) goto out_unlock; atomic_inc(&imr->num_deferred_work); - call_srcu(&mr->dev->odp_srcu, &mr->odp_destroy.rcu, + call_srcu(&mr_to_mdev(mr)->odp_srcu, &mr->odp_destroy.rcu, free_implicit_child_mr_rcu); out_unlock: @@ -476,12 +476,13 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, if (IS_ERR(odp)) return ERR_CAST(odp); - ret = mr = mlx5_mr_cache_alloc(imr->dev, MLX5_IMR_MTT_CACHE_ENTRY, - imr->access_flags); + ret = mr = mlx5_mr_cache_alloc( + mr_to_mdev(imr), MLX5_IMR_MTT_CACHE_ENTRY, imr->access_flags); if (IS_ERR(mr)) goto out_umem; mr->ibmr.pd = imr->ibmr.pd; + mr->ibmr.device = &mr_to_mdev(imr)->ib_dev; mr->umem = &odp->umem; mr->ibmr.lkey = mr->mmkey.key; mr->ibmr.rkey = mr->mmkey.key; @@ -517,11 +518,11 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, goto out_mr; } - mlx5_ib_dbg(imr->dev, "key %x mr %p\n", mr->mmkey.key, mr); + mlx5_ib_dbg(mr_to_mdev(imr), "key %x mr %p\n", mr->mmkey.key, mr); return mr; out_mr: - mlx5_mr_cache_free(imr->dev, mr); + mlx5_mr_cache_free(mr_to_mdev(imr), mr); out_umem: ib_umem_odp_release(odp); return ret; @@ -555,6 +556,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, imr->umem = &umem_odp->umem; imr->ibmr.lkey = imr->mmkey.key; imr->ibmr.rkey = imr->mmkey.key; + imr->ibmr.device = &dev->ib_dev; imr->umem = &umem_odp->umem; imr->is_odp_implicit = true; atomic_set(&imr->num_deferred_work, 0); @@ -588,7 +590,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) { struct ib_umem_odp *odp_imr = to_ib_umem_odp(imr->umem); - struct mlx5_ib_dev *dev = imr->dev; + struct mlx5_ib_dev *dev = mr_to_mdev(imr); struct list_head destroy_list; struct mlx5_ib_mr *mtt; struct mlx5_ib_mr *tmp; @@ -658,10 +660,10 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) void mlx5_ib_fence_odp_mr(struct mlx5_ib_mr *mr) { /* Prevent new page faults and prefetch requests from succeeding */ - xa_erase(&mr->dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key)); + xa_erase(&mr_to_mdev(mr)->odp_mkeys, mlx5_base_mkey(mr->mmkey.key)); /* Wait for all running page-fault handlers to finish. */ - synchronize_srcu(&mr->dev->odp_srcu); + synchronize_srcu(&mr_to_mdev(mr)->odp_srcu); wait_event(mr->q_deferred_work, !atomic_read(&mr->num_deferred_work)); @@ -705,7 +707,7 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp, if (ret < 0) { if (ret != -EAGAIN) - mlx5_ib_err(mr->dev, + mlx5_ib_err(mr_to_mdev(mr), "Failed to update mkey page tables\n"); goto out; } @@ -795,7 +797,7 @@ static int pagefault_implicit_mr(struct mlx5_ib_mr *imr, MLX5_IB_UPD_XLT_ATOMIC); mutex_unlock(&odp_imr->umem_mutex); if (err) { - mlx5_ib_err(imr->dev, "Failed to update PAS\n"); + mlx5_ib_err(mr_to_mdev(imr), "Failed to update PAS\n"); return err; } return ret; @@ -815,7 +817,7 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt, { struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem); - lockdep_assert_held(&mr->dev->odp_srcu); + lockdep_assert_held(&mr_to_mdev(mr)->odp_srcu); if (unlikely(io_virt < mr->mmkey.iova)) return -EFAULT; @@ -1783,7 +1785,7 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *w) /* We rely on IB/core that work is executed if we have num_sge != 0 only. */ WARN_ON(!work->num_sge); - dev = work->frags[0].mr->dev; + dev = mr_to_mdev(work->frags[0].mr); /* SRCU should be held when calling to mlx5_odp_populate_xlt() */ srcu_key = srcu_read_lock(&dev->odp_srcu); for (i = 0; i < work->num_sge; ++i) { diff --git a/drivers/infiniband/hw/mlx5/restrack.c b/drivers/infiniband/hw/mlx5/restrack.c index 887270dd3ce2..4ac429e72004 100644 --- a/drivers/infiniband/hw/mlx5/restrack.c +++ b/drivers/infiniband/hw/mlx5/restrack.c @@ -116,7 +116,7 @@ static int fill_res_mr_entry_raw(struct sk_buff *msg, struct ib_mr *ibmr) { struct mlx5_ib_mr *mr = to_mmr(ibmr); - return fill_res_raw(msg, mr->dev, MLX5_SGMT_TYPE_PRM_QUERY_MKEY, + return fill_res_raw(msg, mr_to_mdev(mr), MLX5_SGMT_TYPE_PRM_QUERY_MKEY, mlx5_mkey_to_idx(mr->mmkey.key)); }

3 years, 10 months

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror December 2020